feat(skill): CODEMAN_WORKER_ADVISOR gives spawned claude workers an advisor

spawn_worker builds its quick-start body itself ({caseName, mode,
parentSessionId}), so an agent driving the skill had no way to give a worker
the advisor without hand-building the call and losing the readiness ladder,
hooks vetting and trust-dialog fallback. Setting CODEMAN_WORKER_ADVISOR
(fable / opus / sonnet) now adds `advisorModel` for every claude worker that
spawn_worker or spawn_workers starts; other modes ignore it.

A refused value fails the spawn with the server's INVALID_INPUT message. A
server without advisor support drops the field silently (the schema is not
strict), so spawn_worker reads it back and says so on stderr.

The preamble changed, so CODEMAN_PREAMBLE is bumped to 1.33.4 and stale
cached copies are rewritten instead of silently ignoring the variable.
SKILL.md's heredoc and the plugin mirror are synced.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "codeman",
       "source": "./plugins/codeman",
       "description": "Drive Codeman from inside a Claude Code session: spawn worker sessions, prompt them, wait for them, read their answers, clean up. Acts only inside a Codeman-managed session.",
-      "version": "1.31.0",
+      "version": "1.33.3",
       "author": {
         "name": "Ark0N",
         "url": "https://github.com/Ark0N"

.github/CONTRIBUTING.md

@@ -28,12 +28,15 @@ The frontend is plain JS served from `src/web/public/` with no bundler in dev: e
 CI runs all of these, so save yourself a round trip:
 
 ```bash
-npm run typecheck              # tsc --noEmit, strict mode
+npm run typecheck               # tsc --noEmit, strict mode
 npm run lint
 npm run format:check
-npm run check:frontend-syntax  # syntax-checks the plain-JS frontend modules
+npm run check:frontend-syntax   # syntax-checks the plain-JS frontend modules
+npm run check:browser-excludes  # every browser-driven test is kept out of `npm test`
 ```
 
+`npm install` also installs a `pre-push` git hook that runs these static checks (about 10-40s, machine-dependent) and blocks the push if one fails. It skips itself when you push something other than the checked-out HEAD, or when the tree has uncommitted changes the checks would read. Skip it once with `CODEMAN_SKIP_PREPUSH=1 git push`; it never replaces a `pre-push` hook of your own.
+
 ### Tests
 
 ```bash

.github/workflows/ci.yml

@@ -34,6 +34,13 @@ jobs:
       - name: Frontend JS syntax check
         run: npm run check:frontend-syntax
 
+      # Asks `vitest list` what CI would actually collect, rather than matching
+      # filenames: a browser-driven test missing from BROWSER_TEST_GLOBS
+      # (config/test-suites.ts) passes locally and dies in the test job with
+      # "browserType.launch: Executable doesn't exist".
+      - name: Browser-test exclusion check
+        run: npm run check:browser-excludes
+
       - name: Format check
         run: npm run format:check
 
@@ -100,6 +107,50 @@ jobs:
             fi
             echo "bash $BASH_VERSION: dsh identity probe survives a missing timeout"
           '
+          # Installer v2: the question phase runs before the build, and every decision it
+          # takes is bash logic over stubbed tailscale state. Drive the flags, the launch
+          # default, the occupied-:443 menu and the rename question with canned answers,
+          # so a bash-4 construct or a flipped default in any of them fails here, not on a
+          # Mac. The JSON parsers need node (absent in this image) and are stubbed; their
+          # own coverage is test/install-sh-invariants.test.ts plus the vitest gate.
+          docker run --rm -v "$PWD":/w -w /w -e CODEMAN_INSTALL_SH_LIB=1 -e HOME=/tmp/h bash:3.2 bash -c '
+            set -euo pipefail
+            mkdir -p /tmp/h
+            . /w/install.sh
+            parse_flags --tailscale --service --name Build-Box --port 4000
+            [[ "$CODEMAN_TAILSCALE" == "1" && "$LAUNCH_PRESET" == "2" && "$TS_NAME" == "Build-Box" && "$CODEMAN_PORT" == "4000" ]]
+            [[ "$(ts_sanitize_name "$TS_NAME")" == "build-box" ]]
+            has_tty() { return 0; }
+            ANSWER=""; read_reply() { eval "$1=\"\$ANSWER\""; }
+            systemctl() { return 0; }
+            LAUNCH_PRESET=""; NONINTERACTIVE=0
+            choose_launch_mode linux >/dev/null 2>&1
+            [[ "$LAUNCH_CHOICE" == "2" ]]
+            check_tailscale() { return 0; }
+            ts_status_field() { case "$1" in "s.BackendState") printf Running ;; "s.Self && s.Self.DNSName") printf "box.tail.ts.net." ;; esac; }
+            ts_backend_state() { printf Running; }
+            ts_dns_name() { printf box.tail.ts.net; }
+            ts_serve_443_target_port() { printf 8080; }
+            ts_serve_find_port_mapping() { :; }
+            ts_serve_port_used() { return 1; }
+            detect_tailscale_serve_url() { :; }
+            tailscale_choose_mapping >/dev/null 2>&1
+            [[ "$TS_SERVE_MODE" == "path" && "$BIND_BASE_URL" == "/codeman" ]]
+            RENAMED=""; tailscale_rename_node() { RENAMED="$1"; }
+            TS_NAME=""; tailscale_choose_name >/dev/null 2>&1
+            [[ -z "$RENAMED" ]]
+            # A flag re-run keeps the password the unit already carries (and so
+            # never writes the unauthenticated ack), and the hand-start line the
+            # done screen prints carries every non-default value.
+            read_existing_binding() { EXISTING_FOUND=1; EXISTING_HOST=0.0.0.0; EXISTING_PASSWORD=s3cret; EXISTING_ACK=0; EXISTING_BASE_URL=""; }
+            CODEMAN_HOST=0.0.0.0; CODEMAN_TAILSCALE=0; unset CODEMAN_PASSWORD; BIND_ACK=0
+            choose_network_binding >/dev/null 2>&1
+            [[ "$BIND_PASSWORD" == "s3cret" && "$BIND_ACK" == "0" ]]
+            BIND_HOST=0.0.0.0; BIND_PASSWORD=x; BIND_ACK=0; BIND_BASE_URL=/codeman; CODEMAN_PORT=4000
+            [[ "$(start_command_hint)" == "CODEMAN_HOST=0.0.0.0 CODEMAN_PASSWORD="*" CODEMAN_BASE_URL=/codeman CODEMAN_PORT=4000 codeman web" ]]
+            RECONFIGURE=0; parse_flags --port 4001; [[ "$RECONFIGURE" == "1" ]]
+            echo "bash $BASH_VERSION: question phase (flags, launch default, occupied :443, rename opt-in, kept password, start line) ok"
+          '
 
       - name: CLI catalogue artifacts are in sync with stock.ts
         run: npm run generate:cli-catalog -- --check

CHANGELOG.md

@@ -1,5 +1,166 @@
 # aicodeman
 
+## 1.33.3
+
+### Patch Changes
+
+- f776ad8: ### Thanks
+  - @JDProfresh for rendering Markdown in the File Viewer (#503) through the chat's existing markdown pipeline and sanitizer rather than a second one, plus the Lines and Wrap toggles and the sanitizer fix that stops a document from clobbering `document.app`.
+  - @timkjr for bringing the Shell scroll-to-top history pull to the split view's second pane (#506), following #494's rules down to the back-off, with tests that fail on the code before each fix.
+  - @irisitymichaelgrundberg for the `#session=<id>` dashboard link (#507), so a page that keeps one Codeman window open can switch it between sessions without reloading it.
+  - @dignfei for handing focus back when the Command Palette or the Session Manager closes (#509), and for the six-overlay measurement that showed exactly which two were broken.
+
+  **Markdown files render in the File Viewer (#503).** Opening a `.md` or `.markdown` file now shows it as a document: headings, tables, code blocks with the same copy buttons as the chat, images relative to the file, and links to other documents that open inside the viewer. An `MD` pill switches back to the source, and Edit works from either view. Plain text gets a `Lines` gutter (never part of a copy) and a `Wrap` toggle, all three remembered per device. `.avif` images preview inline, and printed `.avif`/`.ico` paths open the viewer instead of the tail view. An in-workspace file path clicked in the terminal still opens the live tail view.
+
+  **Link a dashboard window to a session (#507).** An outside page, such as a task board, that keeps one Codeman window open can now switch it to a session by pointing it at `/#session=<id>`. Only the fragment changes, so the page stays loaded and the switch is an ordinary tab selection. A link to a session the dashboard does not list yet waits up to 30 seconds for it to appear and then shows "Session not found"; picking another tab, going Home or opening a web tab cancels the wait. Following a link does not count as looking at the session, so its idle alert stays armed. The fragment is documented in `docs/extending-codeman.md` and is now a stable surface under `docs/versioning-policy.md`.
+
+  **Escape no longer strands the keyboard (#509).** Closing the Command Palette or the Session Manager now hands focus back to whatever held it before they opened, usually the terminal, so you can keep typing without clicking first. An Escape pressed while neither is open changes nothing.
+
+  **Split view: a Shell Pane B scrolls back into tmux history (#506).** Wheel up at the top of a Shell session in the split view's second pane now pulls the most recent 1 MiB of its tmux history and keeps your place, the same as the primary pane since 1.33.2.
+
+  **Fixes applied while landing.** Markdown opened from an attachment card no longer resolves relative images and links against the workspace root, where they could show a missing image or open a different file of the same name; they render as their alt text and link text instead. Rendered files no longer turn every source line break into a hard break the way chat messages do, so a README wrapped at 80 columns reads as flowing paragraphs. Absolute-path links inside a rendered document open in that document's session. A disconnected Pane B keeps its "disconnected" marker as the last line even when the socket closes in the middle of a history pull. Closing the Session Manager through a row's "Switch to session" or "Open folder" no longer pulls focus back from the terminal to the header button.
+
+## 1.33.2
+
+### Patch Changes
+
+- e439cf0: ### Thanks
+  - @aakhter for keeping web-tab events private to their owner in multi-user mode (#501), with end-to-end isolation tests that fail without the fix, and for the browser-test exclusion check and pre-push hook (#500), including the hooks-dir resolution that never writes outside the repo's own `.git/hooks`.
+  - @opticon454 for keeping CLIs installed from Settings across Docker container updates (#490) and for the static Git identity for the Docker images (#492).
+  - @timkjr for letting a Shell pane's scroll-to-top reach tmux history (#494), with tests that fail on the commit before each fix.
+  - @JDProfresh for tracking down why wheel and touch scrolling did nothing in Claude's default inline view (#498), with the tmux measurements that proved it.
+  - @irisitymichaelgrundberg for the follow-up that makes an agent waiting on artifact comments raise its alert again (#491).
+
+  **A tab stays busy while Claude waits for its own workers.** When Claude hands work to an ultracode workflow or background agents, it ends its turn with `✻ Waiting for 1 dynamic workflow to finish` and resumes by itself when they report back. The idle probe used to call that session idle for the whole wait, and at phone width nothing on screen changes for minutes. A new optional registry field, `capabilities.workDetect.awaitingLine`, names that closing row, and only the newest column-0 row directly above the composer counts, so the session goes idle normally once the follow-up turn ends.
+
+  **Prompts sent through the API are no longer left unsent.** A prompt posted to `POST /api/sessions/:id/input` without `useMux` was written into the pane in one piece, and Claude Code (measured on 2.1.283) takes a burst of about a hundred characters or more as a paste, so the trailing `\r` became a newline and the prompt sat on the composer while the route answered 200. Short prompts went through, which is why it looked random; Codex and OpenCode showed the same thing. A plain prompt (printable text plus exactly one trailing `\r`) now goes through tmux: the text is typed, Enter is pressed as its own key, and the server presses it again while the prompt is still on the composer. Raw frames (escape sequences, a bracketed paste, a line feed, a bare `\r`) and an explicit `"useMux": false` keep the direct write. The same fix reaches cron jobs in "Paste (direct)" input mode, which reported `prompt_sent` for a prompt that never left the composer: the text is written raw, Enter follows as its own write 300 ms later, and the session presses it again while the prompt is still unsent. A cron run with no session to write to now fails instead of reporting the prompt as sent.
+
+  **Scrolling works again in Claude's default inline view (#498).** Wheel and touch gestures were forwarded to every Claude 2.1.187+ session as mouse reports, but only Claude's fullscreen renderer (`CLAUDE_CODE_NO_FLICKER=1`, or `"tui": "fullscreen"` in `~/.claude/settings.json`) listens for them, so in the default view scrolling did nothing. Codeman now forwards them only while Claude has mouse tracking switched on, and otherwise scrolls the terminal's own scrollback.
+
+  **Shell panes scroll back into tmux history (#494).** Scrolling to the top of a Shell pane now pulls the most recent 1 MiB of its tmux history, so output that arrived in a burst is reachable without pressing **Load full history**, which still loads the rest.
+
+  **An agent waiting on artifact comments alerts again (#491).** A session whose agent published an artifact and is waiting for somebody to comment on it now raises the normal idle alert and lands in NEEDS YOU, instead of being treated as busy with background work.
+
+  **Web-tab changes stay private in multi-user mode (#501).** The `webview:changed` event reached every connected user, exposing the ids of other users' web-tab creates, edits and deletes. It now carries the tab's owner and reaches that owner plus admins only. Single-user mode is unchanged apart from a new optional `owner` field on the event.
+
+  **Phone header tabs look like tabs (#504).** On phones every header tab is now a chip with a fill and a border, the Alt+N digit (a keyboard hint a phone cannot use) is hidden, names get 80px instead of 50px, and the strip fades at whichever edge still has tabs scrolled out of view.
+
+  **Docker: CLIs installed from Settings survive container updates (#490).** On the Compose deployment, CLIs installed from App Settings (DeepSeek, Pi and other npm-based CLIs) now go to `~/.local` on the persistent home mount, and `~/.local/bin` is on the image PATH, so recreating the container no longer discards them. Anything installed from Settings before this release has to be installed once more after the rebuild.
+
+  **Docker: a static Git identity for the server and agent images (#492).** Set `GIT_USER_NAME` and `GIT_USER_EMAIL` in `docker/.env` (or `CODEMAN_AGENT_IMAGE_GIT_USER_NAME` / `CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL` on a bare-host install) and the identity is written to `/etc/gitconfig` in the server image and the Docker-case agent image. A half-set pair is refused on every build path. Both Docker changes edit `server.Dockerfile`, so the in-app updater asks Compose deployments to rebuild with `docker/Start-Codeman.sh` instead of updating in place.
+
+  **Contributor tooling (#500).** `npm run check:browser-excludes`, now a CI step, fails when a test that drives a real browser is still collected by `npm test`. `npm install` also installs a pre-push hook that runs the static CI checks before a push; it steps aside when the pushed ref is not HEAD or the tree has uncommitted changes the checks would read, and `CODEMAN_SKIP_PREPUSH=1 git push` skips it once.
+
+  **Fixes applied while landing.** A Shell pane's scroll-to-top (#494) no longer re-pulls the same window on every gesture once the browser's 50,000-row scrollback is full, and a pull that hit the byte cap no longer claims the older history is gone. The scroll-routing diagnostics (#498) now log whether Claude has mouse tracking on. The artifact-comment check (#491) also refuses a footer cut off in the middle of the chip. The pre-push hook (#500) steps aside when `npm` is not on PATH, as in some GUI git clients, instead of blocking every push. The Docker Git identity error (#492) names the two variables to set. New tests pin the image PATH order, the identity on both agent-image build paths, and the `?full=1&tail=` terminal route.
+
+## 1.33.1
+
+### Patch Changes
+
+- ### Thanks
+  - @irisitymichaelgrundberg for closing sessions whose agent exited cleanly (#486), built carefully around every way a pane exit can lie (a SIGKILL with no status, a single misread), with the `.claude-images` guard split into its own commit as asked.
+  - @opticon454 for the live-refreshing case picker and Manage search (#483), and for the uv/uvx, libsecret and pnpm additions to the Docker images (#487, #485).
+
+  **Finished sessions close themselves (#486).** A session whose agent you ended with `/exit` is now closed the same way the X button closes it, so finished sessions stop piling up on the board; the conversation stays resumable from the Resume list and the lifecycle log records "agent exited cleanly (status 0)". Only an explicit exit status 0 with no signal, confirmed by two pane reads, qualifies: a crashed or OOM-killed agent keeps its row with the exit code on the tab. The phone overview and desktop home rail now say `exited` instead of `idle`, reboot restore no longer offers to rebuild a session whose agent had exited, and closing one session no longer deletes the `.claude-images` directory that a sibling session in the same case still uses. Thanks @irisitymichaelgrundberg.
+
+  **Search in the phone Select Case sheet (#488).** The bottom sheet gains a "Search cases" field that filters by name (every word must match, any order, ignoring case), Enter picks the case when exactly one row is left, and Escape clears then closes. Also fixes a dead band under Create New Case and a list shorter than the sheet could show.
+
+  **An oversized paste no longer jams a session's input (#484).** A single input over the 64 KiB frame limit used to be refused by both transports, retried every 2 s forever, block every later input for that session and come back from localStorage on each reload. Pastes over the limit are now split into in-limit frames delivered in order (up to 1 MiB; larger ones are refused with a toast and never queued), a refused frame is dropped instead of retried, frames persisted by an older build are pruned on load, and the WebSocket answers an oversized frame with an explicit `too_large` error instead of silence.
+
+- 8841bcc: Add a search box to the Manage tab of the Add Case dialog. It filters the case list by name or path, and the reorder arrows are disabled while a filter is active so a swap cannot involve a hidden case.
+- 8841bcc: The case picker now refreshes its list from `/api/cases` when it opens and every 5 seconds while it stays open, so folders deleted or created on disk appear without a page reload. If the selected case has been removed, the picker falls back to another case without saving it as the last-used one.
+
+  Thanks @opticon454.
+
+- 77ba41f: Install `uv` and `uvx` in the Compose server image and the agent image, so MCP servers launched with `uvx` (such as the Nginx Proxy Manager MCP) can be enabled by Codex instead of failing with `uvx` not found. Both images also install `libsecret-1-0`, the native library the `keytar` dependency of the Azure DevOps MCP (`@azure-devops/mcp`) needs; without it the server crashes before answering the MCP initialize handshake.
+
+  The Compose server image now also carries `pnpm`: `dsh plugin` spawns a literal `pnpm` with no npm fallback, so the Run menu's "DeepSeek - add a terminal profile" button failed with `dsh: pnpm not found on PATH` there. Because this release changes `server.Dockerfile`, the in-app updater asks Compose deployments to rebuild the image (`Update-Codeman.sh`) rather than applying it in place.
+
+  Thanks @opticon454 (#487, #485).
+
+## 1.33.0
+
+### Minor Changes
+
+- CLI management from Settings (#476, finishing the CLI registry work from #343). `~/.codeman/clis.json` used to be hand-edit only; with the new opt-in `cliManagementEnabled` switch (synced, default OFF) App Settings → Agents & CLIs can enable or disable any CLI, install a missing stock CLI with its vetted install command, and add, edit or remove custom CLIs. Six new endpoints back it (`GET`/`POST /api/clis`, `PUT /api/clis/:id`, `POST /api/clis/:id/install`, `PUT /api/clis/custom/:id`, `DELETE /api/clis/:id`), documented in `docs/api-reference.md`. Every write is refused while the switch is off, is admin-only in multi-user mode, is serialized on one queue, and refuses to overwrite a `clis.json` that does not parse or has group/world permission bits. A custom entry is re-validated through the same schema as the stock ones and its install text is never executed. `shell` cannot be disabled. The Run menu and the welcome screen are now built from the enabled catalogue, so the welcome screen also offers Codex, Shell and any custom CLI, and the stock Claude entry is labelled "Claude Code".
+
+  Models: Opus 5.5 (`claude-opus-5-5`, 1M context capable) is offered in App Settings → Models and in task routing (#480).
+
+  Self-update: on a macOS `launchd-daemon` install, a Homebrew node upgrade could leave `update-status.json` stuck at `queued`, which made every later update fail with "An update is already in progress." The updater now falls back to `node` on PATH when the server's own node binary is gone, and an in-flight status that has not been written for 15 minutes is failed on the next read. A graceful shutdown that hangs is now force-exited after 10 s (and the launchd updater SIGKILLs a server that has not exited after 30 s), so launchd can start the new build instead of leaving the service down (#478). Both fixes protect updates that start FROM this release.
+
+  Session Manager (Cmd+K): rows keep their `mode`, `claudeSessionId` and `resumeId`, so the ⋯ menu's Resume session relaunches a Codex row as Codex on its own conversation, and the mode badge shows as it does on the home list (#477).
+
+  Maintainer fixes applied while landing #457: renaming a tab to the name it already has (the Session Options field saves on blur) is now a no-op, so it no longer pins the placeholder as the `/resume` title again; Docker sessions skip the transcript title sync, since their transcript lives in the container; and the agent skill's messaging examples no longer use a `w<N>-` name as the peer name.
+
+  Tests: the suite strips every inherited `CODEMAN_*` variable, so running it inside a Docker Compose deployment no longer writes into the deployment's real case root (#479).
+
+  ### Thanks
+  - @opticon454 for CLI management (#476), the last piece of the CLI registry, with every review item answered in one round, and for splitting the test isolation fix out into #479.
+  - @shenlvkang-collab for the `/resume` title fix (#457) and the careful diagnosis behind it.
+  - @julian3xl for the Session Manager row fix (#477), their first contribution.
+
+### Patch Changes
+
+- 69a7128: fix(sessions): stop pinning the `w1-myapp` placeholder as Claude's session title. Local Claude spawns passed the tab name as `--name`, which is also the `/resume` picker entry and the terminal title, and a pinned title stops Claude generating its own, so every conversation of a case showed up in `/resume` as the same `w1-myapp` and none got a generated title. Only a name the user chose is pinned now; placeholder and auto-named tabs let Claude title the conversation again. Renaming a Claude tab also reaches `/resume`: the new name is appended to the conversation's transcript as the `custom-title` row `/rename` writes (a tab that was spawned with `--name` keeps re-appending its own title until its next respawn, so the rename wins from then on). Orchestrators that rely on a fixed peer name should give workers a descriptive `sessionName` rather than a `w<N>-` one.
+
+## 1.32.1
+
+### Patch Changes
+
+- 13e652e: Terminal copy: copying text out of a Claude Code or Codex pane no longer puts the pane's two-column transcript gutter on the clipboard, so pasted lines arrive flush instead of indented (#469). The width comes from the CLI registry (`capabilities.transcriptGutter`, 2 for claude and codex, measured on live panes) and is only a ceiling: a selection only ever shifts as a block, so its own indentation survives. Other CLIs and shells are untouched. It works in split panes and detached session windows too, and can be turned off per device in App Settings under Selection & clipboard.
+- 13e652e: Sessions: recovering a Claude session whose tmux pane had died relaunched `claude --session-id <id>`, which Claude refuses once that id has a transcript, so the pane died again straight away and the conversation was stranded. The relaunch now resumes the conversation (`--resume <id> || --session-id <id>`), including when tmux lost the whole session (#467).
+- 00f022c: Terminal: when a burst of output overflows the render queue and a frame has to be dropped, the repaint that repairs it is now retried until it actually happens, instead of being scheduled once and silently skipped when another load was in flight (#470).
+- 13e652e: Mobile: a long press on blank terminal space on Android Chrome no longer opens the keyboard and blanks the terminal (#471, fixes #360). The long-press guards are now armed before the press is checked for selectable text, so a press on empty space is swallowed the same way a press on a word already was.
+- 13e652e: Sessions: a tab whose agent has exited (the CLI quit, but tmux kept the pane) now says so with a muted dot and an `exited (137)` badge, instead of looking like an idle session (#466, part 1 of #446). The state is published as `paneExit` on the session and survives a restart. Nothing closes such sessions yet; that is part 2.
+- 13e652e: Docker: optional GitHub CLI and Azure CLI for private repositories (#472). Both are off by default. With `CODEMAN_INSTALL_GH=1` / `CODEMAN_INSTALL_AZ=1` as build args in `docker-compose.override.yml`, the server image gets `gh` and/or `az` (with the `azure-devops` extension) wired in as git credential helpers, so after one `gh auth login` or `az login` from a shell session, Add Case → Clone Repo can clone private GitHub and Azure DevOps repositories. `CODEMAN_AGENT_IMAGE_INSTALL_GH` / `_AZ` do the same for the Docker-case agent image, and only then are the sign-ins copied into new case containers. In multi-user mode a non-admin's clone runs with the credential helpers cleared. This changes `server.Dockerfile`, so Compose deployments need a `Start-Codeman.sh` rebuild rather than an in-app update.
+- 13e652e: Run menu: the Gemini, Antigravity and OMP run buttons now show their own colours on every skin; they rendered in Claude blue on all skins except OG (#463). The CLI registry's `accent` values were also corrected to the colours the UI really paints, and a test now guards the stylesheet trap that caused it.
+- 13e652e: Terminal: five ways the browser terminal could silently stop being correct are fixed (#431, #464). The browser terminal and the PTY can no longer disagree about their width, which is what produced doubled lines and half-overwritten text ("text gets muffled sometimes"): there is now one function that sizes the terminal, and every resize is answered with the geometry the PTY really holds. A replay clear goes through the terminal's own queue, so bytes written just before it no longer fuse into the next snapshot. A renderer that stops painting after an iOS PWA is backgrounded heals itself instead of needing a reload. Every terminal capture has a deadline that also covers the response body, and a capture that runs out of time during a tab switch falls back to the bounded tail instead of leaving a blank pane. Output lost to a half-open WebSocket is repainted on the next successful open. The service worker's precache list is now generated by the build and its cache is rotated per build, so old releases' assets no longer pile up.
+- 13e652e: Docker: new `docker/Update-Codeman.sh` for the major-update path the docs used to describe by hand (#465). It rebuilds the image with `--no-cache` before taking the stack down, clears the build-artefact volumes, refuses to run when another checkout's Compose project already owns the same name, and then hands over to `Start-Codeman.sh`.
+- 13e652e: Approvals: a session that is idle only because it is waiting on its own background work (Claude Code's `1 monitor` footer chip, or a Codex background terminal) no longer raises the yellow NEEDS YOU alert or a push (#473, fixes #468). Its idle item is opened already acknowledged, and the tab, the home screens and the rail show a small `watching` badge next to the state instead. The item still exists in the Approvals Inbox, and the TUI's pending count now leaves acknowledged items out.
+- b404dac: Maintainer fixes applied while landing this batch:
+  - Terminal (#431): while another device holds the pane's width, a resize retry no longer re-fits xterm to the container and re-wraps the whole buffer every 30 s, and no longer clears scrollback for a redraw that never comes. The PTY's spawn geometry is now recorded at attach, so `ptyGeometry` never reports a size the PTY never held.
+  - Terminal (#470): the `TERMINAL DROP` crash-trail line is logged once per recovery window instead of once per dropped frame (which wiped the rest of the trail within a second), and a refresh that died at its fetch deadline is no longer retried.
+  - Sessions (#467): the resume pin also covers the branch where tmux lost the whole session, the conversation id Codeman reports follows what the relaunch actually resumed, and the test setup strips `CLAUDE_CONFIG_DIR` so the suite stays green for anyone running a separate Claude config dir.
+  - Sessions (#466): detailed sidebar and rail rows show an `exited` pill instead of `idle`, the exit is announced to screen readers, and the user manual's tab-appearance table lists the new state.
+  - Approvals (#473): a failed pane capture clears the `watching` badge rather than keeping a stale one (a failure now falls toward an alert, not toward silence), and the header bell's count leaves acknowledged items out, matching the TUI.
+  - Run menu (#463): the Gemini and Antigravity run buttons no longer render two-tone on phones, Gemini's registry accent matches its tab badge, and a test now guards the stylesheet trap for every run mode.
+  - Docker (#465): `Update-Codeman.sh` removes exactly the two build-artefact volumes it names instead of every named volume in the project, reports a failing `docker compose` instead of exiting silently, and its docs and comments were corrected. (#472): the multi-user notes say that a non-admin's seeded Docker case also receives the gh/az sign-in when those switches are on.
+
+  ### Thanks
+  - @irisitymichaelgrundberg for four PRs in this release: the `watching` badge that stops background work from raising false alerts (#473, from their own report #468), the exited-agent badge (#466) and the dead-pane resume fix (#467), both from their report #446, and the transcript-gutter strip for copied text (#469), a follow-up to their #451.
+  - @rounakdatta for the terminal resilience work (#431) and the dropped-frame recovery (#470), both from their report #464, and for answering four rounds of review in full.
+  - @opticon454 for private-repository support in the Docker images (#472), the `Update-Codeman.sh` script (#465) and the run-button colour fix (#463).
+  - @DodgyBadger for the Android long-press fix (#471), from their own report #360.
+
+## 1.32.0
+
+### Minor Changes
+
+- d47f93a: feat(custom-model): the model picker puts the ready model first
+
+  When a custom endpoint has more than one model, the Run menu's picker now promotes one row to the top instead of showing raw discovery order: the model llama-swap reports loaded and ready right now (tagged "Currently loaded", the one a launch attaches to with zero wait), else the model you last launched on that harness and endpoint (tagged "Last used", remembered per device). The endpoint's default keeps its own pill, nothing is ever auto-chosen, and a plain OpenAI-compatible server or an endpoint that does not answer within a second simply keeps the old order. The probe is bounded on the client too, so a GPU box that is off no longer holds the picker closed for five seconds.
+
+- d47f93a: feat(split-pane): view two live sessions side by side
+
+  A new Split button in the header (opt-in in App Settings, off by default, desktop only at 1180px and wider) opens a picker and shows a second live session beside the active one: its own terminal, its own WebSocket, and a divider you can drag. When either session ends the view collapses back to one pane, with Pane B promoted to the primary when it is Pane A that ended. Nothing is persisted on purpose in this first cut, so a page reload always returns to a single pane. Pane B is deliberately plainer than the primary pane (no local-echo overlay, CJK input, touch handling or keyboard accessory bar); the design and the v2 boundaries are in discussion #452.
+
+- 72d437a: Installer v2. `curl -fsSL https://getcodeman.com/install | bash` now looks at the machine first, asks at most three questions up front (how the dashboard is reached, optionally what to call the machine on your tailnet, whether to run Codeman as a background service), does the install unattended behind progress spinners with the output in `~/.codeman/install.log`, and ends on the URL with a QR code to scan. One consent covers every missing package and sudo asks for your password once. Flags pipe through `bash -s --` (`--tailscale | --lan | --local`, `--name <n> | --no-rename`, `--service | --run | --no-start`, `--yes`, `--password`, `--port`), `install.sh status` prints the URL and the QR code again, and the cloudflared question moved out of the main flow into `install.sh cloudflared`. On the Tailscale route, a `:443` that already belongs to another app gets Codeman under `https://<node>/codeman` (or on a second port) instead of a dead end, the node can be renamed opt-in (`--name`, `install.sh name`, undone by uninstall), and the HTTPS-certificates toggle is polled with the admin page opened for you. Also fixed on the way: the installer's own `npm install` no longer lets the postinstall start a stray server on port 3000 (the service crash-looped on EADDRINUSE while the done screen said "running"), the LAN address comes from the default route rather than the first interface, a hand-written LaunchDaemon on a headless Mac is left alone, a flag re-run keeps an existing dashboard password, and the done screen's start command carries the sub-path and port it was installed with.
+- d47f93a: feat(mobile): a Compose key for writing prompts on a phone
+
+  The agent keyboard bars on phones replace their Paste key with Compose: a real multiline editor with autocorrect and spellcheck, per-session drafts kept in memory only, image attach that never writes into the terminal early, and a Send that delivers the text as one paste followed by Enter, so a long prompt no longer has to be typed blind into the terminal composer. Anything you had already typed into the terminal is picked up into the editor. Shell sessions keep the direct Paste key. This is the manual first slice from #359; the auto-open setting and terminal tap routing are a separate follow-up.
+
+### Patch Changes
+
+- d47f93a: refactor(run-menu): one table-driven launcher for every external CLI
+
+  The eight near-identical per-CLI launch functions in the Run menu collapsed into one launcher driven by a table that a CI test keeps in step with the CLI registry, and a second no-id-branching guard now covers the frontend the way the backend guard covers the server. No behaviour change: the refactor was verified byte-identical across 288 launch permutations against the previous code.
+
+- e899af4: Maintainer fixes applied while landing the above. The model picker's promoted row keeps its Default pill (the promotion tag and the default marker are two pills now, and they render as pills in the picker rather than as plain text). The phone composer keeps its bottom gutter on folding devices (the generic fold rule used to erase it), a whitespace-only draft is no longer sent, and its dialog is translated on a zh-CN UI. A split that collapses mid-drag no longer leaves the page stuck in resize-cursor mode, Pane B refuses a session that has no live process, and a burst of refresh frames replays once instead of twice. The `</head>` script injections on the page render use replacer functions, so a CLI label containing `$'` can no longer splice the document into the inline script, and the frontend no-id-branching guard now catches comparisons on any variable name.
+- 6ef71ec: ### Thanks
+  - @timkjr for split-pane sessions (#453): five review rounds turned around in two days, and the pointer-capture edge case measured in a real browser rather than reasoned about.
+  - @DodgyBadger for the mobile prompt composer (#444), a first contribution that took the scope back down to one slice when asked, and that verified the delivery path against a live tmux pane and a live Claude Code composer instead of trusting the diff.
+  - @opticon454 for putting the ready model first in the picker (#459) and for collapsing the eight Run-menu launch functions into one (#458), proven byte-identical across 288 launch permutations instead of argued.
+
 ## 1.31.0
 
 ### Minor Changes

CLAUDE.md

@@ -34,6 +34,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 - To land a commit on master **without** switching branches (which would yank the tree out from under the other session): `git push origin HEAD:master` then `git branch -f master HEAD`. Never `git checkout master` to "fix" it.
 - **Never `git add -A`/`git add .`** — stage explicit paths. A sweep will pick up another session's WIP.
 - Another session's broken WIP can block `npm run build`, since `tsc` is the first step and the build gates on it. That is not your bug to fix. ⚠️ `tsc` still EMITS on type errors, so a failed `npm run build` leaves a rebuilt `dist/index.js` compiled from their tree; check what it pulled in before restarting the service. To deploy frontend-only changes past a blocked `tsc`, run the asset stage of `scripts/build.mjs` (everything after the `tsc`/`chmod` lines is independent of it).
+- **A pre-push failure in a file you did not touch is another session's WIP.** Push with `CODEMAN_SKIP_PREPUSH=1 git push` and leave it alone. (The hook already skips itself when the tree has uncommitted changes in a path it checks, so this mostly happens once the other session has committed.)
 
 ## CRITICAL: Always Test Before Deploying
 
@@ -77,7 +78,7 @@ When user says "COM":
 
 CI runs `npm run check:lockfile` on every push/PR, so lockfile drift fails the build even if the `version-packages` script is bypassed.
 
-**Version**: 1.31.0 (must match `package.json`)
+**Version**: 1.33.3 (must match `package.json`)
 
 ## Project Overview
 
@@ -112,6 +113,8 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 | Gesture playground             | `npm run dev` **in** `packages/gesture-control/` (standalone vite demo, fake tabs)                                                                                                                             |
 | Check public-asset formatting  | `npm run check:public-assets` (prettier-checks `src/web/public/**` text assets; `scripts/check-public-assets.mjs`)                                                                                             |
 | Frontend JS syntax check       | `npm run check:frontend-syntax` (`scripts/check-frontend-syntax.mjs`; runs in CI)                                                                                                                              |
+| Browser-test exclusion check   | `npm run check:browser-excludes` (`scripts/check-browser-test-excludes.mjs`; runs in CI, <1s). Fails if a test importing playwright/puppeteer is still collected by `config/vitest.ci.config.ts`; add it to `BROWSER_TEST_GLOBS` in `config/test-suites.ts` |
+| Pre-push hook                  | Installed by `npm install` (`scripts/git-hooks.mjs`, via postinstall): runs the static CI checks (~10-40s) before `git push`. Skip once: `CODEMAN_SKIP_PREPUSH=1 git push`. Skips itself with a notice when HEAD is not the pushed commit or the tree has uncommitted changes the checks would read. Marker-owned, so a hand-written `pre-push` is never overwritten; installs ONLY into the repo's own `<git-common-dir>/hooks` (worktree-safe; a `core.hooksPath` elsewhere, e.g. a global one, is left alone) |
 | Excluded-suite runners         | `npm run test:browser` · `npm run test:mobile` · `npm run test:perf` · `npm run test:all` (everything, environmental failures included) — see Testing                                                           |
 | Production start               | `npm run start`                                                                                                                                                                                                |
 | Production logs                | `journalctl --user -u codeman-web -f`                                                                                                                                                                          |
@@ -120,7 +123,7 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 | Dependency doctor              | `codeman doctor` (alias `check-deps`; `--json`, `--category core\|office\|other`). Probes Node/Claude CLI/tmux/LibreOffice/MS Office against `config/dependency-registry.ts`; engine is pure given an injectable `ProbeHost` |
 | Multi-user accounts            | `codeman users add <name>` / `passwd <name>` / `list` / `rm <name>` (writes `~/.codeman/users.json`, mode 0600; see Multi-user mode)                                                                            |
 
-**CI**: `.github/workflows/ci.yml` (push to master/main + PRs, Node 22) runs two jobs: **(1)** `check:lockfile`, `typecheck`, `lint`, `check:frontend-syntax`, `format:check`, then a **server boot smoke test** (`tsx src/index.ts web --port 3151` must answer `/api/status` within 30s); **(2)** the **unit/integration test suite** via `npm run test:ci` (`config/vitest.ci.config.ts` — excludes the browser-driven `test/mobile/**` suite, `perf-*` benchmarks, and 9 Playwright tests; globs live in `config/test-suites.ts`), followed by the **`packages/xterm-zerolag-input` package tests** (a bare `npx vitest run` in that directory; its vitest is hoisted by the root `npm ci`, so no separate install, and `npm test` at the root does NOT run them). `npm test` runs this same config, so local green == CI green. Tests are tmux-safe in CI: `TmuxManager` no-ops all shell commands under `VITEST` (see Testing). A third workflow, `wiki-sync.yml`, fires only on master pushes touching `docs/wiki/**` and mirrors that directory to the GitHub wiki (browser edits to the wiki are overwritten by the next sync, so fix pages via `docs/wiki/`).
+**CI**: `.github/workflows/ci.yml` (push to master/main + PRs, Node 22) runs two jobs: **(1)** `check:lockfile`, `typecheck`, `lint`, `check:frontend-syntax`, `check:browser-excludes`, `format:check`, then a **server boot smoke test** (`tsx src/index.ts web --port 3151` must answer `/api/status` within 30s); **(2)** the **unit/integration test suite** via `npm run test:ci` (`config/vitest.ci.config.ts` — excludes the browser-driven `test/mobile/**` suite, `perf-*` benchmarks, and 14 Playwright tests; globs live in `config/test-suites.ts`), followed by the **`packages/xterm-zerolag-input` package tests** (a bare `npx vitest run` in that directory; its vitest is hoisted by the root `npm ci`, so no separate install, and `npm test` at the root does NOT run them). `npm test` runs this same config, so local green == CI green. Tests are tmux-safe in CI: `TmuxManager` no-ops all shell commands under `VITEST` (see Testing). A third workflow, `wiki-sync.yml`, fires only on master pushes touching `docs/wiki/**` and mirrors that directory to the GitHub wiki (browser edits to the wiki are overwritten by the next sync, so fix pages via `docs/wiki/`).
 
 **Code style**: Prettier (`singleQuote: true`, `printWidth: 120`, `trailingComma: "es5"`) — config lives in the **`"prettier"` key of `package.json`**, not a `.prettierrc` (keeps the repo root short; editors read it natively). `.prettierignore` stays at the root because Prettier resolves it relative to cwd. ESLint flat config (`config/eslint.config.js`) allows `no-console`, warns on `@typescript-eslint/no-explicit-any`. Ignores: `app.js`, `scripts/**/*.mjs`, `src/web/public/vendor/**`, `scripts/remotion/**`.
 
@@ -128,12 +131,13 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 
 ## Common Gotchas
 
-- **Single-line prompts only** — `writeViaMux()` sends text+Enter separately; multi-line breaks Ink. ⚠️ **Input must END with `\r` or Enter is never sent**: `sendInput()` only issues `send-keys Enter` when the payload contains a carriage return, a `\r`-less `POST /api/sessions/:id/input` still succeeds (send-and-wait even reports `delivered:true`) while the text sits unsubmitted on the composer, and any `wait` burns its whole timeout on a turn that never started. Embedded newlines are stripped, not rejected, so `"echo A\necho B\r"` runs the joined `echo Aecho B`. ⚠️ **Claude Code 2.1.277+ ignores Enter for the first 30-50 s after the composer paints** while still taking the typed text (measured 2026-09-19: an Enter at 28 s stranded the prompt, one at 51 s submitted it), so text+`\r` sent at readiness sits unsent with `0 tokens` and a `wait` burns its timeout. So the SERVER verifies every programmatic write that carried a `\r`: `SubmitVerifier` (`session-submit-verifier.ts`, armed from `writeViaMux`) reads the pane on a 2 s to 60 s schedule and re-sends Enter only while the LAST composer line (the CLI's own `promptGlyph`) verifiably still holds the head of what was sent; an empty composer, other text, or no composer line at all (a shell, a direct-PTY session) ends it, and a newer write replaces the schedule. The skill's `sendwait` keeps its own copy of the loop (`_composer_text` in `skills/codeman/preamble.sh`) for servers that predate this. The `shift+tab` footer only means the composer painted, never that Enter is accepted
+- **Single-line prompts only** — `writeViaMux()` sends text+Enter separately; multi-line breaks Ink. ⚠️ **Input must END with `\r` or Enter is never sent**: `sendInput()` only issues `send-keys Enter` when the payload contains a carriage return, a `\r`-less `POST /api/sessions/:id/input` still succeeds (send-and-wait even reports `delivered:true`) while the text sits unsubmitted on the composer, and any `wait` burns its whole timeout on a turn that never started. Embedded newlines are stripped, not rejected, so `"echo A\necho B\r"` runs the joined `echo Aecho B`. ⚠️ **Claude Code 2.1.277+ ignores Enter for the first 30-50 s after the composer paints** while still taking the typed text (measured 2026-09-19: an Enter at 28 s stranded the prompt, one at 51 s submitted it), so text+`\r` sent at readiness sits unsent with `0 tokens` and a `wait` burns its timeout. So the SERVER verifies every programmatic write that carried a `\r`: `SubmitVerifier` (`session-submit-verifier.ts`, armed from `writeViaMux`) reads the pane on a 2 s to 60 s schedule and re-sends Enter only while the LAST composer line (the CLI's own `promptGlyph`) verifiably still holds the head of what was sent; an empty composer, other text, or no composer line at all (a shell, a direct-PTY session) ends it, and a newer write replaces the schedule. The skill's `sendwait` keeps its own copy of the loop (`_composer_text` in `skills/codeman/preamble.sh`) for servers that predate this. The `shift+tab` footer only means the composer painted, never that Enter is accepted. ⚠️ **A prompt must never be written into the pane as ONE burst**: Claude Code 2.1.283 takes a `<text>\r` burst of ~100+ chars as a paste, its `\r` lands as a NEWLINE and the prompt strands (a later raw `\r` does not recover it, a tmux `send-keys Enter` does). So `POST .../input` routes a plain prompt (`isPlainPromptInput()`, route-helpers.ts: printable text + exactly one trailing `\r`) through `writeViaMux` even without `useMux`, AWAITED so the browser's serialized POST fallback keeps frame order; raw frames and an explicit `useMux:false` keep the direct write
 - **ESM only** — Never `require()`, use `await import()`. `tsx` masks CJS/ESM issues in dev but production breaks
 - **Package ≠ product name** — npm: `aicodeman`, product: **Codeman**. Release renames tags accordingly. Both `aicodeman` and `codeman` bin aliases are installed (`package.json` `bin`)
 - **Global regex `lastIndex`** — Shared `g`-flag patterns in loops must reset `lastIndex = 0` first, or use the `execPattern()` helper in `utils/regex-patterns.ts` (resets automatically)
 - **`envOverrides` flow `CLAUDE_CODE_*` / `OPENCODE_*` / `CODEX_*` / `GEMINI_*` / `GOOGLE_*` / `ANTIGRAVITY_*` / `PI_*` / `GROK_*` / `XAI_*` / `DSH_*` / `DEEPSEEK_*` env vars, plus exact-key `CLAUDE_CONFIG_DIR`** — Set via `POST /api/sessions { envOverrides }`, stored on `Session._envOverrides`, exported by `tmux-manager.buildEnvExports()` at spawn time, persisted in `SessionState.envOverrides`. **Do NOT** write these to `<case>/.claude/settings.local.json` — that's the old path and creates UI/disk drift. (`GOOGLE_*` is the deliberately-broad Vertex-AI namespace for Gemini — see Multi-CLI prefix discipline.) `CLAUDE_CONFIG_DIR` (#255, exact match via `ALLOWED_ENV_KEYS` in `schemas.ts`) points a session at a separate Claude account/config dir for per-client subscriptions; it persists to state.json (a path, not a secret; losing it on restart would silently switch accounts). ⚠️ A relocated config dir writes transcripts outside `~/.claude/projects`, so the response viewer, subagent windows, ultracode panel and Read My Mind capture go blind for that session unless the user symlinks `projects` back into the shared tree (`ln -s ~/.claude/projects <configDir>/projects`). ⚠️ It is also one of claude's `privilegedEnvKeys` (Custom Model Endpoint Profiles, since it can redirect a session's traffic same as any other injected var), so in multi-user mode setting it via `envOverrides` is admin-only, and a non-granted owner's already-persisted `CLAUDE_CONFIG_DIR` is stripped on reboot-restore — silently returning that session to the default Claude account rather than the one it was pointed at (see `session-env-clamp.ts`). → [architecture-invariants#per-session-env-overrides-exact-key-allowlist-and-claude_config_dir](docs/architecture-invariants.md#per-session-env-overrides-exact-key-allowlist-and-claude_config_dir)
 - **Effort is NOT an env var** — never carry effort as `CLAUDE_CODE_EFFORT_LEVEL`: the env var hard-locks effort and blocks in-session `/effort` switching (incl. ultracode). It flows as the dedicated `effort` payload field → `Session._effort` → `claude --effort <level>` for regular levels incl. `max` (the settings `effortLevel` key is `enum(["low","medium","high","xhigh"]).catch(undefined)` — `max` gets SILENTLY dropped there), or `claude --settings '{"ultracode":true}'` for ultracode (rejected by `--effort`). Both are soft defaults the user can override anytime. Legacy env-var entries are auto-migrated by the Session constructor and unset from tmux sessions in `applyEnvOverrides()`. See `buildEffortCliArgs()` in `session-cli-builder.ts`, tests in `test/effort-injection.test.ts`
+- **The advisor rides `--settings`, NEVER the `--advisor` flag**: Claude Code's advisor tool (a stronger model consulted at decision points, code.claude.com/docs/en/advisor) flows as the `advisorModel` payload field → `Session._advisorModel` (persisted, so respawn and reboot restore keep it) → the `advisorModel` key in the launch's ONE `--settings` JSON, merged with ultracode and the statusLine exporter by `buildAdvisorSettings()` (`session-cli-builder.ts`). ⚠️ The flag EXITS at launch on any pairing the CLI refuses (`claude --advisor haiku` exits 1, so does Fable before its usage-credit consent), which would leave a dead pane on every respawn; the settings key degrades to "no advisor" instead. ⚠️ `isAdvisorModel()` (fable/opus/sonnet aliases or full ids, no haiku) is also the injection guard for the single-quoted argument. Soft default: `/advisor` still switches it in-session. App Settings key `claudeAdvisorModel` (SYNCED, `''` = leave it to the CLI). Remote/docker quick-start refuses it, like `effort`. Tests: `test/advisor-model.test.ts`
 - **Model choice flows via `settings.local.json`, NOT `--model` or env** — the App Settings **Claude Model** picker (`claudeModel` in `settings.json`) is read by `session-ui.js` at session create (wins over the legacy 1M-Opus toggles `opusContext1m`/`opusContext1mEnabled`), sent as the `modelOverride` payload field, and `updateCaseModel()` (`hooks-config.ts`) writes/deletes the `model` key in `<case>/.claude/settings.local.json`. This is the intended exception to the envOverrides rule above: model legitimately lives in `settings.local.json` (a soft default — in-session `/model` still works); env vars do not
 - **Multi-CLI prefix discipline** — env-var prefix is CLI-specific (`CLAUDE_CODE_*` vs `OPENCODE_*` vs `CODEX_*` vs `GEMINI_*` vs `ANTIGRAVITY_*` vs `PI_*` vs `GROK_*` vs `DSH_*`) and the `ALLOWED_ENV_PREFIXES` allowlist in `schemas.ts` enforces this; non-prefix exceptions are exact keys in `ALLOWED_ENV_KEYS` (currently only `CLAUDE_CONFIG_DIR`), never a widened prefix. Gemini additionally allowlists the **broad `GOOGLE_*`** namespace (intentional: Vertex AI auth needs `GOOGLE_CLOUD_PROJECT`/`GOOGLE_APPLICATION_CREDENTIALS`/`GOOGLE_GENAI_USE_VERTEXAI`; it is the loosest allowlist entry, affecting only the user's own spawned CLI), and Grok allowlists **`XAI_*`** for the same vendor-namespace reason (`XAI_API_KEY` is grok's documented auth var). When adding a setting, decide which CLI(s) it applies to and gate the env export accordingly. Never blanket-forward all prefixes. ⚠️ Pi is the case that proves the rule: its ~34 provider keys (`ANTHROPIC_API_KEY`, `OPENAI_API_KEY`, `HF_TOKEN`, …) share NO prefix, and the allowlist is one GLOBAL list applied by a refine with no mode context, so admitting them for pi would widen it for every mode at once — they stay out, and pi users authenticate via `/login` or the server process's own env. ⚠️ DeepSeek repeats pi's lesson exactly: a dsh `settings.yaml` can nominate ANY env var as a provider credential (`apiKeyEnv`), so only the vendor namespaces `DSH_*` (launcher inputs incl. `DSH_PERMISSION_MODE`) and `DEEPSEEK_*` (`DEEPSEEK_API_KEY`/`DEEPSEEK_BASE_URL`) are admitted; foreign provider keys authenticate from dsh's own files or the server env. Resolver design pattern: `docs/opencode-integration.md`, `docs/pi-integration.md`, `docs/grok-integration.md`, `docs/deepseek-integration.md`
 - **Zod `.optional()` rejects `null`** — accepts `undefined` only. When the frontend builds a request body with `JSON.stringify`, an explicit `null` field is preserved on the wire and fails validation with `INVALID_INPUT`. Convert `null` → `undefined` before stringifying (e.g. `field: value ?? undefined`), or declare the schema `.nullish()`. This has caused real shipped bugs twice
@@ -170,15 +174,15 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 | **Search**       | `src/search-service.ts`                                                                                | Pure in-memory core for `GET /api/search`                                                        |
 | **Attachments**  | `src/attachment-registry.ts`, `attachment-magic`, `generated-artifact-attachments`, `session-attachment-history`, `document-preview-cache`, `document-thumbnailer`, `document-conversion-limiter`, `config/attachment-guard` | See Key Patterns                                                                                 |
 | **Plan**         | `src/plan-orchestrator.ts`, `src/prompts/*.ts`, `src/templates/` (`claude-md.ts` + `case-template.md`) | `templates/` holds the CLAUDE.md scaffold generated into new cases                                |
-| **Web**          | `src/web/server.ts` ★, `sse-events.ts`, `routes/*.ts` (27 modules + barrel; `session-routes.ts` ★), `route-helpers.ts`, `ports/*.ts`, `middleware/auth.ts`, `schemas.ts`, `self-update.ts`, `plan-usage-latest.ts`, `ws-connection-registry.ts`, `heic-jpeg-converter.ts` + `heic-jpeg-worker.ts` |                                                                                                  |
-| **Frontend**     | `src/web/public/app.js` (~6.9K lines, core) + 34 modules + `sw.js` (+ `voice-pcm-worklet.js`, fetched from JS, not in the load order) | See Frontend section for the load order, which is authoritative                                  |
-| **Types**        | `src/types/index.ts` (barrel) → 22 domain files; also `src/types.ts` root re-export                    | See `@fileoverview` in index.ts                                                                  |
+| **Web**          | `src/web/server.ts` ★, `sse-events.ts`, `routes/*.ts` (one module per domain + barrel; `session-routes.ts` ★), `route-helpers.ts`, `ports/*.ts`, `middleware/auth.ts`, `schemas.ts`, `self-update.ts`, `plan-usage-latest.ts`, `ws-connection-registry.ts`, `heic-jpeg-converter.ts` + `heic-jpeg-worker.ts` |                                                                                                  |
+| **Frontend**     | `src/web/public/app.js` (core) + the modules listed in the Frontend load order + `sw.js` (+ `voice-pcm-worklet.js`, fetched from JS, not in the load order) | See Frontend section for the load order, which is authoritative                                  |
+| **Types**        | `src/types/index.ts` (barrel) → domain files; also `src/types.ts` root re-export                    | See `@fileoverview` in index.ts                                                                  |
 
 ★ = Large, central file (>50KB) — read its `@fileoverview` first. All files have `@fileoverview` JSDoc — read that before diving in. Discovery aid: `grep -l '@fileoverview' src/web/routes/*.ts` lists all route modules; same grep works for `src/types/`, `src/web/public/*.js`.
 
 **Local packages**: `packages/xterm-zerolag-input/` (local echo overlay, single-source, see Gotchas). `packages/gesture-control/` (`codeman-gesture-control`, hand-tracking overlay source, built via `npm run build:gesture`).
 
-**Config**: `src/config/` — 23 files plus the `cli-registry/` subdir, no barrel (`index.ts`) exists; import from the specific file. ⚠️ There are TWO `config/` directories: the repo-root `config/` holds tooling only (ESLint, knip, the vitest configs, `test-suites.ts`), while runtime config lives in `src/config/`. Throughout this file a bare `config/<name>.ts` in a code context means `src/config/<name>.ts`.
+**Config**: `src/config/` — flat files plus the `cli-registry/` subdir, no barrel (`index.ts`) exists; import from the specific file. ⚠️ There are TWO `config/` directories: the repo-root `config/` holds tooling only (ESLint, knip, the vitest configs, `test-suites.ts`), while runtime config lives in `src/config/`. Throughout this file a bare `config/<name>.ts` in a code context means `src/config/<name>.ts`.
 
 **Utilities**: `src/utils/` — re-exported via index. Key: `CleanupManager`, `LRUMap` (⚠ NOT in the barrel — import from `./utils/lru-map.js` directly), `StaleExpirationMap`, `BufferAccumulator`, `stripAnsi`, `Debouncer`, `KeyedDebouncer`. Also: `claude-cli-resolver`/`opencode-cli-resolver`/`codex-cli-resolver`/`gemini-cli-resolver`/`antigravity-cli-resolver`/`pi-cli-resolver`/`grok-cli-resolver`/`deepseek-cli-resolver`/`omp-cli-resolver` (CLI path resolution, one per `SessionMode`, all nine sharing the lookup chain in `cli-executable-resolver`: server PATH, then that CLI's install dirs, then an interactive login shell LAST, since it is the only step that spawns anything and it is what finds nvm/Homebrew installs under a service manager's minimal PATH; ⚠ `pi-`, `grok-` and `deepseek-cli-resolver` additionally probe the binary's identity, since `pi` is a generic name, `grok` has npm squatters, and Debian ships an unrelated `dsh`), `file-query` (⚠ Files-panel search matcher, glob-by-two-pointer, never RegExp), `string-similarity` (fuzzy matching), `regex-patterns` (ANSI/token/spinner patterns), `assertNever` (exhaustive checks), `token-validation` (auth tokens), `nice-wrapper` (process priority), `shell-resolver` (⚠ resolves a real login shell for `mode: 'shell'`; the literal string `$SHELL` used to be expanded by the SERVER's shell, which is empty in a container), `event-loop-monitor` (a sync `execSync` freezes the port while the process stays alive, leaving no trace), `dependency-checker` + `dependency-report` (the `codeman doctor` probe engine, registry in `config/dependency-registry.ts`).
 
@@ -193,106 +197,118 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 
 **Input**: `session.writeViaMux()` for programmatic/curl input via tmux `send-keys -l` + `send-keys Enter`, single-line only. Interactive **browser** input goes through a durable **exactly-once** layer: a stable `clientId` + monotonic per-session `seq` persisted to localStorage until the server ACKs, so a dropped link cannot lose or double-deliver a prompt. `ws-connection-registry.ts` supersedes only same-TAB reconnects, so two tabs on one session coexist. → [architecture-invariants#input-delivery-and-ws-resilience](docs/architecture-invariants.md#input-delivery-and-ws-resilience)
 
-**Agent wait primitives**: bounded long-polls so an agent driving Codeman from a shell can block instead of poll: `GET /api/sessions/:id/wait` (lifecycle signal), `GET /api/sessions/:id/wait-output` (literal substring, **never** regex) and `wait`/`waitTimeout` on `POST /api/sessions/:id/input`. Registry in `session-wait-registry.ts` (pure, no `Session` reference), bounds in `config/agent-wait.ts`. ⚠️ **A timeout is a 200** (`wait.timedOut`), never an error, so callers loop over short waits. ⚠️ `stop`/`blocked` are hook-driven and fire for **`claude` and `deepseek` ONLY** (`shell` installs none either); asking for one explicitly on any other mode is a 400, the default set silently drops them. `deepseek` qualifies because the DeepSeek Harness TUI REPORTS idle/working/blocked to its supervisor and Codeman is that supervisor (`deepseek-status-shim.ts`), so its signals are definitive rather than inferred — `hooksAvailableForMode()` in `session-wait-registry.ts` is the one place that rule lives. ⚠️ Send-and-wait registers the waiter BEFORE the write (a separate POST-then-wait races and reports the PREVIOUS turn), and both teardown paths must `notifySignal('exit')` BEFORE `cancelAll()`. ⚠️ Client-hangup abort listens on **`reply.raw`** guarded by `writableFinished`: on `req.raw`, `close` fires when the request BODY ends, which on a POST killed every send-and-wait instantly and no `app.inject()` test could see it. ⚠️ Worker liveness cannot come from `session.pid` — for a tmux session that is the local attach client, which outlives a worker dying inside its pane — so it is probed at the mux layer (`isPaneDead`, ~750 ms cache) on blocking waits only, never on the input hot path. ⚠️ Signals are edge-triggered with no history: one that fires with no waiter registered is unobservable afterwards, so gather fan-outs with send-and-wait or latched `wait-output` markers, never fire-and-forget-then-sequential-signal-waits. ⚠️ **`deepseek` is therefore the one non-claude mode the skill drives like claude** — `spawn_workers alpha beta:deepseek` is a mixed fleet in one call, and `sendwait`/`last_text` need no variant. Two traps are baked into the preamble rather than left to the agent: the harness's boot `idle` report lands ~300 ms BEFORE its composer paints (2.26 s vs 2.56 s, measured), so readiness must come from the composer and never from the signal, or a send-and-wait resolves on the boot edge and reports a turn that never ran; and `sendwait` asks for `wait:"stop,exit"` rather than the default set, because that set also carries `idle`, which for an external CLI is inferred from output stabilization — on a dsh worker whose TUI repaints rarely, a re-wait resolved in 0 ms with `signal:"idle"` on a turn with minutes left to run. The primitives are packaged as the **`skills/codeman` agent skill**: installable via `codeman skill install [--case <name>]` / `skill uninstall`, as a Claude Code plugin from the repo's own marketplace (`/plugin marketplace add Ark0N/Codeman` + `/plugin install codeman@codeman`, see the root-files note above; ⚠️ plugin skills are namespaced, so a Claude Code holding BOTH the plugin and a user-level or per-case copy lists the skill twice, `codeman` and `codeman:codeman`, measured 2026-09-14: neither shadows the other, both work, the docs tell users to pick one route), or auto-injected into a case's `.claude/skills/` on Claude session create behind `agentSkillEnabled` (SYNCED, default OFF). Injection is ADD-ONLY at create, marker-owned (`applyAgentSkill` in `hooks-config.ts` never touches an unmarked user copy) and refuses symlinks (this repo's own `.claude/skills/codeman` is a symlink to the source, which the injector must never write through). ⚠️ Claude Code loads a same-named USER-LEVEL skill (`~/.claude/skills/codeman`, written once by `codeman skill install` with no `--case`) over the per-case copy, and nothing used to refresh it: a stale Aug-9 user copy shadowed every fresh injection (2026-08-14: agents ran the old recipes, spawned workers serially and lost their lineage arcs), so session create now also refreshes a marker-owned user copy (`refreshUserAgentSkill`; refresh-only, never installs, foreign/symlink refused). Session create additionally pre-seeds the skill's §0 preamble cache (`seedAgentSessionPreamble` → `${XDG_CACHE_HOME:-~/.cache}/codeman-agent-<id>.sh`, local claude sessions only), single-sourced from `skills/codeman/preamble.sh` and pinned byte-identical to SKILL.md's §0 heredoc by `test/agent-skill.test.ts`, so the skill's bootstrap is a two-line loader instead of a ~150-line paste the model types out (~47 s of generation, measured live). → [architecture-invariants#agent-wait-primitives](docs/architecture-invariants.md#agent-wait-primitives), `docs/api-reference.md`
+**Agent wait primitives**: bounded long-polls: `GET /api/sessions/:id/wait`, `GET .../wait-output` (literal substring, **never** regex) and `wait`/`waitTimeout` on `POST .../input`. Registry `session-wait-registry.ts` (pure), bounds `config/agent-wait.ts`. ⚠️ A timeout is a 200 (`wait.timedOut`). ⚠️ `stop`/`blocked` exist for `claude` and `deepseek` ONLY (rule lives in `hooksAvailableForMode()`): explicit request elsewhere is a 400. ⚠️ Send-and-wait registers the waiter BEFORE the write; teardown must `notifySignal('exit')` BEFORE `cancelAll()`; hangup abort listens on `reply.raw` (guarded by `writableFinished`), never `req.raw`; liveness comes from `isPaneDead`, never `session.pid`. ⚠️ Signals are edge-triggered with no history: gather fan-outs via send-and-wait or `wait-output` markers. Packaged as the `skills/codeman` skill (`codeman skill install`, plugin marketplace, or injection behind `agentSkillEnabled`, SYNCED, default OFF): injection is add-only, marker-owned (`applyAgentSkill`), refuses symlinks, and refreshes a marker-owned user-level copy (`refreshUserAgentSkill`). → [architecture-invariants#agent-wait-primitives](docs/architecture-invariants.md#agent-wait-primitives), `docs/api-reference.md`
 
-**Agent-created case marker** (`src/agent-case-marker.ts`): a case directory `POST /api/quick-start` **creates** for an agent-driven spawn gets a `.codeman-agent-case.json` marker, so the scratch workspaces a long orchestration leaves behind (one per worker, and deleting the session does not remove them) can still be told apart from the user's real projects months later. `GET /api/cases` publishes it as `agentCreated`; `GET /api/cases/agent-created` is the read-only cleanup listing, adding `inUse` (a live session's `workingDir` is that case) and `modifiedAt`; Add Case → Manage badges each one and offers a review-then-delete sweep. The signal is the skill preamble's `X-Codeman-Agent-Origin` header (or an `agentOrigin` body field), falling back to a RESOLVED `parentSessionId` — nothing in the browser UI sets lineage, so a create request naming its spawning session came from an agent by construction, and that fallback is what still labels workers spawned by a stale skill copy. ⚠️ **Only the branch that CREATES the directory may write it.** A linked case, a cloned repo or any pre-existing path must never be labelled: the label drives a recursive-delete affordance, and mislabelling someone's repo there is the one failure mode that costs real work. `POST /api/sessions` takes an existing `workingDir`, so it writes no marker at all, by construction. ⚠️ Reading is TOTAL: anything that is not a well-formed version-1 marker (truncated write, hand-edited junk) reads as *not* agent-created rather than as a half-trusted entry, and deleting the file is the supported way to adopt a scratch case as a real one — which is what the `note` written into it tells whoever finds it. ⚠️ Removal stays on the existing `DELETE /api/cases/:name`, one name at a time, so there is exactly ONE recursive-delete path; the UI's sweep names every directory in its confirm and EXCLUDES an `inUse` case outright rather than confirming it away. ⚠️ Marker in the case dir rather than a registry under `~/.codeman`: it survives a wiped data dir or a different instance, is removed by the same `rm -rf` that removes the case (so no stale-entry pruning), and a user who runs `ls -a` can see what labelled their directory. Adding the header changed the preamble, so `CODEMAN_PREAMBLE` was bumped (1.22.0) — a cached copy is version-checked, and forgetting the bump leaves every already-seeded agent sending the old headers. Tests: `test/agent-case-marker.test.ts`, `test/routes/agent-case-marker-routes.test.ts`.
+**Agent-created case marker** (`src/agent-case-marker.ts`): a case dir that `POST /api/quick-start` CREATES for an agent-driven spawn (signal: the preamble's `X-Codeman-Agent-Origin` header / `agentOrigin` field, else a resolved `parentSessionId`) gets `.codeman-agent-case.json`, published as `agentCreated` on `GET /api/cases`; `GET /api/cases/agent-created` is the cleanup listing (`inUse`, `modifiedAt`) behind Add Case → Manage. ⚠️ Only the branch that CREATES the directory may write it: never label a linked case, cloned repo or pre-existing path (it drives a recursive delete). ⚠️ Reading is total: anything but a well-formed v1 marker reads as not agent-created. ⚠️ Removal stays on `DELETE /api/cases/:name` (the ONE recursive-delete path), and the sweep excludes `inUse` cases. ⚠️ Changing the preamble's headers requires bumping `CODEMAN_PREAMBLE`. → [architecture-invariants#agent-created-case-marker](docs/architecture-invariants.md#agent-created-case-marker)
 
 **Agent preamble cache GC**: the §0 preamble seeded per claude session (`$XDG_CACHE_HOME/codeman-agent-<id>.sh`) is now REMOVED with the session (`removeAgentSessionPreamble` from `_doCleanupSession`, `killMux` only — a detach leaves the session recoverable and its agent would come back to a loader whose file we deleted) and swept at boot (`pruneAgentSessionPreambles(this.sessions.keys())`, once, after restore, so every session this instance owns is in the keep set). Nothing removed them before: 236 leftovers measured on a working machine, the oldest three weeks old. ⚠️ The sweep needs BOTH guards — never a live session's file at any age (the two-line loader reads it mid-run), and `AGENT_PREAMBLE_MAX_AGE_MS` (7d) of age on top, which is what keeps ANOTHER instance's sessions (whose ids this process cannot see) out of the blast radius. Losing one is degradation, not breakage: the §0 fallback block rewrites it. Tests live with the seed's in `test/agent-skill.test.ts`.
 
 **Idle detection**: Multi-layer (completion message → AI check → output silence → token stability). See `docs/respawn-state-machine.md`.
 
-⚠️ **A `❯` sighting is NOT the end of a turn, and neither is silence.** Claude redraws the composer (`❯`) about once a second all through a turn, so the old "saw a ❯, wait 2s → idle" rule flipped every working session to idle two seconds in (measured: a session mid-tool-call at 17 minutes reporting `status:"idle"`). Its working indicator is `✻ Actualizing… (13m 23s · ↓ 47.5k tokens)`: the glyph animates through `· ✢ ✳ ∗ ✻ ✽`, the gerund is randomized, and the finished line (`✻ Cooked for 2m 49s`) carries the same glyph, so neither `SPINNER_PATTERN` (braille, not what current versions draw) nor a keyword list can see it. Matching the new line in the STREAM does not work either: tmux ships partial repaints, so the whole line reaches the PTY only every few tens of seconds. So: `_confirmIdle()` (session.ts) requires the pane to go quiet, and then asks the SCREEN via `capturePaneText()` + `CLAUDE_WORKING_LINE_PATTERN` before believing it; a sustained run of repaints (`session-activity.ts`, pure + unit tested) is what marks a turn as started, with the same screen probe vetoing keystroke echo. Idle now lands ~3-5s after a turn ends instead of 2s into one. ⚠️ **The composer glyph and the working line are per-CLI registry DATA** (`capabilities.workDetect`, #385), not Claude constants: claude declares `❯` plus the pattern above, codex declares `›` plus `[Ee]sc to interrupt`, and a CLI that declares neither falls back to Claude's pair, which is what every session used before the registry carried one. Before that, this whole mechanism was gated Claude-mode-only on the reasoning that an external CLI has no `❯`, which was true and still left every Codex session reporting `idle` for its entire life. ⚠️ `workingLine` is config-supplied (a user `clis.json` can set it) and the compiled pattern runs on the PTY hot path, so it goes through `compileVersionRegex()` in BOTH the schema refine and `_workingLinePattern()`: a nested quantifier there is a ReDoS against the event loop, and the helper returns null rather than throwing so the fallback is structural.
+⚠️ **A `❯` sighting is NOT the end of a turn, and neither is silence.** Claude redraws the composer all through a turn, and its working line (`✻ Actualizing… (13m 23s · …)`) is invisible to `SPINNER_PATTERN`, keyword lists and the raw stream. `_confirmIdle()` (session.ts) requires the pane to go quiet AND the SCREEN (`capturePaneText()` + the working-line pattern) to agree; a sustained run of repaints (`session-activity.ts`) marks a turn as started. ⚠️ The composer glyph and working line are per-CLI registry DATA (`capabilities.workDetect`), never Claude constants; a CLI declaring neither falls back to Claude's pair. ⚠️ `workingLine` is config-supplied and runs on the PTY hot path, so it must compile through `compileVersionRegex()` in BOTH the schema refine and `_workingLinePattern()` (ReDoS guard; null, not throw). → [architecture-invariants#idle-detection-composer-glyph-and-working-line](docs/architecture-invariants.md#idle-detection-composer-glyph-and-working-line)
 
-**Workspace-trust dialog auto-accept** (`session-trust-dialog.ts`, pure + unit tested): Claude Code asks once per directory ("Is this a project you created or one you trust?") before it will read or edit anything, and since Codeman sessions run permission-skipping or classifier-guarded modes the answer is always yes, so a session parked on that dialog is simply stuck. ⚠️ **Match the compacted SCREEN, never the stream.** tmux repaints a row by writing each word and then a cursor-forward (`\x1b[C`) instead of a space, and Ink colours each word separately, so the wire carries `I\x1b[Ctrust\x1b[Cthis\x1b[Cfolder`; stripping the escapes leaves `Itrustthisfolder`, because the spaces are not there to strip, they were never sent. A plain `includes('trust this folder')` therefore never matched a single chunk and the auto-accept was silently DEAD for every session that hit the dialog. `compactScreenText()` removes ALL whitespace instead (plus the `ESC ( B` charset selects that `stripAnsi` does not cover, which would otherwise land inside a phrase as a literal `(B`), which survives both that repaint style and the spaced full-screen redraw. ⚠️ **Never answer it with a blind `\r`.** The layout has changed under us at least twice, and Claude Code 2.1.252 dropped the option numbers, put "No, exit" FIRST and highlights IT by default, so the Enter that answered the old dialog now picks *exit* and the pane dies (`Pane is dead (status 1)`) seconds after the session starts. `trustDialogNextKey()` reads the `❯` marker and returns ONE step at a time (an arrow while the cursor is on the wrong option, Enter only once the screen shows it on the trust option), with the pane re-read between steps, so a dropped arrow costs a repaint instead of the session; a frame that does not say which option is highlighted returns null and waits for the next repaint. ⚠️ The LAST marked option in the text wins, because the direct-PTY fallback reads an append-only buffer where every repaint since launch is still present and an older frame must not out-vote the freshest one. ⚠️ Answering types into a live session, so THREE guards must all hold and none is redundant: a **startup-only window** (`TRUST_DIALOG_WINDOW_MS`, 90s, since the dialog renders before the main UI and leaving it open forever would let an agent transcript that merely QUOTES the dialog trigger an Enter, this file being an example), a **two-marker match** requiring a trust phrase AND one of the dialog's own confirm affordances (`isTrustDialogScreen`), and an **attempt cap** (`TRUST_DIALOG_MAX_ATTEMPTS`, 6: a keystroke can land while Ink is still mounting the widget and be dropped, which is the other half of why sessions got stuck here, but retrying forever would hammer keys into whatever came next; it was 3 while one Enter answered the dialog, and answering now costs at least two keystrokes). ⚠️ It reads `capturePaneText()` and falls back to a deliberately SHORT tail of the terminal buffer only on a direct-PTY session, which has no pane: that buffer is append-only, so a longer tail would keep re-matching a dialog answered minutes ago. ⚠️ **The scan must schedule its own next read** (`_trustDialogTimer`, cleared in `_clearAllTimers()`): it runs from the PTY `onData` handler, which was enough while one Enter answered the dialog, but the arrow that moves the cursor is the LAST output the pane produces, so a two-keystroke answer waiting on more output parks forever with the cursor sitting on the right option (measured on a live 2.1.252 spawn: cursor moved at 6 s, then nothing).
+⚠️ **A turn that ENDED waiting for its own workers is working, not idle.** Claude closes such a turn with `✻ Waiting for 1 dynamic workflow to finish` (background agents / ultracode) and resumes by itself; `capabilities.workDetect.awaitingLine` makes the idle probe count it as work. ⚠️ Claude never redraws that row, so it stays on screen after the workers finish: test it ONLY as the newest column-0 row above the composer (`isAwaitingWorkers()`), never pane-wide and never on the stream. → [architecture-invariants#idle-detection-composer-glyph-and-working-line](docs/architecture-invariants.md#idle-detection-composer-glyph-and-working-line)
 
-**Process-tree walks are bounded** (`proc-tree.ts`, pure + unit tested): `collectDescendants(pid, byParent)` is the ONE descendant traversal, fed by a single cached `ps -eo pid=,ppid=` snapshot (`refreshProcSnapshot()` in tmux-manager.ts: in-flight-shared, async because `execSync`'s timeout cannot return at all while spawnSync waits on an unkillable child, and ANY error discards the result rather than caching a truncated `ps`, which would make whole subtrees invisible to the kill path). ⚠️ **The unbounded version took a machine down** (2026-07-30): it ran `pgrep -P <pid>` once per node and recursed with no visited set, no depth limit and no node cap, so across ~28 adopted tmux trees the fan-out exploded while each `pgrep` blocked in the WSL kernel reading `/proc/<pid>/cgroup`, ending at ~13,000 `pgrep` processes in D-state, a load average above 13,000, and a machine recoverable only by restarting WSL, which cost every running session. Three properties make that impossible and each has a test: a cycle terminates (a real tree has none, a stale snapshot can still produce one), depth is capped (`PROC_WALK_MAX_DEPTH`), node count is capped (`PROC_WALK_MAX_NODES`). The fourth is structural: the function takes a snapshot and cannot spawn anything at all. ⚠️ It lives in its own module because as a private method of `tmux-manager.ts` the regression test had to keep its own COPY of the algorithm, which is a test that passes while the shipped code rots. ⚠️ Truncation is reported through `onTruncated` rather than silently, with BOTH caps named: a silent depth cap hides a deep tree exactly as effectively as a silent node cap hides a wide one.
+⚠️ **A quiet pane is not always a pane that wants you.** A CLI can declare an optional `capabilities.workDetect.watchingLine` (a monitor, background shell or cloud hand-off it is still running); the idle probe reads it into `Session.watching` and `notePrompt()` opens that idle item ALREADY acknowledged, so no surface alerts. Only `idle` is eligible, and the label is pane-derived and prompt-injectable, so a pattern must anchor on chrome only that CLI draws. → [architecture-invariants#the-watching-signal-a-quiet-pane-that-is-not-waiting-for-you](docs/architecture-invariants.md#the-watching-signal-a-quiet-pane-that-is-not-waiting-for-you). Tests: `test/session-watching.test.ts`, `test/watching-no-alert.test.ts`.
+
+**An exited agent in a live pane** (`paneExit`, #446): panes use `remain-on-exit on`, so `/exit` leaves a pane, session and pid that look alive; `TmuxManager.startPaneExitWatcher()` publishes `SessionState.paneExit` via `session:updated`. ⚠️ Never set `status: 'error'` or null the `pid` for it; the field is TRI-STATE (absent = UNKNOWN, never alive, scoped by `Session.paneExitApplies`); an absent `#{pane_dead_status}` is not 0; a path that starts a command in a pane must clear the record AND persist. A clean exit is CLOSED via `cleanupSession()` (`pane-exit-sweep.ts`): only an explicit numeric status 0 with no signal, confirmed by 2 reads, with no start/attach in flight (`paneLifecycleInFlight`) and not within 10 s of one (a startup error keeps its row); a crashed agent keeps its row. → [architecture-invariants#an-exited-agent-in-a-live-pane-paneexit](docs/architecture-invariants.md#an-exited-agent-in-a-live-pane-paneexit)
+
+**Dead-pane respawn resume pin** (`_buildRespawnPaneOptionsWithResumePin()`, session.ts): recovering a dead pane, like a custom-model `restartCli()`, must pin the conversation or claude refuses the reused `--session-id`. The pin takes the first transcript-backed candidate (chain tail, launch seed, own id), never `_claudeSessionId`, adds nothing when none is backed, and is never applied to remote or docker sessions. → [architecture-invariants#dead-pane-respawn-the-resume-pin](docs/architecture-invariants.md#dead-pane-respawn-the-resume-pin)
+
+**Workspace-trust dialog auto-accept** (`session-trust-dialog.ts`, pure): Claude Code's per-directory trust dialog is always answered yes, or the session is stuck. ⚠️ Match the compacted SCREEN (`compactScreenText()`, all whitespace removed), never the stream (tmux sends words joined by cursor-forwards, not spaces). ⚠️ Never answer with a blind `\r` (newer versions highlight "No, exit" first): `trustDialogNextKey()` returns ONE key per re-read frame (arrow, then Enter only once `❯` is on the trust option), and the LAST marked option wins. ⚠️ All three guards must hold: startup window `TRUST_DIALOG_WINDOW_MS` (90s), two-marker match (`isTrustDialogScreen`), attempt cap `TRUST_DIALOG_MAX_ATTEMPTS` (6). ⚠️ Read `capturePaneText()`; only a direct-PTY session falls back to a SHORT buffer tail. ⚠️ The scan must schedule its own next read (`_trustDialogTimer`, cleared in `_clearAllTimers()`), not rely on PTY output. → [architecture-invariants#workspace-trust-dialog-auto-accept](docs/architecture-invariants.md#workspace-trust-dialog-auto-accept)
+
+**Process-tree walks are bounded** (`proc-tree.ts`, pure): `collectDescendants(pid, byParent)` is the ONE descendant traversal, fed by one cached `ps -eo pid=,ppid=` snapshot (`refreshProcSnapshot()` in tmux-manager.ts: async, in-flight-shared, and ANY error discards the result rather than caching a truncated `ps`). ⚠️ Never walk a process tree with per-node `pgrep` or unbounded recursion (the unbounded version took a machine down): the walk must terminate on cycles, cap depth (`PROC_WALK_MAX_DEPTH`) and node count (`PROC_WALK_MAX_NODES`), and never spawn anything. ⚠️ Keep it in its own module so the test exercises the shipped code, and report truncation through `onTruncated` naming both caps, never silently. → [architecture-invariants#process-tree-walks-are-bounded](docs/architecture-invariants.md#process-tree-walks-are-bounded)
 
 **Auto-resume on usage limit** (opt-in per session, top of the Respawn tab): when Claude halts on a subscription limit, `usage-limit-patterns.ts` (pure, unit-tested) parses the reset time and `SessionAutoOps` arms a timer for reset+2min, then sends Esc + `continue`. ⚠️ Respawn cycles are blocked while paused (`isLimitPaused` guard in `onIdleDetected`), which is what prevents `/clear` from wiping the paused conversation. Claude-mode only. → [architecture-invariants#auto-resume-on-usage-limit](docs/architecture-invariants.md#auto-resume-on-usage-limit)
 
-**Plan-usage chip** (`showPlanUsageLimits`, per-device: desktop default **ON**, handhelds OFF via the mobile block in `getDefaultSettings()`): resolve DISPLAY ONLY through `planUsageChipEnabled()` in settings-ui.js, which backs the two call sites that must never disagree (the App Settings checkbox, the chip's visibility). The SAME persisted setting also doubles as the server-side telemetry COLLECTION switch — `readPlanUsageTelemetryEnabled()` (hooks-config.ts) reads it fresh from `settings.json` at every claude session create/respawn (`TmuxManager.createSession`/`respawnPane`), so it applies uniformly to every claude-creation path (interactive Run, cron, Ralph Loop API, quick-start) with no per-session state and no per-request field — a Codeman restart cannot silently kill it (there is nothing per-session to lose). ⚠️ An ABSENT key reads as ON (mirroring `readWorkspaceHooksEnabled()`), so the default is resolved by the READER and `GET /api/settings` stays a plain read that never writes: a reconcile write there ran on every page load and could replace an unreadable `settings.json` with a one-key file. ⚠️ A save sends `showPlanUsageLimits` ONLY when it FLIPS the chip on that device (`planUsageCollectionFlip()` in settings-ui.js): the chip defaults OFF on handhelds, so a phone saving its font size used to persist `false` and switch collection off for every desktop. Claude data comes from Codeman's marked `statusLine.command` exporter (injected as an EPHEMERAL `claude --settings` CLI flag, never written to disk — see `resolveStatusLineCliCommand`), which POSTs `rate_limits` to `POST /api/status-telemetry`, never overwrites a user's hand-authored statusLine (it WRAPS it instead — `findEffectiveUserStatusLineCommand`), and prints the footer through. Main Codex usage comes from a read-only host `account/rateLimits/read` app-server poll at startup and every 5 minutes; exclude model-specific buckets such as Spark, and omit the Codex row when no signed-in limit is available. Distinct from auto-resume, which reacts to Claude's limit *message* rather than showing live %. → [architecture-invariants#plan-usage-chip-statusline-telemetry](docs/architecture-invariants.md#plan-usage-chip-statusline-telemetry), `docs/usage-limits-display-plan.md`
+**Plan-usage chip** (`showPlanUsageLimits`, per-device: desktop default **ON**, handhelds OFF): resolve DISPLAY only through `planUsageChipEnabled()` (settings-ui.js). The same setting is the server-side COLLECTION switch, read fresh by `readPlanUsageTelemetryEnabled()` (hooks-config.ts) at every claude create/respawn. ⚠️ An ABSENT key reads as ON in the reader; `GET /api/settings` must never write. ⚠️ A save sends `showPlanUsageLimits` ONLY when it flips the chip on that device (`planUsageCollectionFlip()`), or a phone switches collection off for every desktop. Claude data comes from the statusLine exporter, injected as an EPHEMERAL `claude --settings` flag (`resolveStatusLineCliCommand`), never written to disk, WRAPPING a user's own statusLine, posting to `POST /api/status-telemetry`. Codex comes from a read-only `account/rateLimits/read` poll (main bucket only). → [architecture-invariants#plan-usage-chip-statusline-telemetry](docs/architecture-invariants.md#plan-usage-chip-statusline-telemetry), `docs/usage-limits-display-plan.md`
 
 **Orchestrator**: State machine that turns a user goal into a phased plan and drives it to completion: `idle → planning → approval → executing → verifying → (replanning) → completed/failed`. `OrchestratorLoop` (engine) delegates plan generation to `orchestrator-planner` and per-phase verification gates to `orchestrator-verifier`, executing phases via team agents/`task-queue`. State persists under the `orchestrator` key in `state.json`. Distinct from Ralph (single-session autonomous loop) — orchestrator coordinates multi-phase, multi-agent execution. See `docs/orchestrator-loop-architecture.md`.
 
 **Cron (`CronJob`s)**: saved, named jobs on a recurring schedule (`once`/`interval`/`daily`/`weekly`) with per-job run history. ⚠️ **Distinct from the legacy `ScheduledRun`** (`/api/scheduled`, a run-now duration-bounded loop); the two never interact and keep separate `Scheduled*` / `Cron*` names. `CronService` **reuses the existing session layer** rather than rebuilding tmux logic. Next-run math is pure and unit-tested in `cron-time.ts` (server-local timezone). The schedule is advanced BEFORE launch so a slow launch cannot re-trigger. → [architecture-invariants#cron-jobs](docs/architecture-invariants.md#cron-jobs), `docs/cron-discovery.md`
 
-**Remote sessions + remote SSH cases**: a case can point at a remote host. The agent runs inside a durable remote `tmux -L codeman-remote` (session name `codeman-ssh-<id>`, deliberately failing the remote Codeman's `SAFE_MUX_NAME_PATTERN` so an instance on the target host never adopts it), fronted by a LOCAL tmux pane running `ssh`. Attached (`owned:false`) sessions **detach, never kill** on tab close; owned ones propagate `kill-session`. A bounded-backoff watcher auto-reconnects dropped sessions (`remoteAutoReconnect`, default ON). ⚠️ **It revives ONLY when the durable remote tmux session is verifiably still alive** (`remoteTmuxSessionAlive()`, a `has-session` probe over ssh, #355): a clean agent exit (Ctrl-C, Ctrl-D, `exit`) tears that session down, and `isPaneDead()` cannot tell it from a transport drop, so the watcher used to relaunch a FRESH agent after every clean exit (claude only looked fine because its `|| --resume` fallback masked it). An unreachable host answers `undefined`, which also means do not revive. ⚠️ `has-session` prints NOTHING on success, so the probe is classified by EXIT STATUS (`classifyRemoteAliveExit`: 0 alive, ssh's 255 or a timeout unknown, anything else gone); reading stdout classified every live session as gone and silently disabled transport-drop reconnects. The answer is cached per session and forgotten whenever the pane is seen alive again, or a stale `true` from one transport drop would revive the next clean exit. ⚠️ **File reads in a remote case are the second ssh surface** (#415, `src/remote-files.ts`): they go through `buildSshConnectionArgs()` as well, a browser-supplied path is only ever a `shellescape`d token, an unreachable host answers 502 (never 404), the size cap uses the REMOTE size, and no remote file is ever copied onto the server's disk — which is why writes, office previews and thumbnails are deliberately unsupported over ssh (the `PUT` guard sits BEFORE the local path validation, or a same-named local directory such as an sshfs mount takes the write). The probe's symlink resolution FAILS CLOSED (a path it cannot canonicalize is a 404, never its own unresolved string: the directory-only fallback let a `notes.txt -> ~/.ssh/id_rsa` link pass containment), and ssh children are BOUNDED by `src/remote-ssh-limiter.ts` plus one batched probe per attachment-history listing, because terminal output in a remote session is written on the remote host and a prompt-injected agent can print hundreds of `codeman://attach` links. The ATTACHMENT routes (a clicked path outside the case dir) go through the same layer, and which host a record is read from follows the SESSION, never the path string. ⚠️ **Command-injection surface: every ssh command line must flow through `buildSshConnectionArgs()`**, which `shellescape`s every user field. Never hand-build an ssh line elsewhere. ⚠️ Run flows must route remote cases through `POST /api/quick-start`, not `POST /api/sessions` (which stat-validates `workingDir` locally and has no `caseName`). → [architecture-invariants#remote-sessions-over-ssh](docs/architecture-invariants.md#remote-sessions-over-ssh), [#remote-ssh-cases](docs/architecture-invariants.md#remote-ssh-cases), `docs/remote-sessions.md`
+**Remote sessions + remote SSH cases**: a case can point at a remote host. The agent runs in a durable remote `tmux -L codeman-remote`, fronted by a LOCAL tmux pane running `ssh`. Attached (`owned:false`) sessions **detach, never kill**; owned ones propagate `kill-session`. Auto-reconnect (`remoteAutoReconnect`, default ON) revives ONLY when `remoteTmuxSessionAlive()` proves the remote session alive. ⚠️ Classify that probe by EXIT STATUS (`classifyRemoteAliveExit`), never stdout. ⚠️ **Command-injection surface: every ssh command line must flow through `buildSshConnectionArgs()`**; never hand-build one. ⚠️ Remote file reads (`src/remote-files.ts`, attachment routes too) take browser paths only as `shellescape`d tokens, resolve symlinks fail-closed, cap on the REMOTE size, never copy to local disk, are bounded by `src/remote-ssh-limiter.ts`, and pick the host from the SESSION, never the path; no writes over ssh (the `PUT` guard must precede local path validation). ⚠️ Route remote cases through `POST /api/quick-start`, not `POST /api/sessions`. → [architecture-invariants#remote-sessions-over-ssh](docs/architecture-invariants.md#remote-sessions-over-ssh), [#remote-ssh-cases](docs/architecture-invariants.md#remote-ssh-cases), `docs/remote-sessions.md`
 
-**Wake-on-LAN (`remote-wake.ts`)**: an optional `RemoteHost.wakeMac` (Codeman builds the magic packet itself) or `RemoteHost.wakeCommand` (single executable path, run without a shell, takes precedence) lets the INPUT route, `POST /api/sessions/:id/wake`, and the user's own create/attach request (`POST /api/quick-start`, `POST /api/sessions` with `attachRemoteSession`, via `ensureHostAwake`) wake a sleeping host instead of writing into a stalled ssh pane. ⚠️ An explicit request — input, the wake button, or the user pressing Run/Attach — and NOTHING else may wake: the auto-reconnect watcher, `handleRemoteSessionDropped`, boot recovery and `cron-service.ts` have no access to the registry (a wake there would re-wake the host seconds after every suspend, and the create wake is wired in the route rather than the shared session service for exactly that reason), which `test/remote-wake.test.ts` asserts as two wiring guards — the second also pins that `server.ts` holds the registry for its LIFETIME only (`drop` on cleanup, `stop` on shutdown) and never calls a waking method. `GET /api/sessions/:id/reachability` merely probes and never wakes. Detection is a throttled bare TCP probe — deliberately no `ServerAliveInterval`, because keepalives move bytes into an idle connection every interval and that is what a byte-threshold idle detector must not read as activity. ⚠️ A host behind `jumpHost`/`socksProxy`/a `ProxyCommand` option is reachability-UNKNOWN (`isProbeable()`): the probe connects to `host:port`, which such a host does not answer even while ssh works, so the registry never buffers for it, never gates create/attach on it (`'unprobeable'`), and `/reachability` answers `reachable: null, probeable: false` — the banner keys on a PROVEN `false`, and the banner's 30 s poller runs only for a host with a wake target (a timer connecting to a host Codeman cannot wake is the same timer-driven traffic the keepalive rule forbids). Input arriving during a wake is buffered (a chunk over 4 KB is dropped whole, never delivered as a fragment; the route answers `{buffered:true}` / `{buffered:true, dropped:true}` so the caller can tell) and flushed in order after `reattachRemote()` with `fromUser` — a flush write that fails drops the rest (logged) rather than retaining it for a wake hours later; send-and-wait blocks instead and answers `OPERATION_FAILED` when the host never returns. ⚠️ In multi-user mode the attach path 403s a non-admin BEFORE the host is looked up: the wake runs an executable, and remote hosts are admin-only infra everywhere else. ⚠️ Browser keystrokes travel over the WebSocket, which deliberately does NOT pass through the registry (that is the hot path), so only the HTTP input path ever queues anything — the banner must not promise queued input for the Wake button. A request that waits on the wake (create/attach, and the button) uses the 40 s `REMOTE_WAKE_REQUEST_READY_TIMEOUT_MS`, not the 90 s session default, because the dashboard's reverse proxy cuts a request at its own 60 s `proxy_read_timeout`. The wake fields are re-read from `remote-hosts.json` on recovery and, throttled+cached via `RemoteWakeDeps.resolveRemote`, for a LIVE session, since the persisted `remote` snapshot never sees a field added later. UI: the amber `#hostWakeBanner` (`host-wake-ui.js`) with Wake / "Configure WoL" → `#wakeConfigModal`. The `remote:` SSE family is session-scoped in multi-user mode; a create/attach wake names its requester (`username`) since it has no session yet. `remote-wake.ts` refuses real IO under `VITEST` like `remote-files.ts`.
+**Wake-on-LAN (`remote-wake.ts`)**: optional `RemoteHost.wakeMac` (magic packet) or `RemoteHost.wakeCommand` (single executable, no shell, takes precedence) lets HTTP input, `POST /api/sessions/:id/wake` and the user's create/attach (`ensureHostAwake`) wake a sleeping host. ⚠️ Only an explicit user request may wake: never give the registry to the auto-reconnect watcher, `handleRemoteSessionDropped`, boot recovery or `cron-service.ts`, and `GET /api/sessions/:id/reachability` must never wake. ⚠️ Detection is a throttled bare TCP probe; never add `ServerAliveInterval`, and a `jumpHost`/`socksProxy`/`ProxyCommand` host is reachability-UNKNOWN (`isProbeable()`): never buffer, gate or banner on it. ⚠️ In multi-user mode a non-admin attach 403s BEFORE host lookup. ⚠️ WS keystrokes bypass the registry, so the banner (`host-wake-ui.js`) must not promise queued input. Waiting requests use the 40 s `REMOTE_WAKE_REQUEST_READY_TIMEOUT_MS`. → [architecture-invariants#remote-ssh-cases](docs/architecture-invariants.md#remote-ssh-cases)
 
-**Docker cases**: a case can point at a **container**, with any of the CLI run modes running inside it. Like remote-SSH this is a **LOCATION OVERLAY on cases, never a `SessionMode` of its own**. Exactly one long-lived container **per case**, shared by all its sessions, so killing a session kills only that session's in-container tmux and **never** `docker stop` while siblings remain. The workspace is a real host dir bind-mounted at the **same absolute path**, which is what keeps file-routes/watchers on real host bytes and makes the in-container transcript projHash match the host. Credentials are **seeded** (RO mount, copied into the container once) rather than shared RW, so in-container CLIs never write refreshed tokens back to the host, and bind mounts are excluded from `docker commit` so exports stay secret-free. **NEVER a create-time `-e` for secrets, NEVER `--privileged`, NEVER the docker socket.** Config drift is detected via a label hash and a drifted launch is REFUSED rather than silently launched with stale config. ⚠️ A case may instead **ADOPT** a container the user already runs (`DockerCase.owned === false`, mirror of remote-SSH's `owned:false`): Codeman only `exec`s into it and never creates, starts, stops, restarts or removes it, so a missing or stopped container FAILS CLOSED with an actionable message instead of being fixed. Absent = owned, so existing cases are byte-identical. ⚠️ An ADOPTED container may back SEVERAL cases at different in-container directories (`classifyAdoptContainerConflict` in `docker-hosts.ts`: an exact twin on the same container AND directory is refused, an owned container still backs exactly one case, and a container another user adopted is refused), which is what the Add Case panel's "copy an existing case" picker relies on; the wire carries `CaseInfo.docker.owned` ONLY when false, so the picker tests `=== false`, never truthiness. The guarantee is enforced at four independent layers because it cannot be observed by using the feature: `buildDockerStopCommand`/`buildDockerRemoveCommand` throw during pure STRING CONSTRUCTION, `removeDockerContainer` refuses again, drift reports "none" (an adopted container carries no `codeman.confighash` label, so a real comparison would 409 the launch forever), and the boot reaper skips it. ⚠️ Two lifecycle touches the original design missed and that are easy to re-introduce: the full-image export `docker commit`s the container (refused for an adopted case) and the workspace export `docker pause`s it first (skipped — it freezes the owner's processes for the length of the tar). ⚠️ `owned` is applied AFTER `dockerConfigHash`, which takes an explicit field list, or every pre-existing case would trip the drift gate at once. ⚠️ Run modes for a container case come from the CONTAINER (`availableModes`, live-probed): gating the run menu on HOST CLIs (#201) is right for local sessions and wrong here, since a host with no `claude` may run a container that ships one. ⚠️ **A failed probe means opposite things per ownership** — for an ADOPTED case it is a fault worth reporting, for an OWNED one it is the NORMAL state before the first session (the launch chain creates the container), so treating it as a fault hid every agent mode on every freshly linked Docker case behind "start it yourself first". That is why `CaseInfo.docker.owned` is on the wire. ⚠️ Claude is launched WITHOUT `--dangerously-skip-permissions` when the container's exec user is root (Claude Code refuses the flag as root and the refusal is visible only inside the container); which flag to drop is a per-CLI fact, so it is the registry's `overlays.docker.rootCommand`, never a branch. ⚠️ Adoption is **admin-only in multi-user mode**, unlike `docker-link`: linking creates OUR container, whose one bind mount `isWorkingDirAllowed` has already confined, while an adopted container's mounts belong to its owner and one mounting `/` hands the adopter the host. The same reasoning admin-gates the container listing and the in-container directory browser; the preflight instead admits a non-admin for a container already linked to a case they own, because the run menu probes it for every docker case. ⚠️ On the loopback-only prod bind a container cannot reach 127.0.0.1, so in-container hooks need `CODEMAN_DOCKER_BRIDGE_HOOKS=1`; otherwise idle detection falls back to output-based. → [architecture-invariants#docker-cases](docs/architecture-invariants.md#docker-cases), `docs/docker-cases.md` (user guide), `docs/docker-cases-plan.md` (design)
+**Docker cases**: a case can point at a **container** running any CLI mode inside it, a **LOCATION OVERLAY on cases, never a `SessionMode`**. One long-lived container **per case**, shared by its sessions: killing a session kills only its in-container tmux, **never** `docker stop` while siblings remain. The workspace is bind-mounted at the **same absolute path**. Credentials are **seeded**, never shared RW. **NEVER a create-time `-e` for secrets, NEVER `--privileged`, NEVER the docker socket.** A drifted config (label hash) REFUSES the launch. ⚠️ An **adopted** container (`DockerCase.owned === false`) is only `exec`ed into: never create, start, stop, restart, remove, `docker commit` or `docker pause` it; fail closed. Test `owned === false`, never truthiness. ⚠️ Apply `owned` AFTER `dockerConfigHash`. ⚠️ Run modes come from the CONTAINER (`availableModes`), and a failed probe is normal for an OWNED case. ⚠️ Root exec user drops the bypass flag via the registry's `overlays.docker.rootCommand`, never a branch. ⚠️ Adoption is admin-only in multi-user mode. ⚠️ Loopback prod needs `CODEMAN_DOCKER_BRIDGE_HOOKS=1` for in-container hooks. → [architecture-invariants#docker-cases](docs/architecture-invariants.md#docker-cases), `docs/docker-cases.md`
 
-**Docker Compose deployment** (`docker/`, contributed): Codeman itself runs in a container and spawns Docker cases as **SIBLING** containers through the mounted host socket (Docker-outside-of-Docker), never nested. That inverts one assumption the bare-host path takes for granted: the daemon no longer shares Codeman's filesystem, so a bind source valid *inside* Codeman means nothing to it. `resolveDockerDaemonMountSource()` translates sources under HOME into the daemon's namespace via `CODEMAN_DOCKER_HOST_HOME`, and `CODEMAN_CASES_PATH` points the cases dir at a host-absolute bind mount so a workspace resolves to the SAME absolute path on both sides (which is what keeps the transcript projHash matching, per Docker cases above). ⚠️ **`CODEMAN_CASES_PATH` must move every consumer or none**: it is resolved once in `config/cases-dir.ts` because `src/cli.ts` resolves case paths too, and when only the server's `CASES_DIR` learned the override, `codeman skill install --case <name>` reported "Case not found" on exactly the deployment the override exists for. ⚠️ **`.dockerignore` patterns match the WHOLE context-relative path**, so a bare `.env` line excludes only the ROOT file: `docker/.env` (which holds `CODEMAN_PASSWORD` and any provider keys) rode `COPY . .` into the image until `**/.env` was added — verified in both directions with a real build context. ⚠️ A Compose LONG-form bind (`type: bind`) **creates a missing host source directory ROOT-OWNED** rather than refusing. `Start-Codeman.sh` pre-creates both `CODEMAN_APPDATA_PATH` and `CODEMAN_CASES_PATH` on the host before `up`, which is what keeps the daemon from ever having to materialise either as root in the first place; the container ALSO starts as root (`cap_add: [CHOWN, DAC_OVERRIDE, KILL, SETGID, SETUID]` against the base `cap_drop: ALL`; `test/docker-entrypoint.test.ts` pins that list) so `docker/entrypoint.sh` can correct a bind source that turns up root-owned anyway (a restored backup, a cleared directory, plain `docker compose up` run without the script) before dropping to `PUID:PGID` via `setpriv` — a directory owned by neither root nor `PUID:PGID` is never re-owned, since that ownership is not this container's to reassign; it is PROBED for writability as the runtime account (`setpriv ... test -w`, so ACLs, group-writable trees and CIFS/NFS mounts pass) and refused with a message naming path, owner and PUID:PGID if that fails. ⚠️ `KILL` is in that list for tini, not the entrypoint: `init: true` keeps tini as root while the server runs as PUID, and without CAP_KILL its SIGTERM forward fails and the server is SIGKILLed on every `compose down`/`restart` instead of flushing state. ⚠️ `/opt/codeman-cli` (the runtime-owned CLI prefix) is APPENDED to `PATH`, never prepended, and the entrypoint pins its own `PATH` to the system dirs: the root part of the start resolves `setpriv` by bare name, and a prefix ahead of `/usr/bin` let a planted `setpriv` run as uid 0 (measured). `CODEMAN_DOCKER_DISABLE_SWAP_LIMIT=1` drops `--memory-swap` (and filters only that one kernel warning) for hosts without swap accounting; `--memory` still applies. ⚠️ The deployment ALSO self-updates in place (the repo bind mount at `/opt/codeman` + a restart-by-exiting supervisor) — see Self-update below and `docs/docker-self-update.md` before touching `server.Dockerfile`, the compose file or `.env.example`, since each is an input to the updater's environment gate. `docs/docker-compose.md` + `docker/README.md` (user guides)
+**Docker Compose deployment** (`docker/`): Codeman runs in a container and spawns Docker cases as **SIBLING** containers via the host socket, never nested. `resolveDockerDaemonMountSource()` maps HOME bind sources into the daemon's namespace (`CODEMAN_DOCKER_HOST_HOME`); `CODEMAN_CASES_PATH` makes workspaces resolve to the same absolute path on both sides. ⚠️ `CODEMAN_CASES_PATH` must move every consumer: resolve it only via `config/cases-dir.ts`. ⚠️ `.dockerignore` matches whole paths: keep `**/.env` or `docker/.env` secrets ship in the image. ⚠️ Long-form binds create missing sources ROOT-OWNED: `Start-Codeman.sh` pre-creates them, and `docker/entrypoint.sh` (root, `cap_add: [CHOWN, DAC_OVERRIDE, KILL, SETGID, SETUID]` against `cap_drop: ALL`, `KILL` for tini; pinned by the test) fixes ownership then drops to `PUID:PGID` via `setpriv`, never re-owning foreign dirs. ⚠️ Append `/opt/codeman-cli` and `~/.local/bin` to `PATH`, never prepend. ⚠️ `server.Dockerfile`, the compose file and `.env.example` feed the self-updater's environment gate (`docs/docker-self-update.md`). → [architecture-invariants#docker-compose-deployment](docs/architecture-invariants.md#docker-compose-deployment), `docs/docker-compose.md`
 
-**CLI registry** (`src/config/cli-registry/`): every run mode is a `CliEntry` — discovery (search dirs, version + identity probes), the launch argv template, env handling, the `capabilities` flags that replace per-CLI branching, and the `overlays` that back the remote/docker pane commands. **No code outside `stock.ts` may branch on a CLI id**; behaviour that genuinely differs is either a capability field or a NAMED PROFILE selected by one (`profiles.ts`), and `test/cli-registry-no-id-branching.test.ts` fails the build if an id check reappears — it matches `===`, `!==`, `case '<id>':` and `[...].includes(mode)`, because an earlier `===`-only version let 36 negated branches survive the conversion (including a seven-mode Ralph chain whose own comment asked the next person to keep it in step with `isExternalCliMode()` by hand). ⚠️ Config contains no shell text: an entry declares typed argv tokens, literals are validated against a safe-word pattern at LOAD time (a bad literal rejects the whole entry — a silently dropped `--no-approve` is not cosmetic), and values resolve through patterns NAMED in code, so a user `clis.json` cannot widen its own validation. ⚠️ `external`, `hooks` and `altScreen` are three INDEPENDENT capabilities on purpose; deriving one from another shipped the `until=stop`-hangs-on-shell bug. ⚠️ Two capability fields carry a REGEX from config (`discovery.version.regex` and `capabilities.workDetect.workingLine`) and both must compile through `compileVersionRegex()`, which caps length and refuses nested quantifiers; `workingLine` is the one that runs on the PTY hot path. ⚠️ **`param` is TWO namespaces.** `launch.params` keys, `env.configSetenv[].fromParam` and `capabilities.privilegedParams[].param` all name a LAUNCH PARAM; the legacy `<Mode>Config` wire field is a separate namespace, bridged only by `launch.legacyConfigAliases`. Getting `privilegedParams[].param` wrong is SILENT — it is the multi-user bypass clamp's only handle on a CLI's privilege switch, and a wrong name clamps nothing with no load error and no failing test — so `schema.ts` rejects an entry naming a param it never declared. Codex is the entry where the two names differ (`bypassApprovals` vs `dangerouslyBypassApprovals`) and therefore the one that catches a regression. ⚠️ Six fields are DECLARED-FOR-LATER and read by nothing (`shortBadge`, `accent`, `capabilities.echo`/`wheelForward`/`keyboardAccessory`/`maxFrameBytes`): all frontend behaviour, transcribed rather than measured, so re-measure before wiring one up; the list is pinned so it cannot quietly grow. Spawn commands are pinned as literal strings in `test/cli-registry-spawn-golden.test.ts`, remote/docker pane commands in `test/location-overlay-commands.test.ts`. ⚠️ That second golden no longer covers **remote claude or remote omp**: both now have their own arm in `buildRemoteLaunchCommand` (a `--session-id || --resume` pair, and `--continue`, so a respawn continues the same conversation) and never reach `defaultRemoteCommandForMode`, which is what that test asserts. Their real pins are `toContain` substrings in `test/tmux-manager.test.ts` and `test/remote-shared-sessions.test.ts`; changing either arm will NOT fail the golden. ⚠️ Anything reading the registry resolves it AT CALL TIME (`sessionModeSchema()`, `allowedEnvPrefixes()`, `dependencyRegistry()`, the resolvers' `searchDirs` thunks) — a module-level const freezes at first import, so a CLI enabled while the server ran moved the run menu but not that surface. `~/.codeman/clis.json` overrides any entry (read-only in this release; nothing writes it, so importing the registry has no filesystem side effects). → `docs/cli-registry.md`
+**CLI registry** (`src/config/cli-registry/`): every run mode is a `CliEntry` (discovery, launch argv template, env handling, `capabilities`, and the `overlays` behind remote/docker pane commands). **No code outside `stock.ts` may branch on a CLI id**: use a capability field or a NAMED PROFILE (`profiles.ts`); `test/cli-registry-no-id-branching.test.ts` and `test/frontend-cli-no-id-branching.test.ts` enforce it. ⚠️ Config holds typed argv tokens, never shell text; literals are validated at LOAD time and a bad one rejects the whole entry. ⚠️ Keep `external`, `hooks` and `altScreen` independent; never derive one from another. ⚠️ Config regexes (`discovery.version.regex`, `capabilities.workDetect.workingLine`, `capabilities.workDetect.watchingLine`, `capabilities.workDetect.awaitingLine`) must compile through `compileVersionRegex()`. ⚠️ `privilegedParams[].param` names a LAUNCH PARAM, not the legacy `<Mode>Config` field (bridged only by `launch.legacyConfigAliases`); a wrong name silently clamps nothing. ⚠️ Resolve the registry AT CALL TIME, never in a module-level const. ⚠️ Remote claude/omp arms of `buildRemoteLaunchCommand` are not covered by the pane-command golden. `~/.codeman/clis.json` overrides entries. It is WRITTEN only by the opt-in CLI management routes (`cliManagementEnabled`, default OFF; `/api/clis`, `cli-registry-routes.ts`), and only through `mutateRegistryFile()` in `registry-writer.ts`, which serializes mutations and refuses (409) a file that does not parse or has group/world permission bits rather than overwriting it. Importing the registry still writes nothing. → [architecture-invariants#cli-registry](docs/architecture-invariants.md#cli-registry), `docs/cli-registry.md`
 
-**External CLI modes (OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek, OMP)**: `isExternalCliMode()` in `session.ts` gates Claude-specific behavior off (Ralph tracker, BashToolParser, token/CLI-info parsing, ❯-prompt readiness); these CLIs render their own TUIs, so readiness is output stabilization instead. ⚠️ **Work detection is no longer part of that gate**: it is per-CLI `capabilities.workDetect` data (see the ❯ note above), so a CLI that declares its own glyph and working line gets the same screen-probed idle confirmation claude gets, and one that declares neither keeps the output-stabilization behaviour. All eight **require tmux with no direct PTY fallback**, because secrets are injected via socket-scoped `tmux setenv` and never on the spawn command line. ⚠️ `run*()` in `session-ui.js` MUST unwrap the `{success,data}` envelope; reading the raw shape silently breaks the run. ⚠️ **Codex sessions use PREDICTIVE WRITE-THROUGH echo, never the buffer overlay** (`_localEchoPolicy` in `_updateLocalEchoState`, terminal-ui.js): codex's composer reacts per keystroke ("/" pops a live-filtering picker, arrows edit server-side state, the composer grows as it wraps), so buffer-until-Enter starved it into issues #218/#219/#220/#222 and stays disabled (`_localEchoEnabled` remains false for codex). Instead, `PredictiveEchoAddon` (separate `vendor/xterm-predictive-echo.js` bundle) paints each keystroke at the predicted cell while the wire path stays BYTE-IDENTICAL: the onData hook (`_predictHookOnData`) is a plain statement with no `return`, so control always falls through into the untouched send path — pinned by vm and E2E byte-identity tests. Predictions reconcile against the parsed buffer and only while the cursor sits on the measured composer row (`isCodexComposerRow`, `/^› /`). Codex also **drops keystrokes that share a PTY read with a bracketed paste**, so flushed text and the paste sequence must go out as separate delayed writes (mirroring the Enter branch's delayed `\r`). Tests: `test/local-echo-codex-gating.test.ts`, `test/codex-predictive-echo.test.ts` (E2E vs real codex), `packages/xterm-zerolag-input/test/codex-replay.test.ts`. ⚠️ **Pi is the opposite kind of CLI and needs the opposite instincts**: it has NO permission prompts and no sandbox, so there is no bypass flag to send and Codeman must not invent one; its privileged knob is the tri-state `approveProjectTrust` (`--approve`/`--no-approve`), which makes pi EXECUTE repo-local `.pi/extensions` TypeScript, so the multi-user clamp puts pi in the **materialize** branch (an absent config still yields `--no-approve` for a non-granted owner) and `--api-key` is never wired. Pi stays OUT of `isAltScreenStripMode()` (main-screen TUI, and its 0.84.0 fullscreen mode is runtime-switchable via `/settings`, where the alt screen is load-bearing), and lands on the `'buffer'` echo policy via the `_updateLocalEchoState` fallthrough. Pi's own tests: `test/pi-mode.test.ts`, `test/routes/external-cli-bypass-clamp.test.ts`; user guide `docs/pi-integration.md`. ⚠️ **Grok is codex-shaped on permissions but opencode-shaped on rendering**: its bypass switch is `alwaysApprove` (`--always-approve`, grok's `bypassPermissions` mode — the Run button sends it `true` like antigravity's, and the clamp's only-if-sent branch strips it for non-granted owners), while its fullscreen alt-screen TUI keeps it OUT of `isAltScreenStripMode()`; the resolver version-probes `grok --version` like pi's (npm squatters exist for the name — `GET /api/grok/status` surfaces path + version), and grok lands on the `'buffer'` echo policy via the fallthrough (UNMEASURED against a live authenticated session; if its composer turns out per-keystroke-reactive like codex, flip it to the `'off'` branch). Grok's own tests: `test/grok-mode.test.ts`, `test/grok-cli-resolver.test.ts`; user guide `docs/grok-integration.md`. ⚠️ **DeepSeek breaks three of this family's assumptions, so do not pattern-match it onto its siblings.** (1) The agent is a **PROFILE, not the binary**: `dsh` is a launcher over `$DSH_HOME/profiles/<name>` and DeepSeek ships only `web`/`headless`/`base`, so the terminal front door is ALWAYS third-party and "installed" ≠ "runnable" — the Run button gates on `isDeepSeekRunnable()` (binary AND a pane-capable profile) while `isDeepSeekAvailable()` gates the "add a profile" affordance; a `web`/`headless` profile is refused at spawn because it cannot drive a pane. (2) The permission switch is the **`DSH_PERMISSION_MODE` env export, not a flag** (`read-only`/`workspace-write`/`danger-full-access`) — the harness has none, and this is the one legitimate exception to the effort-style env-var ban because it is read with `??` as a boot-time default, so it stays soft; absent = `workspace-write`, which asks, hence the only-if-sent clamp branch, clamping to `workspace-write` (never `read-only`, which would break the workspace). ⚠️ **That clamp needs a second half Line truncated
+**External CLI modes (OpenCode, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek, OMP)**: `isExternalCliMode()` in `session.ts` gates Claude-specific behavior off (Ralph tracker, BashToolParser, token parsing, ❯ readiness; readiness is output stabilization); work detection is per-CLI `capabilities.workDetect` data, not this gate. All eight **require tmux, no direct PTY fallback** (secrets go via socket-scoped `tmux setenv`, never the command line). ⚠️ `run*()` in `session-ui.js` MUST unwrap the `{success,data}` envelope. ⚠️ **Codex uses predictive write-through echo, never the buffer overlay**: `_predictHookOnData` must never `return` (wire path stays byte-identical), and flushed text and a bracketed paste must go out as separate delayed writes. ⚠️ **Pi**: no bypass flag, never invent one; `approveProjectTrust` executes repo code, so it is in the clamp's **materialize** branch; never wire `--api-key`. ⚠️ **Grok**: `alwaysApprove` is stripped for non-granted owners (only-if-sent). ⚠️ **DeepSeek**: the agent is a PROFILE (Run gates on `isDeepSeekRunnable()`); the permission switch is the `DSH_PERMISSION_MODE` env var, so `clampEnvOverridesForOwner()` must DROP `DSH_PERMISSION_MODE`, `DSH_HOME` and `DEEPSEEK_BASE_URL` for non-granted owners; `hooksAvailableForMode()` is per-SESSION for it (pass `sessionHookOptions(session)`) and is never a stand-in for `mode === 'claude'`; answers come from `deepseek-transcript.ts`, paired by header `cwd` + boot window, never newest-mtime. ⚠️ **OMP**: `OMP_AUTH_BROKER_URL`/`_TOKEN` are clamped the same way. → [architecture-invariants#external-cli-modes-opencode-codex-gemini-antigravity-pi-grok-deepseek-omp](docs/architecture-invariants.md#external-cli-modes-opencode-codex-gemini-antigravity-pi-grok-deepseek-omp)
 
-**DeepSeek web UI** (`POST`/`GET`/`DELETE /api/deepseek/web`, `deepseek-web-server.ts`): the Run menu's "DeepSeek web UI..." entry supervises ONE background `dsh web` child process, deliberately **NOT a shell session**. The session version worked and was still wrong in use: it put a terminal tab on screen next to the web tab the user actually asked for, every single time, and nothing about a long-lived HTTP server needs to be a tab. ⚠️ What a session gave for free now has to be paid for explicitly, and every piece is load-bearing: **exactly one** server (a second click REUSES it rather than racing it for a port, which two sessions structurally could not do), **restarted when the browser authority changes** (`--trusted-host` fences dsh's `/api` against the browser authority, and a Codeman reachable at both loopback and a tailnet name has two, so whoever asks last wins: the asker is by definition the origin about to load the page), **killed on shutdown** (`stopDeepSeekWeb()` in the server teardown, because the child is detached so its whole plugin tree can be signalled at once, which also means it would OUTLIVE Codeman and hold its port against the next start), and **failures returned to the caller**, since with no tab there is nowhere for a stack trace to land. ⚠️ The port search starts at dsh's own default 3080 and walks 40, never fixed: that default is precisely the port most likely to be taken already by the user's own `dsh web`, and hardcoding it killed this feature with EADDRINUSE once. Free-port detection BINDS rather than connects (a connect probe cannot tell "free" from "listening but not answering yet"), so it is racy by nature and the caller still waits for the server to really answer before reporting success. ⚠️ Both `POST` and `DELETE` sit at the **same privilege bar as the profile installer** (`canUsernameRunPrivilegedCommands`) even though the action reads as "open a page": booting a dsh profile executes the plugin code in it, and the server is a single shared instance, so stopping it in multi-user mode takes it out from under other users' tabs.
+**DeepSeek web UI** (`POST`/`GET`/`DELETE /api/deepseek/web`, `deepseek-web-server.ts`): the Run menu's "DeepSeek web UI..." entry supervises ONE background `dsh web` child process, deliberately **NOT a shell session**. ⚠️ Every piece is load-bearing: exactly one server (a second click REUSES it), restarted when the browser authority changes (`--trusted-host`, last asker wins), killed on shutdown via `stopDeepSeekWeb()` (the detached child would otherwise outlive Codeman and hold its port), and failures returned to the caller. ⚠️ Never hardcode the port: search from 3080 across 40, detect free ports by BINDING, then wait for the server to really answer. ⚠️ Both `POST` and `DELETE` must stay behind `canUsernameRunPrivilegedCommands` (booting a profile runs its plugin code; the server is shared). → [architecture-invariants#deepseek-web-ui](docs/architecture-invariants.md#deepseek-web-ui)
 
-**Custom Model Endpoint Profiles** (opt-in, `customModelEndpointsEnabled`, SYNCED, default OFF; `docs/custom-model-endpoints.md`, design doc `docs/custom-model-endpoints-plan.md`; full stack — settings-panel CRUD + the Run-menu picker, on top of the backend below): points a session at a user-configured custom OpenAI-compatible endpoint — local (llama.cpp, DGX Spark, Strix Halo) or cloud (Azure AI Foundry, OpenRouter) — instead of its harness's native cloud backend. Endpoints are a read/write-array store (`custom-model-hosts.ts`, `~/.codeman/custom-model-hosts.json`) discovered via `GET <baseUrl>/v1/models`; `CustomModelHost.authStyle` is `'bearer'` (default, `Authorization: Bearer`) or `'api-key'` (Azure's convention) — **never both**, live-tested against a real server: sending both headers on one request reliably hangs it indefinitely, reproduced 3×. ⚠️ The actual per-CLI redirect is `capabilities.customModelInjection` on the CLI registry (four kinds: `env` for claude/gemini/deepseek, `configContentEnv` reusing opencode's existing `OPENCODE_CONFIG_CONTENT`, `configDir` for codex/pi/grok/omp — writes an isolated per-session config file, NEVER the user's real `~/.codex`/`~/.pi`/`~/.omp`/grok config — and `unsupported` for antigravity, which has no known mechanism), computed by the pure `custom-model-injection.ts` (mirrors `session-cli-builder.ts`'s no-IO discipline). ⚠️ `PI_CONFIG_DIR` does NOTHING for pi or omp (grepped pi's entire bundled JS source — the string appears nowhere); both hardcode `~/.pi/agent/models.json` / `~/.omp/agent/models.yml` with no dedicated override, so the real redirect for both is the child process's own **`HOME`**, and both need `models` as an ARRAY of `{id}` objects (an object keyed by id silently loads zero models). Grok's real mechanism turned out to be a `config.toml` `[model.<name>]` block redirected via `GROK_HOME` — its original env-var-based recipe was flat-out wrong (produced "Not signed in" against a real binary), not just unverified. ⚠️ **Two launch paths, chosen by mechanism, not preference — see the second paragraph below for why**: opencode/codex/gemini/pi/grok/deepseek/omp apply the selection ONE-SHOT, before the session/process ever exists, with no restart at all; claude alone still applies a selection by **restarting the session's CLI process in place** via `Session.restartCli()` — a de-restricted `reattachRemote()` reusing the same `respawn-pane -k` primitive local/remote respawns already share — because every one of these harnesses reads its endpoint config at process start, never per-turn, so there is no live hot-swap; `Session.setCustomModel()` undoes the PREVIOUS selection's env keys (and deletes its old `configDir`) before merging the new ones in, so switching endpoints or clearing back to native cloud never leaves a stale key behind. ⚠️ Deleting a key from `_envOverrides` is NOT enough on its own: `tmux setenv` persists at the tmux-session level and is inherited by `respawn-pane` (measured: `setenv FOO bar` survived two successive `respawn-pane -k`), so the retired keys are queued (`_pendingEnvUnsets`) and ride `RespawnPaneOptions.unsetEnvKeys` into `applyEnvOverrides()`, which `setenv -u`s them BEFORE re-applying the live overrides. ⚠️ `restartCli()` kills a WORKING pane, so a CLI whose launch declares a `fallback` chain (claude) gets the live conversation id pinned as `resumeSessionId` for that one respawn: `--session-id <id>` refuses an id that already has a transcript (`Session ID ... is already in use`), and without the `--resume <id> || --session-id <id>` shape the docker/remote pane commands already use, applying a model killed the pane and lost the session. ⚠️ pi, omp and grok need the config file AND a `model` launch param (`custom/<id>` for pi/omp, grok's `[model.codeman-custom]` block name): that is the registry's `customModelInjection.launchModel` template, applied onto the respawn options through `legacyConfigField` by `_withCustomModelLaunchModel()`, never by id, and a model id the CLI's `model` token pattern cannot carry is refused with a 400 rather than silently dropped by the argv engine. ⚠️ Remote (SSH) and Docker sessions are REFUSED (400): their `restartCli()` reattaches a durable tmux rather than restarting the agent and the env lands on the local pane, so they used to report `restarted:true` and change nothing. The selection survives a Codeman restart as the disk-only `__customModel` (bookkeeping: env KEYS, config dir, launch model; never the values, which carry the API key and are re-derived from the endpoint store on recovery), the config dir is removed with the session, and every secret-bearing file (`custom-model-hosts.json`, the per-session config dir) is written 0600. ⚠️ **Security**: every env var this feature can redirect (`ANTHROPIC_BASE_URL`, `GOOGLE_GEMINI_BASE_URL`, `CODEX_HOME`, `GROK_HOME`, `HOME` for pi/omp, `OPENCODE_CONFIG_CONTENT`, etc.) is in that CLI's `privileLine truncated
+**Custom Model Endpoint Profiles** (opt-in, `customModelEndpointsEnabled`, SYNCED, default OFF; `docs/custom-model-endpoints.md`): points a session at a user-configured OpenAI-compatible endpoint (store `custom-model-hosts.ts`, `~/.codeman/custom-model-hosts.json`, 0600). `authStyle` is `bearer` or `api-key`, never both headers (hangs the server). The per-CLI redirect is registry data, `capabilities.customModelInjection` (`env` / `configContentEnv` / `configDir` / `unsupported`), computed by the pure `custom-model-injection.ts`; ⚠️ `configDir` writes an isolated per-session config, NEVER the user's real `~/.codex`/`~/.pi`/`~/.omp`/grok config. ⚠️ Claude applies via `Session.restartCli()` (a relaunch in the existing pane, so the conversation is pinned as `resumeSessionId`), the rest one-shot at launch; retired env keys must also be `setenv -u`'d (`_pendingEnvUnsets`), since tmux env survives `respawn-pane`. ⚠️ Remote/Docker sessions are refused (400). ⚠️ Persist only KEYS (`__customModel`), never values (they carry the API key). ⚠️ Every redirectable var must be in that CLI's `privilegedEnvKeys`, and `ANTHROPIC_*` stays out of claude's `allowedPrefixes`. ⚠️ The Run-menu picker builds entries from `window.__codemanCustomModelClis` (escaped via `escapeScriptJson()`), never a hardcoded CLI id list, and launches through `run()` via a temporary `_runMode` swap, never `setRunMode()`. → [architecture-invariants#custom-model-endpoint-profiles](docs/architecture-invariants.md#custom-model-endpoint-profiles)
 
-**Everything below landed after the initial backend + picker cut, each confirmed live against a real llama-swap deployment.** ⚠️ **llama-swap runs one model at a time, and switching can disrupt ANOTHER live session** — before applying, both apply routes call llama-swap's own `GET /running` (feature-detected via `getLlamaSwapStatus()`, `custom-model-routes.ts`; a plain llama.cpp/OpenAI-compatible server has no such endpoint and is simply never checked). If a different model is loaded and ready AND another live session's own selection is using it, the apply returns `{requiresConfirmation, currentlyLoadedModel, affectedSessions}` instead of switching silently; retrying with `confirmedSwap: true` skips the check, and switching with nothing else affected proceeds immediately. ⚠️ **The swap question and the context-floor question below have SEPARATE flags** (`confirmedSwap`, `confirmedContext`), because the context check runs first and while both shared one `confirmed` a user who clicked past a too-small context silently consented to evicting another session's model too; the legacy `confirmed` still means both, since it shipped in the HTTP-API-only cut. llama-swap also has no dedicated "switch model" endpoint — the only thing that actually starts a swap is a real inference request naming the model (confirmed live: applying a selection alone never reached llama-swap's own logs, since nothing had asked it to load anything) — so both routes also fire `triggerLlamaSwapLoad()`, a fire-and-forget `POST <baseUrl>/v1/chat/completions` with `max_tokens: 1`, whenever the target model isn't already loaded and ready. ⚠️ **That launch-time check cannot catch a swap caused by a DIFFERENT session's LATER, ordinary use** — confirmed live: a second Codex session picking a different model launched with no warning at all (nothing conflicted at that exact instant), yet it silently evicted the first session's model regardless, since llama-swap has no push notification of its own. `detectCustomModelSwapDisplacements()` (`custom-model-routes.ts`) is a separate periodic sweep (`server.ts`, `CUSTOM_MODEL_SWAP_CHECK_INTERVAL_MS` = 20s) that compares each live custom-model session's own `modelId` against what `/running` actually reports loaded, broadcasting a `custom-model:swapped-out` SSE event — shown as a global toast, never tied to the displaced session's own tab, since the whole point is telling the user before they type into it — the first time a mismatch appears, via a caller-owned de-dupe `Set` cleared once that session's own model is loaded and ready again so a later, genuinely new displacement notifies again rather than staying silently un-notified forever after the first one. ⚠️ **Context length is read from the REAL launch command, never `/props`** — `/props?model=`'s `default_generation_settings.n_ctx` was confirmed live to report a `--fit-ctx`-launched backend's theoretical/trained maximum rather than the real runtime-configured size (a measured 154112-vs-16384 discrepancy, caught only because the unfixed value still overflowed), so discovery parses the actual configured size straight out of `/running`'s own `cmd` field instead (`parseCtxFromCmd`: `--fit-ctx <N>` first, then plain llama.cpp `-c`/`--ctx-size`), falling back to `/props` only when `cmd` states no recognizable flag at all. ⚠️ **Claude alone gets a context-window FLOOR check, on top of the ceiling `contextLengthVar` already fixes** — `exceedsSafeContextFloor()` (gated on the registry declaring `contextLengthVar`, so a no-op for every other CLI by construction) compares a model's discovered context against `CLAUDE_MIN_SAFE_CONTEXT_TOKENS` (40000): confirmed live, twice, that Claude Code's own system prompt and tool schemas cost roughly 36.4K tokens on the very first message, before any conversation history exists to compact, so a smaller real context fails outright regardless of what `CLAUDE_CODE_MAX_CONTEXT_TOKENS` says (that var only controls when HISTORY gets compacted, and there is none yet on message one). Below the floor, the apply returns `{requiresContextWarning, modelId, contextLength, minSafeContextTokens}` instead of launching, shown as an in-app dialog naming the actual fix: give the model an explicit larger `-c`/`--ctx-size` in llama-swap's config instead of relying on `--fit-ctx` auto-fit, which optimizes for the biggest MODEL that fits rather than the biggest CONTEXT. ⚠️ **A fresh, isolated `CLAUDE_CONFIG_DIR` looks like a brand-new Claude Code profile and replays its ENTIRE first-run sequence on every launch** — the theme picker, the security-notes screen, the per-project "trust this folder?" dialog, and (running with a bypass-permissions flag) a one-time warning about it, confirmed live, none of which a real, already-onboarded profile shows again. `skipFirstRunPrompts` (claude's entry only, requires `apiKeyTrustFile` since it reuses the same file) pre-seeds that same "already been through this" state: `hasLine truncated
+⚠️ **llama-swap endpoints** (one model at a time): the apply routes check `GET /running` and return `requiresConfirmation` before evicting a model another live session uses; `confirmedSwap` and `confirmedContext` are SEPARATE flags and must stay so. Claude alone gets a context floor (`CLAUDE_MIN_SAFE_CONTEXT_TOKENS`); context is parsed from `/running`'s `cmd`, never trusted from `/props`. Backend log lines come from llama-swap's `/api/events` `upstream` source, never `/logs`. → [architecture-invariants#custom-model-endpoint-profiles](docs/architecture-invariants.md#custom-model-endpoint-profiles)
 
-**Run launch synchronization**: the Run entrypoint holds an in-flight lock and disables `#runBtn` for the whole launch (≥500ms), so a double click cannot create duplicate sessions with the same `w<n>-<case>` name. `_ensureCreatedSessionVisible()` runs before `selectSession()`, and `_onSessionCreated()` stays an idempotent upsert, so POST-first and SSE-first ordering both produce exactly one rendered tab. ⚠️ **Closing has the mirror-image race and one owner**: `closeSession()` reads `wasActive` BEFORE its `await` and announces the delete via `_closingSessions`, while `_onSessionDeleted` skips the active-session handoff for an id in that set. Both used to read `activeSessionId` after the fact, so the `session_deleted` broadcast for your own delete could null it first and closing the tab you were on landed on the welcome screen instead of the next session, on the same build, depending on timing. The fallback also picks the first order entry that is still in `sessions` (a dead id can linger in `sessionOrder`, same reason Alt+N indexes a live-filtered list). A delete from ANOTHER client still shows the welcome screen, which is the honest answer when what you were looking at was taken away. Tests: `test/session-close-fallback.test.ts`. → [architecture-invariants#run-launch-synchronization](docs/architecture-invariants.md#run-launch-synchronization)
+**Run launch synchronization**: the Run entrypoint holds an in-flight lock and disables `#runBtn` for the whole launch (≥500ms) so a double click cannot create duplicate `w<n>-<case>` sessions; `_ensureCreatedSessionVisible()` runs before `selectSession()` and `_onSessionCreated()` stays an idempotent upsert, so POST-first and SSE-first both render exactly one tab. ⚠️ **Closing has the mirror-image race**: `closeSession()` must read `wasActive` BEFORE its `await` and announce the delete via `_closingSessions`, and `_onSessionDeleted` skips the active-session handoff for ids in that set; never read `activeSessionId` after the fact. The fallback picks the first `sessionOrder` entry still in `sessions`. Tests: `test/session-close-fallback.test.ts`. → [architecture-invariants#run-launch-synchronization](docs/architecture-invariants.md#run-launch-synchronization)
 
-**Session lineage lines** (tab → tab it spawned, `sessionLineageLines`, per-device, desktop default ON): a create request may name the session that spawned it, as a `parentSessionId` body field on `POST /api/sessions` / `POST /api/quick-start` or the `X-Codeman-Parent-Session` header (the agent skill sets that once on its shared curl invocation, so every spawn recipe carries it). `resolveParentSessionId()` (route-helpers.ts) **resolves rather than trusts** it: exact id, else a UNIQUE ≥8-char prefix (ids reach agents truncated), it must be a live session the caller can see AND carry the same owner, and **anything unresolvable is DROPPED, never a 400** — a cosmetic field must not be able to fail a worker spawn. It rides `toState()` into `session_created`, so there is no new SSE event. ⚠️ Rendering is an ADDITIONAL LAYER on the existing SVG pass (`_appendLineageConnectionLines` called at the tail of `_updateConnectionLinesImmediate()`, exactly like ultracode), sharing one batched read→write reflow and the `tab:<id>` rect cache; geometry is pure in `computeLineagePath()` (constants.js). ⚠️ **ONE shape, and the second one was the bug**: every pair (flat strip or wrapped) gets a U-bridge hanging below the strip, anchored on both tabs' BOTTOM edges. A wrapped strip used to get a parent-bottom → child-TOP bezier with a ~14px row gap to bend in, which drew a flat line hidden in the gap with siblings overprinting. ⚠️ The dip is a **mis-tuned-in-both-directions corridor** (44px cap = straight thread at strip-wide spans, #285; 104px cap + full row offset = ~106px over-bow into the terminal, 2026-08-15): it now hangs from the **STRIP's bottom edge** (fallback: lower tab bottom), capped at 64px, with NO per-row offsets stacked on top — the strip-bottom baseline is also what keeps a row-1 pair's arc from drawing through row 2's tab labels. ⚠️ **Colors are keyed on the SPAWNING tab, not per child**: every arc leaving one tab is the same color however many workers it spawns, so the strip reads as "these five came from w1, those two came from w2" — per-child coloring gave one tab's own children a different color each, which is the distinction the colors exist to make. A child that spawns in turn is a parent in its own right and gets its own color for the arcs below it, so a chain changes color at each generation while each generation's fan-out stays uniform. Assignment cycles `CodemanLineage.COLORS` in first-seen order per parent id (first entry empty = the skin-tuned `--session-blue`, so the first spawning tab keeps it; the rest vivid fixed hexes), memoized rather than derived from draw index (the SVG is wiped and rebuilt constantly, so an index-based color would flicker), and set inline as `--lineage-color` so styles.css keeps owning opacity/glow/dash. `test/session-lineage-lines.test.ts` drives the real `_appendLineageConnectionLines()` and asserts the painted property, since testing the color function alone would pass just as happily with the child id passed back in. ⚠️ **Desktop only**: the overlay is `z-index: 999` and the desktop header is 100 (arcs paint over it, which is what lets them touch tab bottoms), but under 1024px mobile.css makes the header `fixed; z-index: 1200` and would bury them. ⚠️ Paths carry `data-agent-id="lineage:<childId>"` because that is what `_applyLineEntrances()` queries — that one attribute is what gives them the entrance animation and its negative-`animation-delay` resume across `svg.innerHTML=''`. ⚠️ `.session-tabs` is `overflow-x: auto`, so a scrolled-out tab still HAS a rect (over the logo); edges with an endpoint outside the strip are skipped, and a passive `scroll` listener re-anchors the rest.
+**Session lineage lines** (tab → tab it spawned, `sessionLineageLines`, per-device, desktop default ON): a create request may name its spawner via a `parentSessionId` body field or the `X-Codeman-Parent-Session` header; `resolveParentSessionId()` (route-helpers.ts) resolves it (exact id or unique ≥8-char prefix, live, visible, same owner) and ⚠️ anything unresolvable is DROPPED, never a 400. Rides `toState()`, no new SSE event. ⚠️ Rendering is a LAYER on the existing SVG pass (`_appendLineageConnectionLines` at the tail of `_updateConnectionLinesImmediate()`), geometry pure in `computeLineagePath()`: one U-bridge shape hanging from the strip bottom, colors keyed on the SPAWNING tab and memoized (never by draw index). ⚠️ Desktop only (z-index vs the fixed mobile header). ⚠️ Paths must keep `data-agent-id="lineage:<childId>"` (the entrance animation queries it); skip edges whose endpoint is scrolled out of the strip. → [architecture-invariants#session-lineage-lines-tab--tab-it-spawned](docs/architecture-invariants.md#session-lineage-lines-tab--tab-it-spawned)
 
-**Auto-named sessions** (`autoNameSessions`, SYNCED, default OFF; #376): a placeholder tab (`w3-myapp`) takes its first real prompt as a title, in the `<prefix>: <title>` form (`w3-myapp: fix the login redirect`) that `parseSessionPrefix()` (app.js, #232) already renders as the title alone with the prefix in the tooltip and that `_nextCaseSessionStartNumber()` still counts, so the case identity and the `w<n>` counter survive. Ownership is the tri-state `SessionState.nameSource`: `placeholder` (Codeman's own `w<n>-<case>` or no name, inferred by `isGeneratedSessionName()` when a persisted state predates the field), `auto` (titled once), `manual` (the `name` setter, i.e. `PUT /api/sessions/:id/name`, which auto-naming never touches again). ⚠️ **First prompt means the FIRST**: `applyAutoName()` flips a placeholder to `auto` whether or not the string changed, so a later "1" cannot rename the tab; a prompt that yields no title (`/clear`, a `!` shell escape) leaves the session eligible for the next one. ⚠️ **Only user-originated input counts** (`SessionWriteOptions.fromUser`, set by the browser WS path and `POST /api/sessions/:id/input` ONLY, so a forgotten flag on a new path fails toward not naming): Ralph kick-starts, respawn `/clear`s, cron launches, approval answers and the trust-dialog keys write through the same `write()`/`writeViaMux()` and used to name every Ralph tab "Read @ralph_prompt.md…". A `startMode: 'shell'` CLI never feeds the tracker (a capability, not an id check; a shell tab was renamed after every `ls`), and the send-key route's Shift+Enter line feed bypasses the session entirely, so it calls `trackUserInput()` or the two lines join with no separator. ⚠️ **The tracker (`session-auto-name.ts`, pure) sits on the raw keystroke stream**, so every key has an explicit rule: a bare Esc is resolved at the END of the chunk it arrives in (it used to stay in escape mode and eat the next prompt's first character, or a whole CJK prompt); SGR mouse reports, Tab, cursor keys and Shift+Tab leave the draft alone (a wheel tick mid-word used to drop the first half); Up/Down and Ctrl+P/N/R TAINT the draft so Enter submits nothing rather than a fragment; bracketed-paste newlines are newlines IN the composer, never Enter. The title is the first sentence past a minimum length ("e.g. fix this now" is not "e.g."), capped at 72 code points, and the composed name honours `MAX_SESSION_NAME_LENGTH`. The listener (`session-listener-wiring.ts`) checks eligibility BEFORE reading the setting, so an already-named session costs no settings read per prompt. Opt-in because the prompt lands in the tab name, `mux-sessions.json`, every `session:updated` and `/api/search` (Read My Mind keeps prompts 0600 for the same reason). Tests: `test/session-auto-name.test.ts`, `test/session-listener-wiring.test.ts`, `test/routes/session-name-routes.test.ts`. → [architecture-invariants#auto-named-sessions-first-prompt--tab-title](docs/architecture-invariants.md#auto-named-sessions-first-prompt--tab-title)
+**Auto-named sessions** (`autoNameSessions`, SYNCED, default OFF): a placeholder tab (`w3-myapp`) takes its first real prompt as a title in the `<prefix>: <title>` form, so the case identity and `w<n>` counter survive. Ownership is `SessionState.nameSource` (`placeholder` | `auto` | `manual`; the `name` setter / `PUT /api/sessions/:id/name` makes it `manual`, never touched again). ⚠️ `applyAutoName()` flips to `auto` even if the string is unchanged, so only the FIRST titled prompt names the tab. ⚠️ Only user input counts: `SessionWriteOptions.fromUser` is set by the browser WS path and `POST /api/sessions/:id/input` ONLY; any new user-input path must set it (and the send-key Shift+Enter path must call `trackUserInput()`). ⚠️ The pure tracker (`session-auto-name.ts`) sits on the raw keystroke stream with an explicit rule per key; add a rule for any new key class. ⚠️ `nameSource` also decides `--name`: only a `manual` name is pinned on the claude CLI (`Session.cliPinnedName`), since `--name` is also the `/resume` title; a rename appends a `custom-title` row to a LOCAL, non-docker transcript, and a same-name PUT is a no-op (never flips to `manual`). Tests: `test/session-auto-name.test.ts`. → [architecture-invariants#auto-named-sessions-first-prompt--tab-title](docs/architecture-invariants.md#auto-named-sessions-first-prompt--tab-title)
 
 **Maintainer bot (external)**: the Telegram bot that reviews open PRs and triages discussion threads in Codeman sessions used to live at `scripts/pr-bot/`. It moved OUT of this repository on 2026-09-14, to `~/codeman-cases/prbot/` (its own private git repo, systemd unit `codeman-pr-bot`, guide + agent rules in its own `README.md` and `CLAUDE.md`). It is a CLIENT of Codeman's HTTP API like any other, so nothing here depends on it and it is not part of the server, the CLI or the npm package. ⚠️ It spawns real sessions named `prbot-<n>` / `dscbot-<n>` on the local Codeman and holds clones under `~/.codeman/pr-bot/`, so those session names and that data dir are taken; it also fetches PR heads into `refs/pr-bot/*` of this checkout and must never check out, reset or clean it. The CHANGELOG entries for 1.25.0 and earlier still describe it, which is history rather than drift.
 
-**Unified session list**: `GET /api/sessions/unified` merges live sessions, persisted state, lifecycle-log history, and transcript files into one deduped list (pure core in `src/services/unified-session-service.ts`). ⚠️ **Transcript history is THREE stores, not one**, because each CLI keeps its conversations in its own: Claude's `~/.claude/projects`, omp's `~/.omp/agent/sessions` and codex's `~/.codex/sessions` (#386). Rows fold into their owning session via the `claudeSessionId → Codeman id` alias map, so resumed and `/clear`-respawned sessions do not appear twice; that field is named for Claude and carries whatever id the CLI names its conversation with, which for every non-Claude row diverges from the Codeman id by construction. ⚠️ **`resumeId` is set by a SCANNER row only, never by a live session**, and that is what makes it safe to resume on: a row carrying one is a conversation already on disk, so `resumeHistorySession()` sends `codexConfig.resumeSessionId` and a row without one is a genuinely fresh session. Every surface that re-projects these rows has to carry the field through, the phone overview included, or a tap on that surface silently starts a second conversation. No terminal buffers in the response, unlike `/api/sessions`. Backs the Cmd+K Session Manager, plus pinning and cross-device tab order (`PUT /api/session-order`; pure merge helpers in `src/session-order.ts`, pushing device wins and server-only ids are never dropped). → [architecture-invariants#unified-session-list-and-session-manager](docs/architecture-invariants.md#unified-session-list-and-session-manager)
+**Unified session list**: `GET /api/sessions/unified` merges live sessions, persisted state, lifecycle-log history and transcript files into one deduped list (pure core `src/services/unified-session-service.ts`), backing the Cmd+K Session Manager, pinning and cross-device tab order (`PUT /api/session-order`, `src/session-order.ts`). ⚠️ Transcript history is THREE stores (`~/.claude/projects`, `~/.omp/agent/sessions`, `~/.codex/sessions`), folded via the `claudeSessionId → Codeman id` alias map (not Claude-only despite the name). ⚠️ `resumeId` is set by a SCANNER row only, never a live session; every surface that re-projects these rows (phone overview included) must carry it through, or a tap silently starts a second conversation. → [architecture-invariants#unified-session-list-and-session-manager](docs/architecture-invariants.md#unified-session-list-and-session-manager)
 
-**Owner tab layouts** (COD-359, `tab-layout*.ts` + `GET`/`PUT /api/tab-layout`): named tab GROUPS over the flat tab strip, scoped per owner (`SINGLE_USER_LAYOUT_OWNER` = `@single` when multi-user is off), persisted under the `tabLayouts` key in state.json. A layout is `{version, groups[], ungrouped[], updatedAt}` whose refs point at either a session or a saved webview (`TabRefKind`), capped at 32 groups / 512 refs. ⚠️ **BACKEND ONLY as of 1.24.1**: nothing in `src/web/public/` calls these routes yet, so a UI built on top is new frontend work, not a rewiring job. ⚠️ **`TabLayoutService` is the single mutation boundary** and every lifecycle caller (session created/removed, webview created/deleted, a legacy order PUT) describes ONE completed server action and gets AT MOST ONE versioned write; writing layout state from a route or a manager directly is what the service exists to prevent. ⚠️ The layout does not replace `PUT /api/session-order`, it PROJECTS onto it: `tab-layout-legacy-order.ts` is the pure translation both ways (`putLegacyOrder()` recomposes a global order from the owner's groups), so changing one side without the other silently desyncs the tab strip from the stored layout. ⚠️ **Reconciliation is gated on a SUCCESSFUL restore** (`markRestorationComplete` / `markRestorationFailed` / `markRestorationSkipped`, plus `assertDeletionReady()`): pruning refs against a session list that failed to load would delete live tabs, so a failed restore must leave the layout untouched. `PUT` takes exactly `{baseVersion, layout}` (any other key shape is a validation error), answers a stale `baseVersion` with the current layout rather than clobbering, and is capped at 128 KiB. Broadcasts `tab:layoutChanged`, owner-routed via `deriveTabLayoutSseHint`.
+**Owner tab layouts** (`tab-layout*.ts` + `GET`/`PUT /api/tab-layout`): named tab GROUPS over the flat strip, scoped per owner (`@single` when multi-user is off), persisted as `tabLayouts` in state.json. BACKEND ONLY: no frontend calls these routes yet. ⚠️ `TabLayoutService` is the single mutation boundary (one completed server action = at most one versioned write); never write layout state from a route or manager directly. ⚠️ The layout PROJECTS onto `PUT /api/session-order` via `tab-layout-legacy-order.ts`; change both sides together. ⚠️ Reconciliation is gated on a SUCCESSFUL restore (`markRestorationComplete`/`assertDeletionReady()`): a failed restore must leave the layout untouched or live tabs get pruned. → [architecture-invariants#owner-tab-layouts](docs/architecture-invariants.md#owner-tab-layouts)
 
-**Hook events**: Claude Code hooks trigger via `/api/hook-event`. Key events: `permission_prompt`, `elicitation_dialog`, `elicitation_complete`, `elicitation_response`, `idle_prompt`, `stop`, `teammate_idle`, `task_completed`, `prompt_submitted` (UserPromptSubmit, #367: a Claude pane reports its live conversation id first-hand). See `src/hooks-config.ts`; upstream hook semantics mirrored in `docs/claude-code-hooks-reference.md`. ⚠️ **Every claude session INSTALLS the hooks block into its workspace** (`applyWorkspaceHooks` in hooks-config.ts → `ensureCodemanHooks`, an add-only merge that keeps a user's own handlers), from EVERY claude create path — both interactive routes, cron fires, legacy scheduled runs, the plan-orchestrator one-shots — and from `restoreMuxSessions()` for sessions recovered on server start (that boot sweep skips a workspace that no longer exists, so a deleted repo with a surviving tmux session is never resurrected as an empty dir). Before 2026-08-15 hooks were written ONLY when Codeman created the case DIRECTORY, so a linked case / cloned repo — where most sessions actually run — had no hooks at all and every hook-driven surface was silently dead there: an AskUserQuestion dialog blocked the pane while the tab and the phone overview both read a calm `idle`, with no Approvals Inbox item, no push, no definitive `stop`/`idle_prompt` for respawn and no `stop`/`blocked` for the wait endpoints. The escape hatch is the synced `workspaceHooksEnabled` setting (App Settings → Agents & CLIs → Claude, **default ON**); OFF restores the old behavior, where a Codeman block that is already there is still refreshed when stale (COD-91) but one is never added. ⚠️ Route the decision through `applyWorkspaceHooks` rather than calling `ensureCodemanHooks` at a new site, or the setting silently stops applying to that path. ⚠️ Claude Code RE-READS `settings.local.json`, so an already-running session starts firing hooks without a restart (measured 2026-08-15) — and the notification for a blocking dialog is delayed by Claude Code (~30s), so the alert trails the dialog. ⚠️ An AskUserQuestion / plan-selection dialog arrives as **`permission_prompt`**, not `elicitation_dialog` (that one is MCP elicitation), so it renders as the RED "needs you" alert, not the yellow idle one.
+**Hook events**: Claude Code hooks trigger via `/api/hook-event` (`permission_prompt`, `elicitation_dialog`, `elicitation_complete`, `elicitation_response`, `idle_prompt`, `stop`, `teammate_idle`, `task_completed`, `prompt_submitted`); see `src/hooks-config.ts` and `docs/claude-code-hooks-reference.md`. ⚠️ Every claude session installs the hooks block into its workspace (add-only merge) from every create path and from `restoreMuxSessions()`, gated by `workspaceHooksEnabled` (SYNCED, default ON). ⚠️ Route that decision through `applyWorkspaceHooks`, never call `ensureCodemanHooks` at a new site, or the setting silently stops applying. ⚠️ An AskUserQuestion / plan-selection dialog arrives as `permission_prompt` (RED alert), not `elicitation_dialog` (MCP elicitation). → [architecture-invariants#hook-events-and-workspace-hook-installation](docs/architecture-invariants.md#hook-events-and-workspace-hook-installation)
 
-**Reboot restore** (#411/#442, `src/reboot-restore.ts` pure + `web/reboot-restore-registry.ts` + `routes/reboot-restore-routes.ts` + `reboot-restore-ui.js`): a host reboot takes the tmux server with it, so every pane dies and the board comes up empty with no explanation. At boot Codeman works out which sessions that reboot destroyed, holds the plan IN MEMORY (no new state file, and a server restart simply drops the offer), and the banner asks. ⚠️ **The heuristic decides whether to ASK, never whether to act**: two signals have to agree (the socket holds no panes at all while state still lists sessions, AND the host booted after the newest persisted activity), and a wrong yes costs one dismissable line rather than N CLI processes nobody asked for. ⚠️ Rebuilding is TAKE-then-build: entries leave the plan synchronously before the first `await` and the route is single-flighted per owner, so a double-click or a second device cannot put two panes on one conversation. Anything that never became a pane goes BACK on offer, with one deliberate exception, `already-live`, which unlike a missing workspace or a withdrawn grant cannot stop being true. ⚠️ Three things are re-checked at click time rather than trusted from boot (the owner's privilege grant, the workspace still being on disk, and the conversation not already being live), and the already-live sets are read FRESH per iteration rather than snapshotted: the loop awaits a real `startInteractive()` per entry, so a snapshot taken before it is tens of seconds stale by the tenth entry and would miss a conversation the user resumed by hand in that window. The confinement re-check is keyed on the entry's OWNER, never the caller, or an admin spending another user's entry is waved through by `isWorkingDirAllowed`. ⚠️ A rebuilt session comes back **attached, idle and disarmed**: the pane is NEW, so terminal scrollback is gone (the banner says so) while the conversation continues, respawn controllers and Ralph loops are never re-armed, and `reapplyPersistedSessionState(..., { rearmAutoResumeSchedule: false })` keeps auto-resume ENABLED but drops the pre-reboot `autoResumeAt` stamp, or one click has every restored session type `continue` into itself a minute later, unattended. That option exists only for this path; a Codeman restart still re-arms, because the limit footer will not reprint on its own. ⚠️ The rebuild passes `nameSource` through, or the constructor re-infers it from the name and a hand-renamed session shaped like `w<n>-<case>` comes back as `placeholder` for auto-naming to overwrite. ⚠️ Claude-mode only (others carry their conversation id in their own config object), and remote/docker sessions are never offered (`remote-or-docker`), because both need another host or container to be up. ⚠️ A failed rebuild is undone with `discardPartiallyBuiltSession()`, deliberately NOT `cleanupSession()`: the delete path would count the session's tokens into the lifetime totals, demote a pinned record to `stopped` (which this pass reads as an intentional kill, making the session permanently unrestorable) and recursively remove the WORKSPACE's `.claude-images`. ⚠️ `os.uptime()` reports the HOST's uptime, which a container shares, and that cuts both ways: after a genuine host reboot a containerized Codeman does see a short uptime and the banner works, but a container-only restart is invisible to it, which is the case where this would help most. Tests: `test/reboot-restore.test.ts`, `test/routes/reboot-restore-routes.test.ts`, `test/routes/reboot-restore-rebuild-failure.test.ts`, `test/discard-partially-built-session.test.ts`.
+**Reboot restore** (`src/reboot-restore.ts` pure + `web/reboot-restore-registry.ts` + `routes/reboot-restore-routes.ts` + `reboot-restore-ui.js`): after a host reboot kills every pane, Codeman holds an IN-MEMORY plan of the destroyed sessions and a banner offers to rebuild them. ⚠️ The heuristic only decides whether to ASK. ⚠️ Rebuild is TAKE-then-build (entries leave the plan before the first `await`, single-flighted per owner). ⚠️ Re-check grant, workspace and already-live at click time, reading already-live FRESH per entry; key confinement on the entry's OWNER, never the caller. ⚠️ Rebuilt sessions come back disarmed: no respawn/Ralph, `rearmAutoResumeSchedule: false`, and pass `nameSource` through. ⚠️ Undo a failed rebuild with `discardPartiallyBuiltSession()`, NEVER `cleanupSession()`. Claude-mode only, never remote/docker. Tests: `test/reboot-restore.test.ts`. → [architecture-invariants#reboot-restore](docs/architecture-invariants.md#reboot-restore)
 
-**Approvals Inbox** (cross-session queue of prompts waiting on a human; `approvalsInboxEnabled`, SYNCED, default OFF: every surface is opt-in; only the store and answer endpoints run regardless, so flipping it ON shows anything already pending): `web/approval-inbox.ts` is a `sessionWaits`-style singleton fed by `/api/hook-event`, holding at most ONE item per session (a new prompt supersedes), claude-mode only, in-memory. Cards are answered via `POST /api/approvals/:id/answer`, which sends a digit / Esc / idle-prompt text through `writeViaMux` (menu answers never carry `\r`). ⚠️ `option` digits are accepted ONLY when they match options parsed from the captured pane frame, and the answer path RE-CAPTURES the pane first (a dialog that no longer parses on screen means the keystroke would land in the composer, so refuse with 409). ⚠️ Resolution on the heuristic `working` signal ALONE is restricted to `idle` items; a permission/question item gets the pane-VERIFIED variant on that same signal (`resolveIfDialogGone()` → `verifyStillAnswerable()`), so the heuristic only decides when to LOOK and the screen decides the outcome. That is what clears a dialog answered in the terminal mid-turn; the other definitive signals are `stop`, `elicitation_complete`/`elicitation_response`, exit/delete, answer, supersede and the 12h TTL. ⚠️ **Viewing a session ACKNOWLEDGES its idle item, it does not resolve it** (`POST /api/approvals/session/:sessionId/viewed` → `acknowledgedAt` → `approval:updated`): the item stays pending (still answerable, still Read My Mind context) and only stops arming the yellow tab alert. That flag is what makes the clear durable, since the view-clears-idle rule used to live in one browser's memory and `seedApprovals()` re-armed the alert on the next reload while other devices never heard about it at all; the local half is `markIdleAlertSeen()` (app.js), called from BOTH `selectSession` paths, including the already-active early return, where a click could otherwise never clear the alert. ⚠️ **Only a HUMAN opening a session acknowledges**: `selectSession(id, { auto: true })` marks the three selections the APP makes (boot restore, a solo window opening its target, the fallback after the active session is closed) and skips the acknowledgement, so a page load cannot silently spend an alert the user never saw. The flag defaults to user-initiated, so an untagged call site fails toward acknowledging rather than toward an alert nothing can clear; `test/session-select-ack-gate.test.ts` pins both the gate and the tagged call sites. Idle-only by construction (`acknowledge()` defaults to `['idle']`): looking at a permission/question dialog does not answer it. ⚠️ Same rule on the input path: `_ackDelivery` (app.js) spends the IDLE alert only, via that same `markIdleAlertSeen()`. It used to `clearPendingHooks(sessionId)` with no kind, so one keystroke wiped a RED alert on that device while the dialog was still up, the other devices stayed red, and a reload re-seeded it. ⚠️ Claude Code fires no "permission answered" hook (only `elicitation_complete`/`elicitation_response`, i.e. the question flavor), so an answered-in-the-terminal dialog would otherwise sit pending until `stop`: `GET /api/approvals` therefore runs a **staleness sweep** over the caller's own items via `verifyStillAnswerable()`, which is deliberately the conservative check the answer path uses (only an item whose ORIGINAL frame parsed options can be dropped, so an unreadable capture keeps the alert rather than losing a live one). ⚠️ **`applyCapture()` is therefore ADD-ONLY for `options`**: a re-capture that parses nothing must never erase a parse an earlier one found. Claude Code delays the Notification hook behind the dialog (measured 6s, documented ~30s), so the 600ms re-capture routinely lands on a frame the user has ALREADY answered; clearing the field there made the item permanently unsweepable, because `verifyStillAnswerable()` reads a MISSING `options` as "we never could read this dialog" and keeps such items answerable by design. The red "needs you" then survived every sweep AND every page reload, went away only on `stop` (2026-08-20: a confirmed question left a tab flowing red for ~8 minutes while the turn ran on), and the stale card still accepted an answer, typing a bare `1` into a composer with no dialog under it. Pinned by `test/approval-inbox.test.ts`. ⚠️ A frame that parses no options is CONCLUSIVE in exactly two cases, and the second one closes the late-hook hole: the item once parsed options (they cannot vanish while the dialog is up), or the frame shows Claude actively running a turn. A modal dialog BLOCKS the turn, so the two cannot coexist — measured on v2.1.237, a live-dialog frame carries neither the `… (13s` timer NOR the `esc to interrupt` footer, which the dialog replaces with `Enter to select · ↑/↓ to navigate · Esc to cancel`. Anything else stays answerable, so an unreadable capture Line truncated
+**Approvals Inbox** (`approvalsInboxEnabled`, SYNCED, default OFF; the store and answer endpoints run regardless): `web/approval-inbox.ts` is an in-memory, claude-only queue fed by `/api/hook-event`, at most ONE item per session, answered via `POST /api/approvals/:id/answer` through `writeViaMux` (menu answers never carry `\r`). ⚠️ Accept `option` digits ONLY if they match options parsed from a fresh RE-CAPTURE of the pane; a dialog no longer on screen is a 409. ⚠️ Resolve permission/question items only via the pane-verified `verifyStillAnswerable()`; the heuristic `working` signal alone may resolve `idle` items only. ⚠️ `applyCapture()` is ADD-ONLY for `options`. ⚠️ Viewing ACKNOWLEDGES an idle item (never resolves it) and only a human selection does: app-made selections pass `selectSession(id, { auto: true })`; `_ackDelivery` spends the IDLE alert only. ⚠️ `handleInit` seeds tab alerts from `GET /api/approvals` REGARDLESS of the setting. → [architecture-invariants#approvals-inbox](docs/architecture-invariants.md#approvals-inbox)
 
-**Read My Mind intent profiles** (phase 1 of `docs/readmymind-plan.md`; `readMyMindEnabled`, SYNCED, default OFF): per-CASE profiles (user-stated `goals` + the user's recent real prompts), keyed by owner + realpath(workingDir) so they survive `/clear`/respawns and multi-user scoping is structural. Capture rides the transcript (`transcript:user_prompt` from `transcript-watcher.ts`), NOT the input paths: `POST /input` sees only programmatic prompts and the WS channel is raw keystrokes. The listener lives inside `startTranscriptWatcher()`'s `if (!watcher)` block (outside it would duplicate per hook event) and is claude-only + gated on the setting per event. Store: `src/intent-store.ts` singleton, `intents.json` written 0600 tmp+rename (prompts can contain secrets; never fed to `/api/search`). Endpoints: GET/PUT/DELETE `/api/sessions/:id/intent` + POST `/api/sessions/:id/readmymind` (`readmymind-routes.ts`, ownership via `findSessionOrFail` WITH `req`; registrations stay the bare `app.<method>('path')` shape, the endpoints.md drift scanner cannot see generics). **Phase 2 (predictor + 🧠 button)**: `readmymind-context.ts` is the PURE budgeted assembler (9 ranked sources, drop order siblings→away→workspace→tools, sections 1-4 truncate only); IO lives in `readmymind-collectors.ts` (transcript TAIL read — the live watcher keeps only a 500-char snippet — + git signals, skipped for remote-SSH cases) and the route; `readmymind-predictor.ts` reuses the AiCheckerBase spawn mechanics standalone (verdict-shaped base vs freeform JSON) as a mutable singleton routes call and tests stub. Claude-mode only (400), one in flight per session (409 CONFLICT), model = `readMyMindModel` setting defaulting to `AI_CHECK_MODEL` (opus, decided). Frontend `readmymind-ui.js`: header 🧠 marker-hidden (`btn-readmymind--hidden`) until the setting is ON; phones hide it in mobile.css and get a keyboard-accessory 🧠 key instead (ships in BOTH bar templates, revealed by the `rmm-enabled` class on the BAR element — setMode() rebuilds button innerHTML, so per-key state would be wiped; synced at init + every `applyHeaderVisibilitySettings()`). Alternate suggestions render as tappable rows that swap into the editable field without losing edits; Rethink rejects the whole shown set and carries the optional steer note (`#readMyMindSteer`, sent as `steer`, shown in ready + empty-result phases, cleared on each open). Suggestions render via value/`textContent` ONLY and Send/Insert go through `POST /input` (server-side, so the sendEnterKey/local-echo trap does not apply) — nothing auto-sends, ever. User guide: `docs/readmymind.md`.
+**Read My Mind intent profiles** (`readMyMindEnabled`, SYNCED, default OFF; `docs/readmymind-plan.md`): per-CASE profiles (goals + recent prompts) keyed by owner + realpath(workingDir), captured from the transcript (`transcript:user_prompt`), never the input paths; the listener must stay inside `startTranscriptWatcher()`'s `if (!watcher)` block. Store `src/intent-store.ts` → `intents.json`, ⚠️ written 0600 tmp+rename and never fed to `/api/search` (prompts carry secrets). Routes in `readmymind-routes.ts` (ownership via `findSessionOrFail` WITH `req`); predictor = pure `readmymind-context.ts` + IO in `readmymind-collectors.ts` + `readmymind-predictor.ts`, claude-only, one in flight per session (409). ⚠️ Suggestions render via value/`textContent` ONLY and nothing auto-sends, ever. Frontend `readmymind-ui.js`. → [architecture-invariants#read-my-mind-intent-profiles](docs/architecture-invariants.md#read-my-mind-intent-profiles)
 
-**Voice dictation via Claude** (`claudeVoiceEnabled`, SYNCED, default OFF): the mic button can transcribe through this machine's Claude Code login instead of a Deepgram key, using the same speech-to-text service the CLI's own `/voice` mode uses. ⚠️ **Claude Code's voice mode itself is unusable here**: it opens the HOST's microphone (`sox`/`arecord`), and the CLI runs in a headless tmux pane while the human is in a browser elsewhere. So Codeman captures in the browser and borrows only the backend. Audio goes browser → Codeman → Anthropic (`src/web/voice-stream.ts`): the OAuth token never reaches the page, and the browser only sends PCM and receives text. ⚠️ Credentials are **read-only** (`src/claude-credentials.ts`) and Codeman never refreshes them — a refresh rotates the refresh token and could sign the user out of their own CLI; an elapsed token reports `expired` instead. ⚠️ Capture MUST be linear16/16 kHz/mono, so it uses an **AudioWorklet**, not MediaRecorder (which cannot emit raw PCM); `voice-pcm-worklet.js` is fetched from JS, so it is invisible to `cacheBustAssets` and borrows voice-input.js's `?v=` token — **edit the two together**. ⚠️ Transcript frames carry the WHOLE running transcript, not deltas: the Claude path replaces where the Deepgram path appends. Provider choice is `voiceSettings.provider` (`auto` prefers Claude → Deepgram → Web Speech). → `docs/claude-voice-plan.md`
+**Voice dictation via Claude** (`claudeVoiceEnabled`, SYNCED, default OFF): the mic transcribes through this machine's Claude Code login (the CLI `/voice` backend) instead of Deepgram; the browser captures, `src/web/voice-stream.ts` relays to Anthropic. ⚠️ The OAuth token never reaches the page. ⚠️ Credentials are READ-ONLY (`src/claude-credentials.ts`): never refresh them (it rotates the refresh token and can sign the user out of their CLI). ⚠️ Capture must be linear16/16 kHz/mono via an AudioWorklet; `voice-pcm-worklet.js` borrows voice-input.js's `?v=` token, so edit the two together. ⚠️ Claude transcript frames are cumulative: replace, never append. → [architecture-invariants#voice-dictation-via-claude](docs/architecture-invariants.md#voice-dictation-via-claude)
 
 **Agent Teams**: `TeamWatcher` polls `~/.claude/teams/`, matches to sessions via `leadSessionId`. Teammates are in-process threads appearing as subagents. Enable: `CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1`. See `docs/agent-teams/`.
 
 **Circuit breakers**: the Ralph breaker prevents respawn thrashing (`CLOSED` → `HALF_OPEN` → `OPEN`; reset via `/api/sessions/:id/ralph-circuit-breaker/reset`). **Distinct: the PTY-exit breaker** (`session-pty-exit-breaker.ts`) trips after repeated rapid PTY exits and blocks auto-restarts. ⚠️ It resets ONLY via an explicit `{clearBreaker:true}` body on `POST /api/sessions/:id/interactive`; the frontend's auto-reattach in `selectSession()` sends no body and must never clear it. → [architecture-invariants#circuit-breakers-ralph--pty-exit](docs/architecture-invariants.md#circuit-breakers-ralph-and-pty-exit)
 
-**Full-scrollback replay**: `GET /api/sessions/:id/terminal?full=1` returns the entire tmux scrollback, bounded by the configured history limit. On success the capture is returned ALONE (`source='mux-full-history'`), superseding the byte buffer so nothing duplicates. The first load of each non-shell TUI session per page requests `full=1` (`_fullHistoryLoaded` Set); Shell selection and automatic drop recovery always use a bounded 1 MiB `?tail=` window. Shell loads the rest only when **Load full history** is pressed; ordinary scrolling must not trigger a multi-megabyte reset+replay on xterm's main thread. Other modes may re-pull at the TOP (cooldown-guarded — tmux repaints bursty output in place, so browser scrollback shrinks while tmux's history stays complete). Live writes are one-chunk-in-flight, released by xterm's parse callback, so xterm's private queue cannot bypass the browser's 128 KiB render cap. While WebSocket owns terminal I/O, duplicate SSE terminal events are dropped before JSON parsing, and recovery is single-flight per active session. ⚠️ **A `full=1` capture ENDS with a cursor move back to the pane's own caret position**, counted UP from the last replayed row — without it the caret stays where the last character landed, which for an agent CLI is the status line, and every cursor-relative update the CLI sends afterwards is measured from the wrong row. The move is relative, not `CUP`: absolute row addressing is only right while the browser's rows equal the pane's, and `resizeWindow` does not wait for tmux, so a capture can be taken before a requested resize applies. That makes row alignment load-bearing on this path: no transform that can DELETE A LINE may run over the capture, so it keeps its trailing blank rows and skips redraw-bloat stripping, the banner trim and the leading-whitespace strip. ⚠️ Those three skips key on whether a capture actually CAME BACK (`isFullCapture`), never on `?full=1` alone — the fallback to the byte history is a stream of successive frames that must still be stripped, and a session with no mux takes it on every load. A capture holding nothing visible returns '' so the byte history survives instead of a blank screen replacing it. ⚠️ A full re-pull must never DOWNGRADE the buffer: a repaint-mode CLI pane keeps no tmux history, so its capture is one frame and the reset+rewrite would delete history mid-scroll — `_replayWouldShrinkBuffer()` refuses it and slows that session's cooldown to 60s. ⚠️ **A visible capture now REPORTS the geometry it was taken at** (`captureCols`/`captureRows`, #435), because a frame built for a pane taller or wider than the browser is damaged two ways at once (overflow rows clamp onto the last line; a narrower browser wraps every painted row) and nothing in the response used to say so. Both fields are ABSENT when no frame was positioned, so every consumer tests `Number.isFinite`, never truthiness: a `display-message` cursor query that fails makes `capturePaneBuffer` return the raw capture while the route still labels it `mux-visible`. The comparison runs on `mux-visible` ONLY, the replay is capped at one attempt, and a pane that cannot be sized to fit latches in `_geometryRetryUseless` so it is diagnosed once per session rather than on every tab switch. → [architecture-invariants#full-scrollback-replay](docs/architecture-invariants.md#full-scrollback-replay)
+**Full-scrollback replay**: `GET /api/sessions/:id/terminal?full=1` returns the whole tmux scrollback ALONE (`source='mux-full-history'`), superseding the byte buffer. First load of each non-shell TUI session requests it (`_fullHistoryLoaded`); Shell selection and drop recovery use a bounded 1 MiB `?tail=`, and a Shell scroll-to-top pulls a bounded `?full=1&tail=` window (a window no longer than the browser's buffer is skipped before the downgrade guard, so it never marks the session exhausted); the unbounded pull stays behind **Load full history**. A Shell split-pane Pane B has its own copy of the bounded pull against its own xterm (`SplitTerminalPane._pullHistory`, terminal-split.js); keep the two in step. → [architecture-invariants#split-pane-sessions](docs/architecture-invariants.md#split-pane-sessions) ⚠️ The capture ends with a RELATIVE cursor move back to the pane's caret (never `CUP`), so no line-deleting transform may run over it; those skips key on `isFullCapture`, never on `?full=1` alone. ⚠️ A re-pull must never shrink the buffer (`_replayWouldShrinkBuffer()`). ⚠️ `captureCols`/`captureRows` are absent when no frame was positioned: test `Number.isFinite`, never truthiness. ⚠️ A frame dropped at the 128 KiB render cap MUST be recovered, and the recovery verifies itself: `_scheduleDroppedOutputRecovery` re-arms (bounded by `DROP_RECOVERY_MAX_ATTEMPTS`) while `_onSessionNeedsRefresh` reports no repaint, but never after a capture-fetch `'deadline'`. → [architecture-invariants#full-scrollback-replay](docs/architecture-invariants.md#full-scrollback-replay)
 
-**Terminal touch gestures: link taps and text selection**: on a touch device xterm's own handlers see neither — `touch-action: none` plus touchstart's preventDefault suppress the browser's compatibility mouse events, `_installMobileTapMouseGuard` drops the trusted ones that still arrive, and the synthetic `mousedown`/`mouseup` pair dispatched for mouse REPORTING goes to the `.xterm` root, an ANCESTOR of the screen element the linkifier and SelectionService listen on. So both gestures are driven explicitly. ⚠️ **A tap activates the link under it** through the SAME provider that feeds the hover linkifier (`_terminalLinkAtPoint`, containment mirroring xterm's `_linkAtPosition`), synchronously inside `touchend` — that is what keeps the user gesture `window.open` needs — and BEFORE any mouse report, mirroring `_handleDesktopTerminalClick`'s skip for a hovered link. Two rows keep their meaning: the caret's logical line (`_tapIsOnCaretLine`, where a tap places the cursor in text the USER typed) and TUI-owned rows (`_isActionableMobileTerminalTap`, answering a dialog). ⚠️ The caret line is the boundary rather than the tap INTENT, because a shell classifies every tap as `'input'` and gating on that would leave every URL in shell output inert. ⚠️ **Long-press selects** by driving xterm's public `select()` (renderer-independent — under WebGL the glyphs are pixels and native selection cannot exist), drag or a further tap extends, and Copy goes through `copyTerminalSelection()` for its execCommand fallback on plain-HTTP installs. Three guards are load-bearing and each came from a real phone: the compat mouse pair after `touchend` (xterm focuses on mousedown and SelectionService resets the model there, so the keyboard sprang up and the selection vanished on lift), the platform's own ~500ms long-press (Android Chrome focuses the nearest editable element — the helper textarea — through no event a handler can preventDefault, so a bounded focus guard blurs it and `contextmenu` is suppressed for the gesture window), and `copyTerminalSelection()`'s closing `terminal.focus()` (right on desktop, wrong on a phone). Tests: `test/terminal-touch-tap.test.ts`.
+**Split-pane sessions** (`showSplitButton`, header button, default OFF, desktop-only, per-device): a second live session ("Pane B") beside the active one, in its own `SplitTerminalPane` (terminal-split.js) with its own xterm + WebSocket, resizable via a draggable divider. Deliberately plainer than the primary pane — no local-echo overlay, CJK IME, or touch handlers — and NOT persisted across reloads. → [architecture-invariants#split-pane-sessions](docs/architecture-invariants.md#split-pane-sessions)
 
-**Auto Copy (copy-on-select)** (`autoCopySelection`, per-device, default OFF): a finished terminal selection lands on the clipboard with no keystroke. ⚠️ It fires at the END of a gesture, never in `onSelectionChange` (that callback runs per cell crossed, so copying there is one clipboard write per mouse move); it only ARMS `_autoCopyPending`, and a document-level `mouseup` listener flushes. ⚠️ The flush is SYNCHRONOUS inside the handler because both clipboard paths need user activation (Firefox gates `navigator.clipboard.writeText` on it, and the plain-HTTP `execCommand` fallback must run in the gesture's own task); a timer or a wait for `onSelectionChange` loses it, invisibly in Chrome. ⚠️ Touch needs its OWN calls from `_endTouchSelectionGesture()`/`_selectTouchSelectionLine()`: that path `preventDefault()`s its touchend, so no mouseup ever arrives and the toggle would be dead on phones. ⚠️ Unlike `copyTerminalSelection()` it must NOT clear the selection (the text would vanish under the cursor that highlighted it) and must NOT focus the terminal (that opens the on-screen keyboard over it); focus is RESTORED to whatever held it, which only matters for the `execCommand` fallback. Guards are pure in `decideAutoCopy()` (constants.js): off, blank/whitespace-only, and a 1M-char cap (an autoscrolling drag can sweep the whole 50k-line scrollback), refused rather than truncated with a toast pointing at Ctrl+C. Silent on success except once per page load; failures toast, throttled 10s. Tests: `test/terminal-auto-copy.test.ts`.
+**Terminal touch gestures: link taps and text selection**: on touch devices xterm's linkifier and SelectionService never see the gesture, so both are driven explicitly (terminal-ui.js). ⚠️ A tap activates the link under it through the SAME provider as the hover linkifier (`_terminalLinkAtPoint`), synchronously inside `touchend` (keeps the user gesture `window.open` needs) and BEFORE any mouse report; the caret's logical line (`_tapIsOnCaretLine`) and TUI-owned rows (`_isActionableMobileTerminalTap`) keep their meaning. ⚠️ Gate on the caret line, never on tap intent (a shell calls every tap `'input'`). ⚠️ Long-press selects via xterm's public `select()`; keep the three guards: suppress the compat mouse pair after `touchend`, the bounded focus guard + `contextmenu` suppression for the platform long-press, and no closing `terminal.focus()` on phones. Tests: `test/terminal-touch-tap.test.ts`. → [architecture-invariants#terminal-touch-gestures-link-taps-and-text-selection](docs/architecture-invariants.md#terminal-touch-gestures-link-taps-and-text-selection)
 
-**Ctrl+V paste trap** (`image-input.js`): `Ctrl+V` routes through `_handleImagePaste()`, which appends a hidden `contenteditable` trap, focuses it, and reads the clipboard out of the paste event that lands there. Images upload and their saved paths are typed into the session; text goes through `terminal.paste()` so bracketed-paste markers survive. ⚠️ **The trap must consume exactly ONE paste event.** Two routes deliver one for a single keypress and Firefox fires both: `document.execCommand('paste')` dispatches a trusted event and still returns `false`, because the trap cancels it, while Chromium refuses that command and dispatches nothing; separately, the keydown's own default action delivers a paste to the now-focused trap, because returning `false` from the custom key handler never cancels the DOM event (see smart copy above). Measured on a live install: Firefox two events per keypress, Chromium and WebKit one. Handling both wrote the clipboard to the PTY twice, and right-click → Paste stayed correct because it carries no keydown. ⚠️ Removing the `execCommand('paste')` call would also end the doubling, and all three engines still deliver one event without it, but it stays for the mobile engines a desktop measurement cannot reach: where a browser aims the key's default action at the element focused when the keydown began, the command is the only route into the trap, and the trap is the only place image blobs are read. The one-shot flag lives on the trap rather than on a browser check, so any count produces one insert. Tests: `test/image-paste-trap.test.ts`. → [architecture-invariants#terminal-paste-ctrlv](docs/architecture-invariants.md#terminal-paste-ctrlv)
+**Auto Copy (copy-on-select)** (`autoCopySelection`, per-device, default OFF): a finished terminal selection lands on the clipboard with no keystroke. ⚠️ Copy at the END of a gesture, never in `onSelectionChange` (per-cell); it only arms `_autoCopyPending` and a document-level `mouseup` flushes. ⚠️ The flush must be SYNCHRONOUS in the handler (both clipboard paths need user activation); never defer it to a timer. ⚠️ Touch needs its own calls from `_endTouchSelectionGesture()`/`_selectTouchSelectionLine()` (no mouseup arrives). ⚠️ Unlike `copyTerminalSelection()`, never clear the selection or focus the terminal; restore prior focus. Guards are pure in `decideAutoCopy()` (constants.js, 1M-char cap, refused not truncated). Tests: `test/terminal-auto-copy.test.ts`. → [architecture-invariants#auto-copy-copy-on-select](docs/architecture-invariants.md#auto-copy-copy-on-select)
 
-**Terminal scrollback strip + wheel/touch forwarding** (#205): codex/claude/gemini get the FULL strip (alt-screen, `3J`, mouse DECSETs); tmux-backed shell/opencode/antigravity/omp get a NARROW strip (alt-screen toggles only — it removes tmux's own attach-time `smcup`, which otherwise parks xterm in the scrollback-less alt buffer and turns the wheel into arrow keys). ⚠️ Gated on `useMux`: direct-PTY fallback sessions must keep the alt screen for vim/less/htop. Wheel AND touch forward to the CLI transcript for **claude ≥ 2.1.187 ONLY** at ANY scroll position (snap-to-bottom first); Shift+wheel and the `terminalWheelLocalScrollback` setting stay local. ⚠️ Codex was in that list and must never go back without a fresh measurement: codex-cli 0.147.0 ignores SGR wheel reports entirely (`mouse_any_flag=0`, inline viewport, transcript pushed into terminal scrollback), so forwarding produced a dead wheel (#227 follow-up). `_wheelScrollLines()` reads `ev.deltaMode` (Firefox = LINE units). ⚠️ When that gate is FALSE on a claude session whose local buffer is hollow (`baseY === 0`), the gesture becomes coalesced PageUp/PageDown key sends (`_maybePageCliTranscript`) instead of a no-op; ⚠️ and `getClaudeCliVersion()` must never cache a FAILED probe (one timeout used to disable forwarding process-wide until restart). ⚠️ **A click is hand-reported to the CLI only while the CLI actually has mouse tracking on.** The full strip removes the mouse DECSETs, so xterm's `mouseTrackingMode` is permanently `none` there and the browser hand-encodes SGR reports (`_sendSyntheticSgrTap`); without state it did that on EVERY click, so a stripped-mode pane running a plain shell (CLI exited, or a shell started inside a claude-mode session) received reports it never asked for and printed them as literal text (`[<0;88;20M`), garbling the next typed line. `_recordStrippedMouseMode()` (session.ts) records what the strip removes, `toState()` publishes `cliMouseTracking`, and `_shouldReportMouseToCli()` gates all three report sites on it. Only 1000/1001/1002/1003 count (1005/1006 are encodings, 1007 is alt-scroll), and the change broadcasts UNdebounced since a dialog can be clicked inside the 500ms window. `_logScrollRouting()` prints the routing decision and its inputs once per session — read it before diagnosing a scroll report. → [architecture-invariants#terminal-scrollback-strip-flavors-and-wheeltouch-forwarding](docs/architecture-invariants.md#terminal-scrollback-strip-flavors-and-wheeltouch-forwarding)
-**Detached start + service install** (issue #231): `codeman web -d` relaunches the SAME entry script with `detached:true` (setsid), so there is no controlling terminal and no shell job entry. ⚠️ `nohup` is NOT what makes this work: Node re-arms SIGHUP to its default disposition even when it inherits "ignore", and `cli.ts` handles SIGHUP with a graceful shutdown, so a delivered HUP still stops the server. ⚠️ Both `-d` and `service install` must REFUSE when a server is already up on this data dir (pidfile check + `/api/status` probe): a second instance on the shared tmux socket attaches PTYs to the first one's live sessions. ⚠️ Neither may report success it has not observed — the parent polls `/api/status` until the child answers or dies, since `launchctl load` and a clean spawn are both silent about a server that starts and immediately exits. `--stop` verifies the pid still LOOKS like a Codeman server (`ps -o command=`) before signalling, because pids get recycled. Unit/label names live in `config/service-names.ts` so install.sh, `detectSupervisor()` and `service install` cannot drift into supervising two copies; they are instance-scoped, and identical to the historical names for the default instance. `service install` bakes the installing shell's PATH into the unit (launchd gives a job `/usr/bin:/bin:/usr/sbin:/sbin`, which finds neither a Homebrew/nvm `node` nor `tmux`/`claude`) and never writes `CODEMAN_PASSWORD` into it. → [architecture-invariants#detached-start-and-service-install](docs/architecture-invariants.md#detached-start-and-service-install)
+**Ctrl+V paste trap** (`image-input.js`): `Ctrl+V` routes through `_handleImagePaste()`, which focuses a hidden `contenteditable` trap and reads the clipboard from the paste event landing there; images upload and their paths are typed in, text goes through `terminal.paste()` so bracketed-paste markers survive. ⚠️ **The trap must consume exactly ONE paste event** (Firefox delivers two per keypress: the `execCommand('paste')` event and the keydown's default action); the one-shot flag lives on the trap, never on a browser check. ⚠️ Do not remove the `execCommand('paste')` call: on some mobile engines it is the only route into the trap, and the trap is the only place image blobs are read. Tests: `test/image-paste-trap.test.ts`. → [architecture-invariants#terminal-paste-ctrlv](docs/architecture-invariants.md#terminal-paste-ctrlv)
 
-**Self-update** (App Settings → System → Updates): in-app updater for git-clone installs supervised by systemd/launchd (`systemd`, `launchd`, `launchd-daemon`, `docker-compose`, else `none` → "restart manually"). The update restarts the very process running it, so the real work runs in a DETACHED `scripts/self-update.sh` that outlives the restart and writes progress to `update-status.json`, which the browser polls across the connection drop. `src/web/self-update.ts` splits pure helpers (unit-tested) from IO wrappers. npm installs report as non-updatable. ⚠️ **The Compose deployment is the one supervisor that does NOT outlive the restart**: there the restart IS the container exiting (`restart: unless-stopped` relaunches it), which kills the script too — safe only because the terminal `restarting` marker is written BEFORE the kill, so nothing may be appended after it. Two config facts make it work at all and both are load-bearing: the repo is a HOST BIND MOUNT over `/opt/codeman` (a pull into the baked image copy would land in the writable layer and be silently discarded by the next `up`), and the runtime image keeps devDependencies + a build toolchain (`npm run build` is tsc+esbuild, and node-pty has no Linux prebuild), which is why `npm prune --omit=dev` is gone and the updater passes `--include=dev` against `NODE_ENV=production`. ⚠️ An in-place container update applies CODE ONLY — a restart reuses the existing image and config — so `evaluateEnvironmentGate()` REFUSES a release that changes `server.Dockerfile`/`docker-compose.yaml` (sha256 vs the baseline `Start-Codeman.sh` writes to `docker-env-applied.json` on every start) or adds `.env.example` keys the user's `.env` lacks, and refuses when the restart policy would not bring the container back. That third check exists because **Compose resolves an unset `${VAR}` to the EMPTY STRING and starts anyway**, so a new required setting otherwise arrives as a silently blank env var. Every unknown fails OPEN in the gate (no baseline, unreadable `.env`, no socket): failing closed would permanently block containers created before the fingerprint file existed. ⚠️ The KILL does not: the server exits only when `--restart-by-exit 1` was passed, i.e. the Compose file declared `CODEMAN_RESTART_BY_EXIT=1` (set ONLY there, since that file is what sets `restart: unless-stopped`; the image ENV deliberately does not) or the daemon reported an auto-restart policy; otherwise the build lands as `completed-needs-manual-restart`, because exiting blind takes a `docker run` container with no restart policy down with no UI left to recover it. The gate is re-evaluated on `POST /api/system/update`, so hiding the button is UX, not the control. ⚠️ The four global agent CLIs in `server.Dockerfile` are PINNED on purpose — unpinned, a user's CLI versions are a function of when their image was built rather than of any commit, which is the one environment change no diff-derived gate can see; pinning turns it into a Dockerfile change the gate already catches. `test/docker-compose-env-parity.test.ts` is the merge-side guard (every compose `${VAR}` ↔ an `.env.example` entry). → [docs/docker-self-update.md](docs/docker-self-update.md), [architecture-invariants#self-update](docs/architecture-invariants.md#self-update)
+**Terminal scrollback strip + wheel/touch forwarding**: codex/claude/gemini get the FULL strip (alt-screen, `3J`, mouse DECSETs); tmux-backed shell/opencode/antigravity/omp get a NARROW strip (alt-screen toggles only). ⚠️ Gated on `useMux`: direct-PTY sessions must keep the alt screen. Wheel and touch forward to the CLI for **claude ≥ 2.1.187 ONLY, and only while it has mouse tracking on** (`cliMouseTracking`: fullscreen claude sets it, its default inline renderer does not and scrolls locally like codex); ⚠️ never re-add codex without a fresh measurement (it ignores SGR wheel reports). ⚠️ `getClaudeCliVersion()` must never cache a FAILED probe. ⚠️ Hand-report clicks only while the CLI has mouse tracking on: `_shouldReportMouseToCli()` gates all three report sites on `cliMouseTracking` (from `_recordStrippedMouseMode()`, session.ts), or a plain shell prints the reports as literal text. Read `_logScrollRouting()` before diagnosing a scroll report. → [architecture-invariants#terminal-scrollback-strip-flavors-and-wheeltouch-forwarding](docs/architecture-invariants.md#terminal-scrollback-strip-flavors-and-wheeltouch-forwarding)
+**Detached start + service install**: `codeman web -d` relaunches the same entry script `detached:true` (setsid); `nohup` is not what makes it survive. ⚠️ Both `-d` and `service install` must REFUSE when a server is already up on this data dir (pidfile + `/api/status` probe), or a second instance attaches to the first one's live sessions. ⚠️ Never report success not observed: poll `/api/status` until the child answers or dies. `--stop` must verify the pid still looks like Codeman (`ps -o command=`) before signalling. Unit/label names live only in `config/service-names.ts`. `service install` bakes the installing shell's PATH into the unit and never writes `CODEMAN_PASSWORD` into it. → [architecture-invariants#detached-start-and-service-install](docs/architecture-invariants.md#detached-start-and-service-install)
 
-**Reverse-proxy base path** (`--base-url` / `CODEMAN_BASE_URL`, default `/`; `src/config/base-path.ts` is the pure single-source, normalized to `''` for root or `/foo`): lets Codeman be mounted under a sub-path behind a proxy that **forwards the prefix unchanged** (does NOT strip it). Deliberately few choke points, mirrored ingress/egress: **(server ingress)** `stripBasePath()` runs inside Fastify's `rewriteUrl` so ALL routes stay declared prefix-agnostic (`/api/...`, `/ws/...`) — and a request arriving WITHOUT the prefix (hooks, health checks, docker bridge, all hitting the raw port) is left untouched, so the server answers at both; **(server egress)** one `onSend` hook prepends the base to every root-absolute `Location` header, covering all redirects; **(HTML)** `renderIndexHtml` rewrites the shipped `<base href="/">` to the mount and injects `window.__CODEMAN_BASE__` — the template's asset refs are all RELATIVE so `<base>` handles them for free; **(frontend runtime URLs)** root-absolute URLs ignore `<base>`, so `CodemanBase.url()` (constants.js) is the route builder, applied transparently by a `fetch` wrapper and explicitly at the few EventSource/WebSocket/`window.open`/`<img|iframe|a>`-src sites; **(sw.js/manifest)** the worker derives its base from `self.location`, the manifest uses relative `start_url`/`scope`; **(web-tab proxy)** `proxyPrefixFor(cap, basePath)` is the single base-aware root that cascades to the injected `<base>`, root-absolute HTML rewrites, the `runtimeUrlShim`, `Set-Cookie` Path and `Location` rebasing — while the INGRESS parsers (`capabilityFromProxyPath`, `resolveUpstreamUrl`) stay base-agnostic because `rewriteUrl` strips the prefix before routing, and `capabilityFromReferer(referer, basePath)` strips it from the browser-supplied Referer. ⚠️ `--base-url` rides the daemon relaunch via `buildWebArgs` and the service unit via `resolveServicePlan`. Pure helpers unit-tested in `test/base-path.test.ts` + `test/webview-proxy.test.ts`; HTML injection in `test/render-index-html.test.ts`.
+**Self-update** (App Settings → System → Updates): in-app updater for git-clone installs under a supervisor (`systemd`, `launchd`, `launchd-daemon`, `docker-compose`, else `none`). The work runs in a DETACHED `scripts/self-update.sh` writing `update-status.json`, polled across the restart; pure helpers in `src/web/self-update.ts`. ⚠️ Compose: the restart kills the script, so nothing may be appended after the `restarting` marker; the repo must stay a host bind mount over `/opt/codeman` and the image must keep devDependencies + toolchain. ⚠️ `evaluateEnvironmentGate()` refuses releases that change `server.Dockerfile`/`docker-compose.yaml` or add `.env.example` keys, re-evaluated on `POST /api/system/update`; unknowns fail OPEN, but the exit-to-restart needs `--restart-by-exit 1` (`CODEMAN_RESTART_BY_EXIT=1` only in the Compose file). ⚠️ Keep the agent CLIs in `server.Dockerfile` pinned. → [docs/docker-self-update.md](docs/docker-self-update.md), [architecture-invariants#self-update](docs/architecture-invariants.md#self-update)
+
+**Reverse-proxy base path** (`--base-url` / `CODEMAN_BASE_URL`, default `/`; pure single source `src/config/base-path.ts`, normalized to `''` or `/foo`): mounts Codeman under a sub-path behind a proxy that forwards the prefix unchanged. Few choke points: `stripBasePath()` in Fastify's `rewriteUrl` (routes stay prefix-agnostic; unprefixed requests still answer), one `onSend` hook rebasing `Location`, `renderIndexHtml` rewriting `<base href>` + injecting `window.__CODEMAN_BASE__`, and `CodemanBase.url()` (constants.js) for runtime URLs. ⚠️ Keep template asset refs RELATIVE, and route every root-absolute frontend URL (EventSource/WebSocket/`window.open`/src) through `CodemanBase.url()`. ⚠️ Web-tab proxy egress goes through `proxyPrefixFor(cap, basePath)`; ingress parsers stay base-agnostic. ⚠️ `--base-url` must ride `buildWebArgs` and `resolveServicePlan`. Tests: `test/base-path.test.ts`. → [architecture-invariants#reverse-proxy-base-path](docs/architecture-invariants.md#reverse-proxy-base-path)
 
 **Attachments** (live external document references; all wiring in `file-routes.ts`): a **registry** maps a stable `attachmentId` to a realpath-resolved, extension-allowlisted absolute path, so browser requests never carry arbitrary absolute paths. ⚠️ The **magic-link scanner** (`codeman://attach?...` in terminal output) is **prompt-injectable**, so its scan path is force-confined to the session workspace; a hostile prompt could otherwise exfiltrate arbitrary host files over SSE. The security gate is an extension **allowlist**, not a blocklist. `document-conversion-limiter.ts` caps converter spawns globally: without it, N large docs detected at once fork N multi-minute processes, which is a resource-exhaustion vector. → [architecture-invariants#attachments](docs/architecture-invariants.md#attachments)
 
-**File-path links (terminal + chat)**: a path an agent prints is clickable on BOTH surfaces and opens the file-preview overlay. ⚠️ ONE pattern (`FILE_PATH_LINK_PATTERN` / `absoluteFilePathPattern()` in constants.js) feeds the xterm link provider AND the response viewer's `_linkifyFilePaths()`; a fresh instance per call, since `lastIndex` is per-object state. The chat linkifier walks TEXT NODES with DOM APIs (the source is model output; never rebuild sanitized markup as a string) and skips subtrees already inside an `<a>`. ⚠️ **An out-of-workspace path is served through the ATTACHMENT routes, not the file routes** — `file-content`/`file-raw` are workspace-confined and 404 exactly the paths agents print most (a `/tmp` capture, Claude's scratchpad), so `openFilePreview()` registers such a path via `POST /api/sessions/:id/attachments` with **`notify: false`** (suppresses only the `attachment:detected` broadcast — same guard, same routes; without it every click also popped a card announcing the file already on screen) and renders by id. The click is an explicit action on the explicit, Origin-guarded route, which is what distinguishes it from the force-confined magic-link scanner. ⚠️ **Media extensions are single-sourced** (`VIDEO_ATTACHMENT_EXTENSIONS`/`AUDIO_ATTACHMENT_EXTENSIONS` in `attachment-registry.ts`, imported by `file-content`'s classification) so a clip plays the same in or out of the workspace; a player needs all THREE of allowlist + a real `MIME_TYPES` entry (octet-stream renders a dead player) + the range-aware body. ⚠️ **`TEXT_ATTACHMENT_EXTENSIONS` IS `EDITABLE_EXTENSIONS`** (never a second list): if the viewer would edit it inside the workspace, it can be read outside. Widening READ must never widen RUN, so `html`/`htm` joined `svg` in `serveRawFile`'s download-only branch, other text goes out as inert `text/plain`+`nosniff`, and `~/.codeman*/state.json` joined `isSensitivePath` (it persists `envOverrides`, which can hold `GEMINI_API_KEY`). ⚠️ The terminal sends an **out-of-workspace** path to the preview instead of the log viewer (that one spawns `tail -f` and reaches only workspace + `/var/log` + `~/logs`); in-workspace text keeps the tail viewer and `file-stream-manager`'s allowlist is untouched. The image-watcher keeps its own narrow detection list, so none of this cards every file an agent writes. → [architecture-invariants#file-path-links-terminal--response-viewer](docs/architecture-invariants.md#file-path-links-terminal--response-viewer)
+**File-path links (terminal + chat)**: a path an agent prints is clickable on BOTH surfaces and opens the file-preview overlay. ⚠️ ONE pattern (`FILE_PATH_LINK_PATTERN` / `absoluteFilePathPattern()` in constants.js) feeds the xterm link provider AND `_linkifyFilePaths()`, a fresh instance per call (`lastIndex`). The chat linkifier walks TEXT NODES with DOM APIs, never rebuilds sanitized markup as a string. ⚠️ An out-of-workspace path goes through the ATTACHMENT routes (`POST /api/sessions/:id/attachments` with `notify: false`), never by widening `file-content`/`file-raw` or `file-stream-manager`'s `tail -f` allowlist. ⚠️ `TEXT_ATTACHMENT_EXTENSIONS` IS `EDITABLE_EXTENSIONS` (never a second list), and widening READ must never widen RUN: `html`/`htm`/`svg` stay download-only, other text is inert `text/plain`+`nosniff`. Media extensions are single-sourced in `attachment-registry.ts`. → [architecture-invariants#file-path-links-terminal--response-viewer](docs/architecture-invariants.md#file-path-links-terminal--response-viewer)
 
 **Filesystem path picker** (Link Existing "Browse" + the mobile keyboard's `📁 Path` key): lazy one-directory browsing via `GET /api/filesystem/browse`, with `GET /api/filesystem/preview` for the tapped file. Inserts the path **without** Enter, so the prompt is never submitted; the sibling `⌫ All` key clears only the unsent prompt and must never send the agent's `/clear`. ⚠️ This is a **second file-serving surface and inherits neither the attachment confinement nor its ownership scoping** — it allowlists Home, `CASES_DIR`, `/mnt/d` and `CODEMAN_FILE_PICKER_ROOTS`, blocks sensitive trees, and rejects symlink escapes **after** `realpath`. ⚠️ The optional `sessionId` is an ownership boundary that must be `canAccessOwned`-checked by hand (it does not go through `findSessionOrFail`), and in multi-user mode a non-admin gets only their own `userSpacePath` as a root: per-user spaces live INSIDE `homedir()`, so a `Home` root exposes every other user's workspace. Previews go through the same global conversion limiter, and Markdown/TXT/JSON are served as inert `text/plain`. → [architecture-invariants#filesystem-path-picker](docs/architecture-invariants.md#filesystem-path-picker)
 
 **File Viewer edit mode** (issue #212): the file-preview overlay edits workspace text files in place — `GET .../file-content?edit=1` + `PUT /api/sessions/:id/file-content`, policy in `src/config/file-editing.ts`. This is a **third file surface and the only one that WRITES**: read-path confinement (realpath + workspace + ownership) plus sensitive/blocked/`.git` denies and an extension **allowlist**; writes are `wx`-temp + rename (no `O_CREAT` anywhere = edit-in-place is structural); optimistic concurrency via sha256 `baseHash` → 409. ⚠️ `edit=1` never truncates and the client must never save a plain-preview buffer (the 500-line truncation would silently delete the rest). ⚠️ CRLF/UTF-8 guards: EOL re-applied server-side, non-UTF-8 refused via round-trip compare. → [architecture-invariants#file-viewer-edit-mode](docs/architecture-invariants.md#file-viewer-edit-mode), `docs/file-viewer-edit-plan.md`
 
-**Files panel search** (COD-236, the `q` param on `GET /api/sessions/:id/files`): `compileFileQuery()` (`utils/file-query.ts`, pure, no IO, so it unit-tests directly) compiles the query into a reusable predicate, which is what lets the server-side walk prune instead of streaming the whole tree. ⚠️ **A query turns that endpoint into a FLAT match list rather than a nested tree**, and the walk deliberately recurses past non-matching directories, since the whole point of searching is to reach a file whose ancestors do not match. An empty or whitespace-only query compiles to `null`, which is what keeps the default tree response byte-identical when no search is requested. ⚠️ **Globs are never compiled into a RegExp**: `*a*a*a…` translated to `^.*a.*a.*a…$` is a classic backtracking blowup evaluated synchronously against every walked path, so one pathological query would freeze the event loop for the whole server (the same reason `search-service.ts` is regex-free). `globMatch()` is a two-pointer wildcard walk instead, O(text · pattern) with both operands short by construction, and an overlong query (`MAX_QUERY_LENGTH`, 256) also compiles to `null` rather than running. A query containing `/` matches the relative path, otherwise the bare entry name; globs match anchored and case-insensitively (`*` spans any run, slashes included, `?` exactly one character), everything else is a plain case-insensitive substring.
+**File Viewer text view: rendered markdown + Lines/Wrap toggles** (`_renderFilePreviewText()` in panels-ui.js): a `.md`/`.markdown` opens RENDERED by default with an `MD` pill back to source; the plain-text view has `Lines` (CSS-counter gutter) and `Wrap` toggles. ⚠️ ONE markdown pipeline: the viewer calls `_renderMarkdown(text, { breaks: false })` (marked + the DOMPurify allowlist, the Response Viewer's; chat keeps the default `breaks: true`, a file must not turn every hard wrap into a `<br>`) and binds the Response Viewer's click delegate (`_bindResponseViewerInteractions`) on the preview body for code-copy buttons and path links; never a second parser or handler. ⚠️ The document is built inside a `<template>` (a detached div with `innerHTML` set starts fetching every `<img src>` before the rewrite), then `_rebaseFilePreviewMarkdownRefs()` points relative images at the workspace-confined `file-raw` under the document's directory and root-relative ones under the workspace root (never a widened route; a failed load degrades to alt text), after `decodeURIComponent`ing the ref and dropping `?query`/`#fragment` (marked percent-encodes destinations, and the route encodes again), and turns workspace links into `a.rv-path` carrying `data-session-id` for the delegate (the linkifier's absolute paths get it too), stripping the `target` marked gave them. ⚠️ A preview opened by attachment id under a bare file name (attachment cards, history drawer: the registry keeps no relative path) has no directory, so its workspace refs degrade (images to alt text, links to their text), never resolve against the workspace root. ⚠️ The container carries `data-i18n-skip` or the translator rewrites the document's prose. ⚠️ Toggles are per-device localStorage keys (`codeman:filePreview*`), never `SettingsUpdateSchema`; Lines/Wrap are class flips on the ONE `<pre>`, with rules scoped `.file-preview-body > pre.file-preview-text` so they never leak into the document's code blocks. Markdown fetches `lines=10000` (the route ceiling), other text keeps 500. ⚠️ `md` stays OUT of `FILE_PREVIEW_EXTENSIONS`: only an IN-WORKSPACE `.md` path clicked in the TERMINAL keeps the tail viewer (live follow); the Files panel, chat paths, out-of-workspace terminal paths and attachment cards all reach `openFilePreview()` and render it. Tests: `test/file-preview-markdown.test.ts`. → [architecture-invariants#file-viewer-text-view-rendered-markdown-and-text-toggles](docs/architecture-invariants.md#file-viewer-text-view-rendered-markdown-and-text-toggles)
 
-**Raw file bodies are streamed and range-aware**: `file-raw`, the attachments `/raw` route and `GET /api/download` always advertise `Accept-Ranges: bytes` and answer a `Range` header with `206` + `Content-Range` (single-range only; parser is pure + unit-tested in `src/web/http-range.ts`, a malformed spec is ignored → 200 while an out-of-bounds one is a 416). ⚠️ **The size cap on all three is a sanity bound, not memory protection** (`MAX_FILE_DOWNLOAD_BYTES` in `config/buffer-limits.ts`, default 2GB, env `CODEMAN_MAX_DOWNLOAD_BYTES`, `0` = unlimited): the bodies stream, so size costs a read stream and not RSS (measured: a 600MB download moved peak RSS by ~37MB). Its predecessor was a hardcoded 50MB whose comment still said "prevent memory exhaustion" long after the `readFile()` it described was replaced by `sendFileBody()`, so all it did was refuse legitimate downloads of build artifacts, videos and archives. `/api/download` was the last route that really did buffer the whole file, and now shares `sendFileBody()` with the other two. ⚠️ A 200-only response is what made the File Viewer's `<video>` unseekable: Chrome then reports `video.seekable` as `[0, 0]`, the scrub bar is inert and `currentTime = x` silently reverts (measured on an 18MB mp4), and Safari refuses to start the media at all. ⚠️ These bodies go out through `reply.hijack()`, which bypasses Fastify's status handling — `sendRawStream` must copy the status onto `reply.raw` by hand or a partial body ships labelled `200` and the browser treats a slice as the whole file. ⚠️ Closing the preview must **pause and unload** the media (`_stopFilePreviewMedia` in panels-ui.js): dropping the overlay's `visible` class is `display:none` and nothing else, and a DETACHED `HTMLMediaElement` keeps playing, which is how the X button used to leave a video audible with no player to pause.
+**Files panel search** (COD-236, the `q` param on `GET /api/sessions/:id/files`): `compileFileQuery()` (`utils/file-query.ts`, pure) compiles the query into a predicate the server-side walk prunes with; a query returns a FLAT match list and the walk recurses past non-matching directories. An empty, whitespace-only or overlong (`MAX_QUERY_LENGTH`, 256) query compiles to `null`, keeping the default tree response byte-identical. ⚠️ **Never compile a glob into a RegExp** (`*a*a*a…` backtracks and freezes the event loop for the whole server): `globMatch()` is a two-pointer wildcard walk. → [architecture-invariants#files-panel-search](docs/architecture-invariants.md#files-panel-search)
+
+**Raw file bodies are streamed and range-aware**: `file-raw`, the attachments `/raw` route and `GET /api/download` share `sendFileBody()`, advertise `Accept-Ranges: bytes` and answer `Range` with `206` + `Content-Range` (single-range, parser in `src/web/http-range.ts`); without it `<video>` cannot seek. The size cap (`MAX_FILE_DOWNLOAD_BYTES`, default 2GB, env `CODEMAN_MAX_DOWNLOAD_BYTES`, `0` = unlimited) is a sanity bound, not memory protection; never reintroduce a whole-file buffer. ⚠️ Bodies go out via `reply.hijack()`, so `sendRawStream` must copy the status onto `reply.raw` by hand or a partial body ships as `200`. ⚠️ Closing the preview must pause and unload media (`_stopFilePreviewMedia`), since a detached `HTMLMediaElement` keeps playing. → [architecture-invariants#raw-file-bodies-streamed-and-range-aware](docs/architecture-invariants.md#raw-file-bodies-streamed-and-range-aware)
 
 **Ultracode / workflow-run visualization** (opt-in, default OFF): the Workflow tool writes a completion artifact only at run *end*, so live in-flight runs exist solely as transcript dirs. `workflow-run-watcher.ts` therefore synthesizes ACTIVE runs from transcripts until the completion artifact appears and supersedes them. It is **STANDALONE** and deliberately never imports or touches `subagent-watcher.ts`, despite reading the same tree. Two independent toggles: `showUltracodeAgents` (docked panel) and `ultracodeFloatingWindows` (floating windows); the watcher starts if **either** is on. → [architecture-invariants#ultracode--workflow-run-visualization](docs/architecture-invariants.md#ultracode-and-workflow-run-visualization)
 
-**Clone a repository as a case** (issue #236, Add Case → **Clone Repo**): `POST /api/cases/clone` clones a public repo into the caller's case space synchronously (request held open, bounded by `GIT_CLONE_TIMEOUT_MS`, no job store); `POST /api/cases/clone-preflight` reports whether the URL can be cloned anonymously plus its real branches/tags. Core in `src/git-clone.ts`. ⚠️ **The URL is a code-execution surface**: `ext::sh -c <cmd>` (and ANY `<name>::<payload>` helper) makes git run a command, so every `::` form is refused, a leading `-` is refused, and every spawn is an argv array with `--` before the operands. ⚠️ **Non-interactive or the open request hangs** — `gitNonInteractiveEnv()` closes the terminal/askpass/ssh/GCM prompt paths; `HOME`/`PATH` stay inherited, so a user's OWN credential helper may authenticate (Codeman still never collects or stores credentials, and refuses a `user:password@` URL). ⚠️ Timeout kills the process GROUP (clone fans out into child processes), the destination is removed only if this attempt created it, and repository contents win over scaffolding (existing `CLAUDE.md` kept, hooks merged, repo-shipped `.claude/settings*` reported as a warning since its hooks run locally). The **Brain** picker sets the toolbar run mode on success. → [architecture-invariants#clone-a-repository-as-a-case](docs/architecture-invariants.md#clone-a-repository-as-a-case)
+**Clone a repository as a case** (issue #236, Add Case → **Clone Repo**): `POST /api/cases/clone` clones synchronously into the caller's case space (bounded by `GIT_CLONE_TIMEOUT_MS`, no job store); `POST /api/cases/clone-preflight` checks anonymous cloneability and lists refs. Core in `src/git-clone.ts`. ⚠️ **The URL is a code-execution surface**: refuse every `::` form and a leading `-`, spawn only argv arrays with `--` before operands. ⚠️ Stay non-interactive (`gitNonInteractiveEnv()`) or the open request hangs; never collect credentials, refuse `user:password@` URLs. ⚠️ Timeout kills the process GROUP, remove the destination only if this attempt created it, and repo contents win over scaffolding (existing `CLAUDE.md` kept, hooks merged, repo `.claude/settings*` warned about). → [architecture-invariants#clone-a-repository-as-a-case](docs/architecture-invariants.md#clone-a-repository-as-a-case)
 
 **Cross-session search**: `GET /api/search` federates an in-memory search over session metadata, run-summary events, and attachment-history entries. The pure core `searchSources()` does substring matching with hard per-type caps: **no regex (so no ReDoS) and no filesystem reads (so no traversal)**. The server-private `externalPath` is never read. PAST sessions (#261) come from `session-history-index.ts`, a capped snapshot of the unified list filled **outside** the request path (`/api/sessions/unified` publishes it; a stale one is rebuilt fire-and-forget), that indirection is what keeps the no-fs property. ⚠️ The snapshot is stored UNSCOPED with a per-row owner and MUST be re-filtered through `canAccessOwned()` on read; history rows carry `jumpTo.kind:'resume-session'`, since a closed session has no tab to select. → [architecture-invariants#cross-session-search](docs/architecture-invariants.md#cross-session-search)
 
-**Web tabs** (dashboard URLs as tabs): a saved URL renders as a tab beside agent sessions. **NOT a `SessionMode` of its own** (no PTY, no tmux, no respawn), same reasoning that keeps Docker/remote-SSH as case overlays. Dashboards are **proxied through Codeman's own origin** by default, because a direct iframe fails three ways at once: prod is HTTPS so `http://` targets are blocked as mixed content, many dashboards send `X-Frame-Options: DENY`, and our own `default-src 'self'` CSP blocks cross-origin frames. Proxying leaves the prod CSP unchanged (`/webview/...` is `'self'`). ⚠️ The proxy is **NOT an API surface**: it authenticates on an in-memory capability in the path and is correspondingly exempt from the cookie + Origin checks; that exemption is fenced to safe methods and non-`/api` paths and is pinned by `test/webview-auth-exemption.test.ts`. ⚠️ Iframes omit `allow-same-origin` unless a dashboard is explicitly marked `trusted`, and `Authorization`/`codeman_session` are stripped upstream in **both** modes so `CODEMAN_PASSWORD` cannot leak. ⚠️ A sandboxed frame is **opaque-origin**, which breaks two things `curl` can never reproduce: its runtime-built root-absolute URLs escape `<base>` (fixed by an injected `runtimeUrlShim()`), and its same-host `fetch`/XHR are CORS-checked with `Origin: null` (fixed by `buildProxyCorsHeaders()` plus exempting the proxy from the global `OPTIONS`-204 short-circuit in `registerSecurityHeaders`). Both present as the dashboard's own "Failed to fetch" while the page renders fine. ⚠️ **Egress guard**: link-local and cloud-metadata targets (`169.254.0.0/16`, `fe80::/10`, `fd00:ec2::254`, the Azure/Alibaba fixed addresses, `metadata.google.internal`) are refused at save time AND on the RESOLVED address at connect time (`webview-egress-policy.ts`, pure, plus `webview-egress.ts`: a `lookup` hook on the undici Agent behind `webviewFetch()` and on the `ws` client). An IP literal never reaches a lookup hook (`net.connect` skips DNS for it), so the synchronous hostname check at each connect site is NOT redundant. Loopback and RFC1918 stay allowed on purpose: a `localhost` Grafana is the feature. The proxy uses the `undici` PACKAGE's own `fetch` + `Agent`, never Node's global fetch with a foreign dispatcher (Node bundles its own copy; a protocol mismatch fails silently). ⚠️ **A loopback link in agent output opens as a proxied web tab** (`openLinkThroughWebTabIfLoopback` in webview-tabs.js, called from the terminal link provider and the response viewer): a phone cannot reach the box's `localhost:5173`, so the tap routes through Codeman's origin instead, reusing a saved same-origin dashboard or saving one under `host:port`. Two rules that look cosmetic and are not. **`*.localhost` is deliberately NOT in the auto-route set** even though it IS loopback to a browser: the link source is agent-written terminal output and prompt-injectable, every other member of that set is an address literal that can only mean this box, and a `*.localhost` DNS name is not one (a resolver with a search domain retries `evil.localhost` as `evil.localhost.<search domain>`, which an attacker can control, turning agent output plus one tap into a persisted server-side fetch of an agent-chosen origin). A user who really runs `api.localhost` saves it by hand, which is an explicit action. The PAGE-side test is deliberately broader (`isOnBoxHostname`), since a false positive there only declines to proxy. And **`this.webviews` being set does NOT mean it is loaded**: `initWebviews()` assigns a truthy EMPTY map synchronously and only then awaits the list, so a tap during page load must join the in-flight refresh (`_webviewsRefresh`/`_webviewsLoaded`) or it finds nothing to reuse and POSTs a duplicate record for an origin that already exists. Capabilities are revoked on logout / admin logout / user deletion (`revokeOwner`, which had NO caller for two releases while its docstring said otherwise), and proxied responses carry `Referrer-Policy: same-origin` so a dashboard cannot hand the capability-bearing URL to a third party. → [architecture-invariants#web-tabs](docs/architecture-invariants.md#web-tabs), `docs/web-tabs.md`
+**Web tabs** (dashboard URLs as tabs): a saved URL renders as a tab beside sessions, **NOT a `SessionMode`**, and is proxied through Codeman's own origin (`/webview/<cap>/...`). ⚠️ The proxy is NOT an API surface: its capability-based auth exemption stays fenced to safe methods and non-route paths (`test/webview-auth-exemption.test.ts`). ⚠️ Iframes omit `allow-same-origin` unless `trusted`, and `Authorization`/`codeman_session` are stripped upstream in both modes. ⚠️ **Egress guard**: link-local and cloud-metadata targets are refused at save time, by a sync hostname check at each connect (IP literals skip DNS), AND on the resolved address (`webview-egress.ts`); use the `undici` package's own `fetch` + `Agent`, never Node's global fetch. ⚠️ Loopback links in agent output auto-open as proxied web tabs (`openLinkThroughWebTabIfLoopback`), but never auto-route `*.localhost` (prompt-injectable DNS). Capabilities are revoked on logout (`revokeOwner`). → [architecture-invariants#web-tabs](docs/architecture-invariants.md#web-tabs), `docs/web-tabs.md`
 
 **Multi-user mode** (opt-in `--multiuser` / `CODEMAN_MULTIUSER=1`, OFF by default): named users with scrypt-hashed passwords in `~/.codeman/users.json`. Gated everywhere by `isMultiUserMode()`; when OFF, behavior is byte-identical to single-user because every scoping helper short-circuits. ⚠️ **Not a security boundary at the agent layer**: every session still runs as the SAME OS account. This separates WORKSPACES; it does not sandbox users (Docker cases are the isolation story). Ownership threads through `Session.owner` and is enforced in `findSessionOrFail`, list endpoints, SSE routing (fail-closed), WS, search, and file-preview. → [architecture-invariants#multi-user-mode](docs/architecture-invariants.md#multi-user-mode), `docs/multi-user-plan.md`
 
@@ -304,45 +320,55 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 
 ### Frontend
 
-Frontend JS modules have `@fileoverview` with `@dependency`/`@loadorder` tags. Load order: `constants.js`(1) → `i18n.js`(1.5) → `mobile-handlers.js`(2) → `voice-input.js`(3) → `notification-manager.js`(4) → `keyboard-accessory.js`(5) → `input-cjk.js`(5.5) → `terminal-keycode229-recovery.js`(5.55) → `sanitize-html.js`(5.6) → `app.js`(6) → `tab-rail-resize.js`(6.5) → `terminal-ui.js`(7) → `respawn-ui.js`(8) → `ralph-panel.js`(9) → `orchestrator-panel.js`(9.5) → `cron-ui.js`(9.7) → `settings-ui.js`(10) → `panels-ui.js`(11) → `readmymind-ui.js`(11.3) → `ultracode-panel.js`(11.5) → `approvals-ui.js`(11.6) → `reboot-restore-ui.js`(11.65) → `admin-ui.js`(11.7) → `session-ui.js`(12) → `host-wake-ui.js`(12.2) → `webview-tabs.js`(12.5) → `mobile-overview.js`(12.55) → `home-sessions.js`(12.56) → `entrance-animations.js`(12.6) → `ralph-wizard.js`(13) → `api-client.js`(14) → `subagent-windows.js`(15) → `ultracode-windows.js`(15.5) → `session-lineage.js`(15.6) → `image-input.js`(16). `i18n.js` translates static + newly inserted application DOM while skipping terminal/response/file/user-name surfaces; `input-cjk.js` handles CJK IME composition via an always-visible textarea below the terminal (`window.cjkActive` blocks xterm's onData). `terminal-keycode229-recovery.js` forwards a committed `input` event that xterm's `_inputEvent` guard drops (Chrome-on-Android soft keyboards send `composed: true` after a keydown), and only when xterm emitted no canonical data for that keystroke. ⚠️ **That decision is settled at the NEXT keydown as well as on its own zero-delay timer** (#441): the drain runs from xterm's custom key handler, which fires BEFORE xterm processes that key, so a soft keyboard that commits the last character and sends Enter in one InputConnection transaction puts the character on the wire ahead of the `\r`. On the timer alone that character is not merely late, it is LOST: xterm emits the `\r` first and bumps the canonical counter past the candidate's snapshot, so the candidate stands down (measured, `hell\r` where the user typed `hello`). The trade is that a keydown decides with less evidence than the timer did, since xterm's own keyCode-229 rescue has not run yet; that is safe for Enter, which clears the textarea so the pending diff emits nothing. Ordering is pinned by `test/terminal-keycode229-recovery.browser.test.ts`, which the CI gate does NOT run.
+Frontend JS modules have `@fileoverview` with `@dependency`/`@loadorder` tags. Load order: `constants.js`(1) → `i18n.js`(1.5) → `mobile-handlers.js`(2) → `voice-input.js`(3) → `notification-manager.js`(4) → `keyboard-accessory.js`(5) → `input-cjk.js`(5.5) → `terminal-keycode229-recovery.js`(5.55) → `sanitize-html.js`(5.6) → `app.js`(6) → `tab-rail-resize.js`(6.5) → `terminal-ui.js`(7) → `terminal-split.js`(7.5) → `respawn-ui.js`(8) → `ralph-panel.js`(9) → `orchestrator-panel.js`(9.5) → `cron-ui.js`(9.7) → `settings-ui.js`(10) → `panels-ui.js`(11) → `readmymind-ui.js`(11.3) → `ultracode-panel.js`(11.5) → `approvals-ui.js`(11.6) → `reboot-restore-ui.js`(11.65) → `admin-ui.js`(11.7) → `session-ui.js`(12) → `host-wake-ui.js`(12.2) → `webview-tabs.js`(12.5) → `mobile-overview.js`(12.55) → `home-sessions.js`(12.56) → `entrance-animations.js`(12.6) → `ralph-wizard.js`(13) → `api-client.js`(14) → `subagent-windows.js`(15) → `ultracode-windows.js`(15.5) → `session-lineage.js`(15.6) → `image-input.js`(16). `i18n.js` translates static + newly inserted application DOM while skipping terminal/response/file/user-name surfaces; `input-cjk.js` handles CJK IME composition via an always-visible textarea below the terminal (`window.cjkActive` blocks xterm's onData). `terminal-keycode229-recovery.js` forwards a committed `input` event that xterm's `_inputEvent` guard drops (Chrome-on-Android soft keyboards send `composed: true` after a keydown), and only when xterm emitted no canonical data for that keystroke. ⚠️ **That decision is settled at the NEXT keydown as well as on its own zero-delay timer** (#441): the drain runs from xterm's custom key handler, which fires BEFORE xterm processes that key, so a soft keyboard that commits the last character and sends Enter in one InputConnection transaction puts the character on the wire ahead of the `\r`. On the timer alone that character is not merely late, it is LOST: xterm emits the `\r` first and bumps the canonical counter past the candidate's snapshot, so the candidate stands down (measured, `hell\r` where the user typed `hello`). The trade is that a keydown decides with less evidence than the timer did, since xterm's own keyCode-229 rescue has not run yet; that is safe for Enter, which clears the textarea so the pending diff emits nothing. Ordering is pinned by `test/terminal-keycode229-recovery.browser.test.ts`, which the CI gate does NOT run.
 
-**Entrance animations** (`entrance-animations.js`, all OFF by default): opt-in animations for the four things that appear when work starts, chosen per surface via `data-tab-anim` / `data-term-anim` / `data-win-anim` / `data-line-anim` on `<html>`. Defaults are the `legacy` theme, so an untouched install behaves exactly as before and every hook short-circuits on its first line. ⚠️ Tabs and connection lines are **destroyed mid-animation** on every re-render (`_fullRenderSessionTabs()` replaces the strip's innerHTML; `_updateConnectionLinesImmediate()` does `svg.innerHTML = ''`), so both are tracked by id and re-applied to the fresh element with a **negative `animation-delay`** to resume rather than restart. ⚠️ The terminal-pane styles may animate **transform / opacity / clip-path only**, xterm's FitAddon derives rows+cols from `getComputedStyle(parent).width/height`, so animating width/height/padding there would resize the PTY; `test/entrance-animations.test.ts` pins that property allowlist, plus the rule→keyframes→theme-option chain a style silently does nothing without. ⚠️ **`blur` is the ONE style that puts a `filter` on the terminal container**, against the standing rule, because every alternative was measured against a live xterm and does not work: a `backdrop-filter` veil on `::before` blurs perfectly while STATIC and Chrome silently drops the backdrop the moment ANY animation runs on that pseudo-element (the veil computes `blur(15.3px)` and the text behind it stays razor sharp), and driving the radius from rAF buys the same full-screen blur per frame plus main-thread work. The cost the rule exists to avoid is inherent to blurring a terminal, so the style buys it knowingly: opt-in, OFF by default, one ~520ms run per session open, class straight back off, `will-change` still unset. Worst-case price, headless SwiftShader with no GPU: frame deltas 16.7ms → 33.3ms for the run, against 16.7ms flat for `fade`. Do not generalise it — a second filtered terminal style needs its own measurement. ⚠️ The `blur` connection line animates `filter` too, so both kinds of line hold their glow in **`--line-glow`** and both of its keyframes say `blur(N) var(--line-glow)`: the function lists then match and interpolate, instead of the glow vanishing for the run and popping back (a lineage line's glow is a different colour entirely, set per element). Its 100% frame deliberately omits `opacity` so the endpoint comes from the element's own resting value — 0.9 subagent, 0.72 lineage, 0.95 working — which is what `line-enter-fade`'s hardcoded 0.9 gets wrong. ⚠️ Window styles other than `beam` transform the window, which moves the rect its connection line is aimed at; `beam` deliberately animates opacity/filter only so its line can draw toward a stable target. Persisted to its own `codeman:*Anim` localStorage keys (per-device, deliberately NOT in the `.strict()` `SettingsUpdateSchema`); picker in App Settings → Appearance, full per-surface lab at `?animlab=1`.
+**Entrance animations** (`entrance-animations.js`, all OFF by default): opt-in animations for tabs, terminal, windows and connection lines, chosen via `data-tab-anim` / `data-term-anim` / `data-win-anim` / `data-line-anim` on `<html>`; the default `legacy` theme short-circuits every hook. ⚠️ Tabs and lines are destroyed mid-animation on re-render, so re-apply to the fresh element by id with a negative `animation-delay` (resume, never restart). ⚠️ Terminal-pane styles may animate only transform / opacity / clip-path (anything else resizes the PTY via FitAddon); `blur` is the ONE sanctioned `filter` exception, do not generalise it. ⚠️ Line glow lives in `--line-glow` so blur keyframes interpolate. Persisted per-device in `codeman:*Anim` localStorage keys, never in `SettingsUpdateSchema`; lab at `?animlab=1`. Test: `test/entrance-animations.test.ts`. → [architecture-invariants#entrance-animations](docs/architecture-invariants.md#entrance-animations)
 
-**Mobile tab strip scrolling** (issue #257): under 768px the tab strip is a horizontal scroller (desktop wraps to a second row instead), so the active tab can sit off-screen. Three rules keep it reachable and they only work together: `_updateActiveTabImmediate()` scrolls the selected tab into view via `computeTabScrollLeft()` (pure, in constants.js) using **rect math on the strip's own `scrollLeft`**, never `scrollIntoView()`, which would also scroll the document under a fixed header; `_fullRenderSessionTabs()` **restores `scrollLeft`** across the `innerHTML` rebuild, since ambient rebuilds (a task badge appearing, a session created elsewhere) otherwise snap a mid-swipe strip back to 0; and it re-reveals the active tab **only when it changed** (`_lastRenderedActiveTabId`), so browsing the far end of the strip is not undone by background renders. ⚠️ **The ACTIVE tab is the only one with action icons, and on a phone they can eat it**: `.session-tab.active .tab-name` reserves `min-width: 44px` in the phone block (under 600px), because a short session name rendered a 13px label against a 50px gear+close cluster, putting the tab's geometric CENTRE on the gear, so a thumb aiming at the tab opened Session Options instead of switching (measured at 360/393/430px; only long names cleared it). ⚠️ **The floor is set by the 10th tab onward, not by the tabs you can see**: `.tab-number` renders only for `_tabIdx < 9`, so tab 10 loses 16px + a gap off its left and its centre sits 10px further right. The centre clears the icons when `reserved > icons + rightEdge - leftRunUp - gap` (= 50 + 9 - 17 - 4 = **38px**), hit-testing snaps to whole pixels so 39px still lands on the gear, and the practical floor is 40px — a NUMBERED tab clears it at 20px, which is exactly why reasoning from the tabs on screen would put the centre back on the gear. `test/mobile-tab-tap-zones.test.ts` recomputes that inequality from the stylesheet, so widening the gear or the padding fails there rather than on a phone. The guarantee is centre-off-the-ICONS, not centre-inside-the-label (on a numberless tab it lands in the gap between them, which still switches). Non-active tabs keep their icons hidden and stay tappable end to end. ⚠️ Mobile no longer hoists the active session to the front of the strip: that reordering ran on full renders only, so tab order flipped depending on which render path fired, and it renumbered the Alt+N badges. Scroll-into-view replaces it; do not reintroduce it.
+**Mobile tab strip scrolling** (issue #257): under 768px the tab strip scrolls horizontally, so the active tab must be kept reachable. `_updateActiveTabImmediate()` reveals it via `computeTabScrollLeft()` (constants.js, rect math on the strip's own `scrollLeft`, never `scrollIntoView()`, which scrolls the document under the fixed header); `_fullRenderSessionTabs()` must restore `scrollLeft` across rebuilds and re-reveal only when the active tab changed (`_lastRenderedActiveTabId`). ⚠️ The phone-block `min-width` on `.session-tab.active .tab-name` keeps the tab's centre off the gear/close icons, sized for numberless tabs 10+ (floor 40px); do not shrink it. ⚠️ Never reintroduce hoisting the active session to the front of the strip. Test: `test/mobile-tab-tap-zones.test.ts`. → [architecture-invariants#mobile-tab-strip-scrolling](docs/architecture-invariants.md#mobile-tab-strip-scrolling)
 
-**Session list layout: header strip or left sidebar** (`sessionListLayout`, App Settings → Appearance → Tabs, default `header`; per-device policy — it IS in `SettingsUpdateSchema` and persists server-side, but `displayKeys` makes a device keep its own value): with many sessions the horizontal strip stops being scannable, so the list can move into a vertical `<aside>` with a filter box and a live count, collapsible to a 44px rail (`--sidebar-width` 260 / `--sidebar-width-collapsed` 44) via **Alt+B** (`toggleSessionSidebar`; Alt, not Ctrl+B, which must reach tmux/readline in the terminal). ⚠️ **There is ONE `#sessionTabs` element and it is MOVED between hosts** (`#sessionTabsHost` in the header, `#sessionSidebarList` in the aside, `#tabRail` for the vertical rail below), never a second list — so every render path, drag-reorder handler and Alt+N index keeps working unchanged. Exactly TWO functions reparent it and they must run in this order: `applySessionListLayout()` first (sidebar wins), then `applyTabOrientation()` (settings-ui.js), which moves the tabs into `#tabRail` only when the sidebar does not own them. ⚠️ It sets `data-session-list` / `data-sidebar` on `<html>` and must run BEFORE `applyTabWrapSettings()`, which is the one owner of `tabs-two-rows`/`tabs-show-folder` and reads those attributes. ⚠️ **The vertical tab rail** (`tabOrientation`/`tabRailWidth`/`sessionSidebarFontSize`, all per-device display keys that ARE in the schema, like `sessionListLayout`) is a SECOND vertical list next to the sidebar: the orientation setting is silently ignored while the sidebar layout is chosen, desktop/tablet only (`resolveTabOrientation` forces horizontal on mobile), resizable via `tab-rail-resize.js` (which owns terminal refits during the drag). ⚠️ **Detailed rows are a property of a vertical LIST, not of one surface** (`sessionListLayout: 'sidebar-rich'` for the sidebar, `tabRailDetail: 'rich'|'simple'` for the rail, rail default **rich**): both draw the home screen's per-session line (`created 3d ago · working 12m`) plus a status pill, from the SAME row model (`_sidebarRichRow`/`_sidebarRichMetaHTML` in app.js, classified by `_mobileOverviewState`/`_mobileOverviewSince`), and the render paths ask ONE gate, `isRichTabRows()` (= `isSessionSidebarRich() || isTabRailRich()`). ⚠️ Detail rides on its own attribute (`data-sidebar-detail` / `data-tab-rail-detail`) so every existing `[data-session-list="sidebar"]` / `[data-tab-orientation='vertical']` rule keeps matching both variants untouched; a flip of detail ALONE still needs a full render (the stamps line is emitted by the row template, not toggled by CSS) and must re-run `applyTabWrapSettings()`, which owns the folder line and is now rail-aware. ⚠️ The rich CSS rules carry a rail twin as a COMMA-GROUPED selector, never `:is()` (an `:is()` list takes its most specific argument, which would lift the sidebar arm from (0,3,1) to the rail's (0,5,1)). ⚠️ Width is the whole reason there are thresholds: the rich sidebar is 300px (`--sidebar-width-rich`) and a rail that has never been sized defaults to **320** (`RICH_DEFAULT_WIDTH`, the existing Wide preset) instead of 256, because at 256 the stamps line ellipsizes mid-word; a user-narrowed rail drops the created stamp below 288 (`tab-rail-tight`, CSS only) and drops rich rows entirely below 240 (`tab-rail-compact`, which re-renders). A stored width is never overridden. ⚠️ Only detailed rows carry stamps that go stale with no event behind them, so `_startSidebarRichClock()` (20s, rewrites text in place — a re-render would restart every row's animation) must be armed and disarmed by BOTH `applySessionListLayout()` and `applyTabOrientation()`. ⚠️ **Axis decisions must use `_isVerticalTabList()`** (sidebar OR rail), never `isSessionSidebarActive()` alone: the rail leaves `data-session-list` at `header`, and the sidebar-only predicate shipped four rail bugs at once (drag insertion side read from clientX, active tab never scrolled into view, floating windows anchored below tabs instead of beside them, connector redraws skipped on rail scroll). The pre-paint script stamps `data-tab-orientation` (+ `--tab-rail-width`) like it stamps the sidebar keys, or vertical mode flashes through the header strip; the name font size defaults to 12px, the sidebar's historical size, so untouched installs are never restyled. ⚠️ Leaving sidebar mode **clears `_sidebarFilter`**: the filter box only exists in the aside, so a stale filter would hide sessions from the header strip with no reachable control to clear it. ⚠️ On handhelds the aside is an off-canvas overlay rather than a docked rail, and a closed drawer keeps `display: flex`, so it is marked `inert` + `aria-hidden` (`_isSessionSidebarOverlay()`) or its filter box and ~4 tab stops per session stay in the tab order; the DOCKED desktop rail must never be inerted, its rows are still clickable. The desktop home rail (`home-sessions.js`) dLine truncated
+**Session list layout: header strip or left sidebar** (`sessionListLayout`, default `header`; per-device via `displayKeys`, also in `SettingsUpdateSchema`): the list can move into a collapsible `<aside>` (Alt+B, `toggleSessionSidebar`) or, via `tabOrientation`, a resizable vertical `#tabRail` (desktop/tablet only). ⚠️ There is ONE `#sessionTabs`, MOVED between hosts, never a second list: `applySessionListLayout()` runs first, then `applyTabOrientation()`, both BEFORE `applyTabWrapSettings()`, and both arm/disarm `_startSidebarRichClock()`. ⚠️ Axis decisions use `_isVerticalTabList()`, never `isSessionSidebarActive()` alone. ⚠️ Rich rows share one gate, `isRichTabRows()`; rich CSS pairs sidebar+rail with comma-grouped selectors, never `:is()`, and card rules stay rail-scoped. ⚠️ Rail sort (`tabRailSort`, default `activity`) is the flex `order` property only, never a DOM reorder; the arrow-key walk alone follows computed `order`. ⚠️ Leaving sidebar mode clears `_sidebarFilter`; the handheld overlay drawer is `inert` when closed, the docked rail never. → [architecture-invariants#session-list-layout-header-strip-vs-left-sidebar](docs/architecture-invariants.md#session-list-layout-header-strip-vs-left-sidebar)
 
-**Phone overview home screen** (`mobile-overview.js`, phones only, per-device `mobileOverviewEnabled`, default ON): under 600px the "C" logo shows a session overview (NEEDS YOU / CURRENT SESSIONS / PAST SESSIONS) instead of the welcome overlay; tablet and desktop are unchanged. The branch lives in `showWelcome()`/`hideWelcome()` (terminal-ui.js) behind `shouldUseMobileOverview()`, which is **width-driven** (`getDeviceType() === 'mobile'`) because this is a layout decision, unlike the settings namespace which stays handheld-based. ⚠️ The container ships with the `hidden` attribute and only this module removes it: never give `.mobile-overview` a bare `display` rule, since desktop does not load `mobile.css` (`media="(max-width: 1023px)"`) and would then render it unstyled. Live re-renders ride on the tail of `_renderSessionTabsImmediate()` (every state change it needs already funnels there); PAST rows come from one `_fetchUnifiedSessions(60)` per home-screen visit and resume through the shared `resumeHistorySession()`, so they behave exactly like the welcome screen's Resume list. ⚠️ Two things must stay in lockstep with surfaces outside this module, because divergence reads as a bug rather than a style: the split Run button carries the **toolbar's own classes** (`btn-toolbar btn-run mode-<backend>` / `btn-run-gear`) so the per-backend gradient and the light-skin overrides apply unchanged (mobile.css must therefore set no `background`/`color` on it), and row status uses the **session-tab language** (green dot when fine, `pulse` while working, yellow blinking row when waiting for input, red blinking row when a question is pending, mirroring `tab-alert-idle`/`tab-alert-action`). The picker mirrors the toolbar run-mode menu (`setRunMode()` + `run()`, `openWebviewFromMenu()` for saved dashboards) and deliberately omits its Recent-Sessions block, since PAST SESSIONS is that. Status pills carry `data-i18n-skip` (generic words like "idle" collide with state strings elsewhere).
+**Phone overview home screen** (`mobile-overview.js`, per-device `mobileOverviewEnabled`, default ON): under 600px the "C" logo shows NEEDS YOU / CURRENT / PAST SESSIONS instead of the welcome overlay, branched in `showWelcome()`/`hideWelcome()` via width-driven `shouldUseMobileOverview()`. ⚠️ The container ships `hidden` and only this module removes it: never give `.mobile-overview` a bare `display` rule (desktop does not load `mobile.css`). ⚠️ The split Run button must carry the toolbar's own classes (`btn-toolbar btn-run mode-<backend>` / `btn-run-gear`) and mobile.css must set no `background`/`color` on it; row status must mirror the session-tab alert language. PAST rows resume through the shared `resumeHistorySession()`. Status pills carry `data-i18n-skip`. → [architecture-invariants#phone-overview-home-screen](docs/architecture-invariants.md#phone-overview-home-screen)
 
-**Desktop home tab rail** (`home-sessions.js`, desktop only): the welcome overlay centers ~560px of content in a ~1400px window, so its left gutter is dead space; it carries the open tabs as a rail **docked flush to the left edge, full height** (a vertically centered card floating mid-gutter read as debris). Rows are in **overview order** (see below), and each carries a **created** stamp plus the **state duration** the order is computed from (`created 3d ago · working 12m`, word and anchor from `_mobileOverviewSince()` so both home screens say the same thing). A rail sorted by a number it does not show reads as arbitrarily shuffled, and a working row's plain last-active stamp always says "just now". ⚠️ The number badge is the **Alt+1..9 index**, i.e. the position in the TAB STRIP, so on a sorted rail it deliberately does NOT run 1,2,3 downward: it names a shortcut, not a row position, and renumbering it to look tidy would make every badge lie. State classification is REUSED from mobile-overview.js (`_mobileOverviewState`/`_mobileOverviewCaseFor`), which is why the module loads after it. ⚠️ The rail is `position: absolute` so the centered content never moves, which is exactly why it needs a **width gate in two places** — `HOME_SESSIONS_MIN_WIDTH` (1180) in the JS plus a `max-width: 1179px` media query as the backstop for a resize that outruns the matchMedia listener; drift between them means a rail overlapping the search panel, and `test/home-sessions.test.ts` pins them equal. ⚠️ `.home-sessions` is `display: flex`, so `[hidden]` must be re-asserted as `display: none` or the module's only visibility lever does nothing. ⚠️ Size scales with the viewport off **one knob**: `width: clamp(250px, 19vw, 430px)` plus a fluid `font-size` on `.home-sessions`, with every child sized in `em` — reintroducing `rem`/px type inside the block silently breaks the scaling, and widening the clamp past the gutter reintroduces the overlap the gate exists to prevent. The age stamps are refreshed **in place** by a 20s clock (`_tickHomeSessionsTimes()`, disarmed in `hideHomeSessions()`), never by re-rendering, which would restart every row's blink and working ring. Working state is deliberately byte-identical to the phone's: pulsing green dot + the `tab-load-spin` ring reused from the tab strip + the same green halo (added to `.mobile-overview-dot--working` at the same time), so "working" reads the same on every surface; **idle** is deliberately NOT that green — dot and pill mix toward `--text-muted` so a glance separates running from sitting. Live re-renders ride the tail of `_renderSessionTabsImmediate()` alongside the phone overview.
+**Desktop home tab rail** (`home-sessions.js`, desktop only): the welcome overlay's left gutter carries the open tabs as a rail docked flush left, full height, in overview order, each row showing `created … · <state> <duration>` from `_mobileOverviewSince()`; state classification is reused from mobile-overview.js (so it loads after it). ⚠️ The number badge is the Alt+1..9 tab-strip index, never renumber it to row position. ⚠️ The width gate lives in two places that must stay equal: `HOME_SESSIONS_MIN_WIDTH` (1180) and a `max-width: 1179px` media query. ⚠️ `.home-sessions[hidden]` must re-assert `display: none`. ⚠️ Size all children in `em` off the one `clamp()` knob, never `rem`/px. Age stamps tick in place (`_tickHomeSessionsTimes()`), never by re-render. Test: `test/home-sessions.test.ts`. → [architecture-invariants#desktop-home-tab-rail](docs/architecture-invariants.md#desktop-home-tab-rail)
 
-**Home-screen session order** (`CodemanSessionOrder` in constants.js, pure + unit-tested in `test/session-overview-order.test.ts`): BOTH home screens (phone overview and desktop rail) order rows through this ONE comparator, because they list the same sessions and must answer "which of these wants me next?" the same way. Rank is `needs` → `error` → `waiting` → `working` → `idle` → `done`, and ⚠️ **the tiebreak flips direction halfway down**: states a session is still IN sort **oldest-first** (blocked longest / running longest = most urgent), states it has STOPPED in sort **newest-first** (the session that just went quiet is the one you came back for). ⚠️ The running group keys off **`lastSubmitAt`** (the pane's last Enter), never `lastActivityAt`: a working Claude pane repaints about once a second, so its last-activity stamp is always "now" and would rank every running turn as freshly started. A working pane with no submit stamp falls back to last activity, which lands it at the SHORT end of the group rather than falsely leading it. ⚠️ A **0 stamp means "unknown", not "the epoch"**, and it sorts last within its state either way, or a brand-new session would head every oldest-first group. Final tiebreak is the user's tab order (`orderIndex`), so the list is deterministic and cannot shuffle between renders. The tab strip itself is NOT sorted by this; it stays user-ordered and drag-reorderable.
+**Home-screen session order** (`CodemanSessionOrder` in constants.js, pure): BOTH home screens (phone overview, desktop rail) must order rows through this ONE comparator. Rank `needs` → `error` → `waiting` → `working` → `idle` → `done`. ⚠️ The tiebreak flips: states a session is still IN sort oldest-first, states it has STOPPED sort newest-first. ⚠️ The running group keys off `lastSubmitAt`, never `lastActivityAt` (a working pane repaints constantly). ⚠️ A 0 stamp means unknown and sorts last within its state. Final tiebreak is `orderIndex`, so the list never shuffles. The tab strip itself is NOT sorted by this. Test: `test/session-overview-order.test.ts`. → [architecture-invariants#home-screen-session-order](docs/architecture-invariants.md#home-screen-session-order)
 
 **Welcome "Resume Conversation" list** (terminal-ui.js): `loadHistorySessions()` fetches once and caches the corpus on `_historyAll`/`_historyCases`; every subsequent view (filter box, sort select, expand, the periodic refresh in panels-ui.js) goes through `_renderHistoryList()`, so never append rows to `#historyList` directly or re-fetch to re-sort. ⚠️ The box height is **class-driven**: expanding the list without `.history-list.expanded` leaves the collapsed `max-height` in place and just deepens a scroll well, which is the bug #260 reported (35 sessions in a ~4-row box). ⚠️ The A–Z sort keys off `_historyRowLabel()`, the SAME string the row renders (`name || firstPrompt || path`), most rows are transcript-backed and have no session name, so sorting on `name` alone silently does nothing. ⚠️ A filter implies expansion, and `_renderSearch()` hides `#historyHeader` (title + controls) as one unit while a search is active. Tests: `test/history-list-controls.test.ts`.
 
-**Command palette + shortcut registry**: `Ctrl/Cmd/Alt+K` opens the session palette; shortcuts live in a rebindable registry (`DEFAULT_SHORTCUTS`/`getShortcutRegistry()`/`matchesShortcutEvent()` in app.js, overrides in `settings.shortcutOverrides`). ⚠️ Palette-chord keys must ALSO be swallowed in `attachCustomKeyEventHandler` (terminal-ui.js) or xterm writes the control byte (0x0B) into the PTY. ⚠️ `saveAppSettings()` rebuilds settings from the DOM, so keys edited elsewhere (`shortcutOverrides`, `showTokenCount`, `showCost`) need explicit `_prev` carry-over. ⚠️ **Smart copy (`Ctrl+C`)** lives in that same handler: with a selection it copies, with none it must `return true` **without** `preventDefault()` or the interrupt is lost. `copyTerminalSelection` is deliberately absent from `SHORTCUT_ACTIONS` because the generic capture loop preventDefaults every match it dispatches. ⚠️ **The gate tests the CLEANED selection, not the raw one** (`CodemanCopySelection.clean` in constants.js, pure; `cleanedTerminalSelection()` reads the live terminal): xterm returns whole screen ROWS and trims only never-written cells, so the spaces a full-screen TUI paints across the rest of a row are content and reach the clipboard (138 of them per line, measured in a 282-column pane). The clean drops each line's TRAILING run and nothing else. ⚠️ **A shared LEADING indent is deliberately NOT stripped**, and that is a decision, not a gap: it was built, measured and dropped before #451 merged, because it fired on 73% of real non-TUI text (401,445 windows sampled) and no width threshold separates a TUI margin from content (a claude pane's own margins are 2 and 5 columns; the commonest non-TUI shared run is 4). Do not re-add it without reading the rule in architecture-invariants. ⚠️ Alt+drag COLUMN selections are returned untouched (`_activeSelectionMode === 3`), and the padding-only clear is FEEDBACK rather than interrupt protection, since a padding-only selection now cleans to `''` and falls through to the PTY on its own. → [architecture-invariants#command-palette-and-shortcut-registry](docs/architecture-invariants.md#command-palette-and-shortcut-registry)
+**Command palette + shortcut registry**: `Ctrl/Cmd/Alt+K` opens the session palette; shortcuts live in a rebindable registry (`DEFAULT_SHORTCUTS`/`getShortcutRegistry()`/`matchesShortcutEvent()` in app.js, overrides in `settings.shortcutOverrides`). ⚠️ Palette-chord keys must ALSO be swallowed in `attachCustomKeyEventHandler` (terminal-ui.js) or xterm writes the control byte into the PTY. ⚠️ The global Escape handler (app.js) calls EVERY close method on every Escape, in the capture phase, so a close method that does more than hide (the palette and Session Manager restore focus) must return early when its overlay is not open. ⚠️ `saveAppSettings()` rebuilds settings from the DOM, so keys edited elsewhere (`shortcutOverrides`, `showTokenCount`, `showCost`) need explicit `_prev` carry-over. ⚠️ **Smart copy (`Ctrl+C`)**: with no selection it must `return true` without `preventDefault()` or the interrupt is lost; keep `copyTerminalSelection` out of `SHORTCUT_ACTIONS`. The gate tests the CLEANED selection (`CodemanCopySelection.clean`: trailing padding, plus a LEADING margin only up to the width the CLI declares in `capabilities.transcriptGutter`, never one derived from the pane); the strip is not idempotent, so clean once and pass the RAW selection on, and leave Alt+drag column selections untouched. → [architecture-invariants#command-palette-and-shortcut-registry](docs/architecture-invariants.md#command-palette-and-shortcut-registry)
 
 **Per-device vs synced settings**: the `displayKeys` set in settings-ui.js is a **client-side merge policy**, not a wire filter. A display key seeds from the server only when localStorage has no value for it, which is what prevents one device overwriting another; `showPlanUsageLimits` is additionally `delete`d from the incoming payload outright. Separately, `SettingsUpdateSchema` is `.strict()` and simply **does not declare** `skin`, `showFileViewerButton`, `showCronButton`, `webglRendererEnabled`, `localEchoEnabled`, `cjkInputEnabled`, or `extendedKeyboardBar`, so sending one of those is a validation error. The rest (`showResponseViewer`, `showPlanUsageLimits`, `language`, and most `show*` keys) ARE in the schema and do persist server-side; they are per-device by client policy only. ⚠️ Adding a new per-device setting means deciding **both** questions: membership in `displayKeys`, and presence in the schema.
 
-**Settings surface** (`#appSettingsModal` + `#sessionOptionsModal` + `#createCaseModal`): the `set-*` language (left rail, groups of rows, control pinned right) is shared by all three modals through ONE `:is(#appSettingsModal, #sessionOptionsModal, #createCaseModal)` scope in styles.css: an `:is()` list takes its most specific argument's specificity, so every rule keeps the id weight it had and nothing downstream shifts. **App Settings** is a rail that is a **table of contents over ONE scrolling document**, not a tab switcher: every section stays mounted (`.set-section`, ids `settings-updates|terminal|layout|appearance|models|clis|notifications|voice|shortcuts|system`, in that order, the version and the updater leading and the rest of the system settings tailing), and `switchSettingsTab(id)` keeps its historical name but SCROLLS instead of hiding. **Session Options** and **Add Case** use the same surface with a rail that really SWITCHES (`switchOptionsTab` / `switchCaseModalTab` show one `.set-section` and `.hidden` the rest, since Summary owns its own scroller, Respawn is long, and Add Case is six independent forms). ⚠️ They also take a deliberate **size-up** that App Settings does not (900px shell, 236px rail, `height:auto` between `min(560px,80vh)` and 88vh, vs App Settings' tight 760×620): they are short task panels, not a document you scan, and at scanning density they read as a few fields marooned in an empty frame. Those per-modal blocks are the design, not drift. Phones (≤860px) give App Settings the sticky `#appSettingsJump` pill and give the other two a horizontal rail strip, which neither has a pill for. ⚠️ The Session Options rail entry labelled **Session** still keys off `context` (`data-tab="context"`, `#context-tab`, `switchOptionsTab('context')`), the rename is label-only. Add Case keeps its legacy `.form-row` markup (six panels of it, every id read back by session-ui.js) and is mapped onto the look by an adapter block scoped to `#createCaseModal .set-doc`. Do not restructure those forms just to reach the row classes. ⚠️ That adapter's `summary { display:flex }` **kills the native disclosure triangle**, so every `<details>` there needs the explicit `.set-adv-chev` and both marker suppressions (`list-style` + `::-webkit-details-marker`); without it five collapsed blocks render as plain headings nobody clicks. ⚠️ **The load/save contract is `getElementById` by id**: `openAppSettings()`/`saveAppSettings()`/`openSessionOptions()` read every control by a fixed id, so moving a control between sections is free but renaming or dropping one silently stops it loading or saving. Static guards: `test/app-settings-structure.test.ts` + `test/session-options-structure.test.ts` (rail↔section pairing, one-visible-section, the `data-claude-only` entries external CLIs drop). ⚠️ Model cards (`#appSettingsModelCards`) and the effort segment are **views over hidden `<select>`s** that remain the source of truth; the cards hold the BASE model and the "1M context window" switch composes `base + [1m]` back into `claudeModel`, which is what retires the old "takes precedence over the toggle below" trap. ⚠️ `.modal-tabs`/`.modal-tab-btn`/`.modal-tab-content` are RETIRED: no modal uses them and their CSS is deleted, and a reappearance means a modal drifted off the shared surface. ⚠️ The **Header & Panels live preview** is a scale model rebuilt from the chips (`_syncLayoutPreview`); it owns NO icons, it CLONES `.set-chip-ico` out of the chip, so each icon has exactly one copy in index.html. A chip joins it via `data-preview` (slot) + `data-preview-order`, or `data-preview-text` for readouts that are not buttons. Its frame is painted from skin tokens only (hardcoded black alphas turned it into a grey slab on the light skins) and is `data-i18n-skip`. ⚠️ In Session Options → Respawn, auto-resume is a `.set-callout` whose `<label>` **wraps its own switch with no `for=`** (nesting associates them; the label+`for` pair has historically double-fired), and the cycle steps are real checkboxes (`.set-checks`), not chips. ⚠️ `admin-ui.js` injects the multi-user Users entry into `.set-rail-items` + `.set-doc`, so those hooks must survive any restructure. → [architecture-invariants#settings-surface-app-settings-session-options-add-case](docs/architecture-invariants.md#settings-surface-app-settings-session-options-add-case)
+**Settings surface** (`#appSettingsModal` + `#sessionOptionsModal` + `#createCaseModal`): one `set-*` language shared through a single `:is(...)` id scope in styles.css. App Settings' rail is a table of contents over ONE scrolling document (`switchSettingsTab` scrolls); Session Options and Add Case really switch (`switchOptionsTab` / `switchCaseModalTab`), and their larger per-modal size blocks are the design, not drift. ⚠️ **The load/save contract is `getElementById` by id**: renaming or dropping a control id silently stops it loading or saving. ⚠️ The Session Options "Session" entry still keys off `context` (label-only rename). ⚠️ Add Case keeps its legacy `.form-row` markup via an adapter; every `<details>` there needs `.set-adv-chev` plus both marker suppressions. ⚠️ Model cards and the effort segment are views over hidden `<select>`s, which stay the source of truth. ⚠️ `.modal-tabs*` classes are retired; `admin-ui.js` needs `.set-rail-items` + `.set-doc` to survive any restructure. Guard: `test/app-settings-structure.test.ts`. → [architecture-invariants#settings-surface-app-settings-session-options-add-case](docs/architecture-invariants.md#settings-surface-app-settings-session-options-add-case)
 
 **Header button visibility**: most header controls are opt-in and hidden by a marker class (`btn-multimonitor--hidden`, `btn-response-viewer-header--hidden`, `btn-file-viewer--hidden`, `btn-cron--hidden`) that `applyHeaderVisibilitySettings()` (settings-ui.js) toggles after settings load; the multi-monitor button is instead stripped at render by `renderIndexHtml`. ⚠️ Hiding must go through the marker class: the base rules are `display:inline-flex !important`, so an inline style cannot override them. Current desktop default is WS/CPU/MEM + File Viewer + gear, with the token chip and lifecycle-log button OFF. ⚠️ New header controls must not leak onto phones; `test/mobile-header-buttons-policy.test.ts` is the static guard. → [architecture-invariants#header-button-visibility-multi-monitor-response-viewer-file-viewer-cron](docs/architecture-invariants.md#header-button-visibility-multi-monitor-response-viewer-file-viewer-cron)
 
 **Gesture control** (camera hand-tracking overlay, opt-in, default OFF): `CODEMAN_GESTURE=1` makes the feature *available*; `gestureControlEnabled` turns it on. The bundle is injected by `renderIndexHtml` only when enabled, which is why that method is `async` and reads settings with `readSettings(true)` (a fresh read: a post-save reload lands inside the 2s cache TTL and would otherwise render the pre-toggle state). **Source lives in `packages/gesture-control/`; edit there, run `npm run build:gesture`, and commit the regenerated bundle** because dev serves the committed bundle with no runtime bundler. The MediaPipe wasm + model are fetched separately and gitignored. ⚠️ Keep `MP_VERSION` in `fetch-gesture-assets.mjs` in sync with `@mediapipe/tasks-vision`. → [architecture-invariants#gesture-control-the-source-package](docs/architecture-invariants.md#gesture-control-the-source-package)
 
-**Terminal font weight** (`terminalFontWeight` / `terminalFontWeightBold`, per-device, default = xterm's own `normal`/`bold`): bold text on the theme's default foreground carries exactly ONE cue, the weight step. Claude Code marks its markdown bold with a bare `ESC[1m` and no colour change, and xterm substitutes a bright colour for bold only when the foreground is a palette index 0-7, so the substitution never fires there. A two-face family keeps that step small and 400 stays 400 whatever family is chosen, which is why the NORMAL slot is settable at all. `CodemanTerminalFont.resolveWeights()` (constants.js, pure) resolves both slots, each against **its own** xterm default, so an unset bold weight can never inherit `normal`. ⚠️ **The `@font-face` descriptor, not the file, is what the browser synthesizes from**: `fonts/jetbrains-mono-variable.woff2` carries a `wght` axis of 100-800, and while `styles.css` declared it `400 700` every weight below 400 rendered identically to 400 and 800 identically to 700 — measured — so the setting was a no-op for anyone without Fira Code or Cascadia Code installed, which is most installs. It is declared `100 800`; re-narrowing it silently guts the feature (`test/terminal-font-weight.test.ts` pins the range). ⚠️ A live save must reach **both echo overlays** (`refreshFont()` — they cache `terminal.options.fontWeight` and paint it into their spans, so typed characters otherwise keep the old weight, most visible on a phone) **and open Agent Teams panes** (they read their options at construction, exactly like `applyTerminalSkin()` propagates). ⚠️ `_awaitTerminalFont()` is deliberately untouched: `CharSizeService` measures through the CSS `font` shorthand, which RESETS the weight, so the measured face is always the 400 one and a weighted descriptor would ask for nothing new.
+**Terminal font weight** (`terminalFontWeight` / `terminalFontWeightBold`, per-device, default = xterm's own `normal`/`bold`): Claude Code's markdown bold is a bare `ESC[1m`, so the weight step is its only cue. `CodemanTerminalFont.resolveWeights()` (constants.js, pure) resolves each slot against **its own** xterm default. ⚠️ The `@font-face` for `fonts/jetbrains-mono-variable.woff2` must stay declared `100 800` (the browser synthesizes from the descriptor, not the file); narrowing it silently makes the setting a no-op. ⚠️ A live save must reach both echo overlays (`refreshFont()`) and open Agent Teams panes. ⚠️ Leave `_awaitTerminalFont()` untouched. Test: `test/terminal-font-weight.test.ts`. → [architecture-invariants#terminal-font-weight](docs/architecture-invariants.md#terminal-font-weight)
 
 **Theme skins / branding / i18n**: `skin` selects a palette via `data-skin` on `<html>`, applied by an **inline pre-paint script** in `index.html` reading `localStorage['codeman:skin']` to avoid a flash of wrong theme. ⚠️ A skin is **four things that must stay in sync**, and missing any one degrades silently: the `html[data-skin="…"]` token block in `styles.css`, the xterm ANSI palette in `terminal-ui.js`, the pre-paint allowlist, and the Settings picker (both in `index.html`). `test/skin-themes.test.ts` is the static guard. Light skins additionally need `color-scheme: light` and xterm `minimumContrastRatio: 4.5`, and `applyTerminalSkin()` must call the local-echo overlay's `refreshFont()` because it caches the terminal fg/bg. `displayName` changes user-facing browser branding only and must NEVER rename npm package, CLI, API, storage, CSS, or protocol identifiers. `language` (`en`/`zh-CN`) keeps English as the canonical source so live switching stays reversible. User display names flow through `textContent`/attribute APIs and the server title's HTML escaper, never `innerHTML`. → [architecture-invariants#theme-skins](docs/architecture-invariants.md#theme-skins)
 
 **Foldable settings identity**: responsive layout is width-driven via `MobileDetection.getDeviceType()`, but the localStorage namespace uses `MobileDetection.isHandheldDevice()` so an unfolded Android foldable keeps `codeman-app-settings-mobile`. ⚠️ Do not switch per-device settings namespaces from instantaneous viewport width: a posture-triggered WebView reload would lose opt-in UI. Regression profile: `OPPO Find N5 (unfolded)` in `test/mobile/devices.ts`. → [architecture-invariants#foldable-settings-identity](docs/architecture-invariants.md#foldable-settings-identity)
 
-**Folding devices: a fold is not a keyboard, and dialogs avoid the hinge** (Apple's [Designing for iPhone Duo](https://developer.apple.com/design/human-interface-guidelines/designing-for-iphone-duo)): ⚠️ **A visual-viewport resize that changes the WIDTH is the device changing shape** (a rotation, or a foldable opening or closing) **and is never the virtual keyboard**, which only ever takes height. `handleViewportResize()` read any height drop over 150px as the keyboard appearing, so closing an iPhone Duo (626→466pt wide, 890→678pt tall) latched `keyboardVisible` with no keyboard on screen: the accessory bar appeared, `main` grew 84px of dead padding, and `updateAppHeight()` (which bails while the keyboard is up) stopped refreshing `--app-height`. The latch is STICKY, since clearing it needs the height back within 100px of a baseline belonging to a display the user is no longer looking at, so it survived until the device was opened again, and rotating any phone hit it too. The shape branch re-baselines instead, which is also what lets a keyboard opened AFTER the fold be detected. ⚠️ `init()` must seed `lastViewportWidth`, or the very first resize reads as a shape change and swallows a real keyboard. ⚠️ **The hinge is a reserved region.** The CSS Viewport Segments media features report two segments only while a foldable is actually bent, and `--fold-inline-end`/`--fold-block-end` (styles.css) measure the strip to keep clear: `0px` on everything else, so the rules are inert by construction rather than by a branch. Codeman's seven centred overlays are all `position: fixed; inset: 0` flex boxes, and each shrinks its CONTENT box with padding rather than the box itself, so the backdrop still covers the far side of the fold and still swallows taps there. ⚠️ Each rule RE-STATES the overlay's own gutter (a later `padding-right` longhand beats the earlier `padding` shorthand it composes with), and the palette needs the compound `.modal.command-palette-modal` because mobile.css loads later and pads it with a shorthand under 768px. `test/foldable-layout.test.ts` DERIVES the overlay list from the stylesheet and compares both numbers, so a new overlay or a moved gutter fails there instead of on hardware nobody has. ⚠️ Physical sides, not logical ones: dialogs sit in the LEFT segment (the TOP one in tabletop pose) in every language, because the HIG keeps Duo's side controls on the same physical edge in RTL. ⚠️ **With the keyboard up, a shape change baselines to `window.innerHeight`** (the layout viewport, keyboard-free on both engines), never the shrunk visual height: the shrunk baseline made the settle event that follows every rotation or fold read as the keyboard closing, and the layout could not recover, since no further drop could re-arm the show branch. ⚠️ **A base gutter that a LATER `@media` block overrides needs its own fold restatement in that block, on a ZERO base**: the phone-width path picker and path preview drop to `padding: 0` under 600px, and the unconditional fold rules at the end of the file put 16px and 18px back on every phone (measured at 393 and 500). The palette's compound rule lives INSIDE the 600-768px band whose mobile.css shorthand it composes with, because outside it there is no side gutter and the addition pushed the shell 6px off centre; the response viewer's tabletop cap has a twin at the end of mobile.css, whose phone block (under 600px) otherwise outranks it. `test/foldable-layout.test.ts` simulates the cascade across BOTH stylesheets at every breakpoint, with and without the fold rules, so a moved gutter or an unscoped composition fails there rather than on hardware nobody has. Profiles: `iPhone Duo (outer)` / `iPhone Duo (inner)` in `test/mobile/devices.ts`; unit coverage in `test/viewport-shape-change.test.ts`. → [architecture-invariants#folding-devices](docs/architecture-invariants.md#folding-devices)
+**Folding devices: a fold is not a keyboard, and dialogs avoid the hinge**: ⚠️ in `handleViewportResize()`, a visual-viewport resize that changes the WIDTH is a shape change (rotation, fold) and must never be read as the keyboard; it re-baselines instead, or `keyboardVisible` latches with no keyboard. ⚠️ `init()` must seed `lastViewportWidth`. ⚠️ With the keyboard up, a shape change baselines to `window.innerHeight`, never the shrunk visual height. ⚠️ The hinge is reserved via `--fold-inline-end`/`--fold-block-end` (0px when unfolded): each overlay fold rule must re-state its own gutter, a base gutter overridden by a later `@media` block needs its own fold restatement there on a zero base, and dialogs use physical sides (left/top segment) in every language. Guard: `test/foldable-layout.test.ts`. → [architecture-invariants#folding-devices](docs/architecture-invariants.md#folding-devices)
 
 **WebGL renderer toggle** (`webglRendererEnabled`, per-device): the GPU-stall watchdog's sticky `codeman-webgl-disabled` marker survives page loads and is cleared only by an explicit OFF→ON save or `?webgl=force`. `?nowebgl` forces the DOM renderer per-load. → [architecture-invariants#webgl-renderer-toggle](docs/architecture-invariants.md#webgl-renderer-toggle)
 
-**Shell keyboard accessory bar + one-shot Ctrl** (issue #262, `keyboard-accessory.js`): a **shell**-mode session automatically swaps the mobile accessory bar for terminal controls (Ctrl, Esc, Tab, four arrows, paste, dismiss); every other mode keeps the agent bar. `setMode()` now records the user's `extendedKeyboardBar` preference as the **base** layout and `refreshForActiveSession()` (called from `selectSession`) resolves base-vs-shell, so a settings save during a shell session cannot yank the bar away and switching back restores the user's choice. ⚠️ **Ctrl is a ONE-SHOT modifier applied in `terminal.onData`, not in a keydown handler**: a virtual keyboard emits no usable key events, so the character only exists as onData text. The hook sits AFTER `shouldSuppressTerminalQueryResponse` (xterm answers DA/CPR through onData too, and one of those would silently spend the modifier) and BEFORE every send path, so the control byte follows the normal control-char route. ⚠️ **Not every onData chunk is a keystroke**, and the query filter is not enough on its own: xterm ALSO emits mouse and focus reports on its own initiative, so the hook skips them via `isTerminalFocusOrMouseReport()` (they still reach the PTY, they just don't count as the next key). The mouse half is live — a shell session keeps the NARROW strip, so mouse DECSETs reach the browser and one tap while vim/htop runs spent the armed modifier silently (measured). The focus half is defense in depth: `FOCUS_ESCAPE_FILTER` in `session.ts` strips `\x1b[?1004h` from every PTY read, so `sendFocusMode` never turns on today; if it ever did, the bar's own post-key refocus would emit `\x1b[I` and eat the modifier before the user typed. ⚠️ It must disarm on ALL of: use, second tap, any other accessory key, session switch, keyboard dismissal, and a layout swap; a modifier left armed turns the next innocent keystroke into a control byte. ⚠️ **onData is not the only input path** — with `cjkInputEnabled` on, the CJK textarea owns the keyboard (onData returns early for everything it swallows, and the focus router sends `terminal.focus()` there, which is where the bar refocuses after every key), so `_handleCjkInput()` applies the modifier too. It is that module's single choke point to the PTY, so one call covers typed characters, IME flushes, Enter, backspace and arrows. Without it an armed modifier could neither fire NOR be spent, and survived to a later keystroke. Mapping is `ctrlByteFor()` (`code & 0x1f` over @A-Z[\]^_ and a-z, plus Ctrl+Space=NUL / Ctrl+?=DEL); characters with no control equivalent pass through unchanged, like a hardware keyboard. ⚠️ The armed style is `.accessory-btn.accessory-btn-ctrl.armed` (0,3,0) in BOTH stylesheets, and it cannot outrank mobile.css's light-skin repaint at **(0,3,1)** (`:is()` inherits its most specific argument, and that list holds `.btn-toolbar.btn-shell`) — so that rule excludes the state by hand as `.accessory-btn:not(.armed)`. Without the exclusion the armed button renders identically to a resting one on all four light skins, which is worse than no armed style at all.
+**Shell keyboard accessory bar + one-shot Ctrl** (`keyboard-accessory.js`): a shell-mode session swaps the mobile accessory bar for terminal controls; `setMode()` records `extendedKeyboardBar` as the base layout and `refreshForActiveSession()` resolves base-vs-shell. ⚠️ Ctrl is a one-shot modifier applied in `terminal.onData` (after `shouldSuppressTerminalQueryResponse`, before every send path), and must skip `isTerminalFocusOrMouseReport()` chunks. ⚠️ It must disarm on use, second tap, any other accessory key, session switch, keyboard dismissal and layout swap. ⚠️ `_handleCjkInput()` must apply it too (the CJK textarea bypasses onData). Mapping: `ctrlByteFor()`. ⚠️ mobile.css's light-skin repaint must keep excluding `.accessory-btn:not(.armed)` or the armed state is invisible. → [architecture-invariants#shell-keyboard-accessory-bar-and-one-shot-ctrl](docs/architecture-invariants.md#shell-keyboard-accessory-bar-and-one-shot-ctrl)
 
-**Dismissing the on-screen keyboard** (PRs #279/#280, `terminal-ui.js`): the terminal parks focus on a hidden textarea that nothing used to release, so TWO gestures now blur it, and they own different regions. **(1)** `_installMobileKeyboardDismiss()` — a document-level `touchend` that fires only while the terminal input actually holds focus, **never inside `#terminalContainer`** (tap classification owns that) and **never on a control** (`MOBILE_KEYBOARD_DISMISS_EXEMPT_SELECTOR`, matched with `closest()` so an icon inside a button counts). Session tabs are covered by the selector's `[tabindex]:not([tabindex="-1"])` arm, which is what stops a tab tap from blurring and then being re-focused by `selectSession()`. **(2)** In `_handleMobileTerminalTap`, a second tap on **inert `content`** (`startedWithTerminalFocus`) blurs instead of re-focusing. ⚠️ Scoped to `content` on purpose: the prompt row (`input`) keeps focus-then-position so a second tap still places the caret, and actionable rows blur earlier via `_isActionableMobileTerminalTap`. ⚠️ **A scroll ends in `touchend` too** — dismissing there closes the keyboard and drops the composer mid-read, so travel is tracked from `touchstart` and multi-touch is never a tap. Both classifiers MUST share one threshold: `initTerminal`'s `TAP_THRESHOLD` reads `MOBILE_KEYBOARD_DISMISS_TAP_SLOP`, since a gesture the terminal calls a scroll and the dismiss handler calls a tap is exactly that bug. ⚠️ **The gate excludes `test/mobile/**`, so CI cannot see the only test covering (1)** — run `npm run test:mobile -- test/mobile/keyboard.test.ts` by hand and diff the FAIL list against master. (Not `npm test --`: the gate's config excludes that path, so a file filter pointing into it matches nothing and exits green having run zero tests.) That blind spot is why merging the two PRs, which conflicted semantically but not textually, produced a red suite with two green CI checks.
+**Mobile prompt composer** (`keyboard-accessory.js`): the agent bars' Paste key is **Compose**, a native multiline dialog where only **Send** submits (the shell bar keeps plain Paste). Opening it adopts the whole terminal prompt (`_takePendingLocalEcho`), erasing the flushed prefix with backspaces counted in code points. ⚠️ Drafts are per-session and in memory only (`_composerDrafts`), never persisted (prompts carry secrets). ⚠️ Delivery is a hand-built bracketed-paste frame via `_sendInputAsync` WITHOUT `useMux`, then a separate delayed Enter WITH it; never `terminal.paste()`, and the frame must never take the mux fallback (it strips newlines). ⚠️ `_composerMaxLength` must stay derived from `MAX_INPUT_LENGTH` minus the markers, or an oversized frame wedges the durable queue. ⚠️ The composer overlay needs its own gutter restatement after the fold rules. Test: `test/mobile-prompt-composer.test.ts`. → [architecture-invariants#mobile-prompt-composer](docs/architecture-invariants.md#mobile-prompt-composer)
+
+**PTY and browser terminal geometry** (#464): a browser terminal whose width differs from the PTY's garbles Claude's redraws, so `syncTerminalGeometry()` (terminal-ui.js) is the ONE function that may resize the main terminal (never a bare `fitAddon.fit()`), a font change is a geometry change, and the fit is withheld wherever the SIGWINCH is. ⚠️ Resize is answered with `Session.ptyGeometry`, and a client adopts its COLUMNS only (never rows); `ptyGeometry` is null without a live pane. → [architecture-invariants#pty-and-browser-terminal-geometry](docs/architecture-invariants.md#pty-and-browser-terminal-geometry)
+
+**Terminal resilience**: a replay clear is the queued in-stream `\x1bc` in `_resetTerminalForReplay()`, never `reset()`/`clear()` (queued bytes fuse into the snapshot); the renderer watchdog `_kickRenderer()` reads xterm privates, pinned by `test/xterm-private-api.test.ts` against the resolved lockfile version; every terminal capture fetch has a deadline that covers the BODY (`_fetchTerminalCapture`). → [architecture-invariants#terminal-resilience-replay-clears-renderer-liveness-fetch-deadlines](docs/architecture-invariants.md#terminal-resilience-replay-clears-renderer-liveness-fetch-deadlines)
+
+**WebSocket output-gap reconcile** (`_wsOutputGapSession`, app.js): output frames carry no sequence number, so an unintentional WS close while SSE stays up marks the session and the next open reconciles. ⚠️ The marker is cleared only once a repaint actually happened (`_markTerminalBufferReconciled()`, never in a `finally`). → [architecture-invariants#websocket-output-gap-reconcile](docs/architecture-invariants.md#websocket-output-gap-reconcile)
+
+**Service worker precache** (`sw.js` + `scripts/build.mjs`): `BUILD_ID` and `HASHED_ASSETS` are build-generated and the build THROWS unless each declaration appears exactly once; `caches.match` must pass `ignoreSearch: true` because `cacheBustAssets` appends `?v=` to hashed names. → [architecture-invariants#service-worker-precache-and-cache-key](docs/architecture-invariants.md#service-worker-precache-and-cache-key)
+
+**Dismissing the on-screen keyboard** (`terminal-ui.js`): two gestures blur the terminal's hidden textarea. (1) `_installMobileKeyboardDismiss()`, a document `touchend` that must never fire inside `#terminalContainer` or on a control (`MOBILE_KEYBOARD_DISMISS_EXEMPT_SELECTOR`, via `closest()`). (2) In `_handleMobileTerminalTap`, a second tap on inert `content` blurs; the prompt row keeps focus-then-position. ⚠️ A scroll also ends in `touchend`: both classifiers must share one threshold (`TAP_THRESHOLD` reads `MOBILE_KEYBOARD_DISMISS_TAP_SLOP`), and multi-touch is never a tap. ⚠️ CI cannot see the only test for (1): run `npm run test:mobile -- test/mobile/keyboard.test.ts` by hand and diff the FAIL list against master. → [architecture-invariants#dismissing-the-on-screen-keyboard](docs/architecture-invariants.md#dismissing-the-on-screen-keyboard)
 
 **Phone toolbar: Enter replaces Shell** (post-1.8.0): inside `@media (max-width: 599px)` `btn-shell` is `display:none` and `btn-enter` takes its slot (`order: 4`); starting a shell moved into the Run dropdown (`Terminal / Shell` → `setRunMode('shell')` → `run()` → `runShell()`, button label "Run SH"). `runMode` is `z.string().max(20)` server-side, so new modes need no schema change. Desktop and tablet keep the green Run Shell button unchanged.
 
@@ -352,9 +378,9 @@ Frontend JS modules have `@fileoverview` with `@dependency`/`@loadorder` tags. L
 
 **Connection-loss UI** (`computeConnectionLossUi()` in constants.js, writer `_updateConnectionLossUi()` in app.js): the service worker serves the cached app shell, so an unreachable server (phone off the tailnet, VPN down, server stopped) used to render a normal-looking empty dashboard whose only tell was the 8px header dot, which reads as "no sessions", not "no connection". Two surfaces now: a full-screen **overlay** while no server state has loaded this page load (nothing behind it is worth preserving), and a non-blocking **banner** once it has (the terminal scrollback stays readable). ⚠️ A **2.5s grace** is load-bearing: a COM deploy restarts the server and SSE is back in ~200ms, and a banner on every deploy trains the user to ignore it. `navigator.onLine === false` skips the grace, since that is never a blip. Retry re-arms SSE **and** the terminal WS (`planWsReconnect` can 'give-up', and the SSE backoff caps at 30s).
 
-**SSE staleness watchdog** (`computeSseStale()` in constants.js, `_checkSseStale()` + a 5s interval in app.js): an `EventSource` that stops delivering does not always error, so `onerror` never fires, the header dot stays green, and every SSE-driven surface (tab status dots, sessions created on another device, renames) freezes until the user reloads. ⚠️ The 15s server keepalive was an SSE **comment** (`:keepalive`), and comments are **invisible to `EventSource` by spec**, so there was nothing a client could observe: it is now the named `sse:heartbeat` event (`cleanupDeadClients()`, sse-stream-manager.ts), which is exactly why the frame had to change type. ⚠️ Staleness is judged **only while the status is `connected`** and the device is online; that guard is the loop breaker, since a forced `connectSSE()` leaves `connected` immediately and cannot re-fire while a reconnect is in flight. ⚠️ The liveness stamp is applied inside `addListener` itself, so every registered handler (the `_SSE_HANDLER_MAP` wrappers AND the directly-registered ones) feeds it from one place; the heartbeat's own listener is a no-op that exists **only** to be registered, since `EventSource` drops named events nobody listens for. ⚠️ The watchdog interval is cleared at the top of `connectSSE()` and nowhere else (its only teardown path); clearing it elsewhere stacks intervals. Recovery needs no new sync path: the reconnect re-runs `handleInit` → `_resetAllAppState()`. The forced reconnect logs one diagnostic line, because a middlebox that strips heartbeats presents as "silently reconnects every 45s".
+**SSE staleness watchdog** (`computeSseStale()` in constants.js, `_checkSseStale()` + a 5s interval in app.js): an `EventSource` can stop delivering without erroring, so the client forces a reconnect when nothing arrives. ⚠️ The server keepalive must stay the named `sse:heartbeat` event (`cleanupDeadClients()`, sse-stream-manager.ts), never an SSE comment, which `EventSource` cannot observe; its no-op client listener must stay registered. ⚠️ Judge staleness only while `connected` and online (the loop breaker). ⚠️ The liveness stamp lives inside `addListener`. ⚠️ Clear the interval only at the top of `connectSSE()`, or intervals stack. → [architecture-invariants#sse-staleness-watchdog](docs/architecture-invariants.md#sse-staleness-watchdog)
 
-**Z-index layers**: subagent windows (1000), plan agents (1100), mobile/tablet fixed header (1200, `mobile.css`), modals on ≤768px (1300 — must beat the fixed header or the modal close button is buried), log viewers (2000), connection-loss overlay (2500, above the fixed header and modals), image popups (3000), response viewer (5000, backdrop 4999), file-preview overlay (5100 — must outrank the response viewer, which can launch it; at its old 2000 a path clicked in the chat opened BEHIND the chat), toasts/path picker (10000+, deliberately above the preview), the custom-model center-status banner (10001, `.center-status-banner` — `[hidden]` must re-assert `display: none` over its own `display: flex`, same trap as `.home-sessions[hidden]`, or `dismiss()` leaves an invisible click-blocker dead centre on screen), the swap-confirm and context-warning modals (10010, `#customModelSwapConfirmModal`/`#customModelContextWarningModal` — must clear both the plain `.modal` z-index of 1000 and the center-status banner it can appear over), terminal touch-selection bar (900 — above terminal content and the local-echo overlay, deliberately BELOW floating agent windows so it can never cover their controls), local echo overlay (7).
+**Z-index layers** (keep new overlays consistent with this stack): local echo overlay (7), terminal touch-selection bar (900, below floating agent windows), subagent windows + split picker menu (1000), plan agents (1100), mobile/tablet fixed header (1200), modals on ≤768px (1300, must beat the fixed header), log viewers (2000), connection-loss overlay (2500), image popups (3000), response viewer (5000, backdrop 4999), file-preview overlay (5100, must outrank the response viewer that launches it), toasts/path picker (10000+), custom-model center-status banner (10001; its `[hidden]` must re-assert `display: none` or `dismiss()` leaves an invisible click-blocker), custom-model swap-confirm/context-warning modals (10010). → [architecture-invariants#z-index-layers](docs/architecture-invariants.md#z-index-layers)
 
 **Respawn presets**: `solo-work` (3s/60min), `subagent-workflow` (45s/240min), `team-lead` (90s/480min), `ralph-todo` (8s/480min), `overnight-autonomous` (10s/480min).
 
@@ -383,11 +409,11 @@ Frontend JS modules have `@fileoverview` with `@dependency`/`@loadorder` tags. L
 
 ### SSE Event Registry
 
-161 event constants in `src/web/sse-events.ts` (backend) and `SSE_EVENTS` in `constants.js` (frontend). **Both must be kept in sync**, and `test/sse-registry-parity.test.ts` is the guard that pins it (currently exactly in sync, 161 = 161, no drift either direction). ⚠️ `hook:agent_working` is the one hook event with no Claude Code hook behind it — the DeepSeek status bridge reports it (see External CLI modes). The backend file's `@fileoverview` carries the per-category breakdown, including the two Web tab events.
+Event constants live in `src/web/sse-events.ts` (backend) and `SSE_EVENTS` in `constants.js` (frontend). **Both must be kept in sync**; `test/sse-registry-parity.test.ts` pins it. ⚠️ `hook:agent_working` is the one hook event with no Claude Code hook behind it — the DeepSeek status bridge reports it (see External CLI modes). The backend file's `@fileoverview` carries the per-category breakdown, including the two Web tab events.
 
 ### API Routes
 
-~236 handlers across 27 route files in `src/web/routes/`: system (56), sessions (37), cases (34), files (17), orchestrator (10), ralph (9), cron (9), admin (8), plan (8), respawn (7), webviews (6 + the `/webview/:cap/*` proxy), mux (5), push (4), scheduled (4, legacy `ScheduledRun`), approvals (4), readmymind (4), custom-model (6), reboot-restore (3), me (2), teams (2), tab-layout (2), search (1), hooks (1), clipboard (1), status-telemetry (1), voice (1 + the `/ws/voice/stream` relay), ws (1 WebSocket). Each file has `@fileoverview` with endpoint details.
+One module per domain in `src/web/routes/` (plus a barrel; `ls src/web/routes/` for the current list). Beyond the `/api` routes: the `/webview/:cap/*` proxy, the `/ws/voice/stream` relay and the terminal WebSocket. Each file has `@fileoverview` with endpoint details.
 
 **HTTP contract** (stable since 0.9.x, see `docs/versioning-policy.md`; full envelope/status/error-code/SSE spec in `docs/api-reference.md`): responses use the `ApiResponse<T>` envelope — `{ success: true, data? }` or `{ success: false, error, errorCode }` (`src/types/api.ts`). `/api/v1/*` is a versioned alias of `/api/*` (URL rewrite in `server.ts`).
 
@@ -405,7 +431,7 @@ Frontend JS modules have `@fileoverview` with `@dependency`/`@loadorder` tags. L
 
 ## State Files
 
-All in `~/.codeman/`: `state.json` (sessions, settings, respawn, orchestrator, cron jobs/runs, owner tab layouts), `mux-sessions.json` (tmux recovery), `settings.json` (user prefs), `push-keys.json` + `push-subscriptions.json`, `session-lifecycle.jsonl` (audit log), `update-status.json` (self-updater progress, polled across the service restart), `docker-env-applied.json` (Compose deployment only: sha256 of the Dockerfile + compose file the running container was built from, written by `Start-Codeman.sh`, read by the self-updater's environment gate), `docker-build-source.json` (Compose deployment only: the checkout's HEAD commit and `package-lock.json` hash the `codeman-node-modules`/`codeman-dist` volumes currently reflect, written by both `Start-Codeman.sh` and a successful in-place self-update, compared to detect and refresh a volume left stale by an externally-triggered rebuild), `linked-cases.json`, `webviews.json` (saved web-tab dashboard URLs), `remote-hosts.json` + `remote-cases.json`, `docker-hosts.json` + `docker-cases.json` + `docker-exports/`, `subagent-window-states.json` + `subagent-parents.json` (subagent window layout, GET/PUT `/api/subagent-window-states`/`-parents`), `hook-secret` (per-instance), `users.json` (multi-user, mode 0600) + `admin-audit.jsonl`, `intents.json` (Read My Mind intent profiles, mode 0600), `certs/` (self-signed TLS for `--https`), `.env` (CODEMAN_USERNAME/PASSWORD fallback for the `codeman attach` CLI). Transient: `self-update-runner.sh`. Multi-user case spaces live OUTSIDE the data dir at `~/codeman-users/<username>/cases` (shared across instances like `~/codeman-cases`, override `CODEMAN_USER_SPACES_DIR`).
+All in `~/.codeman/`: `state.json` (sessions, settings, respawn, orchestrator, cron jobs/runs, owner tab layouts), `mux-sessions.json` (tmux recovery), `settings.json` (user prefs), `push-keys.json` + `push-subscriptions.json`, `session-lifecycle.jsonl` (audit log), `update-status.json` (self-updater progress, polled across the service restart), `docker-env-applied.json` (Compose deployment only: sha256 of the Dockerfile + compose file the running container was built from, written by `Start-Codeman.sh`, read by the self-updater's environment gate), `docker-build-source.json` (Compose deployment only: the checkout's HEAD commit and `package-lock.json` hash the `codeman-node-modules`/`codeman-dist` volumes currently reflect, written by both `Start-Codeman.sh` and a successful in-place self-update, compared to detect and refresh a volume left stale by an externally-triggered rebuild), `linked-cases.json`, `webviews.json` (saved web-tab dashboard URLs), `remote-hosts.json` + `remote-cases.json`, `docker-hosts.json` + `docker-cases.json` + `docker-exports/`, `subagent-window-states.json` + `subagent-parents.json` (subagent window layout, GET/PUT `/api/subagent-window-states`/`-parents`), `hook-secret` (per-instance), `users.json` (multi-user, mode 0600) + `admin-audit.jsonl`, `intents.json` (Read My Mind intent profiles, mode 0600), `certs/` (self-signed TLS for `--https`), `.env` (CODEMAN_USERNAME/PASSWORD fallback for the `codeman attach` CLI), `install.log` (installer step output, written by `install.sh`'s `run_step`) and `tailscale-rename` (the node name before `install.sh` renamed it, so uninstall can offer it back; both installer-route only). Transient: `self-update-runner.sh`. Multi-user case spaces live OUTSIDE the data dir at `~/codeman-users/<username>/cases` (shared across instances like `~/codeman-cases`, override `CODEMAN_USER_SPACES_DIR`).
 
 **Generated top-level dirs** (all gitignored — don't edit or commit): `dist/` (esbuild output), `out/`, `coverage/`, `test-results/`, `tmp/`, `screenshots-echo-diag/`. The committed gesture bundle (`src/web/public/gesture/gesture-codeman.js`) IS tracked, but its runtime wasm/model assets (`src/web/public/gesture/wasm/`, `*.task`) are fetched and gitignored.
 
@@ -436,7 +462,7 @@ Raw `npx vitest` skips the config (and with it `setup.ts`); always use `npm test
 
 **Config**: Vitest with `globals: true`, `fileParallelism: false`. Timeout 30s, teardown 60s. `config/vitest.config.ts` is the everything-config behind `test:all`; `config/vitest.ci.config.ts` is the gate and derives its excludes from `config/test-suites.ts`, which is also what `vitest.browser.config.ts` and `vitest.perf.config.ts` derive their includes from — so the exclusions and the runners cannot drift apart. Keep shared options in sync across them.
 
-**Tmux safety**: under vitest (`VITEST` env var, set automatically), `TmuxManager` no-ops ALL shell commands and becomes a pure in-memory mock — tests physically cannot create/kill/attach real tmux sessions (`IS_TEST_MODE` in `src/tmux-manager.ts`). Every docker IO path is no-op'd the same way. `Session` is test-gated too: instead of attaching a real tmux client, it spawns a raw-mode echo PTY (`TEST_PTY_SCRIPT` in `src/session.ts`), so integration tests get a live input/output loop that echoes each byte exactly once. `test/setup.ts` gives every test file a temporary `HOME`/`USERPROFILE` (all `homedir()`-derived state, `~/.codeman` and `~/codeman-cases` included, resolves into a per-file fixture; the Playwright browser cache path is preserved), and additionally strips `CODEMAN_PASSWORD`/`CODEMAN_USERNAME` (so auth state from the running instance can't leak into tests) and `CODEMAN_GESTURE` (a shell-exported gesture flag would flip render-injection assertions), and strips the three instance-selection vars `CODEMAN_INSTANCE`/`CODEMAN_DATA_DIR`/`CODEMAN_TMUX_SOCKET` (#356/#371; `test/test-env-isolation.test.ts` pins the list, and its STATIC half reads setup.ts so a dropped `delete` fails everywhere rather than only on a box that exports the var). ⚠️ `CODEMAN_DATA_DIR` is the one that matters: `getDataDir()` reads it as an ABSOLUTE override before it ever looks at `homedir()`, so one inherited from the shell (a second instance, a beta run, a shell left over from `codeman web -d`) bypasses the temp HOME entirely, and a bare suite run once overwrote the real `remote-hosts.json` with a route test's fixture. `os.homedir()` itself DOES follow `$HOME`, so the temp HOME is what redirects everything else; `CODEMAN_INSTANCE` must be stripped in the setup file and never in a hook, because `config/instance.ts` captures it into a module-level const on first import. Tests that delete case trees go through `safeRmHomeTree()` (`test/mocks`), which refuses any path outside the temp HOME, so a wrong anchor leaves a temp dir behind instead of deleting `~/codeman-cases`. ⚠️ Raw `npx vitest` without `--config` skips `setup.ts` and with it the temp-HOME isolation.
+**Tmux safety**: under vitest (`VITEST`), `TmuxManager` no-ops ALL shell commands (`IS_TEST_MODE` in `src/tmux-manager.ts`), docker IO is no-op'd likewise, and `Session` spawns an echo PTY (`TEST_PTY_SCRIPT`) instead of attaching tmux. `test/setup.ts` gives each file a temp `HOME`/`USERPROFILE` and strips `CODEMAN_PASSWORD`/`CODEMAN_USERNAME`, `CODEMAN_GESTURE` and `CODEMAN_INSTANCE`/`CODEMAN_DATA_DIR`/`CODEMAN_TMUX_SOCKET` (pinned by `test/test-env-isolation.test.ts`). ⚠️ `CODEMAN_DATA_DIR` overrides the temp HOME, so never drop its strip; strip `CODEMAN_INSTANCE` in the setup file, never in a hook (captured at first import). ⚠️ Delete case trees only via `safeRmHomeTree()`. ⚠️ Raw `npx vitest` without `--config` skips `setup.ts` and its isolation. → [architecture-invariants#test-isolation-tmux-docker-and-home](docs/architecture-invariants.md#test-isolation-tmux-docker-and-home)
 
 **Ports**: Pick unique ports manually, 3150+. Search `const PORT =` before adding new tests. Never 3000 (the live instance).
 
@@ -444,15 +470,15 @@ Raw `npx vitest` skips the config (and with it `setup.ts`); always use `npm test
 
 **Testing against the live instance**: prod is HTTPS-only on :3000 (`curl -sk https://localhost:3000/...`). ⚠️ `w1`/`w2`/`w3` are the user's REAL sessions — never send input to them. Create your own throwaway session (`POST /api/sessions` then `POST /api/sessions/:id/shell`; creation alone leaves `pid: null` and no pane), test against that, and `DELETE` it by exact id when done.
 
-**Respawn tests**: Use `MockSession` from `test/mocks/index.ts` (defined in `test/mocks/mock-session.ts`). **Route tests**: `app.inject({ method, url, payload })` in `test/routes/` — no live port needed. **Mobile tests**: Playwright suite in `test/mobile/` (138 device profiles). Browser-testing infra and practices: `docs/browser-testing-guide.md`.
+**Respawn tests**: Use `MockSession` from `test/mocks/index.ts` (defined in `test/mocks/mock-session.ts`). **Route tests**: `app.inject({ method, url, payload })` in `test/routes/` — no live port needed. **Mobile tests**: Playwright suite in `test/mobile/` (device profiles in `test/mobile/devices.ts`). Browser-testing infra and practices: `docs/browser-testing-guide.md`.
 
 ## Debugging
 
 ```bash
-tmux list-sessions                                 # List tmux sessions
-curl localhost:3000/api/sessions | jq              # Check sessions
-curl localhost:3000/api/status | jq                # Full app state
-curl localhost:3000/api/subagents | jq             # Background agents
+tmux -L codeman list-sessions                      # Codeman's own socket (bare `tmux` shows the default one)
+curl -sk https://localhost:3000/api/sessions | jq  # Check sessions (prod is HTTPS-only; dev on :3000 is plain http)
+curl -sk https://localhost:3000/api/status | jq    # Full app state
+curl -sk https://localhost:3000/api/subagents | jq # Background agents
 cat ~/.codeman/state.json | jq                     # Persisted state
 ```
 
@@ -468,6 +494,6 @@ Two constraints worth knowing before you touch them: the env-derived PTY buffer
 
 ## Scripts & Tunnel
 
-**`install.sh`** (repo root, ~112KB) is the public entry point: `curl -fsSL <raw url> | bash` installs Node/tmux if missing, clones to `~/.codeman/app`, builds, and offers a systemd/launchd service. The network-access prompt is 3-way: **Tailscale** (loopback bind + guided `tailscale serve --bg <port>` HTTPS setup: install/login/operator/tailnet-HTTPS-toggle, then curl-verified end-to-end), **LAN** (0.0.0.0 + password prompt), or **local-only**; it preserves the existing binding on re-runs via `read_existing_binding()`. Tailscale state is detected dynamically from `tailscale serve status --json` (no marker files); the installer must NEVER `tailscale serve reset` or touch serve mappings other than 443→Codeman's port (users have unrelated serve config). `install.sh update`, `install.sh uninstall`, and `install.sh tailscale` (retrofit Tailscale access onto an existing install) also exist; `CODEMAN_NONINTERACTIVE=1` approves system changes for automation, `CODEMAN_TAILSCALE=1` presets the Tailscale choice (never installs Tailscale non-interactively). Its CLI knowledge is a GENERATED block (`npm run generate:cli-catalog`, markers in the file), not a hand-written list: detection, the install menu and the closing reminder all read it, which is what stops the class of bug upstream `b6d0f1fa` fixed by hand (a user with only omp installed being told no AI CLI was found). ⚠️ It must stay **bash 3.2** clean — macOS ships it and the documented install is `curl | bash` under `set -euo pipefail`, so `declare -A`, `mapfile`, namerefs, `${x,,}` and here-strings are all fatal there; CI runs `bash -n` plus a real `bash:3.2` container, since expanding an EMPTY array under `set -u` is a runtime abort `bash -n` cannot see. ⚠️ It executes ONLY commands from the embedded block (`CLI_INSTALL_CMD_TRUSTED`) — there is no network fetch of the catalogue at install time to worry about at all.
+**`install.sh`** (repo root) is the public `curl | bash` installer: it installs Node/tmux/git/build tools, clones to `~/.codeman/app`, builds, and offers a systemd/launchd service, asking every question BEFORE the unattended build (log in `~/.codeman/install.log`). Network access is Tailscale / LAN / local-only; re-runs preserve the existing binding AND password (`read_existing_binding()`). ⚠️ Compose the hand-start env only in `start_command_hint`/`export_bind_env`, and call `stop_background_helpers` before `exec`. ⚠️ Tailscale rename is opt-in (default NO, never under `--yes`/non-interactive); NEVER `tailscale serve reset`, touch a mapping it did not create, run `tailscale funnel` or advertise a Service (`test/install-sh-invariants.test.ts`). ⚠️ Stay **bash 3.2** clean (no `declare -A`, `mapfile`, namerefs, `${x,,}`, here-strings, empty-array expansion under `set -u`). ⚠️ Execute only commands from the generated CLI block (`CLI_INSTALL_CMD_TRUSTED`, `npm run generate:cli-catalog`). → [architecture-invariants#installsh-the-public-installer](docs/architecture-invariants.md#installsh-the-public-installer)
 
 Other key scripts: `scripts/tmux-manager.sh` (safe tmux mgmt), `scripts/tunnel.sh [quick|named] start|stop|status|url` (quick = random trycloudflare URL, default; `named setup|enable` = fixed-hostname tunnel via `scripts/codeman-tunnel-named.service`; bare `start|stop|url` still means quick), `scripts/run-beta.sh` (isolated beta instance), `scripts/build-agent-image.mjs` (docker base image), `scripts/self-update.sh` (detached updater). Production services: `scripts/codeman-web.service`, `scripts/codeman-tunnel.service`. **Always set `CODEMAN_PASSWORD`** before exposing via tunnel.

README.md

@@ -19,6 +19,10 @@
   <a href="https://github.com/Ark0N/Codeman/commits/master"><img src="https://img.shields.io/github/commit-activity/t/Ark0N/Codeman?style=flat-square&color=1e3a5f" alt="Total commits"></a>
 </p>
 
+<p align="center">
+  ⭐ <strong>Like Codeman? <a href="https://github.com/Ark0N/Codeman">Give it a star on GitHub!</a></strong> It takes one click and helps more people find the project. ⭐
+</p>
+
 <p align="center">
   <strong>English</strong> &bull; <a href="README.zh-CN.md">简体中文</a>
 </p>
@@ -61,12 +65,13 @@ The installer asks before every system change, and re-running the same line upda
 curl -fsSL https://getcodeman.com/install | bash
 ```
 
-This installs Node.js, tmux and a build toolchain if missing (node-pty ships no Linux prebuilds, so it compiles from source), clones Codeman to `~/.codeman/app`, and builds it. A few things worth knowing:
+This installs Node.js, tmux and a build toolchain if missing (node-pty ships no Linux prebuilds, so it compiles from source), clones Codeman to `~/.codeman/app`, and builds it. It looks at what is already on the machine, asks at most three questions, then does all the work unattended and ends on the URL with a QR code for your phone. A few things worth knowing:
 
-- **It asks first.** Every system change (package installs, AI CLI download) is prompted, and a menu at the end lets you choose: run Codeman in this terminal, install it as a background service (systemd/launchd, auto-start on boot), or don't start yet. Nothing runs in the background unless you pick it.
-- **How it's reachable, your choice.** The installer offers three ways to reach the dashboard: **Tailscale** (loopback bind fronted by `tailscale serve`, so you get `https://<machine>.<tailnet>.ts.net` with a real certificate and your tailnet as the login, no password needed), **any device on your network** (`0.0.0.0`, with a strongly recommended password prompt), or **this machine only** (`127.0.0.1`, safest). Skipping the password on a network bind requires an explicit confirmation and ends with a loud warning. The highlighted default reflects what is already on the machine (Tailscale when it is already in use, your existing binding on a re-run), and a bare Enter never pulls in new software. A bare `codeman web` started by hand still defaults to loopback.
-- **Re-run to update.** The same one-liner updates a finished install in place: local changes in `~/.codeman/app` are stashed (never discarded), and a running service is restarted and verified. If a first install was interrupted, re-running resumes the full setup instead. `install.sh update` and `install.sh uninstall` also exist.
-- **CI / headless:** without a terminal attached, steps that would change your system abort with instructions instead of running silently. Set `CODEMAN_NONINTERACTIVE=1` to approve them for automation.
+- **Three questions, all up front.** How the dashboard is reached, optionally what to call this machine on your tailnet, and whether to run Codeman as a background service (systemd/launchd, auto-start on boot; Enter says yes). Everything that needs you, including one consent for all missing packages, one sudo password, and the Tailscale login, happens before the build, so you can walk away while it compiles.
+- **How it's reachable, your choice.** **Tailscale** (loopback bind fronted by `tailscale serve`, so you get `https://<machine>.<tailnet>.ts.net` with a real certificate and your tailnet as the login, no password needed), **any device on your network** (`0.0.0.0`, with a strongly recommended password prompt), or **this machine only** (`127.0.0.1`, safest). Skipping the password on a network bind requires an explicit confirmation and ends with a loud warning. The highlighted default reflects what is already on the machine (Tailscale when it is already connected, your existing binding on a re-run), and a bare Enter never pulls in new software. If another app already owns `:443` on your node, Codeman goes under `https://<machine>.<tailnet>.ts.net/codeman` or on a second port instead of replacing it. A bare `codeman web` started by hand still defaults to loopback.
+- **The name is yours to choose.** By default the URL uses the machine's existing tailnet name. Answering yes to the second question renames the machine to `codeman-<hostname>` (which also renames it for SSH, so the default is no); `install.sh name` does it later.
+- **Re-run to update.** The same one-liner updates a finished install in place: local changes in `~/.codeman/app` are stashed (never discarded), and a running service is restarted and verified. If a first install was interrupted, re-running resumes the full setup instead. `install.sh status` prints the URLs and the QR code again; `install.sh update`, `install.sh tailscale` and `install.sh uninstall` also exist.
+- **Flags for the impatient.** `curl -fsSL https://getcodeman.com/install | bash -s -- --tailscale --service` answers the questions from the command line (`--lan`, `--local`, `--run`, `--no-start`, `--name <n>`, `--port <n>`, `--yes` too). **CI / headless:** without a terminal attached, steps that would change your system abort with instructions instead of running silently; set `CODEMAN_NONINTERACTIVE=1` to approve them for automation.
 
 You'll need at least one AI coding CLI installed — [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai), [Codex](https://developers.openai.com/codex/cli), [Antigravity](https://antigravity.google), [Gemini CLI](https://github.com/google-gemini/gemini-cli), [Pi](https://pi.dev), [Grok Build](https://github.com/xai-org/grok-build), [DeepSeek Harness](https://github.com/deepseek-ai/deepseek-harness), or [OMP](https://github.com/can1357/oh-my-pi) (any combination works; Gemini CLI is enterprise-only since Google's consumer cutover, and Antigravity is its successor). The installer detects whichever of the nine is present; if none is found, it offers to install any of them from a menu (DeepSeek excepted, since its npm package installs only a launcher with no runnable profile), or you can skip and install one yourself later. After install:
 
@@ -219,7 +224,7 @@ codeman web --https
 # Open on your phone: https://<your-ip>:3000
 ```
 
-> `localhost` works over plain HTTP. Use `--https` when accessing from another device, or use [Tailscale](https://tailscale.com/) (recommended): the installer can set it up for you (choose **Tailscale** at the network-access prompt, or run `bash ~/.codeman/app/install.sh tailscale` on an existing install). That gives you `https://<your-machine>.<tailnet>.ts.net` with a real certificate: private to your tailnet, no password required, and PWA install + push notifications work on your phone.
+> `localhost` works over plain HTTP. Use `--https` when accessing from another device, or use [Tailscale](https://tailscale.com/) (recommended): the installer can set it up for you (choose **Tailscale** at the network-access prompt, or run `bash ~/.codeman/app/install.sh tailscale` on an existing install). That gives you `https://<your-machine>.<tailnet>.ts.net` with a real certificate: private to your tailnet, no password required, and PWA install + push notifications work on your phone. The installer ends on that URL with a QR code to scan, and `bash ~/.codeman/app/install.sh status` prints it again any time.
 
 ### Secure QR Code Authentication
 

README.zh-CN.md

@@ -23,6 +23,10 @@
   <a href="https://github.com/Ark0N/Codeman/commits/master"><img src="https://img.shields.io/github/commit-activity/t/Ark0N/Codeman?style=flat-square&color=1e3a5f" alt="Total commits"></a>
 </p>
 
+<p align="center">
+  ⭐ <strong>喜欢 Codeman？<a href="https://github.com/Ark0N/Codeman">在 GitHub 上给它点个 Star 吧！</a></strong>只需轻点一下，就能帮助更多人发现这个项目。⭐
+</p>
+
 <p align="center">
   <img src="docs/images/subagent-demo-20260724.gif" alt="Codeman — 并行子智能体可视化" width="900">
 </p>

config/clis.stock.json

@@ -1,7 +1,7 @@
 [
   {
     "id": "claude",
-    "label": "Claude",
+    "label": "Claude Code",
     "shortBadge": "CC",
     "enabled": true,
     "order": 0,

config/test-suites.ts

@@ -30,6 +30,9 @@ export const BROWSER_TEST_GLOBS = [
   'test/capture-load-window.browser.test.ts',
   'test/capture-geometry-retry.browser.test.ts',
   'test/codex-predictive-echo.test.ts', // also needs a real codex binary
+  'test/split-pane-terminal.browser.test.ts',
+  'test/split-pane-orchestration.browser.test.ts',
+  'test/split-pane-auto-collapse.browser.test.ts',
 ];
 
 /**

docker/.env.example

@@ -15,6 +15,12 @@ TZ=Australia/Perth
 # this value rebuilds the image with a matching account.
 CODEMAN_RUNTIME_USER=codeman
 
+# Optional Git identity for commits made by Codeman and Docker-case agents. These values
+# are written to each image's system Git configuration when it is rebuilt, so
+# deployments can configure a consistent default. Set both values together.
+# GIT_USER_NAME=
+# GIT_USER_EMAIL=
+
 # Required. Persistent Codeman application data, CLI credentials, and session
 # state are stored here on the host and mounted at the runtime account's home
 # directory in the container.
@@ -50,6 +56,14 @@ CODEMAN_USERNAME=admin
 # README.md, "Reverse-proxy host allowlist".
 # CODEMAN_ALLOWED_HOSTS=codeman.example.com,.internal.example.com
 
+# The GitHub CLI (gh) and the Azure CLI (az, with the azure-devops extension)
+# can be built into the images as git credential helpers, so Codeman can clone
+# private GitHub and Azure DevOps repositories. Both are OFF by default and are
+# NOT set here: turn them on in docker-compose.override.yml with the build args
+# CODEMAN_INSTALL_GH / CODEMAN_INSTALL_AZ and, for the Docker-case agent image,
+# the environment variables CODEMAN_AGENT_IMAGE_INSTALL_GH / _AZ. See
+# README.md, "Private repositories".
+
 # Optional: authenticate Gemini CLI without an interactive login.
 GEMINI_API_KEY=
 

docker/README.md

@@ -41,6 +41,115 @@ Releases that change `server.Dockerfile`, `docker-compose.yaml`, or add a key to
 changed, and asks you to run `Start-Codeman.sh` here on the host instead. Details:
 [`../docs/docker-self-update.md`](../docs/docker-self-update.md).
 
+### Major updates
+
+`Start-Codeman.sh` rebuilds the image on every start, but with the layer cache,
+and it refreshes the build-artefact volumes selectively: `codeman-dist` when
+the checkout's HEAD moved, `codeman-node-modules` only when `package-lock.json`
+changed. That is right for an ordinary `git pull`. It is not enough when a
+`server.Dockerfile` change bumps the Node base image without touching the
+lockfile: `node-pty` is compiled from source (there is no Linux prebuild), so
+the old `codeman-node-modules` volume would keep a build made for the previous
+Node version. For that case, or whenever you want to be certain of what ships,
+`docker/Update-Codeman.sh` force-rebuilds the image with no layer cache, stops
+the stack, removes the `codeman-node-modules` and `codeman-dist` volumes, then
+hands off to `Start-Codeman.sh` for the usual start:
+
+```sh
+bash docker/Update-Codeman.sh
+```
+
+Pass `--keep-volumes` to skip clearing them (safe only if you know the
+rebuilt image's `node_modules`/`dist` did not change). The scripted default
+is the "Resetting the build artefacts" procedure in
+[`../docs/docker-self-update.md`](../docs/docker-self-update.md). Only those
+two volumes are removed, by name within this Compose project; any volume a
+`docker-compose.override.yml` adds is left alone, and application data and
+case workspaces are host bind mounts, never touched either way.
+
+## Git commit identity
+
+Set `GIT_USER_NAME` and `GIT_USER_EMAIL` in `docker/.env` before rebuilding:
+
+```sh
+GIT_USER_NAME='Your Name'
+GIT_USER_EMAIL='you@example.com'
+```
+
+Compose passes the values to the Codeman server build, and to the server process
+when it builds Docker-case agent images. Both images write the pair to Git's
+system configuration during their build, so commits retain the same identity
+after a container or agent image is recreated. Set both values together; an
+image build with only one value fails rather than using a partial identity. An
+identity already present in `CODEMAN_APPDATA_PATH`'s `~/.gitconfig` overrides
+the server image's system-level default.
+
+Run `bash docker/Start-Codeman.sh` after changing the server values. Rebuild an
+existing agent image with `node scripts/build-agent-image.mjs --no-cache` in the
+server container, then recreate any Docker cases that should use it.
+
+## Private repositories (GitHub and Azure DevOps)
+
+The images can include the GitHub CLI (`gh`) and the Azure CLI (`az`, with the `azure-devops` extension), wired into the system Git configuration as credential helpers, so Codeman can clone private repositories. Both are **opt-in and off by default**, and are turned on per host in `docker-compose.override.yml`.
+
+### Turning them on
+
+Add the build arguments to `docker-compose.override.yml` (see [Local customisation](#local-customisation)), then rebuild with `Start-Codeman.sh`. Set only the one you need:
+
+```yaml
+services:
+  codeman:
+    build:
+      args:
+        CODEMAN_INSTALL_GH: '1'
+        CODEMAN_INSTALL_AZ: '1'
+    environment:
+      # The same two switches for the Docker-case agent image Codeman builds.
+      CODEMAN_AGENT_IMAGE_INSTALL_GH: '1'
+      CODEMAN_AGENT_IMAGE_INSTALL_AZ: '1'
+```
+
+The `build: args:` pair controls the Codeman server image. The `environment:` pair controls the agent image for [Docker cases](../docs/docker-cases.md), which Codeman builds on the first Docker case; an agent image that already exists is not rebuilt by this, so run `node scripts/build-agent-image.mjs --no-cache` inside the container afterwards. The same variables work in front of that command when building it by hand. Values must be `0` or `1`; anything else stops the build with an error naming the argument.
+
+They are not `.env` settings: turning a CLI on is a per-host choice, which is what the override file is for, and a new `.env.example` key makes the in-app updater refuse to update every existing installation until its `.env` gains the key.
+
+The Azure CLI is the large one, about 600 MB of the roughly 670 MB the pair adds. A CLI left off leaves nothing functional behind: no apt repository, no package, no `azure-devops` extension and no credential-helper entry, so git for that host behaves exactly as it does without this feature. With both off the image is functionally unchanged; it still carries the `AZURE_EXTENSION_DIR` variable, an empty extensions directory and one small layer that copies and then removes the helper script.
+
+### Signing in
+
+With a CLI on, the system Git configuration routes credentials through it:
+
+| Host                                                  | Credential helper                         | Sign in with                 |
+| ----------------------------------------------------- | ----------------------------------------- | ---------------------------- |
+| `https://github.com`, `https://gist.github.com`       | `gh auth git-credential`                  | `gh auth login`              |
+| `https://dev.azure.com`, `https://*.visualstudio.com` | `/usr/local/bin/git-credential-azure-cli` | `az login --use-device-code` |
+
+Codeman itself still collects no Git credentials. Sign the container in once from a **Terminal / Shell** session (Run menu). The session runs as the runtime account, so the sign-in is stored under `CODEMAN_APPDATA_PATH` (`~/.config/gh`, `~/.azure`) and survives rebuilds and container recreation:
+
+```sh
+gh auth login                  # GitHub.com -> HTTPS -> "Login with a web browser" (device code)
+az login --use-device-code     # then: az devops configure --defaults organization=https://dev.azure.com/<org>
+```
+
+After that, **Add Case → Clone Repo** accepts private `https://` URLs on those hosts, and `git clone` works from any session. Until a CLI is signed in its helper prints nothing, so a private clone fails immediately with the usual authentication error rather than waiting on a prompt.
+
+**Multi-user mode:** every Codeman user's git runs as the same server account, so these sign-ins would otherwise be shared. Clone Repo therefore runs a **non-admin**'s clone and preflight with every git credential helper cleared (`git -c credential.helper=`): a non-admin can clone public repositories and anything their own SSH setup allows, but not a private https repository through the admin's `gh`/`az` sign-in. Admins, and single-user mode, keep the helpers. A non-admin's own agent sessions still run as that same account, and with the agent-image `gh`/`az` switches on, a non-admin's Docker case with credential seeding on also receives the server account's `gh`/`az` sign-in, the same as the Claude and Codex credentials; see `docs/security-architecture.md`, multi-user mode.
+
+Azure DevOps is authenticated with an Entra ID access token that the helper requests from `az` for each Git operation, so nothing is written to disk beyond `az`'s own sign-in. An account that has to use a personal access token can set `AZURE_DEVOPS_EXT_PAT` for the container instead (for example under `environment:` in `docker-compose.override.yml`); the helper prefers it when present. SSH remotes are unaffected by any of this and keep using the account's own keys.
+
+Docker cases copy these sign-ins into a case container only when the matching agent-image switch is on (`CODEMAN_AGENT_IMAGE_INSTALL_GH=1` for `~/.config/gh/hosts.yml` and `config.yml`, `CODEMAN_AGENT_IMAGE_INSTALL_AZ=1` for the sign-in files from `~/.azure`) and the case has credential seeding on. With a switch off they are never copied, even when the files exist, because a GitHub token or an Azure refresh token is usable by anything in the container. The copies are made when the container is **created**, so an existing case container never picks them up: after turning a switch on, signing in, or rebuilding the agent image, **recreate the case container** (remove it; the next session in that case creates a fresh one).
+
+The GitHub agent skill for `gh` installs into the runtime account's home in the same session:
+
+```sh
+gh skill install cli/cli gh --scope user
+gh skill update gh              # after a later gh release
+```
+
+### Versions
+
+Both CLIs, and the extension, are installed from their vendors' repositories with no version pinned, so they arrive at whatever is current when that build step runs. Docker caches the step, though: `Start-Codeman.sh` rebuilds with the cache, which keeps the versions from the first build until the Dockerfile changes at or above that step or the image is rebuilt with `--no-cache`. They are apt packages owned by root, so they cannot be upgraded from a session; `az extension update --name azure-devops` is the exception and works without a rebuild.
+
 ## Local customisation
 
 Compose merges `docker-compose.override.yml` on top of `docker-compose.yaml`. Keep host-specific changes there rather than editing `docker-compose.yaml`, so this repository can be updated without losing them. Both `docker-compose.override.yml` and `docker-compose.override.yaml` are ignored by Git.

docker/Update-Codeman.sh

@@ -0,0 +1,255 @@
+#!/usr/bin/env bash
+#
+# The scripted major-update path for the Docker Compose deployment.
+#
+# docker/README.md and docs/docker-self-update.md both point operators here for
+# anything the in-app updater itself refuses to apply: a changed
+# `server.Dockerfile`, a changed `docker-compose.yaml`, or a new required
+# `.env.example` key. None of those can be applied by a container restarting
+# itself — a restart reuses the existing image and configuration (see "The
+# environment gate" in docs/docker-self-update.md) — so this script does the
+# three things an in-place update cannot: force a real image rebuild with no
+# layer cache, stop the stack, then hand off to Start-Codeman.sh for the same
+# careful PUID/PGID, override-file and fingerprint handling every other start
+# goes through.
+#
+# ⚠️ Build BEFORE stopping the stack, deliberately, same reasoning as
+# Start-Codeman.sh's own build-then-down ordering: the build needs nothing
+# stopped, so a slow --no-cache rebuild costs no downtime, and a build failure
+# (a bad Dockerfile edit, a network blip pulling a base image) leaves the
+# ALREADY-RUNNING stack untouched instead of stopped with nothing to bring it
+# back.
+#
+# ⚠️ Clears the codeman-node-modules/codeman-dist named volumes by DEFAULT.
+# Docker seeds a named volume from the image only while that volume is EMPTY,
+# so a rebuilt image's fresh node_modules/dist otherwise sit unused behind a
+# volume's old content and the container comes back up looking unchanged —
+# exactly wrong for a script whose whole point is "be certain of what ships".
+# Start-Codeman.sh clears codeman-dist when the checkout's HEAD moved and
+# codeman-node-modules only when `package-lock.json` changed. A released
+# server.Dockerfile change arrives through `git pull`, so HEAD moves and dist
+# is refreshed, but a Dockerfile change that bumps the Node base image leaves
+# the lockfile untouched while every native module (node-pty is compiled from
+# source, there is no Linux prebuild) has to be rebuilt against the new Node
+# ABI. Start-Codeman.sh would keep the old codeman-node-modules volume, and it
+# never builds with --no-cache. This script clears BOTH volumes, and ONLY
+# those two (targeted `docker volume rm` by Compose label, never
+# `down --volumes`, which would also take any volume an override file adds).
+# Pass --keep-volumes to opt out and reuse whatever is already in them.
+#
+# Usage: docker/Update-Codeman.sh [--keep-volumes]
+#   --keep-volumes   Do not clear codeman-node-modules/codeman-dist. Safe to
+#                    combine with a source change Start-Codeman.sh's own
+#                    detection would have cleared anyway; unsafe if the reason
+#                    you are here is a change to server.Dockerfile alone.
+
+set -euo pipefail
+
+script_dir=$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)
+env_file="$script_dir/.env"
+compose_file="$script_dir/docker-compose.yaml"
+
+keep_volumes=0
+for arg in "$@"; do
+  case "$arg" in
+    --keep-volumes)
+      keep_volumes=1
+      ;;
+    --help | -h)
+      printf 'Usage: bash %s [--keep-volumes]\n' "$0"
+      exit 0
+      ;;
+    *)
+      printf 'Error: unrecognised argument: %s\n' "$arg" >&2
+      printf 'Usage: bash %s [--keep-volumes]\n' "$0" >&2
+      exit 1
+      ;;
+  esac
+done
+
+if [[ ! -f "$env_file" ]]; then
+  printf 'Error: Docker environment file is missing: %s\n' "$env_file" >&2
+  printf 'Create it from %s/.env.example before running this script.\n' "$script_dir" >&2
+  exit 1
+fi
+
+# Same override-file discovery as Start-Codeman.sh, and deliberately kept in
+# step with it: a stack built here and started there must resolve to the exact
+# same Compose files, or this script's build could target a configuration the
+# handoff's own `up` never actually uses. Compose's own precedence (measured on
+# v5.5.0 with both present: it uses .yml and ignores .yaml).
+override_yml="$script_dir/docker-compose.override.yml"
+override_yaml="$script_dir/docker-compose.override.yaml"
+if [[ -f "$override_yml" && -f "$override_yaml" ]]; then
+  printf 'Warning: both %s and %s exist; Compose uses .yml and ignores .yaml.\n' \
+    "$override_yml" "$override_yaml" >&2
+fi
+compose_files=(-f "$compose_file")
+for override_file in "$override_yml" "$override_yaml"; do
+  if [[ -f "$override_file" ]]; then
+    compose_files+=(-f "$override_file")
+    printf 'Using Compose override file: %s\n' "$override_file"
+    break
+  fi
+done
+compose_command=(docker compose --env-file "$env_file" "${compose_files[@]}")
+
+# Collision guard. Start-Codeman.sh has no equivalent; this is the only one,
+# and it has to run before this script's own --no-cache build, `down` and
+# volume removal below. docker-compose.yaml hard-codes `name: codeman`, so a
+# second checkout run without COMPOSE_PROJECT_NAME resolves to the SAME Compose
+# project as any other checkout on the host and would operate on ITS
+# containers and volumes.
+#
+# The project name is read from the resolved config's top-level `name` key
+# (the first `name` in the output; nested ones come later), the same parse
+# Start-Codeman.sh uses. `--format json` needs Compose v2.3+. This is the first
+# `docker` call the script makes, so its failure is reported here rather than
+# left to `set -e`, which would exit with no output at all.
+if ! project_config=$("${compose_command[@]}" config --format json); then
+  printf 'Error: `docker compose config --format json` failed (see the message above, if any).\n' >&2
+  printf 'Check that Docker and Compose v2.3+ are installed and on PATH, and that\n' >&2
+  printf '%s and the Compose files in %s are valid.\n' "$env_file" "$script_dir" >&2
+  exit 1
+fi
+project_name=$(
+  printf '%s\n' "$project_config" |
+    sed -n 's/^[[:space:]]*"name":[[:space:]]*"\([^"]*\)".*$/\1/p' | head -n1
+)
+if [[ -n "$project_name" ]]; then
+  # `|| true` on the pipeline's LAST command: under `set -o pipefail`, `grep -v`
+  # exits 1 when nothing survives the filter — the ordinary, no-collision case,
+  # since `docker ps` finds nothing at all on a first-ever deployment or a
+  # single matching (own) working_dir gets filtered out. Without it, that exit
+  # status propagates through the command substitution and `set -e` aborts the
+  # WHOLE script right here, every time, regardless of whether a collision
+  # actually exists — caught only by actually running this end-to-end (a
+  # static text/regex check on the source cannot see it). The empty-line
+  # filter keeps a container with no working_dir label from winning head -n1
+  # and hiding a real collision behind it.
+  other_working_dir=$(
+    docker ps -a --filter "label=com.docker.compose.project=$project_name" \
+      --format '{{.Label "com.docker.compose.project.working_dir"}}' 2>/dev/null |
+      grep -v -F -x -- "$script_dir" | grep -v '^$' | head -n1 || true
+  )
+  if [[ -n "$other_working_dir" ]]; then
+    printf 'Error: Compose project "%s" is already in use by a DIFFERENT checkout:\n' "$project_name" >&2
+    printf '  %s\n' "$other_working_dir" >&2
+    printf 'This checkout is:\n' >&2
+    printf '  %s\n' "$script_dir" >&2
+    printf '\n' >&2
+    printf 'docker-compose.yaml hard-codes `name: %s`, so two checkouts on the same host\n' "$project_name" >&2
+    printf 'collide unless each one sets a distinct COMPOSE_PROJECT_NAME. Continuing would\n' >&2
+    printf 'rebuild and stop the OTHER checkout'"'"'s running container and, by default,\n' >&2
+    printf 'delete its codeman-node-modules/codeman-dist volumes.\n' >&2
+    printf '\n' >&2
+    printf 'Fix: export COMPOSE_PROJECT_NAME=<something-unique-to-this-checkout> before\n' >&2
+    printf 'running this script, then retry.\n' >&2
+    printf '\n' >&2
+    printf 'If instead THIS checkout was moved or renamed after its container was created,\n' >&2
+    printf 'the path above is its own old location: remove the old container (for example\n' >&2
+    printf '`docker rm -f <container>` for the codeman container) and retry, rather than\n' >&2
+    printf 'setting COMPOSE_PROJECT_NAME, which would start a second project beside it.\n' >&2
+    exit 1
+  fi
+fi
+
+# Same owner-detection Start-Codeman.sh uses to derive PUID/PGID for its own
+# build — without it, the --no-cache build below gets Compose's untouched
+# default of 1000:1000, and on any host whose appdata owner differs (99:100 on
+# Unraid, per docker/README.md's chown example), Start-Codeman.sh's own
+# correctly-PUID'd build during the handoff then rebuilds those layers with the
+# right values anyway — so the "no cache, certain of what ships" image this
+# script produces is not the one that actually ends up running.
+#
+# Deliberately NOT the same as Start-Codeman.sh's own handling of a MISSING
+# appdata directory (which creates it): this script updates an EXISTING
+# deployment, so a missing appdata path means there is nothing here yet to
+# update, and creating one would just be this script quietly doing
+# Start-Codeman.sh's first-run job worse.
+appdata_path=$(
+  "${compose_command[@]}" config --environment |
+    awk -F= '$1 == "CODEMAN_APPDATA_PATH" { sub(/^[^=]*=/, ""); print; exit }'
+)
+if [[ -z "$appdata_path" || ! -d "$appdata_path" ]]; then
+  printf 'Error: CODEMAN_APPDATA_PATH is not set or does not exist: %s\n' "${appdata_path:-<unset>}" >&2
+  printf 'Run docker/Start-Codeman.sh first to set up a new deployment.\n' >&2
+  exit 1
+fi
+
+# `stat -c` is GNU, `stat -f` is BSD/macOS; the bind source lives on the Docker
+# host, so both need to work. Identical to Start-Codeman.sh's own helper.
+owner_of() {
+  stat -c '%u:%g' -- "$1" 2>/dev/null || stat -f '%u:%g' "$1" 2>/dev/null
+}
+
+if ! owner_ids=$(owner_of "$appdata_path"); then
+  printf 'Error: Cannot determine the owner of CODEMAN_APPDATA_PATH: %s\n' "$appdata_path" >&2
+  exit 1
+fi
+
+export PUID=${owner_ids%%:*}
+export PGID=${owner_ids##*:}
+
+if [[ "$PUID" == '0' ]]; then
+  printf 'Error: CODEMAN_APPDATA_PATH is owned by root: %s\n' "$appdata_path" >&2
+  printf 'Change the directory ownership to the unprivileged account that should run Codeman.\n' >&2
+  exit 1
+fi
+
+# --no-cache, always: a plain `build` reuses cached layers (npm install, apt
+# packages, the CLI installs baked into the image) and can silently keep them
+# frozen at whatever they were the day the cache was populated — exactly wrong
+# for a major update, whose whole point is being certain of what actually
+# ships. `scripts/build-agent-image.mjs` makes the same call for the same
+# reason (see its entry in CLAUDE.md's Additional Commands table). Runs BEFORE
+# the stack is stopped — see the header comment for why.
+printf 'Building a fresh image (--no-cache)...\n'
+"${compose_command[@]}" build --no-cache
+
+printf 'Stopping the stack...\n'
+if [[ "$keep_volumes" == '1' || -n "$project_name" ]]; then
+  "${compose_command[@]}" down
+else
+  # No resolvable project name means the label filter below could match
+  # nothing, so fall back to Compose's own removal, and say what it really does.
+  printf 'Warning: could not resolve the Compose project name; clearing EVERY named volume\n' >&2
+  printf 'in this Compose project (override file included) with `down --volumes` instead.\n' >&2
+  "${compose_command[@]}" down --volumes
+fi
+
+# Targeted removal of exactly the two build-artefact volumes, scoped by label to
+# THIS project (the volume key alone is shared by any other stack declaring the
+# same key). Same lookup as Start-Codeman.sh's refresh. A failure is reported,
+# not fatal: the stack is already down, and the handoff below is what brings
+# it back up.
+if [[ "$keep_volumes" != '1' && -n "$project_name" ]]; then
+  printf 'Clearing the codeman-node-modules/codeman-dist volumes (pass --keep-volumes to skip).\n'
+  for key in codeman-node-modules codeman-dist; do
+    volume_name=$(
+      docker volume ls -q \
+        --filter "label=com.docker.compose.volume=$key" \
+        --filter "label=com.docker.compose.project=$project_name" |
+        head -n1
+    ) || volume_name=''
+    if [[ -n "$volume_name" ]] && ! docker volume rm -- "$volume_name"; then
+      printf 'Warning: could not remove volume %s; the container may keep serving the\n' "$volume_name" >&2
+      printf 'previous build from it. Remove it by hand and rerun this script.\n' >&2
+    fi
+  done
+fi
+
+# Start-Codeman.sh does everything a plain `up -d` does not: re-derives
+# PUID/PGID, pre-creates CODEMAN_CASES_PATH with the right ownership, resolves
+# DOCKER_SOCKET_GID, records the server.Dockerfile/docker-compose.yaml
+# fingerprint the in-app updater's gate reads on every future update, and
+# starts the (already freshly built) image. Reimplementing any of that here
+# would only risk drifting out of step with it — hand off instead, exactly as
+# docs/docker-self-update.md's own reset procedure does.
+#
+# ⚠️ `bash`, not a bare exec of the path: Start-Codeman.sh is committed
+# non-executable (100644), the same as this script, and is documented
+# everywhere as `bash docker/Start-Codeman.sh` rather than
+# `./docker/Start-Codeman.sh` — execing the bare path fails with EACCES.
+printf 'Handing off to Start-Codeman.sh...\n'
+exec bash "$script_dir/Start-Codeman.sh"

docker/agent.Dockerfile

@@ -17,6 +17,7 @@ FROM node:22-bookworm-slim
 RUN apt-get update \
  && apt-get install -y --no-install-recommends \
       git \
+      libsecret-1-0 \
       tmux \
       ripgrep \
       curl \
@@ -26,6 +27,88 @@ RUN apt-get update \
       openssh-client \
  && rm -rf /var/lib/apt/lists/*
 
+# GitHub CLI and Azure CLI (+ the azure-devops extension) with the same system
+# git credential helpers as docker/server.Dockerfile, so an agent in a Docker
+# case can clone and push to private GitHub / Azure DevOps repositories. The
+# sign-ins themselves are NOT baked in: `~/.config/gh` and `~/.azure` are seeded
+# per container at launch like every other CLI's credentials (CRED_STORES in
+# src/docker-hosts.ts), and a helper whose CLI is not signed in prints nothing,
+# so git fails fast instead of prompting. See server.Dockerfile for why the
+# vendor apt repositories are configured here rather than via deb_install.sh.
+#
+# Each is OPT-IN and OFF by default, like the server image: CODEMAN_INSTALL_GH=1
+# / CODEMAN_INSTALL_AZ=1 turn one on; off leaves no repository, package,
+# extension or helper entry. scripts/build-agent-image.mjs and the in-app
+# auto-build pass them from CODEMAN_AGENT_IMAGE_INSTALL_GH / _AZ in their own
+# environment (for the Compose deployment: `environment:` in
+# docker-compose.override.yml), and pass nothing when those are unset, so
+# these defaults (off) apply.
+ARG CODEMAN_INSTALL_GH=0
+ARG CODEMAN_INSTALL_AZ=0
+RUN set -eux; \
+    for flag in "CODEMAN_INSTALL_GH=${CODEMAN_INSTALL_GH}" "CODEMAN_INSTALL_AZ=${CODEMAN_INSTALL_AZ}"; do \
+      case "${flag#*=}" in 0|1) ;; *) echo "${flag%%=*} must be 0 or 1, got '${flag#*=}'" >&2; exit 1;; esac; \
+    done; \
+    codename="$(. /etc/os-release && echo "${VERSION_CODENAME}")"; \
+    arch="$(dpkg --print-architecture)"; \
+    pkgs=""; \
+    install -d -m 0755 /etc/apt/keyrings; \
+    if [ "${CODEMAN_INSTALL_GH}" = 1 ]; then \
+      curl -fsSL -o /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+        https://cli.github.com/packages/githubcli-archive-keyring.gpg; \
+      chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg; \
+      echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" \
+        > /etc/apt/sources.list.d/github-cli.list; \
+      pkgs="${pkgs} gh"; \
+    fi; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      curl -fsSL -o /etc/apt/keyrings/microsoft.asc \
+        https://packages.microsoft.com/keys/microsoft.asc; \
+      chmod go+r /etc/apt/keyrings/microsoft.asc; \
+      echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/microsoft.asc] https://packages.microsoft.com/repos/azure-cli/ ${codename} main" \
+        > /etc/apt/sources.list.d/azure-cli.list; \
+      pkgs="${pkgs} azure-cli"; \
+    fi; \
+    if [ -n "${pkgs}" ]; then \
+      apt-get update; \
+      apt-get install -y --no-install-recommends ${pkgs}; \
+      rm -rf /var/lib/apt/lists/*; \
+    fi; \
+    if [ "${CODEMAN_INSTALL_GH}" = 1 ]; then gh --version; fi; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then az version --output none; fi
+
+# Outside HOME so the seeded `~/.azure` (auth files only) never has to carry
+# extensions. gid 0 + group-writable, the same arbitrary-uid convention as HOME
+# below, so `az extension update` works as whatever uid the container runs as.
+# Created even without az; an empty directory costs nothing.
+ENV AZURE_EXTENSION_DIR=/opt/az-extensions
+RUN set -eux; \
+    install -d -m 0755 "${AZURE_EXTENSION_DIR}"; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      az extension add --name azure-devops --only-show-errors; \
+      rm -rf /root/.azure; \
+    fi; \
+    chgrp -R 0 "${AZURE_EXTENSION_DIR}"; \
+    chmod -R g=u "${AZURE_EXTENSION_DIR}"
+
+# Only an installed CLI gets a helper entry (see server.Dockerfile).
+COPY docker/git-credential-azure-cli /usr/local/bin/git-credential-azure-cli
+RUN set -eux; \
+    if [ "${CODEMAN_INSTALL_GH}" = 1 ]; then \
+      for host in https://github.com https://gist.github.com; do \
+        git config --system "credential.${host}.helper" '!/usr/bin/gh auth git-credential'; \
+      done; \
+    fi; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      chmod 0755 /usr/local/bin/git-credential-azure-cli; \
+      for host in https://dev.azure.com 'https://*.visualstudio.com'; do \
+        git config --system "credential.${host}.helper" /usr/local/bin/git-credential-azure-cli; \
+        git config --system "credential.${host}.useHttpPath" true; \
+      done; \
+    else \
+      rm -f /usr/local/bin/git-credential-azure-cli; \
+    fi
+
 # The npm-published agent CLIs, supplied by scripts/build-agent-image.mjs from
 # config/clis.stock.json so a new stock CLI needs no edit here. The default is
 # today's literal list, so a bare `docker build` still produces the same image.
@@ -44,6 +127,10 @@ RUN apt-get update \
 # A different order is a different RUN string, which is a different layer hash and
 # so a needless cache miss between a bare `docker build` and a scripted one.
 ARG CLI_NPM_PACKAGES="@anthropic-ai/claude-code opencode-ai @openai/codex @google/gemini-cli"
+# uv/uvx: MCP servers are commonly launched with `uvx <package>` (e.g. the Nginx
+# Proxy Manager MCP), and Codex failed to enable them with "uvx not found". Copied
+# from the pinned upstream image into root-owned /usr/local/bin, never pip-installed.
+COPY --from=ghcr.io/astral-sh/uv:0.9 /uv /uvx /usr/local/bin/
 RUN npm install -g ${CLI_NPM_PACKAGES} \
  && npm cache clean --force
 
@@ -167,6 +254,21 @@ RUN useradd -g 0 -m -d /home/agent -s /bin/bash agent \
  && chgrp -R 0 /home/agent \
  && chmod -R g=u /home/agent
 
+# Docker cases have a fresh, container-owned home directory. Declare the
+# optional identity here so changing it invalidates only this final layer, then
+# configure Git's system defaults. A user-level config still takes precedence.
+ARG GIT_USER_EMAIL=
+ARG GIT_USER_NAME=
+RUN set -eux; \
+    if [ -n "${GIT_USER_NAME}" ] || [ -n "${GIT_USER_EMAIL}" ]; then \
+      if [ -z "${GIT_USER_NAME}" ] || [ -z "${GIT_USER_EMAIL}" ]; then \
+        echo 'Git user name and email must both be set when configuring Git identity' >&2; \
+        exit 1; \
+      fi; \
+      git config --system user.name "${GIT_USER_NAME}"; \
+      git config --system user.email "${GIT_USER_EMAIL}"; \
+    fi
+
 USER agent
 WORKDIR /home/agent
 

docker/docker-compose.yaml

@@ -7,6 +7,8 @@ services:
       dockerfile: docker/server.Dockerfile
       args:
         CODEMAN_RUNTIME_USER: ${CODEMAN_RUNTIME_USER}
+        GIT_USER_EMAIL: ${GIT_USER_EMAIL:-}
+        GIT_USER_NAME: ${GIT_USER_NAME:-}
         PGID: ${PGID:-1000}
         PUID: ${PUID:-1000}
     image: ${CODEMAN_IMAGE}
@@ -32,6 +34,10 @@ services:
       CODEMAN_DOCKER_HOST_HOME: ${CODEMAN_APPDATA_PATH}
       CODEMAN_DOCKER_DISABLE_SWAP_LIMIT: ${CODEMAN_DOCKER_DISABLE_SWAP_LIMIT}
       CODEMAN_CASES_PATH: ${CODEMAN_CASES_PATH}
+      # Passed through only so Codeman can use the same identity when it builds
+      # the Docker-case agent image.
+      CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL: ${GIT_USER_EMAIL:-}
+      CODEMAN_AGENT_IMAGE_GIT_USER_NAME: ${GIT_USER_NAME:-}
       # Extra Host-header allowlist entries for a reverse-proxied deployment
       # (docker/README.md, "Reverse-proxy host allowlist"). Optional, so it
       # defaults to empty rather than requiring a line in every .env.

docker/git-credential-azure-cli

@@ -0,0 +1,34 @@
+#!/bin/sh
+# Git credential helper for Azure DevOps, backed by the signed-in Azure CLI.
+#
+# Configured in the image's system gitconfig for https://dev.azure.com and
+# https://*.visualstudio.com (see server.Dockerfile). On `get` it answers with
+# an Entra ID access token for the Azure DevOps resource as the password, the
+# same token type Git Credential Manager uses for Azure Repos. It never prompts:
+# when `az` is not signed in it prints nothing, so git fails fast with its own
+# authentication error instead of hanging a request that has no terminal.
+#
+# AZURE_DEVOPS_EXT_PAT, the azure-devops extension's own PAT variable, is used
+# instead when it is set, for accounts that authenticate with a PAT.
+
+# `store` and `erase` are no-ops: the token belongs to az, which refreshes it.
+[ "$1" = "get" ] || exit 0
+
+# Drain the request git writes on stdin; the host scoping is in gitconfig.
+cat >/dev/null
+
+if [ -n "${AZURE_DEVOPS_EXT_PAT:-}" ]; then
+  printf 'username=pat\npassword=%s\n' "$AZURE_DEVOPS_EXT_PAT"
+  exit 0
+fi
+
+command -v az >/dev/null 2>&1 || exit 0
+
+# 499b84ac-1321-427f-aa17-267ca6975798 is the fixed application ID of Azure
+# DevOps: https://learn.microsoft.com/azure/devops/integrate/get-started/authentication/service-principal-managed-identity
+token="$(az account get-access-token \
+  --resource 499b84ac-1321-427f-aa17-267ca6975798 \
+  --query accessToken --output tsv 2>/dev/null)" || exit 0
+[ -n "$token" ] || exit 0
+
+printf 'username=azure-cli\npassword=%s\n' "$token"

docker/server.Dockerfile

@@ -39,6 +39,7 @@ RUN apt-get update \
       curl \
       g++ \
       git \
+      libsecret-1-0 \
       make \
       openssh-client \
       procps \
@@ -68,6 +69,111 @@ COPY --from=docker:29-cli \
      /usr/local/libexec/docker/cli-plugins/docker-buildx \
      /usr/local/libexec/docker/cli-plugins/docker-buildx
 
+# GitHub CLI and Azure CLI (with the azure-devops extension), so a user can sign
+# this container in to GitHub and Azure DevOps from a Codeman shell session and
+# then clone PRIVATE repositories, both from that session and through Add Case
+# -> Clone Repo. Codeman still collects no Git credentials itself: the clone
+# path (src/git-clone.ts) only inherits HOME and git's config, so whatever the
+# user signs in to here is what authenticates, and nothing when they have not
+# (the clone then fails fast with AUTH_REQUIRED, exactly as before).
+#
+# Each is OPT-IN and OFF by default: the image is functionally unchanged
+# unless the build gets CODEMAN_INSTALL_GH=1 and/or CODEMAN_INSTALL_AZ=1, which
+# a deployment sets under `build: args:` in docker-compose.override.yml
+# (docker/README.md, "Private repositories"). Off installs no apt repository,
+# package, extension or credential-helper entry; all that remains is the
+# AZURE_EXTENSION_DIR variable, its empty directory and one layer that copies
+# and then removes the helper script. The Azure CLI is the heavy one (~600 MB,
+# mostly its bundled Python). The base docker-compose.yaml
+# and .env deliberately do not carry them: turning a CLI on is a per-host
+# choice, which is what the override file is for, and a new .env.example key
+# would make the self-updater refuse existing installs until their .env gained
+# it (docs/docker-self-update.md).
+#
+# Both come from their vendors' own apt repositories, the same ones the
+# documented one-liners configure (https://github.com/cli/cli/blob/trunk/docs/install_linux.md
+# and https://learn.microsoft.com/cli/azure/install-azure-cli-linux?pivots=apt).
+# Microsoft's `deb_install.sh` is deliberately not piped into the build: it does
+# exactly this plus a `gnupg` install, and a remote script run at build time is
+# the one step a reviewer cannot read in this file. apt reads an ASCII-armoured
+# `.asc` key directly, which is what keeps `gnupg` out of the image.
+#
+# Not pinned, unlike the agent CLIs below: nothing in Codeman depends on a
+# particular gh or az behaviour, so the pinning argument there does not apply.
+# The layer cache still keeps whatever version the first build fetched until a
+# --no-cache rebuild.
+ARG CODEMAN_INSTALL_GH=0
+ARG CODEMAN_INSTALL_AZ=0
+RUN set -eux; \
+    for flag in "CODEMAN_INSTALL_GH=${CODEMAN_INSTALL_GH}" "CODEMAN_INSTALL_AZ=${CODEMAN_INSTALL_AZ}"; do \
+      case "${flag#*=}" in 0|1) ;; *) echo "${flag%%=*} must be 0 or 1, got '${flag#*=}'" >&2; exit 1;; esac; \
+    done; \
+    codename="$(. /etc/os-release && echo "${VERSION_CODENAME}")"; \
+    arch="$(dpkg --print-architecture)"; \
+    pkgs=""; \
+    install -d -m 0755 /etc/apt/keyrings; \
+    if [ "${CODEMAN_INSTALL_GH}" = 1 ]; then \
+      curl -fsSL -o /etc/apt/keyrings/githubcli-archive-keyring.gpg \
+        https://cli.github.com/packages/githubcli-archive-keyring.gpg; \
+      chmod go+r /etc/apt/keyrings/githubcli-archive-keyring.gpg; \
+      echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/githubcli-archive-keyring.gpg] https://cli.github.com/packages stable main" \
+        > /etc/apt/sources.list.d/github-cli.list; \
+      pkgs="${pkgs} gh"; \
+    fi; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      curl -fsSL -o /etc/apt/keyrings/microsoft.asc \
+        https://packages.microsoft.com/keys/microsoft.asc; \
+      chmod go+r /etc/apt/keyrings/microsoft.asc; \
+      echo "deb [arch=${arch} signed-by=/etc/apt/keyrings/microsoft.asc] https://packages.microsoft.com/repos/azure-cli/ ${codename} main" \
+        > /etc/apt/sources.list.d/azure-cli.list; \
+      pkgs="${pkgs} azure-cli"; \
+    fi; \
+    if [ -n "${pkgs}" ]; then \
+      apt-get update; \
+      apt-get install -y --no-install-recommends ${pkgs}; \
+      rm -rf /var/lib/apt/lists/*; \
+    fi
+
+# The azure-devops extension goes into a SYSTEM directory rather than the
+# default ~/.azure/cliextensions: HOME is the application-data bind mount, which
+# hides anything installed there at build time. The directory is handed to the
+# runtime account below (next to /opt/codeman-cli) so `az extension update`
+# works from a session. Nothing that runs as root executes from it. It is
+# created even without az, so the chown below does not have to know.
+ENV AZURE_EXTENSION_DIR=/opt/codeman-az-extensions
+RUN set -eux; \
+    install -d -m 0755 "${AZURE_EXTENSION_DIR}"; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      az extension add --name azure-devops --only-show-errors; \
+      rm -rf /root/.azure; \
+    fi
+
+# Git credential helpers, in the SYSTEM gitconfig so they apply to every
+# account and survive a fresh application-data directory. Each one answers only
+# for its own host and prints nothing when its CLI is not signed in, so git
+# falls through to its normal non-interactive failure. Only an installed CLI
+# gets an entry: a helper naming a missing binary would print an error on every
+# clone from that host.
+#   github.com     `gh auth git-credential`, what `gh auth setup-git` configures.
+#   Azure DevOps   an Entra ID token from `az login` (git-credential-azure-cli),
+#                  for both dev.azure.com and the legacy *.visualstudio.com hosts.
+COPY docker/git-credential-azure-cli /usr/local/bin/git-credential-azure-cli
+RUN set -eux; \
+    if [ "${CODEMAN_INSTALL_GH}" = 1 ]; then \
+      for host in https://github.com https://gist.github.com; do \
+        git config --system "credential.${host}.helper" '!/usr/bin/gh auth git-credential'; \
+      done; \
+    fi; \
+    if [ "${CODEMAN_INSTALL_AZ}" = 1 ]; then \
+      chmod 0755 /usr/local/bin/git-credential-azure-cli; \
+      for host in https://dev.azure.com 'https://*.visualstudio.com'; do \
+        git config --system "credential.${host}.helper" /usr/local/bin/git-credential-azure-cli; \
+        git config --system "credential.${host}.useHttpPath" true; \
+      done; \
+    else \
+      rm -f /usr/local/bin/git-credential-azure-cli; \
+    fi
+
 # Keep credentials out of the image. Users authenticate these CLIs at runtime
 # through Codeman sessions, and the configured host bind mount retains state.
 #
@@ -107,13 +213,28 @@ COPY --from=docker:29-cli \
 # minimal image of this exact shape). The four CLIs live only in this prefix,
 # so they still resolve; entrypoint.sh additionally pins its own PATH to the
 # system directories for the root part of the start.
+# uv/uvx: MCP servers are commonly launched with `uvx <package>` (e.g. the Nginx
+# Proxy Manager MCP), and Codex failed to enable them with "uvx not found". Copied
+# from the pinned upstream image into root-owned /usr/local/bin, never pip-installed.
+COPY --from=ghcr.io/astral-sh/uv:0.9 /uv /uvx /usr/local/bin/
 ENV NPM_CONFIG_PREFIX=/opt/codeman-cli
 ENV PATH=$PATH:/opt/codeman-cli/bin
+# CLIs installed at runtime (Settings -> CLIs, npm redirected to ~/.local by installEnv()) live on the
+# persistent home mount, so they survive a container recreate. Appended for the same reason as above.
+ENV PATH=$PATH:/home/${CODEMAN_RUNTIME_USER}/.local/bin
+# pnpm is not an agent CLI: it is here because `dsh plugin` (DeepSeek Harness, which
+# this image leaves to be installed at runtime, see SERVER_INTENTIONAL_OMISSIONS in
+# test/docker-agent-image-coverage.test.ts) spawns a literal `pnpm` with no npm
+# fallback, so the Run menu's "DeepSeek - add a terminal profile" button failed
+# with `dsh: pnpm not found on PATH` (exit 127) on this image. The agent image
+# already carries it for the same reason (#352). It lives in the same
+# runtime-writable prefix as the CLIs, so a session can update it in place.
 RUN npm install --global \
       @anthropic-ai/claude-code@2.1.258 \
       @google/gemini-cli@0.58.0 \
       @openai/codex@0.152.1 \
       opencode-ai@1.18.26 \
+      pnpm@12.6.0 \
  && npm cache clean --force
 
 # Keep the web server and every local Codeman session unprivileged. PUID and
@@ -153,7 +274,7 @@ RUN set -eux; \
         --shell /bin/bash \
         "${CODEMAN_RUNTIME_USER}"; \
     fi; \
-    chown -R "${PUID}:${PGID}" /opt/codeman-cli
+    chown -R "${PUID}:${PGID}" /opt/codeman-cli /opt/codeman-az-extensions
 
 WORKDIR /opt/codeman
 
@@ -181,6 +302,21 @@ EXPOSE 3000
 COPY docker/entrypoint.sh /usr/local/bin/entrypoint.sh
 RUN chmod 0755 /usr/local/bin/entrypoint.sh
 
+# Declare the optional identity immediately before configuring it so a change
+# invalidates only this final layer. This is declarative setup: a persisted
+# ~/.gitconfig in CODEMAN_APPDATA_PATH still overrides the system-level values.
+ARG GIT_USER_EMAIL=
+ARG GIT_USER_NAME=
+RUN set -eux; \
+    if [ -n "${GIT_USER_NAME}" ] || [ -n "${GIT_USER_EMAIL}" ]; then \
+      if [ -z "${GIT_USER_NAME}" ] || [ -z "${GIT_USER_EMAIL}" ]; then \
+        echo 'Git user name and email must both be set when configuring Git identity' >&2; \
+        exit 1; \
+      fi; \
+      git config --system user.name "${GIT_USER_NAME}"; \
+      git config --system user.email "${GIT_USER_EMAIL}"; \
+    fi
+
 ENTRYPOINT ["/usr/local/bin/entrypoint.sh"]
 
 CMD ["node", "dist/index.js", "web"]

docs/agent-control-plan.md

@@ -757,3 +757,13 @@ works, and its replies arrive tagged `from-name="w9-msgtest"` (a derived-name
 worker's replies carry no `from-name`). A quick-start without `sessionName` has an
 empty Codeman name, so the peer name stays derived: agents should name their
 workers. Tests: `test/name-flag-injection.test.ts`.
+
+Later narrowing: `--name` is not only the peer name but also the `/resume` picker
+entry and the terminal title, and a pinned title stops Claude generating its own, so
+pinning the `w1-myapp` placeholder listed every conversation of a case under the same
+name in `/resume`. Only a manual name is pinned now (`Session.cliPinnedName`,
+`nameSource === 'manual'`, carried to the builders as `cliName`); placeholder and auto
+names leave Claude to title the conversation. A rename in Codeman appends a
+`custom-title` row to the conversation's transcript (`claude-session-title.ts`), the
+row `/rename` writes. Tests: `test/claude-resume-title.test.ts`,
+`test/routes/session-name-routes.test.ts`.

docs/api-reference.md

@@ -311,6 +311,15 @@ worker's prompt but never submitted, and the wait then runs its full timeout on
 turn that never started. Verified live; this is the most common silent failure on
 this endpoint.
 
+A **plain prompt** (printable text followed by exactly one `\r`, nothing else) is
+delivered through tmux even without `useMux`: the text is typed, Enter is pressed as
+a separate key, and the server re-presses Enter while the prompt is still visibly
+sitting on the composer. Written straight into the pane in one piece, a prompt of
+about a hundred characters or more is taken as a paste by Claude Code, its `\r`
+becomes a newline, and the prompt stays unsent (measured on 2.1.283). Any other
+input (escape sequences, a bracketed-paste frame, a line feed, a bare `\r`) keeps
+the raw write, and an explicit `"useMux": false` forces it.
+
 ```bash
 curl -s -X POST "$API/api/v1/sessions/$SID/input" \
   -H 'Content-Type: application/json' \
@@ -691,6 +700,19 @@ normal `caseName`/`mode`/etc. body)
   jarring than a full relaunch, and folding it into the one-shot path is
   separate work — see `docs/custom-model-endpoints-plan.md`).
 
+## CLI management
+
+Read and write the CLI registry (`docs/cli-registry.md`). Every **write** route answers `403 FORBIDDEN` while `cliManagementEnabled` is off (the default), and for a non-admin in multi-user mode. A write that would overwrite a `clis.json` which does not parse, or which has group/world permission bits, is refused with `409 CONFLICT` and a message naming the fix; the file is left untouched.
+
+| Method   | Path                          | Body                                                    | Notes                                                                                                   |
+| -------- | ----------------------------- | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
+| `GET`    | `/api/clis`                   | none                                                    | Every entry, disabled ones included: `id`, `label`, `shortBadge`, `order`, `kind`, `enabled`, `stock`, `installed`, and `installCommand` for a stock entry. Not gated; a non-admin in multi-user mode gets `[]`. |
+| `PUT`    | `/api/clis/:id`               | `{ enabled }`                                           | Toggle an existing entry, stock or custom. `404` for an unknown id; `400 INVALID_INPUT` when disabling a `kind: 'shell'` entry. |
+| `POST`   | `/api/clis/:id/install`       | none                                                    | Run a **stock** entry's install command (never a custom one: `400`). `409 CONFLICT` while an install for the same id is running; `422 OPERATION_FAILED` with the output tail when it fails. Never enables the entry. |
+| `POST`   | `/api/clis`                   | `{ id, label, shortBadge, binaries, argv, enabled? }`   | Create a custom entry. `409 ALREADY_EXISTS` for a stock id or an existing custom id. `enabled` defaults to `true`. |
+| `PUT`    | `/api/clis/custom/:id`        | `{ label, shortBadge, binaries, argv, enabled? }`       | Replace an existing custom entry. An absent `enabled` keeps the entry's current state. `400` for a stock id, `404` for an unknown one. |
+| `DELETE` | `/api/clis/:id`               | none                                                    | Delete a custom entry. `400` for a stock id, `404` for an unknown one.                                  |
+
 ## Voice dictation
 
 Browser dictation transcribed through this server's Claude Code login, i.e. the

docs/architecture-invariants.md

@@ -10,12 +10,27 @@ Implementation detail extracted from `CLAUDE.md` so that file stays small enough
 
 ### Default bind, and the non-loopback warning path
 
-**Default bind is loopback-only; non-loopback without a password starts but warns** — since COD-29 (PR #107) the web server defaults to `--host 127.0.0.1` (was `0.0.0.0`). As of **0.9.0** binding a non-loopback host (`--host`/`-H`/`CODEMAN_HOST`) without `CODEMAN_PASSWORD` **no longer refuses to start — it starts and prints a loud warning** listing the fixes (set `CODEMAN_PASSWORD`, bind loopback + tunnel/`tailscale serve`, or `--allow-unauthenticated-network` / `CODEMAN_ALLOW_UNAUTHENTICATED_NETWORK=1` to acknowledge → terser note). Host classification is `isLoopbackBindHost()` in `network-auth-policy.ts`; the warn-vs-start logic is in `server.ts` `start()`; flags wired in `cli.ts`. ⚠️ Operational note: the production systemd unit runs `node dist/index.js web --https` with no `--host`, so it binds **localhost only** — reach it remotely via `tailscale serve`/tunnel to `127.0.0.1`, or add `Environment=CODEMAN_HOST=0.0.0.0` + `Environment=CODEMAN_PASSWORD=…` to `~/.config/systemd/user/codeman-web.service`. A loopback bind is reachable through a same-host tunnel (cloudflared/tailscale → `127.0.0.1`) but NOT by a browser hitting the box's LAN IP. Auth user defaults to `admin`. **Installer note** (1.8.x, `install.sh`): interactive installs now PROMPT for the binding, defaulting to LAN (`0.0.0.0`) with a required password prompt (skipping the password needs an explicit confirm and prints a loud warning); non-interactive installs keep loopback unless `CODEMAN_HOST` is preset, and re-runs/updates preserve the EXISTING binding (`read_existing_binding()` parses the current systemd unit / launchd plist). The server binary's own default is unchanged. **Full model: `docs/security-architecture.md`.**
+**Default bind is loopback-only; non-loopback without a password starts but warns** — since COD-29 (PR #107) the web server defaults to `--host 127.0.0.1` (was `0.0.0.0`). As of **0.9.0** binding a non-loopback host (`--host`/`-H`/`CODEMAN_HOST`) without `CODEMAN_PASSWORD` **no longer refuses to start — it starts and prints a loud warning** listing the fixes (set `CODEMAN_PASSWORD`, bind loopback + tunnel/`tailscale serve`, or `--allow-unauthenticated-network` / `CODEMAN_ALLOW_UNAUTHENTICATED_NETWORK=1` to acknowledge → terser note). Host classification is `isLoopbackBindHost()` in `network-auth-policy.ts`; the warn-vs-start logic is in `server.ts` `start()`; flags wired in `cli.ts`. ⚠️ Operational note: the production systemd unit runs `node dist/index.js web --https` with no `--host`, so it binds **localhost only** — reach it remotely via `tailscale serve`/tunnel to `127.0.0.1`, or add `Environment=CODEMAN_HOST=0.0.0.0` + `Environment=CODEMAN_PASSWORD=…` to `~/.config/systemd/user/codeman-web.service`. A loopback bind is reachable through a same-host tunnel (cloudflared/tailscale → `127.0.0.1`) but NOT by a browser hitting the box's LAN IP. Auth user defaults to `admin`. **Installer note** (`install.sh`, installer v2 since 2026-09-20): interactive installs PROMPT for the binding up front, defaulting to Tailscale when the node is already connected, else LAN (`0.0.0.0`), and to the existing choice on a re-run; a LAN bind asks for a password, and skipping it is a confirm that DEFAULTS TO YES (owner decision 2026-09-20) and ends on a loud red notice; non-interactive installs keep loopback unless `CODEMAN_HOST` is preset, and re-runs/updates preserve the EXISTING binding AND password (`read_existing_binding()` parses the current systemd unit / launchd plist, and the `--lan`/`--tailscale`/env preset paths read `${CODEMAN_PASSWORD:-$EXISTING_PASSWORD}`, since a flag re-run used to rewrite a password-protected unit open). The server binary's own default is unchanged. **Full model: `docs/security-architecture.md`.**
 
 ### Instance isolation and the multi-instance attach danger
 
 **Instance isolation / multi-instance attach danger** — data dir (`~/.codeman`) and tmux socket (`tmux -L codeman`) are PROCESS-WIDE and shared by every Codeman on the machine, derived from `CODEMAN_INSTANCE` via `src/config/instance.ts` (`getDataDir()`/`dataPath()`/`DEFAULT_TMUX_SOCKET`). ⚠️ A 2nd instance on the SAME socket **discovers and attaches PTYs to the first instance's live sessions** (`tmux -L codeman attach-session …`), resizing/mutating them — `$HOME` isolation is NOT enough (tmux is system-global). To run two instances, give each a distinct `CODEMAN_INSTANCE` (scopes BOTH dir+socket: `~/.codeman-<name>` + `-L codeman-<name>`), or set `CODEMAN_TMUX_SOCKET` + `CODEMAN_DATA_DIR` individually. **`CODEMAN_INSTANCE` defaults to empty = the production layout (`~/.codeman`, `-L codeman`, port 3000)**, so this branch is safe to ship to master without disturbing existing installs. To run THIS beta alongside prod, launch with `scripts/run-beta.sh` (`CODEMAN_INSTANCE=beta` + `CODEMAN_PORT=5000`) — it never collides with prod's data dir/socket/port. Any new `~/.codeman/...` path MUST go through `dataPath()`, never `join(homedir(), '.codeman', …)`, and any new `tmux -L` caller through `resolveTmuxSocketName()` (same module): it applies the `CODEMAN_TMUX_SOCKET` override only when the name is safe and falls back to `DEFAULT_TMUX_SOCKET` otherwise. `TmuxManager` was the only such caller until `codeman tui` shelled out to tmux from a SECOND process for its degraded-mode listing and its attach handoff; a hardcoded `codeman` there would have pointed a beta instance straight at prod's panes.
 
+### Reverse-proxy base path
+
+**Reverse-proxy base path** (`--base-url` / `CODEMAN_BASE_URL`, default `/`; `src/config/base-path.ts` is the pure single-source, normalized to `''` for root or `/foo`): lets Codeman be mounted under a sub-path behind a proxy that **forwards the prefix unchanged** (does NOT strip it). Deliberately few choke points, mirrored ingress/egress:
+
+- **(server ingress)** `stripBasePath()` runs inside Fastify's `rewriteUrl` so ALL routes stay declared prefix-agnostic (`/api/...`, `/ws/...`) — and a request arriving WITHOUT the prefix (hooks, health checks, docker bridge, all hitting the raw port) is left untouched, so the server answers at both.
+- **(server egress)** one `onSend` hook prepends the base to every root-absolute `Location` header, covering all redirects.
+- **(HTML)** `renderIndexHtml` rewrites the shipped `<base href="/">` to the mount and injects `window.__CODEMAN_BASE__` — the template's asset refs are all RELATIVE so `<base>` handles them for free.
+- **(frontend runtime URLs)** root-absolute URLs ignore `<base>`, so `CodemanBase.url()` (constants.js) is the route builder, applied transparently by a `fetch` wrapper and explicitly at the few EventSource/WebSocket/`window.open`/`<img|iframe|a>`-src sites.
+- **(sw.js/manifest)** the worker derives its base from `self.location`, the manifest uses relative `start_url`/`scope`.
+- **(web-tab proxy)** `proxyPrefixFor(cap, basePath)` is the single base-aware root that cascades to the injected `<base>`, root-absolute HTML rewrites, the `runtimeUrlShim`, `Set-Cookie` Path and `Location` rebasing — while the INGRESS parsers (`capabilityFromProxyPath`, `resolveUpstreamUrl`) stay base-agnostic because `rewriteUrl` strips the prefix before routing, and `capabilityFromReferer(referer, basePath)` strips it from the browser-supplied Referer.
+
+⚠️ `--base-url` rides the daemon relaunch via `buildWebArgs` and the service unit via `resolveServicePlan`.
+
+Pure helpers unit-tested in `test/base-path.test.ts` + `test/webview-proxy.test.ts`; HTML injection in `test/render-index-html.test.ts`.
+
 ## Session launch modes
 
 **Terminal colour env** — the stock registry decides each CLI's colour vars. Claude, Codex, Gemini, Antigravity, Pi, Grok, DeepSeek and OMP export `COLORTERM=truecolor`; `shell` and `opencode` unset it. All of those except Claude also unset `NO_COLOR`, so a user who exports `NO_COLOR` globally keeps monochrome Claude panes. The variable matters because a CLI inheriting no `COLORTERM` quantizes every RGB color it draws down to whatever palette `TERM` alone implies, and the pane's `TERM` is not a constant. ⚠️ Codeman sets no `default-terminal` and passes tmux no `-f`, so it is tmux's default (`tmux-256color` since 3.2) unless the user's own `~/.tmux.conf` says otherwise, which Codeman's server DOES read. At `tmux-256color` supports-color reports 256 colors and `rgb(55, 55, 55)` lands on `ESC[48;5;237m`: visible, but not the color the theme named. Where `TERM` resolves to a 16-color entry instead (tmux older than 3.2, or a conf setting `default-terminal screen`) every dark background collapses to `ESC[40m`, the terminal's own black, and the block disappears entirely. That is why the same Claude theme looks different on two machines, and why a bug report here is worth pairing with the reporter's `tmux -V` and their pane's real `TERM`. ⚠️ These declarations reach the local tmux pane via `buildEnvExports()`, its attach client via `cliExportsTruecolor()`, and the direct-PTY fallback via `buildClaudeEnv()` — they do NOT reach a remote pane, which `buildRemoteLaunchCommand()` builds with no env exports at all. A Docker pane takes `COLORTERM=truecolor` from the hardcoded `envCreate`/`execEnv` in `tmux-manager.ts`, which apply to every mode including the two the registry says must unset it. A `~/.codeman/clis.json` override replaces these arrays wholesale (`deepMerge`), so a custom entry can drop either list. That is why both consumers apply the entry BEFORE Codeman's own variables rather than after: `buildEnvExports()` emits `...cliEnv` ahead of `export CODEMAN_MUX=1`, and `buildClaudeEnv()` assigns `PATH`/`TERM`/`CODEMAN_*` after its unset/export loop. Reversed, a config-supplied `unset` naming `CODEMAN_HOOK_SECRET_FILE` would strip it on one path and not the other.
@@ -48,22 +63,58 @@ Model is NOT a session field: it is a composition entry in the profile's config
 
 **Codex input path (issues #218/#219/#220/#222)**: codex-mode sessions use **predictive write-through echo, never the buffer overlay**. The buffer overlay stays disabled exactly as 1.12.2 left it (`_updateLocalEchoState` in terminal-ui.js, same branch as shell; `_localEchoEnabled` remains false for codex), and the additive `_localEchoPolicy` field selects `'predict'` for codex when `localEchoEnabled` is on. Codex's composer is interactive per keystroke: typing "/" pops a live-filtering command picker (#222 was "picker never appears" because the "/" sat in the overlay until Enter), the composer grows/rewraps as it fills (#220: a long typed prompt existed ONLY in the overlay DOM, so codex never grew the composer), arrows and Ctrl+Backspace edit server-side state (#218: arrows were forwarded to an EMPTY composer while the typed text sat pending; the `\x08` control-char flush then left the overlay stateless so `\x7f` was swallowed as "nothing to remove"), and pastes arrive bracketed (#219: `terminal.paste()` wraps in `\x1b[200~..201~`, which the multi-byte-ESC branch forwarded WITHOUT flushing pending text, so the paste landed before it). The shared overlay branch (claude/gemini/opencode still buffer) gained three fixes: bracketed pastes flush pending text first, composer nav keys (`isComposerNavKey` allowlist in `CodemanTerminalInput` — arrows/Home/End/Delete/PgUp/PgDn incl. modifiers, deliberately excluding DA/CPR/DSR query responses) flush and hand the session to **pass-through** (plain PTY echo until Enter/Ctrl+C, because after cursor movement the append-only overlay cannot track edits), and a backspace that finds no overlay state is FORWARDED instead of swallowed. ⚠️ **Codex drops keystrokes that arrive in the same PTY read as a bracketed paste** (upstream `bottom_pane/paste_burst.rs` holds rapid chars for paste classification; verified against codex 0.147.0 by writing `hello\x1b[200~PASTED\x1b[201~` into the tmux client PTY in one write → composer shows only `PASTED`, while a 100ms gap yields `helloPASTED`), so the flush sends the typed text immediately and delays the paste sequence by 80ms — the same two-phase shape as the Enter branch's delayed `\r`. Related protocol fact: xterm.js sends `0x08` for Ctrl+Backspace, which codex's keymap binds to delete-ONE-char (`ctrl(Char('h'))`); real word-delete needs the kitty CSI-u encoding (`\x1b[127;5u`), which xterm.js 6.0.0 cannot emit (kitty support lands in 6.1.0-beta) — an upstream limitation, not a Codeman bug. E2E technique: codex 0.147 reaches its composer with any dummy key in `$CODEX_HOME/auth.json` (`{"OPENAI_API_KEY":"sk-test-..."}`), so a real TUI can be driven headlessly (envOverrides `CODEX_HOME` rides the `CODEX_*` allowlist) without real credentials. **Predictive write-through echo invariants** (the codex echo mode, `PredictiveEchoAddon` in `packages/xterm-zerolag-input`): (1) the onData hook `_predictHookOnData` is a PLAIN STATEMENT between the buffer block and Normal Mode — no `return`, try/catch-wrapped, never touches `_pendingInput` — so the wire path is byte-identical with the predictor active, absent or throwing (pinned at vm level and by an end-to-end trace-equality E2E); (2) it ships as a SEPARATE bundle `vendor/xterm-predictive-echo.js` so the zerolag bundle stays byte-identical, and a missing/broken bundle degrades codex to plain 1.12.2 echo (`typeof PredictiveEchoOverlay !== 'undefined'` guard); (3) predictions paint only while the cursor sits on the measured composer row (`isCodexComposerRow`, `CODEX_COMPOSER_ROW_RE = /^› /` — matches the empty-composer placeholder, typing, and the slash picker; rejects modal rows and 2-space wrapped continuation rows, the #220 ghost zone, which deliberately fall back to real echo); (4) reconciliation reads the PARSED buffer with `baseY + row` (xterm's `cursorY` is baseY-relative; `viewportY` only coincides while scrolled to bottom), confirms prefix-only on cell match PLUS cursor advance, cascades only on TWO consecutive foreign NON-BLANK passes (blanks are neutral: codex clears its placeholder on first echo), and TTL-bounds the rest; (5) after an UNPREDICTED wire edit (backspace into echoed text, any 'clear'-classified input, an IME/plain-paste 'text' commit, or every bypass send incl. `_handleCjkInput`) the addon holds new predictions until the next PARSED write: the displayed cursor is stale for one RTT and anchoring on it paints ghosts one cell off; (6) the per-device `localEchoEnabled` toggle is the kill switch returning exact 1.12.2 behavior. Measured constants + fixtures: `docs/predictive-echo-plan.md`, recorded via `scripts/dev/record-codex-frames.mjs` through the production tmux+strip pipeline. Tests: `test/local-echo-codex-gating.test.ts` (vm harness: nav-key + predict classifier truth tables, policy matrix, wire-neutrality pins), `packages/xterm-zerolag-input/test/` (addon laws, real-fixture replay, seeded fuzz), `test/codex-predictive-echo.test.ts` (E2E vs real codex incLine truncated
 
+Further detail: with the registry, a CLI that declares its own composer glyph and working line in `capabilities.workDetect` gets the same screen-probed idle confirmation claude gets (see the ❯ note in CLAUDE.md's idle-detection paragraph), and one that declares neither keeps the output-stabilization behaviour. The tmux-only rule now covers all EIGHT external modes (OMP included): none has a direct PTY fallback, because secrets are injected via socket-scoped `tmux setenv` and never on the spawn command line.
+
+Grok's permission clamp: the Run button sends `grokConfig.alwaysApprove: true` (like antigravity's bypass), and the clamp's only-if-sent branch strips it for non-granted owners in multi-user mode. Grok lands on the `'buffer'` echo policy via the `_updateLocalEchoState` fallthrough, which is UNMEASURED against a live authenticated session; if its composer turns out per-keystroke-reactive like codex, flip it to the `'off'` branch. Grok's user guide is `docs/grok-integration.md`; the resolver's `grok --version` probe is surfaced (path + version) by `GET /api/grok/status`.
+
+DeepSeek: the Run button gates on `isDeepSeekRunnable()` and a `web`/`headless` profile is refused at spawn because it cannot drive a pane. The status bridge gives dsh real `stop`/`blocked` signals, real Approvals Inbox items, and the `agent_working` event that clears an alert answered in the terminal. `clampEnvOverridesForOwner()` drops (rather than rewrites) the three keys, and dropping falls through to what `_configureCliEnv()` exports, which is the clamped value; every OTHER CLI's bypass is a command-line flag reachable only through its config, which is why the config clamp alone is the whole gate for them.
+
+OMP's registry entry declares `privilegedParams: []` and a launch spec that only ever passes `--model`/`--resume`/`--continue`.
+
 ### Remote sessions over SSH
 
 **Remote sessions (SSH)**: Sessions can run the agent inside a durable `tmux -L codeman-remote new-session -A` **on a remote host** so it survives the SSH drop (COD-104), and can also **discover + attach** to `codeman-*` sessions another Codeman launched there — attached (`owned:false`) sessions **detach, never kill** on tab close (COD-105). **Shared/collaborative** (COD-106): remote set-options are scoped per-session (never `-g`) and `window-size latest` lets multiple clients attach the same session at different viewports without clamping to the smallest; a client count surfaces a "shared · N" badge. **Auto-reconnect** (COD-108): a bounded-backoff watcher re-establishes a dropped remote session's local ssh pane and reattaches the still-running durable remote tmux (kill-switch `remoteAutoReconnect`, default ON); the pure pieces (backoff schedule, per-session reconnect state, `decideReconnect` eligibility) live in `src/remote-reconnect.ts` (tests: `test/remote-auto-reconnect.test.ts`), while `tmux-manager.ts` owns the live pane probe + timers. Owned sessions propagate `kill-session` to the remote on close; non-owned never do. ⚠️ Command-injection surface (COD-107): all ssh command lines flow through the single shell-safe `buildSshConnectionArgs()` — every user field (`-J jumpHost`, `-i identity`, `-o`) is `shellescape`d; never hand-build an ssh line elsewhere. Full design: `docs/remote-sessions.md`.
 
+Further detail: ⚠️ **Auto-reconnect revives ONLY when the durable remote tmux session is verifiably still alive** (`remoteTmuxSessionAlive()`, a `has-session` probe over ssh, #355): a clean agent exit (Ctrl-C, Ctrl-D, `exit`) tears that session down, and `isPaneDead()` cannot tell it from a transport drop, so the watcher used to relaunch a FRESH agent after every clean exit (claude only looked fine because its `|| --resume` fallback masked it). An unreachable host answers `undefined`, which also means do not revive. ⚠️ `has-session` prints NOTHING on success, so the probe is classified by EXIT STATUS (`classifyRemoteAliveExit`: 0 alive, ssh's 255 or a timeout unknown, anything else gone); reading stdout classified every live session as gone and silently disabled transport-drop reconnects. The answer is cached per session and forgotten whenever the pane is seen alive again, or a stale `true` from one transport drop would revive the next clean exit.
+
+File reads in a remote case are the second ssh surface (see Remote SSH cases below). The reason writes, office previews and thumbnails are deliberately unsupported over ssh is that no remote file is ever copied onto the server's disk. ssh children are bounded because terminal output in a remote session is written on the remote host, so a prompt-injected agent there can print hundreds of `codeman://attach` links.
+
 ### Remote SSH cases
 
 **Remote host wake-on-LAN from user input**: an optional `RemoteHost.wakeMac` (magic packet built and broadcast by Codeman) or `RemoteHost.wakeCommand` (a single executable path, run WITHOUT a shell, and the explicit override) lets the input route — and an explicit `POST /api/sessions/:id/wake` — wake a SLEEPING host instead of writing into a stalled ssh pane; `tmux send-keys` succeeds against a stalled pane, so the bytes used to vanish silently. The wake flow lives in `src/remote-wake.ts` and is reachable **only** from an EXPLICIT user request: `POST /api/sessions/:id/input`, that explicit wake route, and the create/attach path (`POST /api/quick-start` for a remote case, `POST /api/sessions` with `attachRemoteSession`, via `ensureHostAwake`), because "the user pressed Run on a sleeping host" is the same kind of request and the tmux probe would otherwise fail with a misleading "needs tmux installed". Everything TIMER-driven must never wake a host: the COD-108 auto-reconnect watcher, `Server.handleRemoteSessionDropped` and boot recovery have no access to the registry, or a host would be re-woken seconds after each suspend and could never stay asleep (asserted by wiring guards in `test/remote-wake.test.ts`, not just documented — including that `ensureHostAwake` is called from the HTTP route only, since `cron-service.ts` builds sessions through the shared service with nobody waiting on the answer). `GET /api/sessions/:id/reachability` only ASKS — it never wakes — and feeds the amber "host unreachable" banner (`host-wake-ui.js`) whose action is either Wake or, with no target configured, "Configure WoL" → `#wakeConfigModal` (saved via `PUT /api/remote-hosts/:id`). Detection is a throttled bare TCP probe (no ssh, no `ServerAliveInterval` — keepalives would move bytes into an idle connection every interval; and a host behind a jump host/SOCKS proxy is reachability-UNKNOWN, never "asleep": `isProbeable()` keeps the registry from buffering, gating or bannering on a probe that cannot reach it), input is buffered and flushed in order after `reattachRemote()` (the send-and-wait path blocks instead, as does the create path, with a shorter request budget), and the wake fields are re-read from `remote-hosts.json` on recovery AND (throttled, cached) live for a running session, because the persisted `remote` snapshot would never see a field added later (`rehydrateRemoteHostFields` + `RemoteWakeDeps.resolveRemote`). Design + invariants: `docs/remote-sessions.md` §Wake-on-LAN from user input.
 
 **Remote SSH cases** (COD-94/#145): cases can point at a **remote host** (`~/.codeman/remote-hosts.json` + `remote-cases.json` via `src/remote-hosts.ts`; CRUD under `/api/cases` — cases route file). A remote session launches a LOCAL tmux pane running `ssh <host>` that creates a durable REMOTE tmux session on a **dedicated socket** `-L codeman-remote` with name `codeman-ssh-<id>` — deliberately failing the remote Codeman's `SAFE_MUX_NAME_PATTERN` so a Codeman instance on the target host never adopts it; no `-g` global tmux options are set remotely. `remotePath`/`identityFile` are schema-guarded against shell injection (backticks/`$` rejected — same approach as `extraSshOptions`); remote tmux availability is probed via `checkRemoteTmuxAvailable()` in quick-start (ssh args carry `-o ConnectTimeout=10`). Remote claude defaults to an idempotent `claude --session-id <id> || claude --resume <id>` pair under a login shell, so a respawn or reattach continues the SAME conversation rather than starting a fresh one (remote omp gets the same treatment via `--continue`; ⚠️ because the claude arm is an `a || b` pair under `-c`, that pane's PID is the login shell, not the agent); per-host `commands.*` override. Session kill best-effort kills the remote tmux too. `SessionState.remote`/`MuxSession.remote` round-trip through recovery (`restoreMuxSessions` passes `remote` back into the Session constructor). ⚠️ Run flows must route remote cases through `POST /api/quick-start` (which resolves the remote case and skips LOCAL CLI availability gates) — `POST /api/sessions` stat-validates `workingDir` locally and has no `caseName`. `envOverrides`/`effort`/`modelOverride`/`codexConfig`/`geminiConfig` are rejected for remote quick-starts (not silently dropped). UI: Create Case modal → Remote tab. Tests: `test/remote-hosts.test.ts`, `test/remote-ssh-options.test.ts`. ⚠️ **Reading a file in a remote case goes over ssh too** (#415): `src/remote-files.ts` is the single remote-READ layer (`buildRemoteFileCommand` = `buildSshConnectionArgs` + one shellescaped remote command; `remoteProbePaths` returns remote realpath + stat; `remoteCreateReadStream` streams a `Range` via `tail -c +N | head -c L` and its `close()` must be wired to the response's `close` or the ssh child outlives an aborted download). The guard order matches the local path exactly (`validateSessionFilePathLexical` → remote realpath of BOTH file and workspace root → containment → sensitive-path → size cap on the REMOTE size), a request path arrives from the browser and is only ever interpolated as a `shellescape`d token, and an unreachable host answers **502**, never a 404. ⚠️ The probe's symlink resolution FAILS CLOSED: `readlink -f` where it exists, otherwise a `cd -P`/`pwd -P` directory walk plus a bounded plain-`readlink` loop over the last component, and anything it cannot fully resolve is reported unresolvable (404), never as the unresolved string — the first version resolved the directory chain only, so on a host without `readlink -f` a `ws/notes.txt -> ~/.ssh/id_rsa` link passed containment under its own path while `cat` served the key. Records are NUL-separated and index-keyed so a newline in a filename cannot shift the mapping. ⚠️ ssh children are BOUNDED: probes and buffered reads go through `src/remote-ssh-limiter.ts` (a `document-conversion-limiter`-shaped semaphore, default 4), the attachment-history list probes its whole history in ONE batched call (`probeRemoteAttachmentHistory`, threaded into `registerExternalAttachment({remoteProbes})`), and probes chunk at 40 paths — a prompt-injected agent printing `codeman://attach` links in a remote session used to fork one `ssh` per link. `describeExecError` never returns Node's `Command failed: <ssh line>` message (identity path + probe script in a 502 body). The `PUT /file-content` guard sits AHEAD of `validateSessionFilePath`, which resolves LOCALLY, or a same-named local directory (an sshfs mount) takes the write. Under `VITEST` the three IO functions refuse rather than connect. This covers the ATTACHMENT routes too, which is the half a clicked path needs when the file is OUTSIDE the case directory (`_isExternalPreviewPath` sends it to `POST …/attachments`): registration, by-id `raw`, metadata and the history list all resolve over ssh (`registerExternalAttachment({remote})`, `resolveServableRemoteAttachment`), and what decides the host is the SESSION, never the path string — the same absolute path means a different file on each host. Deliberately NOT supported over ssh: writes (`edit=1`/`PUT` answer 400, `editable` is always false), office previews/thumbnails, the file tree/picker, `tail-file`. Tests: `test/remote-files.test.ts`, `test/routes/file-routes-remote.test.ts`.
 
+Further wake-on-LAN detail: the wiring guards in `test/remote-wake.test.ts` are two; the second also pins that `server.ts` holds the registry for its LIFETIME only (`drop` on cleanup, `stop` on shutdown) and never calls a waking method. The create wake is wired in the route rather than the shared session service for exactly the no-timer-wakes reason. No `ServerAliveInterval`, because keepalives move bytes into an idle connection every interval and that is what a byte-threshold idle detector must not read as activity. For a host behind `jumpHost`/`socksProxy`/a `ProxyCommand` option, the probe connects to `host:port`, which such a host does not answer even while ssh works; the registry never gates create/attach on it (`'unprobeable'`), and `/reachability` answers `reachable: null, probeable: false`. The banner keys on a PROVEN `false`, and the banner's 30 s poller runs only for a host with a wake target (a timer connecting to a host Codeman cannot wake is the same timer-driven traffic the keepalive rule forbids).
+
+Input arriving during a wake is buffered: a chunk over 4 KB is dropped whole, never delivered as a fragment, and the route answers `{buffered:true}` / `{buffered:true, dropped:true}` so the caller can tell. It is flushed in order after `reattachRemote()` with `fromUser`; a flush write that fails drops the rest (logged) rather than retaining it for a wake hours later. Send-and-wait blocks instead and answers `OPERATION_FAILED` when the host never returns. ⚠️ In multi-user mode the attach path 403s a non-admin BEFORE the host is looked up: the wake runs an executable, and remote hosts are admin-only infra everywhere else. ⚠️ Browser keystrokes travel over the WebSocket, which deliberately does NOT pass through the registry (that is the hot path), so only the HTTP input path ever queues anything; the banner must not promise queued input for the Wake button. A request that waits on the wake (create/attach, and the button) uses the 40 s `REMOTE_WAKE_REQUEST_READY_TIMEOUT_MS`, not the 90 s session default, because the dashboard's reverse proxy cuts a request at its own 60 s `proxy_read_timeout`. The `remote:` SSE family is session-scoped in multi-user mode; a create/attach wake names its requester (`username`) since it has no session yet. `remote-wake.ts` refuses real IO under `VITEST` like `remote-files.ts`.
+
 ### Docker cases
 
-**Docker cases** (shipped 1.4.0; user guide `docs/docker-cases.md`, design `docs/docker-cases-plan.md`): a case can point at a **container** instead of a local/remote path, and any of the CLI run modes runs INSIDE it. Like remote-SSH, it is a **LOCATION OVERLAY on cases, never a `SessionMode` of its own** (`SessionMode` is unchanged). Storage `~/.codeman/docker-hosts.json` + `docker-cases.json` via `src/docker-hosts.ts` (direct mirror of `remote-hosts.ts`: `readDockerHosts`/`readDockerCases`, `toSessionDocker`, `dockerDisplayPath`, and the PURE builders `buildDockerBaseArgs`/`buildDockerCreateArgs`/`containerApiUrl`/`hostGatewayAlias`/`dockerConfigHash`). CRUD `/api/docker-hosts` + `/api/cases/docker-link`, plus **one-click** `/api/cases/docker-quickcreate` (Create New "Run in Docker" checkbox → case folder in `CASES_DIR` + auto-provisioned shared `default` host + auto-start a session inside; an expandable Template picker Small/Medium/Large/GPU or any override creates a per-case `q-<name>` host), and export/import (`/api/docker-cases/:name/export`, `/api/docker-cases/import`, `GET/DELETE /api/docker-exports`) — all in `case-routes.ts`. Run flows route through `POST /api/quick-start` like remote (session-routes.ts docker branch, skips LOCAL CLI-availability gates). **Launch model**: exactly one long-lived container **per case** (`codeman-case-<slug>`, PID1 `sleep infinity` under `--init`); a LOCAL tmux pane runs `docker exec -it` into a **durable in-container tmux** on dedicated socket `-L codeman-docker`, session `codeman-dkr-<id8>` (deliberately fails `SAFE_MUX_NAME_PATTERN` so a Codeman running INSIDE the container never adopts it, exactly like remote's `codeman-ssh-<id8>`). Builders `buildDockerLaunchCommand`/`buildDockerKillCommand` in `tmux-manager.ts` (image-check → `docker inspect||create` → start → exec, all idempotent). The container is **shared by all sessions of the case**: `buildDockerKillCommand` kills ONLY that session's in-container tmux session, NEVER `docker stop` while siblings remain; `docker rm -f` happens only on case-delete (plus an instance-scoped boot reaper keyed on the `codeman.instance` label). **Two-layer durability/resume** (the central design point): (1) Codeman-PROCESS restart with the container still up → `tmux new-session -A` reattaches the SAME live agent (paneCommand ignored); (2) container stop/reboot/OOM → inner tmux is gone, so the re-run pane command resumes the conversation from the bind-mounted transcript: claude mode pins a DETERMINISTIC conversation id via `claudeDockerPaneCommand()` (`tmux-manager.ts`) — fresh launch `claude --session-id <sessionId> || claude --resume <sessionId>` (a duplicate `--session-id` exits 1 "already in use", so the fallback RESUMES after a container stop; verified CLI behavior), explicit resume `--resume <rid> || --session-id <sid>` so a stale id never dead-panes (leading `exec ` is stripped — an exec'd first branch could never fall back); codex `resume <id>` / gemini `--resume` keep `appendResumeFlag`. The resume id rides `resumeSessionId` through create/respawn options and persists on `DockerCase.lastClaudeSessionId` via `persistDockerCaseClaudeSessionId()` (written at quick-start launch, and again on hook/last-response conversation-id adoption so post-`/clear` switches track; seeded back when `resumeOnStart`, default true); `-A` makes the pane command self-selecting (inert on reattach, active only when tmux was re-created). **Config drift** (`dockerConfigHash` → `codeman.confighash` label): quick-start compares via `checkDockerConfigDrift()` and REFUSES a drifted launch with `CONFLICT`; the UI confirm calls `POST /api/docker-cases/:name/recreate` (refused while case sessions are live) which `docker rm -f`s so the next launch recreates with the new config — host config edits actually take effect. **Workspace** is a REAL host dir bind-mounted at the SAME absolute path (mirror, `dst==src`), so `Session.workingDir = hostWorkspacePath` keeps file-routes/attachments/watchers on real host bytes AND the in-container transcript projHash matches the host so subagent/workflow correlation (and thus resume-id capture) works; `resolveMuxAttachCwd` returns `/tmp` for docker (the local pane only runs `docker exec`). **Creds** arrive commit-safe and ISOLATED (1.4.1; replaced the whole-dir RW mounts that let in-container CLIs write refreshed tokens/state back to the host): shared RW across the boundary is ONLY what host-side reads/resume need (`~/.claude/projects` transcripts; codex `sessions/` + `history.jsonl` for response-viewer/`codex resume`); everything else is SEEDED (RO mount, copied into container HOME once at launch via `[ -e ] || cp`; the container refreshes its own copy and never writes back): `~/.claude.json` is merged through `buildSeamlessClaudeConfig()` (forces `hasCompletedOnboarding` + theme + workspace trust, so no login wizard/theme picker/trust prompt inside the container), plus `.claude/{.credentials.json,setLine truncated
+**Docker cases** (shipped 1.4.0; user guide `docs/docker-cases.md`, design `docs/docker-cases-plan.md`): a case can point at a **container** instead of a local/remote path, and any of the CLI run modes runs INSIDE it. Like remote-SSH, it is a **LOCATION OVERLAY on cases, never a `SessionMode` of its own** (`SessionMode` is unchanged). Storage `~/.codeman/docker-hosts.json` + `docker-cases.json` via `src/docker-hosts.ts` (direct mirror of `remote-hosts.ts`: `readDockerHosts`/`readDockerCases`, `toSessionDocker`, `dockerDisplayPath`, and the PURE builders `buildDockerBaseArgs`/`buildDockerCreateArgs`/`containerApiUrl`/`hostGatewayAlias`/`dockerConfigHash`). CRUD `/api/docker-hosts` + `/api/cases/docker-link`, plus **one-click** `/api/cases/docker-quickcreate` (Create New "Run in Docker" checkbox → case folder in `CASES_DIR` + auto-provisioned shared `default` host + auto-start a session inside; an expandable Template picker Small/Medium/Large/GPU or any override creates a per-case `q-<name>` host), and export/import (`/api/docker-cases/:name/export`, `/api/docker-cases/import`, `GET/DELETE /api/docker-exports`) — all in `case-routes.ts`. Run flows route through `POST /api/quick-start` like remote (session-routes.ts docker branch, skips LOCAL CLI-availability gates). **Launch model**: exactly one long-lived container **per case** (`codeman-case-<slug>`, PID1 `sleep infinity` under `--init`); a LOCAL tmux pane runs `docker exec -it` into a **durable in-container tmux** on dedicated socket `-L codeman-docker`, session `codeman-dkr-<id8>` (deliberately fails `SAFE_MUX_NAME_PATTERN` so a Codeman running INSIDE the container never adopts it, exactly like remote's `codeman-ssh-<id8>`). Builders `buildDockerLaunchCommand`/`buildDockerKillCommand` in `tmux-manager.ts` (image-check → `docker inspect||create` → start → exec, all idempotent). The container is **shared by all sessions of the case**: `buildDockerKillCommand` kills ONLY that session's in-container tmux session, NEVER `docker stop` while siblings remain; `docker rm -f` happens only on case-delete (plus an instance-scoped boot reaper keyed on the `codeman.instance` label). **Two-layer durability/resume** (the central design point): (1) Codeman-PROCESS restart with the container still up → `tmux new-session -A` reattaches the SAME live agent (paneCommand ignored); (2) container stop/reboot/OOM → inner tmux is gone, so the re-run pane command resumes the conversation from the bind-mounted transcript: claude mode pins a DETERMINISTIC conversation id via `claudeDockerPaneCommand()` (`tmux-manager.ts`) — fresh launch `claude --session-id <sessionId> || claude --resume <sessionId>` (a duplicate `--session-id` exits 1 "already in use", so the fallback RESUMES after a container stop; verified CLI behavior), explicit resume `--resume <rid> || --session-id <sid>` so a stale id never dead-panes (leading `exec ` is stripped — an exec'd first branch could never fall back); codex `resume <id>` / gemini `--resume` keep `appendResumeFlag`. The resume id rides `resumeSessionId` through create/respawn options and persists on `DockerCase.lastClaudeSessionId` via `persistDockerCaseClaudeSessionId()` (written at quick-start launch, and again on hook/last-response conversation-id adoption so post-`/clear` switches track; seeded back when `resumeOnStart`, default true); `-A` makes the pane command self-selecting (inert on reattach, active only when tmux was re-created). **Config drift** (`dockerConfigHash` → `codeman.confighash` label): quick-start compares via `checkDockerConfigDrift()` and REFUSES a drifted launch with `CONFLICT`; the UI confirm calls `POST /api/docker-cases/:name/recreate` (refused while case sessions are live) which `docker rm -f`s so the next launch recreates with the new config — host config edits actually take effect. **Workspace** is a REAL host dir bind-mounted at the SAME absolute path (mirror, `dst==src`), so `Session.workingDir = hostWorkspacePath` keeps file-routes/attachments/watchers on real host bytes AND the in-container transcript projHash matches the host so subagent/workflow correlation (and thus resume-id capture) works; `resolveMuxAttachCwd` returns `/tmp` for docker (the local pane only runs `docker exec`). **Creds** arrive commit-safe and ISOLATED (1.4.1; replaced the whole-dir RW mounts that let in-container CLIs write refreshed tokens/state back to the host): shared RW across the boundary is ONLY what host-side reads/resume need (`~/.claude/projects` transcripts; codex `sessions/` + `history.jsonl` for response-viewer/`codex resume`); everything else is SEEDED (RO mount, copied into container HOME once at launch via `[ -e ] || cp`; the container refreshes its own copy and never writes back): `~/.claude.json` is merged through `buildSeamlessClaudeConfig()` (forces `hasCompletedOnboarding` + theme + workspace trust, so no login wizard/theme picker/trust prompt inside the container), plus `.claude/{.credentials.json,setLine truncated
 
 Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/docker-export.test.ts`, `test/network-host-guard.test.ts`.
 
+Further detail: ⚠️ An ADOPTED container may back SEVERAL cases at different in-container directories (`classifyAdoptContainerConflict` in `docker-hosts.ts`: an exact twin on the same container AND directory is refused, an owned container still backs exactly one case, and a container another user adopted is refused), which is what the Add Case panel's "copy an existing case" picker relies on. The wire carries `CaseInfo.docker.owned` ONLY when false, so the picker tests `=== false`, never truthiness. The export-path closures (refusing `docker commit`, skipping `docker pause`) are two lifecycle touches the original design missed and that are easy to re-introduce.
+
+### CLI registry
+
+**CLI registry** (`src/config/cli-registry/`): every run mode is a `CliEntry` — discovery (search dirs, version + identity probes), the launch argv template, env handling, the `capabilities` flags that replace per-CLI branching, and the `overlays` that back the remote/docker pane commands. **No code outside `stock.ts` may branch on a CLI id**; behaviour that genuinely differs is either a capability field or a NAMED PROFILE selected by one (`profiles.ts`), and `test/cli-registry-no-id-branching.test.ts` fails the build if an id check reappears — it matches `===`, `!==`, `case '<id>':` and `[...].includes(mode)`, because an earlier `===`-only version let 36 negated branches survive the conversion (including a seven-mode Ralph chain whose own comment asked the next person to keep it in step with `isExternalCliMode()` by hand). A second CI-gated guard, `test/frontend-cli-no-id-branching.test.ts`, covers the two frontend files the run-menu consolidation (#458) touched, `session-ui.js` and `mobile-overview.js`: its allowlist is keyed by expression rather than line number, with an occurrence count per entry, so a new branch reusing an already-approved expression fails as a count mismatch instead of riding in on the old approval.
+
+⚠️ Config contains no shell text: an entry declares typed argv tokens, literals are validated against a safe-word pattern at LOAD time (a bad literal rejects the whole entry — a silently dropped `--no-approve` is not cosmetic), and values resolve through patterns NAMED in code, so a user `clis.json` cannot widen its own validation.
+
+⚠️ `external`, `hooks` and `altScreen` are three INDEPENDENT capabilities on purpose; deriving one from another shipped the `until=stop`-hangs-on-shell bug.
+
+⚠️ Four capability fields carry a REGEX from config (`discovery.version.regex`, `capabilities.workDetect.workingLine`, `capabilities.workDetect.watchingLine` and `capabilities.workDetect.awaitingLine`) and all four must compile through `compileVersionRegex()`, which caps length and refuses nested quantifiers; `workingLine` is the one that runs on the PTY hot path.
+
+⚠️ **`param` is TWO namespaces.** `launch.params` keys, `env.configSetenv[].fromParam` and `capabilities.privilegedParams[].param` all name a LAUNCH PARAM; the legacy `<Mode>Config` wire field is a separate namespace, bridged only by `launch.legacyConfigAliases`. Getting `privilegedParams[].param` wrong is SILENT — it is the multi-user bypass clamp's only handle on a CLI's privilege switch, and a wrong name clamps nothing with no load error and no failing test — so `schema.ts` rejects an entry naming a param it never declared. Codex is the entry where the two names differ (`bypassApprovals` vs `dangerouslyBypassApprovals`) and therefore the one that catches a regression.
+
+⚠️ Five fields are DECLARED-FOR-LATER and read by nothing (`accent`, `capabilities.echo`/`wheelForward`/`keyboardAccessory`/`maxFrameBytes`): all frontend behaviour, transcribed rather than measured (except `accent`, measured against styles.css on 2026-09-21), so re-measure before wiring one up; the list is pinned so it cannot quietly grow. (`shortBadge` left the list when the Settings CLI management list started showing it.)
+
+Spawn commands are pinned as literal strings in `test/cli-registry-spawn-golden.test.ts`, remote/docker pane commands in `test/location-overlay-commands.test.ts`. ⚠️ That second golden no longer covers **remote claude or remote omp**: both now have their own arm in `buildRemoteLaunchCommand` (a `--session-id || --resume` pair, and `--continue`, so a respawn continues the same conversation) and never reach `defaultRemoteCommandForMode`, which is what that test asserts. Their real pins are `toContain` substrings in `test/tmux-manager.test.ts` and `test/remote-shared-sessions.test.ts`; changing either arm will NOT fail the golden.
+
+⚠️ Anything reading the registry resolves it AT CALL TIME (`sessionModeSchema()`, `allowedEnvPrefixes()`, `dependencyRegistry()`, the resolvers' `searchDirs` thunks) — a module-level const freezes at first import, so a CLI enabled while the server ran moved the run menu but not that surface. `~/.codeman/clis.json` overrides any entry. Importing the registry still has no filesystem side effects: the only writer is `registry-writer.ts`, imported only by `cli-registry-routes.ts` (the opt-in CLI management routes, `cliManagementEnabled`, default OFF). ⚠️ Every write goes through `mutateRegistryFile()`: mutations run one at a time on a single promise chain, each with a unique temp file (three parallel toggles once lost two and 500'd on a shared temp name), and a file the READER would ignore (group/world permission bits) or quarantine (unparseable) is REFUSED with a 409 rather than rewritten, so one Settings click cannot replace a hand-edit or turn a refused file into trusted 0600 config. Only a missing file starts fresh. After a write the registry is reloaded, so changes apply without a restart. User guide: `docs/cli-registry.md`.
+
 ## Session data and lifecycle
 
 ### Input delivery and WS resilience
@@ -90,6 +141,14 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 **Signal availability is decided by MODE, not by `isExternalCliMode()`.** `stop` and `blocked` come from Claude Code hooks, so `hooksAvailableForMode()` is true only for `claude`: `shell` is not an external-CLI mode but installs no hooks either, so `until=stop` on a shell session is a guaranteed unresolvable wait dressed up as a timeout. The behavior split is deliberate and must survive refactors: an EXPLICIT request for an unavailable signal is a 400 naming the mode, while the DEFAULT set (`stop,idle,exit`) silently drops them and echoes the narrowed set back as `wait.until`, because omitting the parameter must never 400. Signal quality is not uniform either: `stop` is definitive (Claude Code says the turn is over), `idle` is inferred from output stabilization plus prompt detection and can flap mid-turn when a spinner pauses, which is why `stop` is the documented default to orchestrate on and `idle` is the fallback for sessions that emit no hooks. ⚠️ **`idle` being ACCEPTED for a mode does not mean it ever FIRES there.** `startShell()` emits exactly one `idle` on a 500ms readiness timer and nothing afterwards, so a shell session sits at `status:'idle'` no matter what its pane is doing; since send-and-wait and `fresh=1` both require a TRANSITION, both can only time out on a shell worker (measured: a default `wait` on `sleep 4` burned its full 25s). The ❯-prompt and spinner detection that drives the real `working`/`idle` cycle is Claude's output format, so hook-less modes synchronize with `wait-output` markers or `exit`, and the docs must say so rather than listing `idle` as "available" and letting the reader infer it is usable. ⚠️ **Signals are edge-triggered with no history**, and that is a real orchestration limit: a signal that fires while no waiter is registered is gone, unobservable by any later wait variant (`until=stop` after the turn ended just times out, `fresh` or not — measured, R2-A). Documented client patterns must therefore register the waiter before the event can fire (send-and-wait) or gather on latched `wait-output` markers with `from=buffer`; the skill's fan-out flow was rewritten accordingly, and "fire-and-forget N prompts, then gather signal-waits sequentially" must never be documented again. The durable fix, a server-side latched last-signal-per-turn, is deferred with Part 3 of `docs/agent-control-plan.md`. ⚠️ Relatedly, the route corrects liveness that `SessionStatus` cannot express: `currentSignalFor()` answers `exit` whenever `pid === null` (exited, detached, or created-and-never-started) **or the mux pane is dead**, because `Session` parks a DEAD PTY at `_status = 'idle'` and trusting the status would answer the default wait `{signal:'idle', immediate:true}` for a crashed worker while `until=exit` blocked forever on an event that already happened. ⚠️ **`pid` alone cannot carry liveness for a tmux-backed session**: that pid is the local `tmux attach` CLIENT, so a worker exiting inside its pane leaves `pane_dead=1` with the client alive and `pid` never goes null — the `pid === null` branch is unreachable in the normal configuration (unit tests exercise it because `MockSession` sets `pid` by hand; only a live instance showed the gap). Liveness is therefore probed at the mux layer: `workerIsDead()` consults `mux.isPaneDead(muxName)` with a ~750 ms per-pane cache, ONLY on blocking waits (measured: 0 tmux execs across 100 non-wait input POSTs — the browser hot path pays nothing), plus a refcounted 3 s `watchForDeadWorker` interval so a worker dying while a wait is parked resolves it in ~3 s instead of burning the timeout. The probe fails SAFE by construction ("cannot tell" is never "dead": non-mux sessions, a missing or throwing `isPaneDead`, all return false). On send-and-wait, a "successful" `send-keys` into a dead pane additionally overrides `delivered` to `false` and rolls the dedup seq back (`undoOnFailure`), because the bytes went nowhere and a retry against a restarted worker must not be refused as a duplicate. The cost is that a just-created session reads as `exit`, which the wire docs must spell out as "not started yet"; the fix lives at the route rather than in `signalForStatus()` because the registry deliberately holds no `Session` reference. ⚠️ Two `claude`-mode cases still lose hooks for reasons outside the registry: a Docker case cannot reach a loopback-bound Codeman without `CODEMAN_DOCKER_BRIDGE_HOOKS=1`, and a remote-SSH case runs the agent on another host whose hooks may never reach this server. Bounds are env-overridable (`CODEMAN_WAIT_MAX_MS`, `CODEMAN_WAIT_DEFAULT_MS`, `CODEMAN_WAIT_MAX_PER_SESSION`, `CODEMAN_WAIT_MAX_PER_OWNER`, `CODEMAN_WAIT_MAX_TOTAL`, `CODEMAN_WAIT_BUFFER_SCAN_BYTES`) and each is clamped to a hard bound so a typo degrades to the default instead of disabling the protection; they are internal tuning knobs like the rest of `src/config/`, NOT part of the SemVer-covered env-var surface in `versioning-policy.md`. Tests: `tesLine truncated
 
+Further detail: `stop`/`blocked` now fire for **`claude` and `deepseek`** (`shell` installs no hooks either); asking for one explicitly on any other mode is a 400 and the default set silently drops them. `deepseek` qualifies because the DeepSeek Harness TUI REPORTS idle/working/blocked to its supervisor and Codeman is that supervisor (`deepseek-status-shim.ts`), so its signals are definitive rather than inferred, and `hooksAvailableForMode()` in `session-wait-registry.ts` is the one place that rule lives (see the External CLI modes section for the per-session `statusReporting` wrinkle and the two dsh traps baked into the skill preamble: boot `idle` landing ~300 ms before the composer paints, and `sendwait` asking for `wait:"stop,exit"`). That is also why `deepseek` is the one non-claude mode the skill drives like claude: `spawn_workers alpha beta:deepseek` is a mixed fleet in one call, and `sendwait`/`last_text` need no variant.
+
+**Packaging as the `skills/codeman` agent skill.** The primitives are packaged as the `skills/codeman` agent skill, installable three ways: via `codeman skill install [--case <name>]` / `skill uninstall`; as a Claude Code plugin from the repo's own marketplace (`/plugin marketplace add Ark0N/Codeman` + `/plugin install codeman@codeman`, see the root-files note in CLAUDE.md); or auto-injected into a case's `.claude/skills/` on Claude session create behind `agentSkillEnabled` (SYNCED, default OFF). ⚠️ Plugin skills are namespaced, so a Claude Code holding BOTH the plugin and a user-level or per-case copy lists the skill twice, `codeman` and `codeman:codeman` (measured 2026-09-14: neither shadows the other, both work); the docs tell users to pick one route.
+
+Injection is ADD-ONLY at create, marker-owned (`applyAgentSkill` in `hooks-config.ts` never touches an unmarked user copy) and refuses symlinks (this repo's own `.claude/skills/codeman` is a symlink to the source, which the injector must never write through). ⚠️ Claude Code loads a same-named USER-LEVEL skill (`~/.claude/skills/codeman`, written once by `codeman skill install` with no `--case`) over the per-case copy, and nothing used to refresh it: a stale Aug-9 user copy shadowed every fresh injection (2026-08-14: agents ran the old recipes, spawned workers serially and lost their lineage arcs), so session create now also refreshes a marker-owned user copy (`refreshUserAgentSkill`; refresh-only, never installs, foreign/symlink refused).
+
+Session create additionally pre-seeds the skill's §0 preamble cache (`seedAgentSessionPreamble` → `${XDG_CACHE_HOME:-~/.cache}/codeman-agent-<id>.sh`, local claude sessions only), single-sourced from `skills/codeman/preamble.sh` and pinned byte-identical to SKILL.md's §0 heredoc by `test/agent-skill.test.ts`, so the skill's bootstrap is a two-line loader instead of a ~150-line paste the model types out (~47 s of generation, measured live).
+
 ### Auto-resume on usage limit
 
 **Auto-resume on usage limit** ("token pause" control, opt-in per session, top of the Respawn tab): when Claude halts on a subscription limit ("5-hour limit reached ∙ resets 8pm" and all 1.0.x–2.1.x variants), `usage-limit-patterns.ts` (pure, unit-tested) parses the reset time from cleaned output; `SessionAutoOps` arms a timer for reset+2min, then sends Esc (dismisses the rate-limit dialog) + `continue`. Still-limited responses re-arm the loop (5-min retry on stale times); a `working` transition cancels it. Claude-mode only (detection rides `_processExpensiveParsers`). Persists/recovers via `SessionState.autoResumeEnabled`/`autoResumeAt`; respawn cycles are blocked while paused (`isLimitPaused` guard in `onIdleDetected` — prevents `/clear` from wiping the paused conversation). Endpoint: `POST /api/sessions/:id/auto-resume`; SSE: `session:limitPauseScheduled`/`limitResume`/`limitResumeCancelled`. Tests: `test/usage-limit-patterns.test.ts`, `test/session-auto-resume.test.ts`.
@@ -98,6 +157,8 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 **Plan-usage chip** (`showPlanUsageLimits`, per-device: desktop default **ON** since 1.9.3, handhelds OFF) renders compact Claude and Codex provider rows. Claude Code (v2.1.80+) pipes a JSON blob to a configured `statusLine.command` on each render; on Pro/Max it carries a `rate_limits` object (`five_hour`/`seven_day` windows only — no Opus weekly field — each `{used_percentage 0-100, resets_at epoch-SECONDS}`). ⚠️ **Injected as an EPHEMERAL `claude --settings` CLI flag at spawn (2026-09-07), never written to disk** — `resolveStatusLineCliCommand()`/`ensureStatusLineExporterScript()` in `hooks-config.ts` (`generateStatusLineCommand()`/`applyStatusLineConfig()` remain, but only as the legacy disk-write self-heal path: a workspace an older Codeman build touched gets its stale `.claude/settings.local.json` entry stripped the first time a session starts there again). The exporter WRAPS a user's own real statusline (`findEffectiveUserStatusLineCommand()`, walking Claude Code's own settings precedence) rather than replacing it, and POSTs the `rate_limits` blob to `POST /api/status-telemetry`. That route (auth-exempt like `/api/hook-event` — localhost-only, hook-secret-gated whenever auth is active, COD-91) parses via `usage-telemetry.ts` (pure, unit-tested), broadcasts SSE `session:statusTelemetry` (de-duped per session by `telemetrySignature` since the statusline fires on every assistant message), and returns a compact plain-text footer for the exporter to **print-through** (foreground POST in the no-wrap branch so its own stdout becomes the footer, printing NOTHING on failure, `curl -sfk` plus `|| true`, since a bare brand word on the statusline is what discussion #405 opened with; backgrounded — `>/dev/null 2>&1 </dev/null &`, closing stdin too — only in the wrap branch, where the user's own command owns the footer; `curl --max-time 5` bounds a hung, not just refused, Codeman). Main Codex subscription usage comes from the signed-in host CLI's read-only app-server `account/rateLimits/read` request at startup and every 5 minutes; `usage-telemetry.ts` selects only the main `codex` bucket (never model-specific buckets such as Spark), maps whatever 5-hour/7-day windows it supplies, and omits the provider row when unavailable. Credentials stay inside the CLI and no auth material is sent to the browser. `plan-usage-latest.ts` merges both process-wide sources and replays them in the SSE init snapshot (`getLightState`) so `#planUsageChip` renders immediately on page load/reconnect. `planUsageChipEnabled()` remains the single resolver behind the checkbox and chip visibility (DISPLAY only) — the SAME `showPlanUsageLimits` setting also doubles as the server-side telemetry COLLECTION switch, read FRESH from `settings.json` by `readPlanUsageTelemetryEnabled()` at every claude session create/respawn (`TmuxManager.createSession`/`respawnPane`), never cached, with no per-session field and no per-request wire field — applies uniformly across every claude-creation path (interactive Run, cron, Ralph Loop API, quick-start) and survives a Codeman restart by construction (nothing per-session to lose). ⚠️ An ABSENT key reads as ON, the same way an absent `workspaceHooksEnabled` does: the desktop chip already shows as on for an install that never touched the setting, and the exporter posts only to this Codeman over loopback. Resolving the default in the reader is what keeps `GET /api/settings` a plain read. It briefly reconciled the key on first read (persisting `true` when absent), but `readJsonConfig()` answers `{}` for ANY read failure, not only ENOENT, and every page load hits that route, so one unlucky read replaced the whole settings file with a one-key file; pinned by `test/routes/system-routes-settings-get-plan-usage-default.test.ts`. ⚠️ The client sends `showPlanUsageLimits` in a settings save ONLY when that save FLIPS the chip relative to what the device had (`planUsageCollectionFlip()` in settings-ui.js): the chip defaults OFF on handhelds, so sending it on every save let a phone saving its font size persist `false` and switch collection off for every desktop, whose chip then went stale with no error anywhere. An explicit toggle on any device still writes the switch. Injection covers LOCAL tmux-spawned claude sessions only: the non-tmux direct-PTY fallback (`Session.startInteractive` when tmux is unavailable) and the remote/docker pane builders do not carry the flag. Registry-gated on `getCli(mode)?.capabilities.statusLineTelemetry` rather than a hardcoded mode string. **Distinct from auto-resume** (which reacts to the Claude limit _message_; this proactively shows live percentages). Design: `docs/usage-limits-display-plan.md`. Tests: `test/usage-telemetry.test.ts`, `test/codex-plan-usage.test.ts`, `test/plan-usage-chip.test.ts`, `test/plan-usage-latest.test.ts`, `test/hooks-config.test.ts` (statusline exporter script + `readPlanUsageTelemetryEnabled`), `test/statusline-cli-flag.test.ts`.
 
+Further detail: the handheld OFF default comes from the mobile block in `getDefaultSettings()`. `planUsageChipEnabled()` backs the two call sites that must never disagree (the App Settings checkbox and the chip's visibility). The absent-key-reads-as-ON rule mirrors `readWorkspaceHooksEnabled()`.
+
 ### Cron jobs
 
 **Cron (cron-style `CronJob`s)**: saved, named jobs with a recurring schedule (`once`/`interval`/`daily`/`weekly`), enable/disable, Run Now, next-run calc, and per-job run history (`CronJobRun`). ⚠️ **Distinct from the legacy `ScheduledRun`** (`/api/scheduled`, a run-now duration-bounded autonomous loop) — the two never interact; the legacy concept keeps the `Scheduled*` names, the recurring-job feature is `Cron*`. `CronService` (`src/cron/cron-service.ts`) owns CRUD + the 30s background due-tick (`tickDueJobs`, registered via `cleanup.setInterval` in `server.ts`; `init()` recomputes nextRunAt on boot) and **reuses the existing session layer** (create → `addSession` → `setupSessionListeners` → `startInteractive`/`startShell` → prompt via `writeViaMux`/`write`) rather than rebuilding tmux logic. Next-run math is pure/unit-tested in `cron-time.ts` (SERVER-LOCAL timezone for daily/weekly). Dup-launch guard = `lastDueKey` (jobId:fireTime); schedule is advanced BEFORE launch so a slow launch can't re-trigger. `once` jobs self-disable after firing (`completedOnce`). Persisted via `AppState.cronJobs`/`cronJobRuns` (StateStore accessors). Routes `/api/cron/jobs*` + `/api/cron/runs` (`cron-routes.ts`, `CronPort`); schema `CronJobSchema` (cross-field `superRefine`; the `.partial()` update schema does NOT re-run it); SSE `cron:*`. Frontend `cron-ui.js` (#cronModal). Claude/shell/opencode/codex/gemini/antigravity/pi agent types. Tests: `test/cron-time.test.ts`, `test/cron-service.test.ts`. Design: `docs/cron-discovery.md`.
@@ -106,6 +167,8 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 **Unified session list** (COD-160/#139): `GET /api/sessions/unified?limit=&q=` merges live sessions, persisted state, lifecycle-log history, and transcript files into one deduped list (pure core in `src/services/unified-session-service.ts`). ⚠️ **Transcript history is three stores** (#386): Claude's `~/.claude/projects`, omp's `~/.omp/agent/sessions` and codex's `~/.codex/sessions`. Rows are keyed by whatever id that CLI names the conversation with and folded into their owning session via the `claudeSessionId → Codeman id` alias map (resumed//clear-respawned sessions must not appear twice; the field keeps its Claude-era name and is not Claude-only). A codex row additionally carries `resumeId`, the rollout's own thread id, set by the scanner and never by a live session, which is what lets a row be resumed through `codexConfig.resumeSessionId` while a row without one stays a fresh session; the alias chain therefore includes `config.codexConfig?.resumeSessionId`, and a fresh codex pane is matched by `session_meta.originator` (`codeman_<sessionId>` for every pane Codeman spawns); lifecycle name/mode resolution is first-seen-wins (the log returns entries NEWEST-first). No terminal buffers in the response (unlike `/api/sessions`). Consumed by the Cmd+K Session Manager (#146). Session Manager polish (COD-162/#157, 1.6.0): **pinning** via `POST /api/sessions/:id/pin` (`session:pinned` SSE; killing a pinned session demotes it to a lightweight stopped record that stays visible/resumable, and cleanup skips pinned records); **cross-device tab order** via `PUT /api/session-order` (`session:orderChanged` SSE, persisted in `state.json`; pure `normalizeSessionOrder`/`mergeSessionOrder` in `src/session-order.ts`: pushing device wins, server-only ids fall to the end, never dropped); resume from the manager keeps the original session name (COD-143); `firstPrompt` is backfilled for sessions whose id != transcript UUID and the most recent prompt (`lastPrompt`) is shown + searched (COD-140/145).
 
+Further detail: `resumeHistorySession()` is what sends `codexConfig.resumeSessionId` for a row carrying `resumeId` (a conversation already on disk), and a row without one is a genuinely fresh session. Every surface that re-projects these rows has to carry `resumeId` through, the phone overview included, or a tap on that surface silently starts a second conversation.
+
 ### Session lineage lines (tab → tab it spawned)
 
 **The relationship did not exist before this** (1.17.0): `SessionState` had no `parentSessionId`, `quick-start` recorded only the multi-user *human* owner, and an agent's spawn call is plain `curl` from a tmux pane, so nothing in the request identifies the caller (`SO_PEERCRED` needs a unix socket; the API is TCP). The caller therefore supplies it — every managed pane already gets `CODEMAN_SESSION_ID` from `session-cli-builder.ts`. Two equivalent inputs, body wins: a `parentSessionId` field on `POST /api/sessions` / `POST /api/quick-start`, or the `X-Codeman-Parent-Session` header, which exists so the agent skill can set it ONCE on its shared curl invocation and have every present and future spawn recipe carry it.
@@ -118,6 +181,10 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 ⚠️ **`data-agent-id="lineage:<childId>"` is load-bearing**, not a label: `_applyLineEntrances()` queries paths by that attribute, so tagging them this way is the whole reason the arcs get the draw-in animation AND its negative-`animation-delay` resume across `svg.innerHTML = ''` with zero new animation code. ⚠️ `.session-tabs` is `overflow-x: auto`, so a tab scrolled out of the strip still HAS a rect — one lying over the logo or the header buttons; edges with an endpoint outside the strip are SKIPPED (clamping would point at a tab that is not there), and a passive `scroll` listener re-anchors the rest, since a scroll moves both endpoints without firing any render. The incremental tab render also redraws when `_lineageEdgeCount > 0`: a badge appearing widens a tab and shifts every tab after it. Setting: `sessionLineageLines`, per-device (in `displayKeys`, absent from the `.strict()` `SettingsUpdateSchema`), desktop default ON. Tests: `test/session-lineage-lines.test.ts` (geometry), `test/routes/session-routes-parent-lineage.test.ts` (resolution + reject paths).
 
+Further detail (current geometry and colors, superseding the dip numbers above where they differ): ⚠️ **ONE shape, and the second one was the bug**: every pair (flat strip or wrapped) gets a U-bridge hanging below the strip, anchored on both tabs' BOTTOM edges. ⚠️ The dip is a **mis-tuned-in-both-directions corridor** (44px cap = straight thread at strip-wide spans, #285; 104px cap + full row offset = ~106px over-bow into the terminal, 2026-08-15): it now hangs from the **STRIP's bottom edge** (fallback: lower tab bottom), capped at 64px, with NO per-row offsets stacked on top — the strip-bottom baseline is also what keeps a row-1 pair's arc from drawing through row 2's tab labels.
+
+⚠️ **Colors are keyed on the SPAWNING tab, not per child**: every arc leaving one tab is the same color however many workers it spawns, so the strip reads as "these five came from w1, those two came from w2" — per-child coloring gave one tab's own children a different color each, which is the distinction the colors exist to make. A child that spawns in turn is a parent in its own right and gets its own color for the arcs below it, so a chain changes color at each generation while each generation's fan-out stays uniform. Assignment cycles `CodemanLineage.COLORS` in first-seen order per parent id (first entry empty = the skin-tuned `--session-blue`, so the first spawning tab keeps it; the rest vivid fixed hexes), memoized rather than derived from draw index (the SVG is wiped and rebuilt constantly, so an index-based color would flicker), and set inline as `--lineage-color` so styles.css keeps owning opacity/glow/dash. `test/session-lineage-lines.test.ts` drives the real `_appendLineageConnectionLines()` and asserts the painted property, since testing the color function alone would pass just as happily with the child id passed back in.
+
 ### Auto-named sessions (first prompt → tab title)
 
 **Shipped opt-in, in the prefix form, after a review round that found five ways the first cut named a tab wrong** (#376, 1.30.0). The contributed version renamed on EVERY prompt (`applyAutoName` never left the eligible state, so "fix the login bug" then "1" left the tab named **1**), fed its tracker from every write path (shell tabs renamed after each command, every Ralph and respawn tab named "Read @ralph_prompt.md and follow the instructions."), stayed in escape mode after a bare Esc until a byte in `0x40-0x7e` arrived (Esc then "fix the login bug" submitted **ix the login bug**, Esc then a CJK prompt submitted nothing and the following prompt lost its first character, Esc then digits grew the escape buffer to 19001 characters), treated the newlines inside a bracketed paste as Enter, cleared the draft on ANY CSI (including the SGR wheel reports Codeman forwards to claude ≥ 2.1.187, so "fix the " + wheel + "login bug" gave **login bug**) and on Tab (the `@` completer), and replaced the whole name, which dropped the case from the tab and reset `_nextCaseSessionStartNumber()` so every new session in the case became `w1-<case>` again. Each of those is a named rule in `session-auto-name.ts` with a test.
@@ -132,23 +199,29 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 **Opt-in, and the listener orders its checks for cost.** The prompt lands in the tab name, `mux-sessions.json`, every `session:updated` broadcast, the TUI, both home screens and `/api/search` (which matches on `sessionName`), while Read My Mind deliberately keeps prompts 0600 and out of search because prompts can carry secrets; so `autoNameSessions` is synced and default OFF, like `agentSkillEnabled`, `approvalsInboxEnabled` and `readMyMindEnabled`. The listener checks `nameSource` and derives the title BEFORE reading `settings.json`, so an already-named session costs nothing per prompt.
 
+**`nameSource` also decides what claude is told to call the conversation.** `--name` is the prompt-box label, the `/resume` picker entry and the terminal title at once, and a pinned title stops Claude generating its own, so only a `manual` name is passed (`Session.cliPinnedName`); pinning the `w1-myapp` placeholder gave every conversation of a case the same `/resume` entry. A rename through `PUT /api/sessions/:id/name` is carried into `/resume` by appending the `custom-title` row `/rename` writes (`claude-session-title.ts`), for local transcripts only: a remote pane's lives on the remote host and a docker pane's inside the container. The route returns early on an unchanged name, because the Session Options field saves on blur and recomposes the same placeholder, which would otherwise flip it to `manual` and re-pin it.
+
+Further detail: the `<prefix>: <title>` form (`w3-myapp: fix the login redirect`) is the one `parseSessionPrefix()` (app.js, #232) already renders as the title alone with the prefix in the tooltip, and that `_nextCaseSessionStartNumber()` still counts. The `name` setter is reached via `PUT /api/sessions/:id/name`. The listener lives in `session-listener-wiring.ts`. Tests: `test/session-auto-name.test.ts`, `test/session-listener-wiring.test.ts`, `test/routes/session-name-routes.test.ts`.
+
 ### Full-scrollback replay
 
-**Full-scrollback replay** (COD-164/#148, reworked for #205): `GET /api/sessions/:id/terminal?full=1` returns the ENTIRE tmux scrollback (capture-pane `-e -S -<lines>` bounded by the configured history limit, explicit `maxBuffer` from the terminal-history config, early byte-cap before normalization, CRLF-normalized for shell panes). On success the capture is returned ALONE (`source='mux-full-history'` — it supersedes the byte buffer; no duplication). The first load of each non-shell TUI session per page requests `full=1` (`_fullHistoryLoaded` Set in app.js — the old one-shot `_initialFullBufferLoad` flag was consumed by whichever tab auto-selected, leaving every other TUI tab one frame of history). Shell sessions instead load a bounded 1 MiB `?tail=` window on every selection and automatic drop recovery: a 100k-line shell capture can be tens of MiB, and automatically parsing it makes tab-switch latency scale with the entire session. Shell full history is explicit-button-only; reaching the top during an ordinary wheel/touch gesture must not reset xterm and replay the multi-megabyte capture on its main thread. Other modes may still re-pull `full=1` at the TOP, and pressing **Load full history** forces the request for any recoverably truncated session (`_maybeRefetchFullHistory`, 4s per-session gesture cooldown, in-flight + tab-switch guards, viewport position held across the replay); Shell full pulls are not retained in the tab cache, so the next switch stays bounded. Chunked replay enqueues 32 KiB pieces across safe yields, appends an xterm parse marker, then releases the live-output gate; output arriving after that release stays ordered behind the snapshot, and the marker callback supplies accurate parse timing. ⚠️ **How the load ENDS depends on where the payload came from**, and `_bufferLoadFinishOpts` (app.js) is the one place that decides it for all four fetch-and-write paths. A payload built from the server's accumulated byte history is current up to the response, so the events queued during the load already appear in it and stay DISCARDED; replaying them would duplicate output, most visibly Ink's cursor-up redraws. A pane capture (`mux-visible` or `mux-full-history`) is current only up to CAPTURE time, so `_finishBufferLoad` replays the queue from the response's own arrival timestamp (`since`) and the pre-capture events stay dropped. ⚠️ **A path that then restores a scroll position must re-take the sticky-scroll baseline** (`_syncStickyScrollBaseline`): the replay runs inside `chunkedTerminalWrite` before its promise resolves, with the terminal freshly reset, so `batchTerminalWrite` samples `_wasAtBottomBeforeWrite` as true and the next `flushPendingWrites` would scroll to the bottom over the restore. ⚠️ The cutoff is a client-side timestamp and the server broadcasts on a batch timer (8ms WebSocket, 16-50ms SSE), so a batch pending when the capture ran arrives after the response and replays although the capture holds it — bounded by one batch interval, and closable only server side by flushing that batch before the capture. Tests for the three: `test/terminal-flush-budget.test.ts` pins which sources flush, `test/terminal-buffer-flush.test.ts` pins the `since` cutoff and the baseline re-take, and `test/capture-load-window.browser.test.ts` drives both against a live server. Live output is separately one-chunk-in-flight: xterm's callback releases each 32/64 KiB write before the next is submitted, keeping the remainder in the app queue where the 128 KiB cap can observe it instead of hiding an unbounded backlog in xterm's private WriteBuffer. While WebSocket owns terminal I/O, parallel SSE terminal/output-recovery events are discarded before JSON parsing; fallback recovery is single-flight per active session so backpressure cannot start overlapping reset+replay cycles. The route exposes capture/prepare totals in `Server-Timing`, while `[TERMINAL-PERF]` separates TTFB, body/JSON, reset+parse and total time for both selection and on-demand full pulls; parse completion is not a browser compositor/GPU paint measurement. The re-pull exists because xterm's buffer is only a WINDOW onto tmux's history and two things shrink it: tmux coalesces bursty output into pane REPAINTS that overwrite rows instead of emitting linefeeds (measured: a 60-line burst added 1 row of browser scrollback and destroyed 34), and a tab switch replays only the visible frame. tmux's own history is intact throughout — the browser just has to ask for it again. On-demand rather than automatic because at a 100k history limit the capture can be megabytes. ⚠️ **The capture ENDS with a cursor move back to the pane's own caret position** (`formatCursorRestore`, from the same `display-message` query the visible-frame path uses). The linear replay otherwise leaves the caret wherever the last character landed — the bottom-most row carrying text, which for an agent CLI is the status line — so the caret sat on the composer's Line truncated
+**Full-scrollback replay** (COD-164/#148, reworked for #205): `GET /api/sessions/:id/terminal?full=1` returns the ENTIRE tmux scrollback (capture-pane `-e -S -<lines>` bounded by the configured history limit, explicit `maxBuffer` from the terminal-history config, early byte-cap before normalization, CRLF-normalized for shell panes). On success the capture is returned ALONE (`source='mux-full-history'` — it supersedes the byte buffer; no duplication). The first load of each non-shell TUI session per page requests `full=1` (`_fullHistoryLoaded` Set in app.js — the old one-shot `_initialFullBufferLoad` flag was consumed by whichever tab auto-selected, leaving every other TUI tab one frame of history). Shell sessions instead load a bounded 1 MiB `?tail=` window on every selection and automatic drop recovery: a 100k-line shell capture can be tens of MiB, and automatically parsing it makes tab-switch latency scale with the entire session. Shell FULL history is explicit-button-only; reaching the top during an ordinary wheel/touch gesture must not reset xterm and replay the multi-megabyte capture on its main thread. That gesture instead pulls a BOUNDED window of it (`?full=1&tail=<TERMINAL_TAIL_SIZE>`, so a capture beyond 1 MiB comes back `truncationReason: 'tail'` and the banner offers the rest), and skips the replay when the window holds no more rows than the browser already has. ⚠️ **That skip runs BEFORE the downgrade guard, and it never touches the banner state**: the guard reads "smaller than the browser" as "tmux has nothing more to give", true of an unbounded capture and false of a window cut at the tail size, so a bounded window that reached it marked the session `exhausted` and removed **Load full history** while tmux still held the rest; and re-labelling the banner from a skipped payload would call a terminal that holds all of a Load full history pull "the most recent 1 MiB". A skipped window that came back truncated puts the session on the 60 s cooldown (`_fullHistoryRepullUseless`), because it can never reach anything older than the browser shows and `tail` is applied AFTER the server's synchronous `capture-pane` of the whole history, so each ask costs every client an event-loop stall (about 0.3 s at 100k lines); an untruncated one keeps the 4 s cooldown, since it is all of tmux's history and the next burst can add to it. Declining the gesture outright was a dead end: after any burst a shell pane held about one screen of browser scrollback, and the button renders only once a replay was truncated, so a young shell tab had no way back to history tmux still held. Other modes may still re-pull `full=1` at the TOP, and pressing **Load full history** forces the request for any recoverably truncated session (`_maybeRefetchFullHistory`, 4s per-session gesture cooldown, in-flight + tab-switch guards, viewport position held across the replay); Shell full pulls are not retained in the tab cache, so the next switch stays bounded. Chunked replay enqueues 32 KiB pieces across safe yields, appends an xterm parse marker, then releases the live-output gate; output arriving after that release stays ordered behind the snapshot, and the marker callback supplies accurate parse timing. ⚠️ **How the load ENDS depends on where the payload came from**, and `_bufferLoadFinishOpts` (app.js) is the one place that decides it for all four fetch-and-write paths. A payload built from the server's accumulated byte history is current up to the response, so the events queued during the load already appear in it and stay DISCARDED; replaying them would duplicate output, most visibly Ink's cursor-up redraws. A pane capture (`mux-visible` or `mux-full-history`) is current only up to CAPTURE time, so `_finishBufferLoad` replays the queue from the response's own arrival timestamp (`since`) and the pre-capture events stay dropped. ⚠️ **A path that then restores a scroll position must re-take the sticky-scroll baseline** (`_syncStickyScrollBaseline`): the replay runs inside `chunkedTerminalWrite` before its promise resolves, with the terminal freshly reset, so `batchTerminalWrite` samples `_wasAtBottomBeforeWrite` as true and the next `flushPendingWrites` would scroll to the bottom over the restore. ⚠️ The cutoff is a client-side timestamp and the server broadcasts on a batch timer (8ms WebSocket, 16-50ms SSE), so a batch pending when the capture ran arrives after the response and replays although the capture holds it — bounded by one batch interval, and closable only server side by flushing that batch before the capture. Tests for the three: `test/terminal-flush-budget.test.ts` pins which sources flush, `test/terminal-buffer-flush.test.ts` pins the `since` cutoff and the baseline re-take, and `test/capture-load-window.browser.test.ts` drives both against a live server. Live output is separately one-chunk-in-flight: xterm's callback releases each 32/64 KiB write before the next is submitted, keeping the remainder in the Line truncated
 
-**A capture reports the geometry it was taken at** (#435): a visible frame repaints each row at an absolute position, counting up to the pane's height and out to the pane's width, so a terminal smaller than that pane damages it two ways at once. Too short and every address past the browser's own height clamps onto the last line, overwriting the rows underneath (measured: against a 50-row pane, a 30-row terminal rendered 28 of a 45-line command and drew the survivors twice). Too narrow and each row is painted out to the pane's width, so the browser wraps every painted row and the wrap on the last one scrolls the whole frame up by one. Nothing in the response used to say what geometry the frame was built for, so the client could not see either case. `PaneCaptureOptions.capturedGeometry` carries it out, and the terminal response publishes it as `captureCols`/`captureRows`. ⚠️ **Both fields are ABSENT unless a frame was really positioned**, and every consumer must test `Number.isFinite` rather than truthiness: `mux-visible` is necessary but not sufficient, because when the `display-message` cursor query fails `capturePaneBuffer` skips the snapshot repaint and returns the raw capture, and the route still labels that non-empty body `mux-visible`. A body that positioned nothing has no geometry to describe and nothing to repair, so a comparison that fires there buys a second capture, a reset plus chunked rewrite, a dropped and reopened WebSocket and a discarded xterm snapshot for no gain. ⚠️ **The comparison runs on `mux-visible` ONLY.** A full-history body is linear scrollback closed by a RELATIVE cursor move, which is relative precisely so the browser's row count need not match the pane's, and a byte-history body carries no row alignment at all, so a size mismatch damages neither and a replay repairs neither. That gate matters because the first select of every non-shell session per page takes the full-history path, where an ungated comparison would fire most often on the one response it cannot help, at the price of a second whole-scrollback capture. ⚠️ **The replay is capped at one attempt and latches per session when it cannot converge.** `resizeRetry` stops two competing fits trading replays forever; a pane already drawing at the size just requested is left alone, which is the signature of a clamp rather than a race (`getTerminalDimensions()` floors at 40x10 while `fitAddon.fit()` does not, so a terminal under 40 columns or 10 rows reports a pane permanently bigger than itself and would replay on every tab switch); and a pass that still does not converge joins `_geometryRetryUseless`, so the case `Session.resize` declines outright (a small viewport while a desktop viewport's size claim is live, where the retry re-sends the same declined resize and captures the same pane) costs one attempt per session per page load instead of one per select. ⚠️ **A retry pass must not re-arm `_fullHistoryLoaded`**: it did not consume the full-history pull, and re-arming it would spend a whole-scrollback capture on the next select. That branch is currently unreachable by construction, since reaching it needs `source === 'mux-visible'` while a `full=1` pass is answered `mux-full-history` or `history`; a static test over the source is the habit this repo uses for an invariant nothing can execute. Tests: `test/capture-geometry-retry.browser.test.ts` (eight cases, five of which fail against the merge base), `test/tmux-capture-full-history.test.ts`, `test/routes/session-routes.test.ts`.
+**A capture reports the geometry it was taken at** (#435): a visible frame repaints each row at an absolute position, counting up to the pane's height and out to the pane's width, so a terminal smaller than that pane damages it two ways at once. Too short and every address past the browser's own height clamps onto the last line, overwriting the rows underneath (measured: against a 50-row pane, a 30-row terminal rendered 28 of a 45-line command and drew the survivors twice). Too narrow and each row is painted out to the pane's width, so the browser wraps every painted row and the wrap on the last one scrolls the whole frame up by one. Nothing in the response used to say what geometry the frame was built for, so the client could not see either case. `PaneCaptureOptions.capturedGeometry` carries it out, and the terminal response publishes it as `captureCols`/`captureRows`. ⚠️ **Both fields are ABSENT unless a frame was really positioned**, and every consumer must test `Number.isFinite` rather than truthiness: `mux-visible` is necessary but not sufficient, because when the `display-message` cursor query fails `capturePaneBuffer` skips the snapshot repaint and returns the raw capture, and the route still labels that non-empty body `mux-visible`. A body that positioned nothing has no geometry to describe and nothing to repair, so a comparison that fires there buys a second capture, a reset plus chunked rewrite, a dropped and reopened WebSocket and a discarded xterm snapshot for no gain. ⚠️ **The comparison runs on `mux-visible` ONLY.** A full-history body is linear scrollback closed by a RELATIVE cursor move, which is relative precisely so the browser's row count need not match the pane's, and a byte-history body carries no row alignment at all, so a size mismatch damages neither and a replay repairs neither. That gate matters because the first select of every non-shell session per page takes the full-history path, where an ungated comparison would fire most often on the one response it cannot help, at the price of a second whole-scrollback capture. ⚠️ **The replay is capped at one attempt and latches per session when it cannot converge.** `resizeRetry` stops two competing fits trading replays forever; a pane already drawing at the size just requested is left alone, because a retry would capture the identical frame; and a pass that still does not converge joins `_geometryRetryUseless`, so the case `Session.resize` declines outright (a small viewport while a desktop viewport's size claim is live, where the retry re-sends the same declined resize and captures the same pane) costs one attempt per session per page load instead of one per select. ⚠️ **The clamp used to manufacture that equality, and no longer can** (#464). This paragraph previously explained it as the signature of a clamp: `getTerminalDimensions()` floors at 40x10 while `fitAddon.fit()` did not, so a terminal under 40 columns or 10 rows reported a pane permanently bigger than itself and would replay on every tab switch. That divergence is fixed at the source — `syncTerminalGeometry()` (terminal-ui.js) fits, floors and APPLIES in one step, so the browser terminal IS the size it reports. The only remaining reason the two can differ is a resize the server declined, which the server now reports back (`Session.ptyGeometry`, the `{"t":"zc"}` frame and the resize response) for the client to adopt by COLUMNS. The equality guard stays, for the plain case of a pane already at the requested size. ⚠️ **A retry pass must not re-arm `_fullHistoryLoaded`**: it did not consume the full-history pull, and re-arming it would spend a whole-scrollback capture on the next select. That branch is currently unreachable by construction, since reaching it needs `source === 'mux-visible'` while a `full=1` pass is answered `mux-full-history` or `history`; a static test over the source is the habit this repo uses for an invariant nothing can execute. Tests: `test/capture-geometry-retry.browser.test.ts` (eight cases, five of which fail against the merge base), `test/tmux-capture-full-history.test.ts`, `test/routes/session-routes.test.ts`.
+
+⚠️ **A frame dropped at the 128 KiB render cap MUST be recovered, and the recovery must verify itself** (`_scheduleDroppedOutputRecovery`, app.js): a hole in a TUI byte stream is a desynced cursor, which is muffled text (#464). It was a fire-and-forget 2s timer that nulled its own handle and then called `_onSessionNeedsRefresh()` — whose early returns (a buffer load in flight, a refresh already owning the session) are MOST likely to be true during exactly the burst that caused the drop, so the recovery was lost silently and the bytes were never replayed. `_onSessionNeedsRefresh` now returns whether it actually repainted, and the scheduler re-arms while it has not, bounded by `DROP_RECOVERY_MAX_ATTEMPTS` because the early returns it retries past are transient contention. A refresh that died at the capture fetch DEADLINE (it returns `'deadline'`) is a stalled link, not contention, and is NOT retried: each retry would be another `?full=1` capture waiting out a deadline of up to two minutes. The same debounce still collapses a burst into one attempt, and the `TERMINAL DROP` crash-trail line sits behind it, since one line per dropped frame evicted the whole 50-entry trail in under a second. Tests: `test/dropped-output-recovery.test.ts`, whose retry case and no-retry case only pin the fix as a pair.
 
 ### Terminal scrollback: strip flavors and wheel/touch forwarding
 
 **Two strip flavors, one carry** (#205, `session.ts:_handleTerminalOutput`): the FULL strip (`isAltScreenStripMode` = codex/claude/gemini) removes alt-screen toggles, `3J`, and mouse-tracking DECSETs. Every other mode (shell/opencode/antigravity/pi) gets the NARROW strip (`isMuxAltScreenOnlyStripMode`) — alt-screen toggles ONLY — and only when tmux-backed (`useMux`). Rationale: the tmux CLIENT emits `smcup` as its first bytes at attach, before any program runs, parking xterm in the scrollback-less alternate buffer for the whole session (touch scrolling no-ops; xterm's own wheel handler converts the wheel to Up/Down arrows = readline history cycling — both #205 symptoms). tmux never forwards a pane program's alt-screen toggles to its client (it repaints instead; measured — vim/less inside a pane emit zero to the client), so the only thing the narrow strip ever removes is tmux's own smcup. It keeps `3J` (a user's `clear` is a deliberate scrollback wipe) and the mouse DECSETs (tmux passes those through even with `mouse off`; stripping them would break htop/vim mouse support). ⚠️ The `useMux` gate is load-bearing: `startShell()`/`startInteractive()` fall back to a DIRECT PTY when mux creation fails, and there the inner program's own `?1049h` really does reach xterm — stripping it would break vim/less/htop for real. The replay path (`session-routes.ts`, via `session.usesMux`) applies the same narrow branch; the frontend mirror (`_shouldReportMouseToCli()`) stays claude/codex/gemini because only the FULL strip touches mouse DECSETs. The chunk-boundary carry (`_altScreenSeqCarry`) runs for both flavors. Tests: `test/claude-scrollback-strip.test.ts`.
 
-⚠️ **What the full strip removes, it must REMEMBER.** Stripping the mouse DECSETs means xterm's `modes.mouseTrackingMode` is permanently `'none'` for those modes, so the browser hand-encodes click reports to compensate (`_sendSyntheticSgrTap`). With no state to consult it did that on EVERY click, which delivered mouse reports to programs that never asked for them: the same pane runs a plain shell whenever the CLI has exited or a `shell` was started inside a claude-mode session, and a shell prints the report as literal text (`[<0;88;20M`), garbling the next line typed. `_recordStrippedMouseMode()` therefore records each stripped sequence as it goes and publishes `cliMouseTracking` through `toState()`, and `_shouldReportMouseToCli()` requires it. ⚠️ Only the TRACKING modes count (1000/1001/1002/1003): 1005/1006 select an ENCODING and 1007 is alt-scroll, and counting those would put the stray reports straight back. ⚠️ The change broadcasts IMMEDIATELY rather than through `broadcastSessionStateDebounced`, because the flag flips when a dialog opens and the user can click that dialog inside the 500ms debounce window. Measured on a live claude 2.x: the CLI holds a tracking mode on continuously (so clicks keep being reported exactly as before), while a bash prompt in the same stripped mode reports nothing. Fails toward silence: after a server restart the flag is false until the CLI re-emits, which tmux does at client attach.
+⚠️ **What the full strip removes, it must REMEMBER.** Stripping the mouse DECSETs means xterm's `modes.mouseTrackingMode` is permanently `'none'` for those modes, so the browser hand-encodes click reports to compensate (`_sendSyntheticSgrTap`). With no state to consult it did that on EVERY click, which delivered mouse reports to programs that never asked for them: the same pane runs a plain shell whenever the CLI has exited or a `shell` was started inside a claude-mode session, and a shell prints the report as literal text (`[<0;88;20M`), garbling the next line typed. `_recordStrippedMouseMode()` therefore records each stripped sequence as it goes and publishes `cliMouseTracking` through `toState()`, and `_shouldReportMouseToCli()` requires it. ⚠️ Only the TRACKING modes count (1000/1001/1002/1003): 1005/1006 select an ENCODING and 1007 is alt-scroll, and counting those would put the stray reports straight back. ⚠️ The change broadcasts IMMEDIATELY rather than through `broadcastSessionStateDebounced`, because the flag flips when a dialog opens and the user can click that dialog inside the 500ms debounce window. Measured on a live claude 2.x: the CLI holds a tracking mode on continuously in fullscreen (so clicks keep being reported exactly as before; the default inline renderer holds none, measured on 2.1.283 even with `/model` open), while a bash prompt in the same stripped mode reports nothing. Fails toward silence: after a server restart the flag is false until the CLI re-emits, which tmux does at client attach.
 
-**Only claude ≥ 2.1.187 forwards the wheel; every other mode scrolls local scrollback** (#227 follow-up, `terminal-ui.js:_shouldForwardWheelToApp`). Codex was in the forward list until a reporter hit a completely dead wheel in codex tabs while the scrollbar drag worked. Measured against codex-cli 0.147.0 in a bare tmux: it never enables mouse tracking (`mouse_any_flag=0`) and SGR wheel reports fed to its PTY change nothing on screen, because it runs an INLINE viewport (`alternate_on=0`) and pushes its transcript into the terminal's own scrollback (tmux `history_size` grows) instead of paging in-app. So for codex, local scrollback IS the transcript and forwarding swallowed every tick. ⚠️ "The TUI is a strip mode" is NOT evidence that it consumes wheel reports — verify with a real `\x1b[<64;c;rM` write into a live pane before adding a mode here. Hand-encoded SGR TAPS are gated by `_shouldReportMouseToCli()` (strip mode AND the server-observed `cliMouseTracking` flag, recorded by `_recordStrippedMouseMode` in session.ts as it strips): codex never enables mouse tracking, so since #325 no tap report is sent there at all — click-to-position was already a measured no-op in codex, and a pane that has fallen back to a shell no longer receives `[<0;88;20M` junk.
+**Only claude ≥ 2.1.187 with mouse tracking on forwards the wheel; everything else scrolls local scrollback** (#227 follow-up, `terminal-ui.js:_shouldForwardWheelToApp`). Codex was in the forward list until a reporter hit a completely dead wheel in codex tabs while the scrollbar drag worked. Measured against codex-cli 0.147.0 in a bare tmux: it never enables mouse tracking (`mouse_any_flag=0`) and SGR wheel reports fed to its PTY change nothing on screen, because it runs an INLINE viewport (`alternate_on=0`) and pushes its transcript into the terminal's own scrollback (tmux `history_size` grows) instead of paging in-app. So for codex, local scrollback IS the transcript and forwarding swallowed every tick. Claude repeats this exactly in its default INLINE renderer (measured on 2.1.280: `alternate_on=0`, `mouse_any_flag=0`, `history_size` grows), and swipes on iOS Safari were dead there while codex scrolled; only fullscreen claude (`CLAUDE_CODE_NO_FLICKER=1` or `"tui": "fullscreen"` in `~/.claude/settings.json`: alt screen plus modes 1003/1006) pages its transcript on wheel reports. So claude forwards only while the server-observed `cliMouseTracking` flag is true; a stale-false flag after a server restart falls through to the PageUp/PageDown fallback, never a dead wheel. ⚠️ "The TUI is a strip mode" is NOT evidence that it consumes wheel reports — verify with a real `\x1b[<64;c;rM` write into a live pane before adding a mode here. Hand-encoded SGR TAPS are gated by `_shouldReportMouseToCli()` (strip mode AND the server-observed `cliMouseTracking` flag, recorded by `_recordStrippedMouseMode` in session.ts as it strips): codex never enables mouse tracking, so since #325 no tap report is sent there at all — click-to-position was already a measured no-op in codex, and a pane that has fallen back to a shell no longer receives `[<0;88;20M` junk.
 
-**Wheel/touch forwarding is NOT gated on viewport-at-bottom** (#205, `terminal-ui.js:_shouldForwardWheelToApp`): for sessions verified to scroll their own transcript on SGR wheel reports (claude ≥ 2.1.187 — version via the local/docker/remote `--version` probes), the plain wheel AND touch drags forward as coalesced SGR reports (`_forwardScrollToApp` → `_sendSyntheticSgrWheel`, 40ms batches, 5-tick cap, 512-byte queue bound). It used to gate on the viewport being at the bottom so both scrollbacks stayed reachable, but a repaint-mode CLI keeps NO terminal scrollback of its own — xterm's buffer holds only replayed repaint frames, so local scrolling drags the CLI's pinned prompt box up the screen over stale frames; and `scrollToLastNonEmptyLine()` routinely parked the viewport off-bottom, silently pinning the wheel to local. Forwarding now snaps the viewport home first (SGR coordinates address the LIVE screen — a report computed from a scrolled-up viewport would hit-test the wrong row). Local scrollback remains on Shift+wheel and the `terminalWheelLocalScrollback` opt-out (both also cover touch via the shared gate; touch has no Shift, so the setting is its only local pin). `_wheelScrollLines()` normalizes `deltaMode` (Firefox fires LINE deltas ≈3/notch — read as pixels that rounded to 0 and fell to the ±1 fallback, ~4× too slow; PAGE deltas scale by `terminal.rows`) while keeping the #154 Shift-axis trap (macOS trackpads put Shift+scroll magnitude on deltaX). Tests: `test/terminal-touch-tap.test.ts`.
+**Wheel/touch forwarding is NOT gated on viewport-at-bottom** (#205, `terminal-ui.js:_shouldForwardWheelToApp`): for sessions verified to scroll their own transcript on SGR wheel reports (claude ≥ 2.1.187 while `cliMouseTracking` is true, i.e. fullscreen; version via the local/docker/remote `--version` probes), the plain wheel AND touch drags forward as coalesced SGR reports (`_forwardScrollToApp` → `_sendSyntheticSgrWheel`, 40ms batches, 5-tick cap, 512-byte queue bound). It used to gate on the viewport being at the bottom so both scrollbacks stayed reachable, but a repaint-mode CLI keeps NO terminal scrollback of its own — xterm's buffer holds only replayed repaint frames, so local scrolling drags the CLI's pinned prompt box up the screen over stale frames; and `scrollToLastNonEmptyLine()` routinely parked the viewport off-bottom, silently pinning the wheel to local. Forwarding now snaps the viewport home first (SGR coordinates address the LIVE screen — a report computed from a scrolled-up viewport would hit-test the wrong row). Local scrollback remains on Shift+wheel and the `terminalWheelLocalScrollback` opt-out (both also cover touch via the shared gate; touch has no Shift, so the setting is its only local pin). `_wheelScrollLines()` normalizes `deltaMode` (Firefox fires LINE deltas ≈3/notch — read as pixels that rounded to 0 and fell to the ±1 fallback, ~4× too slow; PAGE deltas scale by `terminal.rows`) while keeping the #154 Shift-axis trap (macOS trackpads put Shift+scroll magnitude on deltaX). Tests: `test/terminal-touch-tap.test.ts`.
 
-**A false gate on a Claude session must not mean a DEAD gesture** (#205 round 2, `_maybePageCliTranscript`): every way `_shouldForwardWheelToApp()` returns false leaves a repaint-mode pane scrolling a buffer that has nothing in it (`baseY === 0`) — the version probe came back empty, the CLI really is older than 2.1.187, or the user turned on `terminalWheelLocalScrollback`. The 1.12.0 retest reported exactly that: a wheel that did nothing at all while Fn+Up (PageUp) paged back through intact text, which is the proof that the CLI's own history and the PTY input path were both fine. So under the triple guard (claude mode + gate false + `baseY === 0`) wheel and touch travel is translated into coalesced `\x1b[5~` / `\x1b[6~` through the same 40ms queue as the SGR reports, at half a screen of travel per page key (the key jumps a whole screen; a 1:1 mapping was unusably slow with a discrete wheel). ⚠️ Shift is excluded on purpose — it is the explicit "give me local scrollback" gesture and must keep that meaning. ⚠️ `terminalWheelLocalScrollback` is deliberately NOT scoped away from repaint-mode CLIs even though it is a footgun there: that would silently override an explicit user choice, so the fallback catches it instead. **Server-side counterpart**: `getClaudeCliVersion()` caches SUCCESS for the process lifetime but must never cache FAILURE — it used to, so one timed-out or PATH-starved probe at the first Claude session start disabled wheel-forwarding for every Claude session until the server restarted (a dead wheel on phone, tablet and laptop at once, the signature of a server-side cause). Failures now retry with a 1/2/4…15min backoff; the policy is the pure `resolveClaudeCliVersion()`. Tests: `test/terminal-scroll-routing.test.ts`, `test/claude-cli-version-cache.test.ts`.
+**A false gate on a Claude session must not mean a DEAD gesture** (#205 round 2, `_maybePageCliTranscript`): every way `_shouldForwardWheelToApp()` returns false leaves a repaint-mode pane scrolling a buffer that has nothing in it (`baseY === 0`) — the version probe came back empty, the CLI really is older than 2.1.187, the `cliMouseTracking` flag is unset (inline claude, or fullscreen right after a server restart), or the user turned on `terminalWheelLocalScrollback`. The 1.12.0 retest reported exactly that: a wheel that did nothing at all while Fn+Up (PageUp) paged back through intact text, which is the proof that the CLI's own history and the PTY input path were both fine. So under the triple guard (claude mode + gate false + `baseY === 0`) wheel and touch travel is translated into coalesced `\x1b[5~` / `\x1b[6~` through the same 40ms queue as the SGR reports, at half a screen of travel per page key (the key jumps a whole screen; a 1:1 mapping was unusably slow with a discrete wheel). ⚠️ Shift is excluded on purpose — it is the explicit "give me local scrollback" gesture and must keep that meaning. ⚠️ `terminalWheelLocalScrollback` is deliberately NOT scoped away from repaint-mode CLIs even though it is a footgun there: that would silently override an explicit user choice, so the fallback catches it instead. **Server-side counterpart**: `getClaudeCliVersion()` caches SUCCESS for the process lifetime but must never cache FAILURE — it used to, so one timed-out or PATH-starved probe at the first Claude session start disabled wheel-forwarding for every Claude session until the server restarted (a dead wheel on phone, tablet and laptop at once, the signature of a server-side cause). Failures now retry with a 1/2/4…15min backoff; the policy is the pure `resolveClaudeCliVersion()`. Tests: `test/terminal-scroll-routing.test.ts`, `test/claude-cli-version-cache.test.ts`.
 
 **Why the wheel went where it went is LOGGED** (`_logScrollRouting`): one console line per session per distinct decision — `[scroll] <id> → forward-sgr|page-keys|local-scrollback|repull-refused-downgrade (mode=…, cliVersion=…, localScrollbackOptOut=…, mouseTracking=…, localScrollbackRows=…)`. #205 ran two rounds of remote guesswork over questions this line answers directly; keep it when touching the routing.
 
@@ -158,10 +231,113 @@ Tests: `test/docker-hosts.test.ts`, `test/docker-exec-options.test.ts`, `test/do
 
 **Run launch synchronization**: the main Run entrypoint in `session-ui.js` holds an in-flight lock and disables `#runBtn` for the whole launch (at least 500ms), so a double click cannot create duplicate sessions with the same `w<n>-<case>` name. A successful create/quick-start also calls `_ensureCreatedSessionVisible()` before `selectSession()`: local creates use the response's full session snapshot; quick-start modes fetch `GET /api/sessions/:id` only when `session:created` SSE has not already populated the map. The normal `_onSessionCreated()` handler remains the idempotent upsert, so POST-first and SSE-first ordering both produce one immediately-rendered tab. Tests: `test/run-mode-ui.test.ts`.
 
+Further detail, closing: ⚠️ **Closing has the mirror-image race and one owner**: `closeSession()` reads `wasActive` BEFORE its `await` and announces the delete via `_closingSessions`, while `_onSessionDeleted` skips the active-session handoff for an id in that set. Both used to read `activeSessionId` after the fact, so the `session_deleted` broadcast for your own delete could null it first and closing the tab you were on landed on the welcome screen instead of the next session, on the same build, depending on timing. The fallback also picks the first order entry that is still in `sessions` (a dead id can linger in `sessionOrder`, same reason Alt+N indexes a live-filtered list). A delete from ANOTHER client still shows the welcome screen, which is the honest answer when what you were looking at was taken away. Tests: `test/session-close-fallback.test.ts`.
+
 ### Circuit breakers: Ralph and PTY-exit
 
 **Circuit breaker**: Prevents respawn thrashing. States: `CLOSED` → `HALF_OPEN` → `OPEN`. Reset: `/api/sessions/:id/ralph-circuit-breaker/reset`. **Distinct: PTY-exit breaker** (COD-115/118/#147, `session-pty-exit-breaker.ts`) trips after repeated rapid PTY exits (crash loops on attach), blocks further auto-restarts, broadcasts SSE `session:respawnBreakerTripped` + push (in `PUSH_EVENT_MAP`). Reset ONLY via an explicit `{clearBreaker:true}` body on `POST /api/sessions/:id/interactive` (sent by the user-facing restart control) — the frontend's auto-reattach in `selectSession()` sends no body and must never clear it. Sessions also scrub inherited `TMUX`/`TMUX_PANE` env so Codeman-in-tmux doesn't nest. Tests: `test/respawn-pty-breaker.test.ts`.
 
+### An exited agent in a live pane (`paneExit`)
+
+**Codeman creates every pane with `remain-on-exit on`, so a session whose agent exited still looks alive.** `/exit` ends the CLI, tmux keeps the pane and the tmux session, and the `tmux attach-session` process Codeman records as `Session.pid` runs on, so no PTY exit handler fires and the record keeps its pid and `status: 'idle'` (Ark0N/Codeman#446). `SessionState.paneExit` (`{status?, signal?, at}`) is the fact tmux already knows, published through `toState()` so it rides `session:updated` and lands in `state.json` on the same persist — there is no SSE event for it. One batched `tmux list-panes -a` per tick fills it, from `TmuxManager.startPaneExitWatcher()`, which has its OWN always-on interval: the stats collector cannot carry it, because the browser arms and disarms that one with the Monitor panel (`panels-ui.js`) and boot skips it entirely when no session was recovered. ⚠️ **The field is TRI-STATE and its third state is absence**, meaning UNKNOWN, which renders as nothing and must NEVER read as alive; it covers a running pane, a session the read did not list, a failed probe, and every session shape a dead local pane does not describe. `Session.paneExitApplies` is the single place that scoping lives, and it fails closed for four shapes: a direct-PTY session (no pane), a remote SSH session (the local pane is the ssh client, whose death is a transport drop OR an exit — the whole of #355), a docker case (the local pane is a `docker exec` into the container's own tmux), and a session rebuilt from the socket (`MuxSession.discovered`: its synthetic `restored-<fragment>` id matches no `state.json` entry, so a remote session rediscovered after `mux-sessions.json` was lost would arrive looking local). ⚠️ **Never set `status: 'error'`** for an exited pane — that value is the PTY-exit breaker's and the browser answers it with a "restart it?" confirm — and **never null the `pid`**, which is what makes `selectSession()` re-attach and launch a fresh CLI. Local panes keep `remain-on-exit on`; flipping them to `failed` ends the tmux session, nulls the pid and reintroduces the auto-revive #355 removed. ⚠️ **An absent `#{pane_dead_status}` is not 0**: measured on tmux 3.2a a SIGKILLed pane reports neither a status nor a signal (`#{pane_dead_signal}` did not exist before tmux 3.4), so folding it into 0 would turn an unexplained death into a clean exit. A session answers only when the read listed EXACTLY ONE pane for it, since Codeman never splits a pane and a session the user split by hand has none that speaks for the agent. The three synchronous `isPaneDead()` callers (the `/wait` route, the TUI, the attach path) keep their own probes — this watcher is never fresh enough for them. ⚠️ **A path that starts a command in a pane must clear the record AND persist**, since the watcher's next tick sees the field already cleared and writes nothing. ⚠️ **The always-on timer gates the READ, never the tick.** `hasObservablePaneSession()` (`tmux-manager.ts`) skips the tmux exec while every session on the manager is one of the shapes `paneExitApplies` forces to UNKNOWN, so an instance running only remote or Docker work keeps ticking and costs nothing; the two predicates are two copies of one rule, and `test/session-pane-exit.test.ts` pins them against each other for the four session shapes that exist today — a FIFTH condition added to one and not the other still fails nothing, so change them together. Skipping retracts nothing, for the same reason a failed read does not. ⚠️ **The muted status dot is a specificity fight, and it is fought on three surfaces.** The tab renders `status` as before, and `tab-agent-exited` only quiets the dot, so the rule excludes three states BY HAND: `.tab-alert-action` and `.tab-alert-idle` on the tab, and `.tab-status.error` on the dot itself. Each of those colours means "this needs you" — the two alerts because a human is blocked, `error` because the browser answers it with a "restart it?" confirm — and each must survive the exit. The rich tab rail needs a SECOND copy of the rule, because its own `tab-state-*` dot rules are (0,9,1) against the strip's (0,5,0) — measured, an exited session on a detailed rail kept a full green dot and the working halo beside a badge reading "exited". Its twin matches that specificity exactly and therefore must stay BELOW those rules in source order. mobile.css needs a THIRD copy, with `!important`, because the phone block enlarges a `busy` dot and gives it a green glow that way, and `status` stays `busy` for a pane whose agent died mid-turn — without it a phone renders a grey dot still wearing the green halo. `test/session-pane-exit-ui.test.ts` resolves the real stylesheets in jsdom rather than matching selector text — styles.css for the desktop cases and both files for the phone ones — so the ordering, the hand-written exclusions and a missing phone rule all fail there. Tests: `test/session-pane-exit.test.ts`, `test/tmux-manLine truncated
+
+**A session whose agent exited cleanly is closed, and a crashed one is kept** (Ark0N/Codeman#446, part 2). After every pane read, `closeCleanlyExitedSessions()` (`server.ts`) closes each session that `shouldCloseCleanlyExitedSession()` (`pane-exit-sweep.ts`, pure) accepts, through `cleanupSession(id, true, CLEAN_EXIT_CLOSE_REASON)`. That is the X button's path, so an unpinned session is removed, a pinned one is demoted to `status: 'stopped'`, the lifecycle log records why, and the conversation stays resumable from the Resume list, which reads the lifecycle log and the transcripts rather than the pane. The rule has four parts, and each guards against a wrong close:
+
+- ⚠️ **The status must be an explicit numeric 0 with no signal** (`isCleanPaneExit()`). An absent status is how a SIGKILL presents on tmux 3.2a, so `status ?? 0` would close an agent the OOM killer took. A non-zero status or any signal keeps the row, marked with the exit, as the crash evidence #210 was filed to keep.
+- **At least `CLEAN_EXIT_CONFIRMING_READS` (2) authoritative reads must agree.** `TmuxManager.getPaneExitReadCount()` counts them. A repeat of the same pane pid, status and signal adds one, anything else starts again at 1, and a failed, empty or skipped read never reaches `applyPaneExits()`, so it neither confirms nor resets. A mux without the method never has a session closed.
+- **No start, attach or relaunch may be in flight** (`Session.paneLifecycleInFlight`, raised for the whole of `_setupOrAttachMuxSession()` and `restartCli()`). The dead-pane respawn revives an exited pane on purpose, and the pane reads as dead until `clearPaneExitForNewPane()` runs after its startup delay.
+- **The pane must have been up for `CLEAN_EXIT_MIN_PANE_LIFETIME_MS` (10 s)** since the last start, attach or relaunch finished (`Session.paneStartedAt`). A CLI that prints a startup error and exits 0 would otherwise lose its tab, and the error with it, seconds after launch; its row stays as `exited (0)` instead. An attach to an already running pane stamps it too, so an `/exit` within seconds of a server restart leaves a row to close by hand.
+
+Scoping needs no check of its own here: `setPaneExit()` already forces `paneExit` to UNKNOWN for direct-PTY, remote, docker and discovered sessions. There is no setting, by the maintainer's decision on #446. ⚠️ Do not flip local panes to `remain-on-exit failed` to get the same effect: a destroyed pane ends the tmux session, the PTY exit nulls the pid, and the browser's `selectSession()` then launches a fresh CLI. `cleanupSession()` keeps `{workingDir}/.claude-images` while another session still uses that directory (`pasteImageDirInUseByOtherSession()`, `paste-image-gc.ts`), since the sweep would otherwise routinely delete a live sibling's pasted images. Paths are compared by `realpath`, and a detached session counts through its persisted record, because `killMux=false` removes it from the map while its pane keeps running; only a session being KILLED is exempt. Each exit gets ONE close attempt (keyed by session id and `at`), and a session being closed refuses `startInteractive()`/`startShell()` (`Session.markClosing()`), so a start that races the close cannot orphan a tmux session. `planRebootRestore()` refuses a record whose persisted `paneExit` is clean (`agent-exited`), which covers an agent that exited just before the power went, before the sweep reached it. Tests: `test/pane-exit-sweep.test.ts`, `test/paste-image-dir-shared.test.ts`, `test/reboot-restore.test.ts`, `test/tmux-manager.test.ts`.
+
+### Dead-pane respawn: the resume pin
+
+**The dead-pane respawn needs the same resume pin as a custom-model `restartCli()` and shares it** (`_buildRespawnPaneOptionsWithResumePin()` in `session.ts`, used by `restartCli()`, the dead-pane respawn in `_setupOrAttachMuxSession()`, and its create path when that path RELAUNCHES a CLI: after a failed respawn, or when tmux lost the whole session rather than the pane): a pane whose agent EXITED owns a transcript too, so recovering one with the bare launch line hit the same refusal and the conversation was stranded behind a tab that looked merely idle. The pin walks three candidates in order — the conversation chain's tail, the launch seed, then the session's own id — and takes the first one a transcript backs, never `_claudeSessionId` (which also holds history-correlated GUESSES keyed on the working directory, and launching from one would open and write to a conversation that was never this pane's). ⚠️ The create-path pin is written to `_resumeSessionId` as well, so unlike `restartCli()`'s one-respawn pin it PERSISTS through `toState()` as `resumeSessionId`: that field means "what the user asked to resume at creation, or what recovery pinned", and after a dead-pane respawn `_claudeSessionId` names whatever the walk actually pinned rather than the chain tail. ⚠️ A candidate no transcript backs is passed over, and falling off the end of the walk ADDS no pin (the options keep whatever launch seed they already carried): a divergent pin leaves `--session-id <this.id>` in the fallback branch, where a failed resume collides all over again, while pinning an id with no transcript prints claude's "No conversation found" into a brand-new session's scrollback and costs the running branch its `nice` priority (`wrapWithNice()` prefixes only the first branch of an `a || b`). ⚠️ Remote and docker sessions are never pinned: their pane commands are already self-healing, the conversation lives on the far side, and a local id resolves to nothing there.
+
+### Idle detection: composer glyph and working line
+
+⚠️ **A `❯` sighting is NOT the end of a turn, and neither is silence.** Claude redraws the composer (`❯`) about once a second all through a turn, so the old "saw a ❯, wait 2s → idle" rule flipped every working session to idle two seconds in (measured: a session mid-tool-call at 17 minutes reporting `status:"idle"`). Its working indicator is `✻ Actualizing… (13m 23s · ↓ 47.5k tokens)`: the glyph animates through `· ✢ ✳ ∗ ✻ ✽`, the gerund is randomized, and the finished line (`✻ Cooked for 2m 49s`) carries the same glyph, so neither `SPINNER_PATTERN` (braille, not what current versions draw) nor a keyword list can see it. Matching the new line in the STREAM does not work either: tmux ships partial repaints, so the whole line reaches the PTY only every few tens of seconds.
+
+So: `_confirmIdle()` (session.ts) requires the pane to go quiet, and then asks the SCREEN via `capturePaneText()` + `CLAUDE_WORKING_LINE_PATTERN` before believing it; a sustained run of repaints (`session-activity.ts`, pure + unit tested) is what marks a turn as started, with the same screen probe vetoing keystroke echo. Idle now lands ~3-5s after a turn ends instead of 2s into one.
+
+⚠️ **The composer glyph and the working line are per-CLI registry DATA** (`capabilities.workDetect`, #385), not Claude constants: claude declares `❯` plus the pattern above, codex declares `›` plus `[Ee]sc to interrupt`, and a CLI that declares neither falls back to Claude's pair, which is what every session used before the registry carried one. Before that, this whole mechanism was gated Claude-mode-only on the reasoning that an external CLI has no `❯`, which was true and still left every Codex session reporting `idle` for its entire life.
+
+⚠️ `workingLine` is config-supplied (a user `clis.json` can set it) and the compiled pattern runs on the PTY hot path, so it goes through `compileVersionRegex()` in BOTH the schema refine and `_workingLinePattern()`: a nested quantifier there is a ReDoS against the event loop, and the helper returns null rather than throwing so the fallback is structural.
+
+⚠️ A third, optional `workDetect` field, `watchingLine` (plus `watchingLines`), tells a quiet pane that is still RUNNING something apart from one that wants a human; it is read from the same idle-confirmation capture. See [The watching signal](#the-watching-signal-a-quiet-pane-that-is-not-waiting-for-you).
+
+⚠️ A fourth, optional `workDetect` field, `awaitingLine`, makes a turn that ENDED waiting for workers the CLI started count as WORKING: with background agents or an ultracode workflow still running at turn end, Claude closes the turn with `✻ Waiting for 1 dynamic workflow to finish` instead of `✻ Brewed for 1m 18s`, then resumes by itself when they report back, so the pane is quiet with the composer up and every other signal read it as idle (reported 2026-09-28 on a live 2.1.283 session). `_probePaneWorking()` ORs it into the same capture. ⚠️ It must never be searched across the pane like `workingLine`: Claude renders the row from a `useState` snapshot taken at turn end and never redraws it, so the words stay on screen after the workers finish and a pane-wide match would pin the tab busy until they scroll off. `isAwaitingWorkers()` (pure, `session-activity.ts`) finds the composer (the LAST row carrying `promptGlyph`, bare or boxed), walks up at most `AWAITING_SEARCH_ROWS` past blank, box-drawn and indented rows, and tests only the first column-0 row. ⚠️ Keep the pattern anchored on column 0 (`^✻`): Claude's own rows start there and the agent's prose never does, which is what stops an agent from holding its own session busy. It is deliberately NOT tested on the PTY stream, where redraws of the stale row would re-mark working. Tests: `test/session-awaiting-workers.test.ts`.
+
+### The watching signal (a quiet pane that is not waiting for you)
+
+**A session that armed a monitor, backgrounded a shell or started a background terminal ends its turn and goes quiet, and a minute later Claude Code's idle notification arrives.** Before this existed, that prompt became an approval item like any other, so every surface filed the session under NEEDS YOU with nothing for a human to answer. The CLI says which kind of quiet it is on its own screen, and reading that row is the whole mechanism: `capabilities.workDetect.watchingLine` (optional, per CLI) plus `watchingLines` (how many non-blank rows at the foot of the screen may hold it, default `WATCHING_TAIL_LINES` = 1). `_confirmIdle()` already captures the pane at the moment a turn ends, so `_readWatching()` runs `watchingLabel()` (pure, `session-activity.ts`) over that same capture; the label lands on `Session.watching` and rides `toLightDetailedState()` out to every payload. ⚠️ It is cached BESIDE `_lastPaneProbeWorking` and goes stale with it, because the probe returns its cached boolean without re-capturing inside `PANE_PROBE_MIN_INTERVAL_MS` and a label from a capture nobody took is a guess. ⚠️ A capture that FAILS clears the label (and announces the change) rather than keeping the last one: a stale label opens the next idle prompt already acknowledged, so keeping it would turn a failed `capture-pane` into a missed alert, while clearing it costs at most an alert the next readable capture takes back. ⚠️ It then FREEZES once `_confirmIdle()` concludes — nothing looks at the pane again until it produces output — which is correct rather than tolerable, since work ending repaints the pane either way (a monitor firing wakes the agent; codex drops its background-terminal row by itself); a timer to keep it fresh would spend a `capture-pane` per idle session per tick to learn nothing. ⚠️ A server restart looks like a hole in that and is not one: the field is live state and starts empty, but reconciliation re-attaches the pane and the attach repaint arms the idle confirmation, which probes and re-reads the label with no input from anyone (measured 2026-09-23, back within ~20 s). A restored session showing no label has no chip on its screen.
+
+**The fix is the alert that does not fire; the badge is cosmetic.** `hook-event-routes` passes the label to `notePrompt()`, which opens the idle item ALREADY acknowledged (`acknowledgedAt` + `acknowledgedReason`). Nothing new suppresses anything: `acknowledge()` has always meant "the alert this prompt armed is spent", so the item stays pending, answerable and available as Read My Mind context, and a wrong label costs a card that does not blink rather than an alert that was never created. Every surface follows from that one flag — the broadcast carries `acknowledgedReason` so a live page declines to arm (`_onHookIdlePrompt`, settings-ui.js), the push is skipped, a reloading page reads `acknowledgedAt` in `seedApprovals()` as it always did, `classifySession()` and `pendingApprovalCount()` (tui-model.ts, tui-render.ts) ignore an acknowledged item, and the TUI card drops to the `info` tone and says why. It re-arms for free: the next idle prompt supersedes the item and is built fresh. ⚠️ Only `idle` is eligible, so a permission or question dialog still goes red whatever else the agent started — but a prose question is NOT a dialog, so an agent that arms a monitor and then asks "which branch?" in plain text is silenced along with the false alarms. That is the accepted cost of the design and the reason the kind gate sits at the single place items are created.
+
+⚠️ **A chip that waits on a HUMAN must never count as watching**: Claude's Artifact comment monitor (an agent that published a page and hears nothing until somebody comments) is refused for the whole row by a `^`-anchored negative lookahead keyed on "Artifact" alone, so a footer cut off mid-chip is refused too, and the `^` is what stops the engine retrying past the chip and reporting a shell beside it.
+
+**⚠️ The label is pane-derived, so the window and the anchor are a trust boundary, not formatting.** An agent that gets its own text matched silences its own alert. Two things prevent it, and BOTH belong to whoever adds a pattern for a new CLI: the window must cover only rows that CLI draws, and the pattern must anchor on chrome only that CLI can produce. Claude satisfies both — its chip is the LAST row, so the default window of one row excludes even the status line directly above it, whose content comes from a `statusLine` command a bypassed session can write into its own `.claude/settings.json`. Codex does not: its row sits above the composer, and the slot it occupies holds the last row of the TRANSCRIPT whenever no terminal is running, so matching the complete row raises the bar without closing it. What contains that is `hooks: 'none'` — no hook event from a codex session reaches `notePrompt()`, so a forged label costs a wrong badge and nothing else, and a CLI that gains hook signals must not keep a pattern that soft. The label is also ANSI-stripped and capped (`MAX_WATCHING_LABEL_CHARS`) at the source, and every interpolation of it into markup goes through `escapeHtml()`, since a config-supplied capture group decides what it holds. Tests: `test/session-watching.test.ts` (the label and both CLI patterns), `test/watching-no-alert.test.ts` (the negative claim across all four surfaces).
+
+### Workspace-trust dialog auto-accept
+
+**Workspace-trust dialog auto-accept** (`session-trust-dialog.ts`, pure + unit tested): Claude Code asks once per directory ("Is this a project you created or one you trust?") before it will read or edit anything, and since Codeman sessions run permission-skipping or classifier-guarded modes the answer is always yes, so a session parked on that dialog is simply stuck.
+
+⚠️ **Match the compacted SCREEN, never the stream.** tmux repaints a row by writing each word and then a cursor-forward (`\x1b[C`) instead of a space, and Ink colours each word separately, so the wire carries `I\x1b[Ctrust\x1b[Cthis\x1b[Cfolder`; stripping the escapes leaves `Itrustthisfolder`, because the spaces are not there to strip, they were never sent. A plain `includes('trust this folder')` therefore never matched a single chunk and the auto-accept was silently DEAD for every session that hit the dialog. `compactScreenText()` removes ALL whitespace instead (plus the `ESC ( B` charset selects that `stripAnsi` does not cover, which would otherwise land inside a phrase as a literal `(B`), which survives both that repaint style and the spaced full-screen redraw.
+
+⚠️ **Never answer it with a blind `\r`.** The layout has changed under us at least twice, and Claude Code 2.1.252 dropped the option numbers, put "No, exit" FIRST and highlights IT by default, so the Enter that answered the old dialog now picks *exit* and the pane dies (`Pane is dead (status 1)`) seconds after the session starts. `trustDialogNextKey()` reads the `❯` marker and returns ONE step at a time (an arrow while the cursor is on the wrong option, Enter only once the screen shows it on the trust option), with the pane re-read between steps, so a dropped arrow costs a repaint instead of the session; a frame that does not say which option is highlighted returns null and waits for the next repaint. ⚠️ The LAST marked option in the text wins, because the direct-PTY fallback reads an append-only buffer where every repaint since launch is still present and an older frame must not out-vote the freshest one.
+
+⚠️ Answering types into a live session, so THREE guards must all hold and none is redundant: a **startup-only window** (`TRUST_DIALOG_WINDOW_MS`, 90s, since the dialog renders before the main UI and leaving it open forever would let an agent transcript that merely QUOTES the dialog trigger an Enter, this file being an example), a **two-marker match** requiring a trust phrase AND one of the dialog's own confirm affordances (`isTrustDialogScreen`), and an **attempt cap** (`TRUST_DIALOG_MAX_ATTEMPTS`, 6: a keystroke can land while Ink is still mounting the widget and be dropped, which is the other half of why sessions got stuck here, but retrying forever would hammer keys into whatever came next; it was 3 while one Enter answered the dialog, and answering now costs at least two keystrokes).
+
+⚠️ It reads `capturePaneText()` and falls back to a deliberately SHORT tail of the terminal buffer only on a direct-PTY session, which has no pane: that buffer is append-only, so a longer tail would keep re-matching a dialog answered minutes ago.
+
+⚠️ **The scan must schedule its own next read** (`_trustDialogTimer`, cleared in `_clearAllTimers()`): it runs from the PTY `onData` handler, which was enough while one Enter answered the dialog, but the arrow that moves the cursor is the LAST output the pane produces, so a two-keystroke answer waiting on more output parks forever with the cursor sitting on the right option (measured on a live 2.1.252 spawn: cursor moved at 6 s, then nothing).
+
+### Owner tab layouts
+
+**Owner tab layouts** (COD-359, `tab-layout*.ts` + `GET`/`PUT /api/tab-layout`): named tab GROUPS over the flat tab strip, scoped per owner (`SINGLE_USER_LAYOUT_OWNER` = `@single` when multi-user is off), persisted under the `tabLayouts` key in state.json. The pure model is `tab-layout.ts`, `tab-layout-service.ts` is the sole mutation boundary, plus `tab-layout-persistence.ts` and `tab-layout-legacy-order.ts`. A layout is `{version, groups[], ungrouped[], updatedAt}` whose refs point at either a session or a saved webview (`TabRefKind`), capped at 32 groups / 512 refs.
+
+⚠️ **BACKEND ONLY as of 1.24.1**: nothing in `src/web/public/` calls these routes yet, so a UI built on top is new frontend work, not a rewiring job.
+
+⚠️ **`TabLayoutService` is the single mutation boundary** and every lifecycle caller (session created/removed, webview created/deleted, a legacy order PUT) describes ONE completed server action and gets AT MOST ONE versioned write; writing layout state from a route or a manager directly is what the service exists to prevent.
+
+⚠️ The layout does not replace `PUT /api/session-order`, it PROJECTS onto it: `tab-layout-legacy-order.ts` is the pure translation both ways (`putLegacyOrder()` recomposes a global order from the owner's groups), so changing one side without the other silently desyncs the tab strip from the stored layout.
+
+⚠️ **Reconciliation is gated on a SUCCESSFUL restore** (`markRestorationComplete` / `markRestorationFailed` / `markRestorationSkipped`, plus `assertDeletionReady()`): pruning refs against a session list that failed to load would delete live tabs, so a failed restore must leave the layout untouched.
+
+`PUT` takes exactly `{baseVersion, layout}` (any other key shape is a validation error), answers a stale `baseVersion` with the current layout rather than clobbering, and is capped at 128 KiB. Broadcasts `tab:layoutChanged`, owner-routed via `deriveTabLayoutSseHint`.
+
+### Hook events and workspace hook installation
+
+**Hook events**: Claude Code hooks trigger via `/api/hook-event`. Key events: `permission_prompt`, `elicitation_dialog`, `elicitation_complete`, `elicitation_response`, `idle_prompt`, `stop`, `teammate_idle`, `task_completed`, `prompt_submitted` (UserPromptSubmit, #367: a Claude pane reports its live conversation id first-hand). See `src/hooks-config.ts`; upstream hook semantics mirrored in `docs/claude-code-hooks-reference.md`.
+
+⚠️ **Every claude session INSTALLS the hooks block into its workspace** (`applyWorkspaceHooks` in hooks-config.ts → `ensureCodemanHooks`, an add-only merge that keeps a user's own handlers), from EVERY claude create path — both interactive routes, cron fires, legacy scheduled runs, the plan-orchestrator one-shots — and from `restoreMuxSessions()` for sessions recovered on server start (that boot sweep skips a workspace that no longer exists, so a deleted repo with a surviving tmux session is never resurrected as an empty dir). Before 2026-08-15 hooks were written ONLY when Codeman created the case DIRECTORY, so a linked case / cloned repo — where most sessions actually run — had no hooks at all and every hook-driven surface was silently dead there: an AskUserQuestion dialog blocked the pane while the tab and the phone overview both read a calm `idle`, with no Approvals Inbox item, no push, no definitive `stop`/`idle_prompt` for respawn and no `stop`/`blocked` for the wait endpoints.
+
+The escape hatch is the synced `workspaceHooksEnabled` setting (App Settings → Agents & CLIs → Claude, **default ON**); OFF restores the old behavior, where a Codeman block that is already there is still refreshed when stale (COD-91) but one is never added. ⚠️ Route the decision through `applyWorkspaceHooks` rather than calling `ensureCodemanHooks` at a new site, or the setting silently stops applying to that path.
+
+⚠️ Claude Code RE-READS `settings.local.json`, so an already-running session starts firing hooks without a restart (measured 2026-08-15) — and the notification for a blocking dialog is delayed by Claude Code (~30s), so the alert trails the dialog.
+
+⚠️ An AskUserQuestion / plan-selection dialog arrives as **`permission_prompt`**, not `elicitation_dialog` (that one is MCP elicitation), so it renders as the RED "needs you" alert, not the yellow idle one.
+
+### Reboot restore
+
+**Reboot restore** (#411/#442, `src/reboot-restore.ts` pure + `web/reboot-restore-registry.ts` + `routes/reboot-restore-routes.ts` + `reboot-restore-ui.js`): a host reboot takes the tmux server with it, so every pane dies and the board comes up empty with no explanation. At boot Codeman works out which sessions that reboot destroyed, holds the plan IN MEMORY (no new state file, and a server restart simply drops the offer), and the banner asks.
+
+⚠️ **The heuristic decides whether to ASK, never whether to act**: two signals have to agree (the socket holds no panes at all while state still lists sessions, AND the host booted after the newest persisted activity), and a wrong yes costs one dismissable line rather than N CLI processes nobody asked for.
+
+⚠️ Rebuilding is TAKE-then-build: entries leave the plan synchronously before the first `await` and the route is single-flighted per owner, so a double-click or a second device cannot put two panes on one conversation. Anything that never became a pane goes BACK on offer, with one deliberate exception, `already-live`, which unlike a missing workspace or a withdrawn grant cannot stop being true.
+
+⚠️ Three things are re-checked at click time rather than trusted from boot (the owner's privilege grant, the workspace still being on disk, and the conversation not already being live), and the already-live sets are read FRESH per iteration rather than snapshotted: the loop awaits a real `startInteractive()` per entry, so a snapshot taken before it is tens of seconds stale by the tenth entry and would miss a conversation the user resumed by hand in that window. The confinement re-check is keyed on the entry's OWNER, never the caller, or an admin spending another user's entry is waved through by `isWorkingDirAllowed`.
+
+⚠️ A rebuilt session comes back **attached, idle and disarmed**: the pane is NEW, so terminal scrollback is gone (the banner says so) while the conversation continues, respawn controllers and Ralph loops are never re-armed, and `reapplyPersistedSessionState(..., { rearmAutoResumeSchedule: false })` keeps auto-resume ENABLED but drops the pre-reboot `autoResumeAt` stamp, or one click has every restored session type `continue` into itself a minute later, unattended. That option exists only for this path; a Codeman restart still re-arms, because the limit footer will not reprint on its own.
+
+⚠️ The rebuild passes `nameSource` through, or the constructor re-infers it from the name and a hand-renamed session shaped like `w<n>-<case>` comes back as `placeholder` for auto-naming to overwrite.
+
+⚠️ Claude-mode only (others carry their conversation id in their own config object), and remote/docker sessions are never offered (`remote-or-docker`), because both need another host or container to be up.
+
+⚠️ A failed rebuild is undone with `discardPartiallyBuiltSession()`, deliberately NOT `cleanupSession()`: the delete path would count the session's tokens into the lifetime totals, demote a pinned record to `stopped` (which this pass reads as an intentional kill, making the session permanently unrestorable) and recursively remove the WORKSPACE's `.claude-images`.
+
+⚠️ `os.uptime()` reports the HOST's uptime, which a container shares, and that cuts both ways: after a genuine host reboot a containerized Codeman does see a short uptime and the banner works, but a container-only restart is invisible to it, which is the case where this would help most. Tests: `test/reboot-restore.test.ts`, `test/routes/reboot-restore-routes.test.ts`, `test/routes/reboot-restore-rebuild-failure.test.ts`, `test/discard-partially-built-session.test.ts`.
+
 ## Features
 
 ### Attachments
@@ -212,12 +388,25 @@ The general rule: **any new endpoint that turns a caller-supplied `sessionId` in
 
 Tests: `test/file-editing-policy.test.ts` (pure policy), `test/routes/file-write-routes.test.ts` (deliberately **unmocked fs** against a real temp workspace — symlink/TOCTOU/mode behavior must be exercised for real).
 
+### File Viewer text view: rendered markdown and text toggles
+
+**Rendered markdown + Lines/Wrap** (`_renderFilePreviewText()` and its helpers in `panels-ui.js`, buttons in the `.file-preview-actions` row): a `.md`/`.markdown` opened in the File Viewer renders as a document by default, with an `MD` pill back to source; the plain-text view has `Lines` (a CSS-counter gutter) and `Wrap` toggles. Codeman already had `marked` + DOMPurify behind `_renderMarkdown()` for the Response Viewer, so the viewer reuses that and the codebase keeps ONE markdown pipeline.
+
+- ⚠️ **One pipeline, one delegate.** The viewer calls `_renderMarkdown(text, { breaks: false })` (marked + the `sanitize-html.js` allowlist) and binds `_bindResponseViewerInteractions()` on `#filePreviewBody` (container-bound and idempotent, so once per page) for the code-block copy buttons and `a.rv-path` opening. Never a second parser, never a second click handler for the same markup. `breaks` is the one option that differs: chat keeps the default `true` (a newline is the agent's line break), while a file passes `false`, because a README hard-wrapped at 80 columns would otherwise render every wrap as a `<br>`, unlike GitHub's file view.
+- ⚠️ **Build inside a `<template>`, then rebase.** A detached div whose `innerHTML` is set starts fetching every `<img src>` at once, so the document's relative image paths would hit the server as `/docs/img.png` 404s before being rewritten. `_rebaseFilePreviewMarkdownRefs()` runs on the template content: relative images go to the workspace-confined `file-raw` under the document's directory, root-relative ones (`/docs/x.png`) under the workspace root as on GitHub (the server refuses escapes, so `..` is forwarded as-is), and one `error` handler per image degrades it to alt text, which covers a remote image the page CSP blocks, a 404 for a document outside the workspace, and an SVG that `file-raw` serves as a download. Never widen a route for this. ⚠️ marked percent-encodes destinations (`my image.png` arrives as `my%20image.png`, CJK names as `%E5…`), so the ref is `decodeURIComponent`ed (a malformed escape is kept as written) and stripped of `#fragment` and `?query` BEFORE the route encodes it again; without that `file-raw` looks for a file literally named `my%20image.png`. Workspace links become `a.rv-path` with `data-path` AND `data-session-id` (the preview's session, which the `app.js` delegate prefers over `activeSessionId`, since a preview opened from another session's attachment card must resolve links against that workspace) and lose the `target`/`rel` that `_renderMarkdown` gives every link, which would otherwise open `<origin>/docs/x.md` in a new tab; fragment, protocol-relative and http(s) links are untouched. The absolute paths `_linkifyFilePaths()` then finds in the prose get the same `data-session-id`, set on every `a.rv-path` still lacking one. ⚠️ **An attachment opened under a bare file name has no directory.** Attachment cards and the history drawer call `openFilePreview(relativePath || fileName, sessionId, attachmentId)`, and a registered attachment's `relativePath` is always `''` (`attachmentRecordToEvent`), so `filePath` is just `report.md`: resolving against it sent `docs/report.md`'s `img/chart.png` to the workspace root's `img/chart.png` (a missing image) and its `CONTRIBUTING.md` link to the root's (a silently different file), and an out-of-workspace attachment's refs all landed in the workspace. `filePreviewText` therefore carries `attachmentId`, and when it is set with a non-absolute `filePath` the rebase degrades every workspace ref instead: images become their alt text (as a text node), links are unwrapped to their text. An absolute-path attachment (one `_registerExternalPreview` minted for a clicked path) still resolves against its own directory, as does every workspace preview.
+- ⚠️ **`data-i18n-skip` on the container.** The translator's MutationObserver translates inserted headings and paragraphs, and the `.file-preview-content` entry in its skip list matches nothing (no element has that class), so the attribute is what keeps a Chinese UI from rewriting a README.
+- ⚠️ **Toggles are per-device, in their own localStorage keys** (`codeman:filePreviewMdRendered` / `LineNumbers` / `Wrap`), for the same reason as the Files panel's show-hidden toggle: the app-settings object is rebuilt from the settings modal on every save, and they are display state, not synced settings (`SettingsUpdateSchema` is `.strict()`). MD re-renders from the kept source (`filePreviewContent`, which is also what Copy copies) without a refetch; Lines/Wrap are class flips on the one `<pre>`, whose rules are scoped `.file-preview-body > pre.file-preview-text` so they never leak into the document's own code blocks. Lines are one inline `<span class="fp-line">` per line joined by real newlines, the counter in `::before` with `user-select: none`, so select and copy return the exact text.
+- ⚠️ **Caps.** Markdown fetches `lines=10000` (the route's `MAX_LINES_LIMIT`), because a rendered document cut at 500 lines reads as the whole document; other text keeps 500, which is what stops a huge log locking the tab in one `<pre>`. The attachment (out-of-workspace) branch keeps its 512 KB Range read and skips the 500-line clip for markdown. Edit mode is unchanged and still re-fetches `edit=1`; the three toggles hide while editing and for images, media and PDFs.
+- ⚠️ **`md` is NOT in `FILE_PREVIEW_EXTENSIONS`.** Only an in-workspace `.md` path clicked in the terminal still opens the tail viewer (see File-path links above: in-workspace text keeps live follow, which is what Ralph's `fix_plan.md` needs). Everything else reaches `openFilePreview()` and renders it: the Files panel, a path clicked in the Response Viewer (its delegate calls `openFilePreview()` directly), an out-of-workspace terminal path, and attachment cards. `avif` and `ico` were added to the set (a printed `favicon.ico` used to tail binary noise), with `avif` also in file-content's image set and file-raw's MIME map; out-of-workspace avif/ico stay unregistrable, like svg/bmp.
+
+Tests: `test/file-preview-markdown.test.ts` (jsdom-in-vm, pins every rule above), `test/routes/file-routes.test.ts` (avif).
+
 ### Clone a repository as a case
 
 **Clone Repo tab** (issue #236, proposed by @DodgyBadger): `POST /api/cases/clone` clones a public repository into the caller's case space and registers it as a normal local case; `POST /api/cases/clone-preflight` answers "can this be cloned anonymously, and what refs does it have?" while the user is still typing. Core in `src/git-clone.ts`, split into a PURE half (URL parse, argv/env, `ls-remote` parse, stderr classification) and a thin IO half (`probeGitRemote`, `cloneRepository`).
 
 - ⚠️ **The URL is a code-execution surface, which is why it is parsed rather than forwarded.** `ext::sh -c <cmd>` makes git run an arbitrary command as its transport, and ANY `<name>::<payload>` dispatches to a `git-remote-<name>` helper, so every `::` form is refused outright. A repository starting with `-` is read by git as a flag; that is rejected AND every spawn puts `--` before the operands, because either defence alone is one edit away from being a hole. Spawns are argv arrays, never a shell (unlike `remote-hosts.ts`, which does build a shell line and must `shellescape`). The Zod schema deliberately only length-bounds `repository` — a weaker regex duplicate of `parseGitRepositoryUrl` would be the copy that drifts.
-- ⚠️ **Non-interactive or it hangs the request.** The clone is synchronous by design (no job store, no polling, no cancellation surface), so an invisible credential prompt would pin an open HTTP request until the timeout. `gitNonInteractiveEnv()` closes all four prompt paths at once: `GIT_TERMINAL_PROMPT=0`, empty `GIT_ASKPASS`/`SSH_ASKPASS` + `SSH_ASKPASS_REQUIRE=never` + empty `DISPLAY`, `GCM_INTERACTIVE=never`, and `ssh -oBatchMode=yes`. `HOME`/`PATH` are inherited on purpose — a user whose own agent or credential helper already works keeps working (so a private repo may well clone; Codeman just never collects or stores credentials, and refuses a `user:password@` URL).
+- ⚠️ **Non-interactive or it hangs the request.** The clone is synchronous by design (no job store, no polling, no cancellation surface), so an invisible credential prompt would pin an open HTTP request until the timeout. `gitNonInteractiveEnv()` closes all four prompt paths at once: `GIT_TERMINAL_PROMPT=0`, empty `GIT_ASKPASS`/`SSH_ASKPASS` + `SSH_ASKPASS_REQUIRE=never` + empty `DISPLAY`, `GCM_INTERACTIVE=never`, and `ssh -oBatchMode=yes`. `HOME`/`PATH` are inherited on purpose — a user whose own agent or credential helper already works keeps working (so a private repo may well clone; Codeman just never collects or stores credentials, and refuses a `user:password@` URL). ⚠️ In multi-user mode a NON-ADMIN's clone and preflight run with `git -c credential.helper=` (`cloneWithoutCredentialHelpers`), because the helpers belong to the one server account every user shares; admins and single-user mode keep them. The Docker server image relies on exactly this: when built with the opt-in `CODEMAN_INSTALL_GH`/`CODEMAN_INSTALL_AZ` args it configures `gh` (github.com) and an `az`-backed helper (`docker/git-credential-azure-cli`, Azure DevOps) in its SYSTEM gitconfig, both silent until the user signs the CLI in, so a private clone there still fails fast rather than prompting.
 - ⚠️ **Bounded in time, output and concurrency.** Timeout → SIGTERM → SIGKILL, signalled to the whole process GROUP (`detached: true`, negative pid) because `git clone` fans out into `git-remote-https`/`index-pack` children that a polite signal to the parent leaves running. stderr is kept as a bounded, credential-redacted, control-stripped TAIL; `ls-remote` stdout is capped and refs are capped at 500 each. A small global pool (default 2, `CODEMAN_MAX_GIT_OPERATIONS`) caps concurrent git network ops, same reasoning as `document-conversion-limiter.ts`.
 - **Repository contents beat scaffolding.** An existing `CLAUDE.md` is kept (a generated one is written only when absent) and hooks are MERGED into whatever `.claude/settings.local.json` the repo shipped. A repo that ships its own `.claude/settings*.json` is reported back as a warning, because repo-supplied hooks run on the user's machine as soon as a session starts there.
 - **Failure leaves nothing behind.** The destination is removed only when it did not exist before the attempt, and a pre-existing directory is refused rather than cloned into, so a failed clone never squats on a case name and never touches an existing tree.
@@ -227,6 +416,8 @@ Tests: `test/file-editing-policy.test.ts` (pure policy), `test/routes/file-write
 
 Tests: `test/git-clone.test.ts` (pure half exhaustively, plus REAL git against a REAL local bare repo for clone/ref/timeout/cleanup), `test/routes/case-clone-routes.test.ts` (deliberately **unmocked fs**, real clone through the endpoint).
 
+Further detail: the synchronous clone request is bounded by `GIT_CLONE_TIMEOUT_MS`.
+
 ### Ultracode and workflow-run visualization
 
 **Ultracode / Workflow-run visualization** (opt-in `showUltracodeAgents`, default OFF; released 1.1.2): the Workflow tool ("ultracode") writes a COMPLETION artifact per run at `~/.claude/projects/<projHash>/<sessionUuid>/workflows/wf_*.json` (written only at run end); LIVE in-flight runs exist only as transcript dirs at `…/subagents/workflows/wf_<id>/` (journal.jsonl + `agent-*.jsonl`). `workflow-run-watcher.ts` (STANDALONE — deliberately never imports/touches `subagent-watcher.ts`; separate singleton, though it independently reads the same `subagents/workflows/` tree) scans BOTH sources via periodic poll + per-directory chokidar watchers with per-source mtime skip (LRU agentStatCache + journalCache), synthesizing ACTIVE runs (live per-agent tokens/tools/state from transcripts, title/phases from the workflow script) until the completion `wf_*.json` appears and supersedes, and broadcasts SSE `workflow:run_discovered`/`run_updated`/`run_removed`. The watcher is started when **either** `showUltracodeAgents` **or** `ultracodeFloatingWindows` is on (`server.ts` `isWorkflowAgentTrackingEnabled()` returns `(showUltracodeAgents ?? false) || (ultracodeFloatingWindows ?? false)`). Served via `GET /api/workflows` (optional `?minutes=` filter) and `GET /api/workflows/:runId`. Frontend `ultracode-panel.js` renders a docked master-detail view (LEFT: runs + phases; RIGHT: per-agent tokens + tool-calls; click an agent card → its live transcript via client-side `agentId` join). **Additionally**, `ultracode-windows.js` auto-pops a draggable **floating window per active run** (gated on a **DEDICATED** `ultracodeFloatingWindows` toggle, default OFF — independent of the dock panel's `showUltracodeAgents`; see `_ultracodeFloatingEnabled()`), connected by a glowing line to the originating session tab (resolved by `session.claudeSessionId === run.sessionUuid`) — same line idiom as subagent windows, drawn into the shared `#connectionLines` SVG from the tail of `_updateConnectionLinesImmediate`. The window auto-closes ~8s after its run finishes; explicit dismissals are remembered. Clicking an agent card opens an **in-page** connected transcript window (not a browser popup); both run and transcript windows minimize **into** the originating session tab as a merged `ULTRA` badge (🧬 runs / 📄 transcripts) with a restore/dismiss dropdown — minimized runs are skipped by auto-pop. Gesture beta: floating subagent/ultracode windows are pinch-draggable (a `window` grab kind in `entry.ts`). Types: `src/types/workflow-run.ts`. Config: `src/config/workflow-config.ts`.
@@ -261,6 +452,16 @@ Invariants:
 
 **Self-update** (App Settings → System → Updates): in-app updater for **git-clone installs** supervised by systemd/launchd. Supervisors: `systemd` (user unit), `launchd` (GUI LaunchAgent, gui-domain kickstart), `launchd-daemon` (KeepAlive system LaunchDaemon on headless Macs — restarts rootlessly by killing the server PID and letting launchd respawn it; detected only when the daemon is bootstrapped AND KeepAlive), else `none` → "restart manually" message; on next boot a manual-restart status auto-completes when the running version matches the target. The update restarts the very process running it, so the real work runs in a DETACHED `scripts/self-update.sh` (`git checkout <release tag> && npm install && npm run build && restart`) that outlives the restart; it writes progress to `dataPath('update-status.json')`, which the browser polls across the connection drop. Channel = latest `codeman@X.Y.Z` release tag; dirty trees are auto-stashed. `src/web/self-update.ts` splits PURE helpers (semver/tag parsing, reconcile decision — unit-tested) from IO wrappers (`getInstallInfo`/`checkForUpdate`/`startUpdate`/`reconcileUpdateOnBoot`). Routes: `GET /api/system/update/check`, `POST /api/system/update`, `GET /api/system/update/status`. Types: `src/types/update.ts`. npm installs report as non-updatable.
 
+Further detail on the Docker Compose supervisor (`docker-compose`), see also `docs/docker-self-update.md`:
+
+⚠️ **The Compose deployment is the one supervisor that does NOT outlive the restart**: there the restart IS the container exiting (`restart: unless-stopped` relaunches it), which kills the script too — safe only because the terminal `restarting` marker is written BEFORE the kill, so nothing may be appended after it. Two config facts make it work at all and both are load-bearing: the repo is a HOST BIND MOUNT over `/opt/codeman` (a pull into the baked image copy would land in the writable layer and be silently discarded by the next `up`), and the runtime image keeps devDependencies + a build toolchain (`npm run build` is tsc+esbuild, and node-pty has no Linux prebuild), which is why `npm prune --omit=dev` is gone and the updater passes `--include=dev` against `NODE_ENV=production`.
+
+⚠️ An in-place container update applies CODE ONLY — a restart reuses the existing image and config — so `evaluateEnvironmentGate()` REFUSES a release that changes `server.Dockerfile`/`docker-compose.yaml` (sha256 vs the baseline `Start-Codeman.sh` writes to `docker-env-applied.json` on every start) or adds `.env.example` keys the user's `.env` lacks, and refuses when the restart policy would not bring the container back. That third check exists because **Compose resolves an unset `${VAR}` to the EMPTY STRING and starts anyway**, so a new required setting otherwise arrives as a silently blank env var. Every unknown fails OPEN in the gate (no baseline, unreadable `.env`, no socket): failing closed would permanently block containers created before the fingerprint file existed.
+
+⚠️ The KILL does not: the server exits only when `--restart-by-exit 1` was passed, i.e. the Compose file declared `CODEMAN_RESTART_BY_EXIT=1` (set ONLY there, since that file is what sets `restart: unless-stopped`; the image ENV deliberately does not) or the daemon reported an auto-restart policy; otherwise the build lands as `completed-needs-manual-restart`, because exiting blind takes a `docker run` container with no restart policy down with no UI left to recover it. The gate is re-evaluated on `POST /api/system/update`, so hiding the button is UX, not the control.
+
+⚠️ The four global agent CLIs in `server.Dockerfile` are PINNED on purpose — unpinned, a user's CLI versions are a function of when their image was built rather than of any commit, which is the one environment change no diff-derived gate can see; pinning turns it into a Dockerfile change the gate already catches. `test/docker-compose-env-parity.test.ts` is the merge-side guard (every compose `${VAR}` ↔ an `.env.example` entry).
+
 ### Web tabs
 
 **Web tabs** (saved dashboard URLs rendered as tabs beside agent sessions; user guide `docs/web-tabs.md`). A webview is **NOT a `SessionMode` of its own**: no PTY, no tmux, no respawn, no idle detection. It is a separate resource (`~/.codeman/webviews.json` via `src/webview-store.ts`, types in `src/types/webview.ts`, limits in `src/config/webview-limits.ts`) that shares only the tab strip and the main content area, exactly as Docker and remote-SSH are case overlays rather than modes.
@@ -290,15 +491,169 @@ Invariants:
 
 **Pre-existing bug fixed alongside**: `.toolbar` has `backdrop-filter`, which makes it a stacking context and TRAPS `.run-mode-menu`'s `z-index: 1000` inside it. With the toolbar itself at `z-index: auto`, `.welcome-overlay` (z-index 10, inside `<main>`) painted over the popped-up Run menu, making **every** item in it unclickable whenever no session was open. `.toolbar` now carries `z-index: 20` (must stay below `.modal`'s 1000).
 
+Further detail: the refused egress targets are `169.254.0.0/16`, `fe80::/10`, `fd00:ec2::254`, the Azure/Alibaba fixed metadata addresses and `metadata.google.internal`. The sandboxed-frame breakages (runtime root-absolute URLs escaping `<base>`, fixed by `runtimeUrlShim()`; same-host `fetch`/XHR CORS-checked with `Origin: null`, fixed by `buildProxyCorsHeaders()` plus the `OPTIONS`-204 exemption in `registerSecurityHeaders`) are two things `curl` can never reproduce.
+
+⚠️ **A loopback link in agent output opens as a proxied web tab** (`openLinkThroughWebTabIfLoopback` in webview-tabs.js, called from the terminal link provider and the response viewer): a phone cannot reach the box's `localhost:5173`, so the tap routes through Codeman's origin instead, reusing a saved same-origin dashboard or saving one under `host:port`. Two rules there look cosmetic and are not.
+
+**`*.localhost` is deliberately NOT in the auto-route set** even though it IS loopback to a browser: the link source is agent-written terminal output and prompt-injectable, every other member of that set is an address literal that can only mean this box, and a `*.localhost` DNS name is not one (a resolver with a search domain retries `evil.localhost` as `evil.localhost.<search domain>`, which an attacker can control, turning agent output plus one tap into a persisted server-side fetch of an agent-chosen origin). A user who really runs `api.localhost` saves it by hand, which is an explicit action. The PAGE-side test is deliberately broader (`isOnBoxHostname`), since a false positive there only declines to proxy.
+
+**`this.webviews` being set does NOT mean it is loaded**: `initWebviews()` assigns a truthy EMPTY map synchronously and only then awaits the list, so a tap during page load must join the in-flight refresh (`_webviewsRefresh`/`_webviewsLoaded`) or it finds nothing to reuse and POSTs a duplicate record for an origin that already exists.
+
 ### Multi-user mode
 
 **Multi-user mode** (opt-in `--multiuser` / `CODEMAN_MULTIUSER=1`, OFF by default; shipped 1.5.0 via PR #161, design `docs/multi-user-plan.md`): named users with individually scrypt-hashed passwords in `~/.codeman/users.json` (via `src/user-store.ts`: atomic 0600 write, short-TTL cache, SERIALIZED read-modify-write so a fire-and-forget `touchLastLogin` can't clobber a concurrent route write, last-admin invariants). Gated everywhere by `isMultiUserMode()` (`src/config/multiuser.ts`); when OFF, behavior is byte-identical to single-user (all scoping helpers short-circuit). ⚠️ **Not a security boundary at the agent layer** — every session still runs as the SAME OS account; this separates WORKSPACES, it does not sandbox users (Docker cases are the isolation story). Auth: a PARALLEL async branch in `middleware/auth.ts` (single-user branch untouched) verifies `username:password` against the store, mints identity-carrying cookies (`AuthSessionRecord` gains `username`/`role`/`mustChangePassword`), decorates `req.authUser` (Fastify augmentation; single-user leaves it undefined and the ownership helpers default to a synthetic admin), enforces a per-username failure bucket + the `mustChangePassword` lockbox. Ownership threads through `Session.owner` (stamped from `req.authUser`/`job.owner` at every `new Session()`, round-tripped via `MuxSession.owner` on recovery); `findSessionOrFail(ctx,id,req)` does a NOT_FOUND owner check; list endpoints + `getLightState` + SSE (`deriveSseHint` routes session-scoped events by owner, fail-closed; machine-level + host-plan telemetry admin-only) + WS + search + file-preview all filter by owner. §6.3 permission policy: non-granted users are forced to `--permission-mode auto` (via `resolveClaudeModeForUser` at all spawn sites, incl. one-shots because `buildPromptArgs` now respects the session mode), and shell mode / cron `launchCommand` require the `canBypassPermissions` grant. Cases live in per-user `~/codeman-users/<name>/cases` (`resolveCasesDir`); a non-admin's `workingDir` is realpath-confined there; host CRUD is admin-only. Admin API `src/web/routes/admin-routes.ts` (`/api/admin/users*`, one-time passwords, audit log `admin-audit.jsonl`) + self-service `/api/me` + `/api/me/password` (`me-routes.ts`); frontend `public/admin-ui.js` (identity boot, change-password modal + interceptor, admin Users tab, and the header **Admin Panel** button `#adminPanelBtn`: ships `btn-admin-panel--hidden`, revealed for admins in multi-user mode, phone-hidden via mobile.css; opens the full Admin Panel modal with user CRUD, per-user permission toggles, and case-folder list/delete via `GET/DELETE /api/admin/users/:username/cases[/:caseName]`; live-refreshes on SSE `admin:usersChanged`, wired in app.js). CLI `codeman users add|passwd|list|rm`. Per-user session cap via `sessionCapacityState`/`sessionCapacityMessage`. Tests: `test/user-store.test.ts`, `test/multiuser-auth.test.ts`, `test/ownership-scoping.test.ts`, `test/admin-routes.test.ts`, `test/admin-ui.test.ts`.
 
+### Agent-created case marker
+
+**Agent-created case marker** (`src/agent-case-marker.ts`): a case directory `POST /api/quick-start` **creates** for an agent-driven spawn gets a `.codeman-agent-case.json` marker, so the scratch workspaces a long orchestration leaves behind (one per worker, and deleting the session does not remove them) can still be told apart from the user's real projects months later. `GET /api/cases` publishes it as `agentCreated`; `GET /api/cases/agent-created` is the read-only cleanup listing, adding `inUse` (a live session's `workingDir` is that case) and `modifiedAt`; Add Case → Manage badges each one and offers a review-then-delete sweep. The signal is the skill preamble's `X-Codeman-Agent-Origin` header (or an `agentOrigin` body field), falling back to a RESOLVED `parentSessionId` — nothing in the browser UI sets lineage, so a create request naming its spawning session came from an agent by construction, and that fallback is what still labels workers spawned by a stale skill copy.
+
+⚠️ **Only the branch that CREATES the directory may write it.** A linked case, a cloned repo or any pre-existing path must never be labelled: the label drives a recursive-delete affordance, and mislabelling someone's repo there is the one failure mode that costs real work. `POST /api/sessions` takes an existing `workingDir`, so it writes no marker at all, by construction.
+
+⚠️ Reading is TOTAL: anything that is not a well-formed version-1 marker (truncated write, hand-edited junk) reads as *not* agent-created rather than as a half-trusted entry, and deleting the file is the supported way to adopt a scratch case as a real one — which is what the `note` written into it tells whoever finds it.
+
+⚠️ Removal stays on the existing `DELETE /api/cases/:name`, one name at a time, so there is exactly ONE recursive-delete path; the UI's sweep names every directory in its confirm and EXCLUDES an `inUse` case outright rather than confirming it away.
+
+⚠️ Marker in the case dir rather than a registry under `~/.codeman`: it survives a wiped data dir or a different instance, is removed by the same `rm -rf` that removes the case (so no stale-entry pruning), and a user who runs `ls -a` can see what labelled their directory.
+
+Adding the header changed the preamble, so `CODEMAN_PREAMBLE` was bumped (1.22.0) — a cached copy is version-checked, and forgetting the bump leaves every already-seeded agent sending the old headers. Tests: `test/agent-case-marker.test.ts`, `test/routes/agent-case-marker-routes.test.ts`.
+
+### Docker Compose deployment
+
+**Docker Compose deployment** (`docker/`, contributed): Codeman itself runs in a container and spawns Docker cases as **SIBLING** containers through the mounted host socket (Docker-outside-of-Docker), never nested. That inverts one assumption the bare-host path takes for granted: the daemon no longer shares Codeman's filesystem, so a bind source valid *inside* Codeman means nothing to it. `resolveDockerDaemonMountSource()` translates sources under HOME into the daemon's namespace via `CODEMAN_DOCKER_HOST_HOME`, and `CODEMAN_CASES_PATH` points the cases dir at a host-absolute bind mount so a workspace resolves to the SAME absolute path on both sides (which is what keeps the transcript projHash matching, per Docker cases).
+
+⚠️ **`CODEMAN_CASES_PATH` must move every consumer or none**: it is resolved once in `config/cases-dir.ts` because `src/cli.ts` resolves case paths too, and when only the server's `CASES_DIR` learned the override, `codeman skill install --case <name>` reported "Case not found" on exactly the deployment the override exists for.
+
+⚠️ **`.dockerignore` patterns match the WHOLE context-relative path**, so a bare `.env` line excludes only the ROOT file: `docker/.env` (which holds `CODEMAN_PASSWORD` and any provider keys) rode `COPY . .` into the image until `**/.env` was added — verified in both directions with a real build context.
+
+⚠️ A Compose LONG-form bind (`type: bind`) **creates a missing host source directory ROOT-OWNED** rather than refusing. `Start-Codeman.sh` pre-creates both `CODEMAN_APPDATA_PATH` and `CODEMAN_CASES_PATH` on the host before `up`, which is what keeps the daemon from ever having to materialise either as root in the first place; the container ALSO starts as root (`cap_add: [CHOWN, DAC_OVERRIDE, KILL, SETGID, SETUID]` against the base `cap_drop: ALL`; `test/docker-entrypoint.test.ts` pins that list) so `docker/entrypoint.sh` can correct a bind source that turns up root-owned anyway (a restored backup, a cleared directory, plain `docker compose up` run without the script) before dropping to `PUID:PGID` via `setpriv` — a directory owned by neither root nor `PUID:PGID` is never re-owned, since that ownership is not this container's to reassign; it is PROBED for writability as the runtime account (`setpriv ... test -w`, so ACLs, group-writable trees and CIFS/NFS mounts pass) and refused with a message naming path, owner and PUID:PGID if that fails.
+
+⚠️ `KILL` is in that list for tini, not the entrypoint: `init: true` keeps tini as root while the server runs as PUID, and without CAP_KILL its SIGTERM forward fails and the server is SIGKILLed on every `compose down`/`restart` instead of flushing state.
+
+⚠️ `/opt/codeman-cli` (the runtime-owned CLI prefix) and `~/.local/bin` (where Settings installs CLIs, on the home bind mount so they survive a rebuild) are APPENDED to `PATH`, never prepended, and the entrypoint pins its own `PATH` to the system dirs: the root part of the start resolves `setpriv` by bare name, and a prefix ahead of `/usr/bin` let a planted `setpriv` run as uid 0 (measured). `~/.local/bin` is writable from the host as well, and root `docker exec` and the healthcheck inherit the image `PATH` without the entrypoint's pin; `test/docker-entrypoint.test.ts` requires every `ENV PATH=` line to start `$PATH:`.
+
+`CODEMAN_DOCKER_DISABLE_SWAP_LIMIT=1` drops `--memory-swap` (and filters only that one kernel warning) for hosts without swap accounting; `--memory` still applies.
+
+⚠️ The deployment ALSO self-updates in place (the repo bind mount at `/opt/codeman` + a restart-by-exiting supervisor) — see Self-update and `docs/docker-self-update.md` before touching `server.Dockerfile`, the compose file or `.env.example`, since each is an input to the updater's environment gate. User guides: `docs/docker-compose.md` + `docker/README.md`.
+
+### DeepSeek web UI
+
+**DeepSeek web UI** (`POST`/`GET`/`DELETE /api/deepseek/web`, `deepseek-web-server.ts`): the Run menu's "DeepSeek web UI..." entry supervises ONE background `dsh web` child process, deliberately **NOT a shell session**. The session version worked and was still wrong in use: it put a terminal tab on screen next to the web tab the user actually asked for, every single time, and nothing about a long-lived HTTP server needs to be a tab.
+
+⚠️ What a session gave for free now has to be paid for explicitly, and every piece is load-bearing: **exactly one** server (a second click REUSES it rather than racing it for a port, which two sessions structurally could not do), **restarted when the browser authority changes** (`--trusted-host` fences dsh's `/api` against the browser authority, and a Codeman reachable at both loopback and a tailnet name has two, so whoever asks last wins: the asker is by definition the origin about to load the page), **killed on shutdown** (`stopDeepSeekWeb()` in the server teardown, because the child is detached so its whole plugin tree can be signalled at once, which also means it would OUTLIVE Codeman and hold its port against the next start), and **failures returned to the caller**, since with no tab there is nowhere for a stack trace to land.
+
+⚠️ The port search starts at dsh's own default 3080 and walks 40, never fixed: that default is precisely the port most likely to be taken already by the user's own `dsh web`, and hardcoding it killed this feature with EADDRINUSE once. Free-port detection BINDS rather than connects (a connect probe cannot tell "free" from "listening but not answering yet"), so it is racy by nature and the caller still waits for the server to really answer before reporting success.
+
+⚠️ Both `POST` and `DELETE` sit at the **same privilege bar as the profile installer** (`canUsernameRunPrivilegedCommands`) even though the action reads as "open a page": booting a dsh profile executes the plugin code in it, and the server is a single shared instance, so stopping it in multi-user mode takes it out from under other users' tabs.
+
+### Custom Model Endpoint Profiles
+
+**Custom Model Endpoint Profiles** (opt-in, `customModelEndpointsEnabled`, SYNCED, default OFF; `docs/custom-model-endpoints.md`, design doc `docs/custom-model-endpoints-plan.md`; full stack — settings-panel CRUD + the Run-menu picker, on top of the backend below): points a session at a user-configured custom OpenAI-compatible endpoint — local (llama.cpp, DGX Spark, Strix Halo) or cloud (Azure AI Foundry, OpenRouter) — instead of its harness's native cloud backend. Endpoints are a read/write-array store (`custom-model-hosts.ts`, `~/.codeman/custom-model-hosts.json`) discovered via `GET <baseUrl>/v1/models`; `CustomModelHost.authStyle` is `'bearer'` (default, `Authorization: Bearer`) or `'api-key'` (Azure's convention) — **never both**, live-tested against a real server: sending both headers on one request reliably hangs it indefinitely, reproduced 3×.
+
+⚠️ The actual per-CLI redirect is `capabilities.customModelInjection` on the CLI registry (four kinds: `env` for claude/gemini/deepseek, `configContentEnv` reusing opencode's existing `OPENCODE_CONFIG_CONTENT`, `configDir` for codex/pi/grok/omp — writes an isolated per-session config file, NEVER the user's real `~/.codex`/`~/.pi`/`~/.omp`/grok config — and `unsupported` for antigravity, which has no known mechanism), computed by the pure `custom-model-injection.ts` (mirrors `session-cli-builder.ts`'s no-IO discipline). ⚠️ `PI_CONFIG_DIR` does NOTHING for pi or omp (grepped pi's entire bundled JS source — the string appears nowhere); both hardcode `~/.pi/agent/models.json` / `~/.omp/agent/models.yml` with no dedicated override, so the real redirect for both is the child process's own **`HOME`**, and both need `models` as an ARRAY of `{id}` objects (an object keyed by id silently loads zero models). Grok's real mechanism turned out to be a `config.toml` `[model.<name>]` block redirected via `GROK_HOME` — its original env-var-based recipe was flat-out wrong (produced "Not signed in" against a real binary), not just unverified.
+
+⚠️ **Two launch paths, chosen by mechanism, not preference**: opencode/codex/gemini/pi/grok/deepseek/omp apply the selection ONE-SHOT, before the session/process ever exists, with no restart at all; claude alone still applies a selection by **restarting the session's CLI process in place** via `Session.restartCli()` — a de-restricted `reattachRemote()` reusing the same `respawn-pane -k` primitive local/remote respawns already share — because every one of these harnesses reads its endpoint config at process start, never per-turn, so there is no live hot-swap; `Session.setCustomModel()` undoes the PREVIOUS selection's env keys (and deletes its old `configDir`) before merging the new ones in, so switching endpoints or clearing back to native cloud never leaves a stale key behind. ⚠️ Deleting a key from `_envOverrides` is NOT enough on its own: `tmux setenv` persists at the tmux-session level and is inherited by `respawn-pane` (measured: `setenv FOO bar` survived two successive `respawn-pane -k`), so the retired keys are queued (`_pendingEnvUnsets`) and ride `RespawnPaneOptions.unsetEnvKeys` into `applyEnvOverrides()`, which `setenv -u`s them BEFORE re-applying the live overrides. ⚠️ `restartCli()` relaunches a CLI in an existing pane, so a CLI whose launch declares a `fallback` chain (claude) gets a conversation pinned as `resumeSessionId` for that one respawn: `--session-id <id>` refuses an id that already has a transcript (`Session ID ... is already in use`), and without the `--resume <id> || --session-id <id>` shape the docker/remote pane commands already use, applying a model killed the pane and lost the session. The dead-pane respawn shares this pin, see [Dead-pane respawn: the resume pin](#dead-pane-respawn-the-resume-pin). ⚠️ pi, omp and grok need the config file AND a `model` launch param (`custom/<id>` for pi/omp, grok's `[model.codeman-custom]` block name): that is the registry's `customModelInjection.launchModel` template, applied onto the respawn options through `legacyConfigField` by `_withCustomModelLaunchModel()`, never by id, and a model id the CLI's `model` token pattern cannot carry is refused with a 400 rather than silently dropped by the argv engine. ⚠️ Remote (SSH) and Docker sessions are REFUSED (400): their `restartCli()` reattaches a durable tmux rather than restarting the agent and the env lands on the local pane, so they used to report `restarted:true` and change nothing. The selection survives a Codeman restart as the disk-only `__customModel` (bookkeeping: env KEYS, config dir, launch model; never the values, which carry the API key and are re-derived from the endpoint store on recovery), the config dir is removed with the session, and every secret-bearing file (`custom-model-hosts.json`, the per-session config dir) is written 0600.
+
+⚠️ **Security**: every env var this feature can redirect (`ANTHROPIC_BASE_URL`, `GOOGLE_GEMINI_BASE_URL`, `CODEX_HOME`, `GROK_HOME`, `HOME` for pi/omp, `OPENCODE_CONFIG_CONTENT`, etc.) is in that CLI's `privilegedEnvKeys` — several of these were reachable via the generic `envOverrides` field's prefix allowlist BEFORE this feature existed (the env allowlist is global and prefix-based, not per-CLI-scoped), so building this surfaced and closed a pre-existing gap rather than opening a new one. `ANTHROPIC_*` is deliberately NOT in claude's `allowedPrefixes` at all — Anthropic-traffic redirection can only happen through this feature's own admin-configured, SSRF-guarded route, never a plain client-supplied `envOverrides`.
+
+**Confidence, verified end-to-end against a real llama-swap server via the DYNAMIC `scripts/test-local-llm-harnesses.ts`** (reads the live CLI registry, so a registry change needs zero script edits): claude/opencode/pi/grok/omp **PASS**; codex config structure is correct, and codex only speaks the Responses API since Feb 2026 (`wire_api = "responses"`) — re-verified live against a llama-swap deployment that DOES answer `/v1/responses` (an earlier test's harder failure against a different deployment does not reproduce everywhere): a plain, no-tool-call chat turn gets a real reply, but a real tool-call attempt came back as `agent_message` TEXT (the tool-call JSON printed as the answer) rather than an executable `function_call` item — confirmed via `codex exec --json`'s raw event stream. Tool execution is what makes codex a coding agent, so it remains not usable for real work either way, just with a more precise failure mode than a flat protocol break; gemini fails with `Invalid auth method selected` (an undocumented `GATEWAY` AuthType gemini-cli selects once `GOOGLE_GEMINI_BASE_URL` is set — unresolved after real investigation); deepseek's originally-reported `HTTP_404` is root-caused and fixed — its bundled `@deepseek-ai/dsh-llm-deepseek` module builds `${DEEPSEEK_BASE_URL}/chat/completions` with no `/v1` of its own (confirmed by installing the real package and reading its source), so a new `appendV1Suffix` flag on its registry entry (alone — claude/gemini must not get it) runs `endpoint.baseUrl` through `withV1Suffix()` before writing it, live-confirmed against llama-swap (`.../chat/completions` 404s, `.../v1/chat/completions` succeeds) though not yet re-run through an actual `dsh` binary, which isn't installable in this environment; antigravity has no known mechanism at all. See the confidence table in `docs/custom-model-endpoints-plan.md` for the full detail on each.
+
+⚠️ **The Run-menu picker generates entries from `window.__codemanCustomModelClis`** (`server.ts`, injected at page render from `enabledClis().filter(kind==='agent' && customModelInjection.kind!=='unsupported')`, JSON-escaped against a literal `</script>` via the exported `escapeScriptJson()` since `label` is a user-`clis.json`-settable string unlike the neighbouring booleans-only `__codemanCliAvailable`), never a hardcoded per-CLI id list in the frontend — the same "no branching on CLI id outside stock.ts" discipline the registry itself enforces. One entry per (capable, INSTALLED CLI, saved endpoint) pair, e.g. "Claude Code (llama.cpp)", filtered through `isCliAvailable()` like the stock entries. Clicking one calls `selectCustomModelEntry(mode, endpointId)` (`session-ui.js`), which re-fetches the endpoint (never trusts anything cached from the dropdown's render — the 5-minute sweep below or a settings edit may have changed it since) and decides the model: exactly one discovered model launches straight away, two or more open `#customModelPickModal` to ask, with `defaultModelId` marked but never auto-chosen (asking exists so ONE launch can deliberately differ from the saved default).
+
+⚠️ **The picker promotes exactly one row to the top**: whichever model llama-swap reports `ready` right now (tagged "Currently loaded", queried via `GET /api/model-endpoints/:id/running-status`, client-side bounded to ~800ms via `Promise.race` so a sleeping/firewalled endpoint cannot leave the modal invisible for the route's own 5s server-side timeout) beats a merely remembered choice, and — only when nothing is currently loaded — the model actually launched last for this exact (harness, endpoint) pair (tagged "Last used", read from the per-device `codeman:customModelLastUsed:<mode>:<endpointId>` localStorage key). Neither tag reorders past the top, and the "Default" pill is a SEPARATE span rather than a third value of the same slot, so a promoted row that is also the endpoint's `defaultModelId` shows both (on a single-purpose GPU box that is the common case; an exclusive slot silently dropped the Default marking for exactly that row). "Last used" is written by `_runCustomModelEntryViaRestart` (claude) and `_quickStartWithCustomModelConfirm` (every one-shot launch; `runCustomModelEntry` itself only dispatches between the two) only once the model is actually applied — never on the mere click — because a context-window-warning decline means this exact model cannot work with this CLI at all, and promoting a model that cannot launch would be actively wrong, not just premature.
+
+Either way the actual launch (`runCustomModelEntry`) routes through `run()` itself via a temporary `_runMode` swap — never `setRunMode()`, which would persist it as the user's new default — rather than a parallel dispatch table, which is what gives a custom-model launch the same `_runInFlight` lock every other Run click gets and means a CLI whose injection recipe lands later needs no update here. It then GETs `/api/sessions/:id/wait?until=idle&timeout=20000` on that session BEFORE applying — measured live, a freshly launched CLI reports itself `busy` for its own startup (boot spinner, workspace-trust check) well before the apply call would otherwise reach it, and the apply route's `isBusy()` guard correctly can't tell that apart from a real turn in progress, so every fresh launch failed with `SESSION_BUSY` until this wait was added. A timeout there is a normal 200 per the wait endpoint's own contract, never an error, so a session still busy after 20s just reaches the apply call anyway and gets that route's own honest error. It then calls `POST /api/sessions/:id/custom-model` on the session `run()` produced, guarded by snapshotting `activeSessionId` before the call and requiring it to have actually changed after — every `run*()` handles its own failure internally and returns normally rather than throwing, so a declined/failed launch must not silently re-point and restart whatever session was already open.
+
+⚠️ The apply call reads the response body itself (`_api()`) rather than `_apiJson()`, which unwraps success but silently discards a failure body — losing the one thing (`error`) that distinguishes "still busy", "remote/Docker session" and everything else the route can report (⚠️ neither route validates `modelId` against the endpoint's discovered list, deliberately: discovery can be up to 5 minutes stale, so a 400 there would refuse a launch that works — a typo'd id fails on the CLI's own first request instead); the resulting toast is `type: 'error'` with an explicit `duration: 0` (no auto-dismiss, an explicit close button) at that one call site — not a blanket sticky-error default, which stacked unbounded on `.toast-container` with no cap or eviction — precisely so a message worth diagnosing survives long enough to be read instead of vanishing on the usual 3s timer. Entries are hidden for a remote/docker active case (the apply route refuses both) and for an endpoint with no discovered models at all (nothing to launch with).
+
+⚠️ **Every saved endpoint's models also re-discover themselves automatically**, a `this.cleanup.setInterval` in `server.ts` (`CUSTOM_MODEL_REDISCOVER_INTERVAL_MS`, 5 minutes, off under `testMode` like the Codex plan-usage poll beside it) calling the exported `refreshAllCustomModelHosts()` (`custom-model-routes.ts`) — one endpoint unreachable on a cycle never blocks the others, and a read-modify-write PER HOST (re-reading the store before each splice, keyed by id) means an admin's concurrent edit or delete wins over a sweep that started before it, never the reverse.
+
+**Later additions (llama-swap), each confirmed live against a real llama-swap deployment.**
+
+⚠️ **llama-swap runs one model at a time, and switching can disrupt ANOTHER live session** — before applying, both apply routes call llama-swap's own `GET /running` (feature-detected via `getLlamaSwapStatus()`, `custom-model-routes.ts`; a plain llama.cpp/OpenAI-compatible server has no such endpoint and is simply never checked). If a different model is loaded and ready AND another live session's own selection is using it, the apply returns `{requiresConfirmation, currentlyLoadedModel, affectedSessions}` instead of switching silently; retrying with `confirmedSwap: true` skips the check, and switching with nothing else affected proceeds immediately.
+
+⚠️ **The swap question and the context-floor question below have SEPARATE flags** (`confirmedSwap`, `confirmedContext`), because the context check runs first and while both shared one `confirmed` a user who clicked past a too-small context silently consented to evicting another session's model too; the legacy `confirmed` still means both, since it shipped in the HTTP-API-only cut. llama-swap also has no dedicated "switch model" endpoint — the only thing that actually starts a swap is a real inference request naming the model (confirmed live: applying a selection alone never reached llama-swap's own logs, since nothing had asked it to load anything) — so both routes also fire `triggerLlamaSwapLoad()`, a fire-and-forget `POST <baseUrl>/v1/chat/completions` with `max_tokens: 1`, whenever the target model isn't already loaded and ready.
+
+⚠️ **That launch-time check cannot catch a swap caused by a DIFFERENT session's LATER, ordinary use** — confirmed live: a second Codex session picking a different model launched with no warning at all (nothing conflicted at that exact instant), yet it silently evicted the first session's model regardless, since llama-swap has no push notification of its own. `detectCustomModelSwapDisplacements()` (`custom-model-routes.ts`) is a separate periodic sweep (`server.ts`, `CUSTOM_MODEL_SWAP_CHECK_INTERVAL_MS` = 20s) that compares each live custom-model session's own `modelId` against what `/running` actually reports loaded, broadcasting a `custom-model:swapped-out` SSE event — shown as a global toast, never tied to the displaced session's own tab, since the whole point is telling the user before they type into it — the first time a mismatch appears, via a caller-owned de-dupe `Set` cleared once that session's own model is loaded and ready again so a later, genuinely new displacement notifies again rather than staying silently un-notified forever after the first one.
+
+⚠️ **Context length is read from the REAL launch command, never `/props`** — `/props?model=`'s `default_generation_settings.n_ctx` was confirmed live to report a `--fit-ctx`-launched backend's theoretical/trained maximum rather than the real runtime-configured size (a measured 154112-vs-16384 discrepancy, caught only because the unfixed value still overflowed), so discovery parses the actual configured size straight out of `/running`'s own `cmd` field instead (`parseCtxFromCmd`: `--fit-ctx <N>` first, then plain llama.cpp `-c`/`--ctx-size`), falling back to `/props` only when `cmd` states no recognizable flag at all.
+
+⚠️ **Claude alone gets a context-window FLOOR check, on top of the ceiling `contextLengthVar` already fixes** — `exceedsSafeContextFloor()` (gated on the registry declaring `contextLengthVar`, so a no-op for every other CLI by construction) compares a model's discovered context against `CLAUDE_MIN_SAFE_CONTEXT_TOKENS` (40000): confirmed live, twice, that Claude Code's own system prompt and tool schemas cost roughly 36.4K tokens on the very first message, before any conversation history exists to compact, so a smaller real context fails outright regardless of what `CLAUDE_CODE_MAX_CONTEXT_TOKENS` says (that var only controls when HISTORY gets compacted, and there is none yet on message one). Below the floor, the apply returns `{requiresContextWarning, modelId, contextLength, minSafeContextTokens}` instead of launching, shown as an in-app dialog naming the actual fix: give the model an explicit larger `-c`/`--ctx-size` in llama-swap's config instead of relying on `--fit-ctx` auto-fit, which optimizes for the biggest MODEL that fits rather than the biggest CONTEXT.
+
+⚠️ **A fresh, isolated `CLAUDE_CONFIG_DIR` looks like a brand-new Claude Code profile and replays its ENTIRE first-run sequence on every launch** — the theme picker, the security-notes screen, the per-project "trust this folder?" dialog, and (running with a bypass-permissions flag) a one-time warning about it, confirmed live, none of which a real, already-onboarded profile shows again. `skipFirstRunPrompts` (claude's entry only, requires `apiKeyTrustFile` since it reuses the same file) pre-seeds that same "already been through this" state: `hasCompletedOnboarding` and this session's own `projects[workingDir].hasTrustDialogAccepted` merge into the same `.claude.json` the API-key trust file already writes to, and `skipDangerousModePermissionPrompt` merges into `settings.json` (a different file, same corrupt-tolerant merge).
+
+⚠️ **The loading banner shows the REAL backend log line, not a guess, and has no countdown or auto-timeout at all.** `getLatestLlamaSwapLogLine()` holds one `GET /api/events` SSE connection open per endpoint (confirmed live to stay open indefinitely — read past 220KB over 8s with no `done`; idle-closed after 30s via `pruneIdleLlamaSwapLogTails`, same 20s sweep as the swap-displacement check above), parsing `logData` frames and keeping only `source: "upstream"` (the real `llama-server` process's own stdout) lines, never `source: "proxy"` (llama-swap's own request-access log). ⚠️ `GET /logs` — the endpoint this feature's own first cut targeted, since the name suggested it — was confirmed live to carry ONLY the proxy log and never a single backend line, even seconds after a real, verified model swap; caught and corrected by a live check before merge, not after. The banner itself dropped its size-scaled expected-time estimate and matching auto-timeout (a guess dressed up as a fact that could kill a genuinely slow load partway through on slower hardware) for a generic hardware/model-size disclaimer plus a user-driven **Cancel** button (`_showCenterStatus`'s `onCancel` option, a real button distinct from the plain "×" close glyph an `'error'`-type banner gets) that ends the wait and closes the session on the user's own call rather than a guessed deadline.
+
+### Approvals Inbox
+
+**Approvals Inbox** (cross-session queue of prompts waiting on a human; `approvalsInboxEnabled`, SYNCED, default OFF: every surface is opt-in; only the store and answer endpoints run regardless, so flipping it ON shows anything already pending): `web/approval-inbox.ts` is a `sessionWaits`-style singleton fed by `/api/hook-event`, holding at most ONE item per session (a new prompt supersedes), claude-mode only, in-memory. Cards are answered via `POST /api/approvals/:id/answer`, which sends a digit / Esc / idle-prompt text through `writeViaMux` (menu answers never carry `\r`).
+
+⚠️ `option` digits are accepted ONLY when they match options parsed from the captured pane frame, and the answer path RE-CAPTURES the pane first (a dialog that no longer parses on screen means the keystroke would land in the composer, so refuse with 409).
+
+⚠️ Resolution on the heuristic `working` signal ALONE is restricted to `idle` items; a permission/question item gets the pane-VERIFIED variant on that same signal (`resolveIfDialogGone()` → `verifyStillAnswerable()`), so the heuristic only decides when to LOOK and the screen decides the outcome. That is what clears a dialog answered in the terminal mid-turn; the other definitive signals are `stop`, `elicitation_complete`/`elicitation_response`, exit/delete, answer, supersede and the 12h TTL.
+
+⚠️ **Viewing a session ACKNOWLEDGES its idle item, it does not resolve it** (`POST /api/approvals/session/:sessionId/viewed` → `acknowledgedAt` → `approval:updated`): the item stays pending (still answerable, still Read My Mind context) and only stops arming the yellow tab alert. That flag is what makes the clear durable, since the view-clears-idle rule used to live in one browser's memory and `seedApprovals()` re-armed the alert on the next reload while other devices never heard about it at all; the local half is `markIdleAlertSeen()` (app.js), called from BOTH `selectSession` paths, including the already-active early return, where a click could otherwise never clear the alert.
+
+⚠️ **Only a HUMAN opening a session acknowledges**: `selectSession(id, { auto: true })` marks the four selections the APP makes (boot restore, a solo window opening its target, a `#session=<id>` link from another page, the fallback after the active session is closed) and skips the acknowledgement, so a page load cannot silently spend an alert the user never saw. The flag defaults to user-initiated, so an untagged call site fails toward acknowledging rather than toward an alert nothing can clear; `test/session-select-ack-gate.test.ts` pins both the gate and the tagged call sites. Idle-only by construction (`acknowledge()` defaults to `['idle']`): looking at a permission/question dialog does not answer it.
+
+⚠️ Same rule on the input path: `_ackDelivery` (app.js) spends the IDLE alert only, via that same `markIdleAlertSeen()`. It used to `clearPendingHooks(sessionId)` with no kind, so one keystroke wiped a RED alert on that device while the dialog was still up, the other devices stayed red, and a reload re-seeded it.
+
+⚠️ Claude Code fires no "permission answered" hook (only `elicitation_complete`/`elicitation_response`, i.e. the question flavor), so an answered-in-the-terminal dialog would otherwise sit pending until `stop`: `GET /api/approvals` therefore runs a **staleness sweep** over the caller's own items via `verifyStillAnswerable()`, which is deliberately the conservative check the answer path uses (only an item whose ORIGINAL frame parsed options can be dropped, so an unreadable capture keeps the alert rather than losing a live one).
+
+⚠️ **`applyCapture()` is therefore ADD-ONLY for `options`**: a re-capture that parses nothing must never erase a parse an earlier one found. Claude Code delays the Notification hook behind the dialog (measured 6s, documented ~30s), so the 600ms re-capture routinely lands on a frame the user has ALREADY answered; clearing the field there made the item permanently unsweepable, because `verifyStillAnswerable()` reads a MISSING `options` as "we never could read this dialog" and keeps such items answerable by design. The red "needs you" then survived every sweep AND every page reload, went away only on `stop` (2026-08-20: a confirmed question left a tab flowing red for ~8 minutes while the turn ran on), and the stale card still accepted an answer, typing a bare `1` into a composer with no dialog under it. Pinned by `test/approval-inbox.test.ts`.
+
+⚠️ A frame that parses no options is CONCLUSIVE in exactly two cases, and the second one closes the late-hook hole: the item once parsed options (they cannot vanish while the dialog is up), or the frame shows Claude actively running a turn. A modal dialog BLOCKS the turn, so the two cannot coexist — measured on v2.1.237, a live-dialog frame carries neither the `… (13s` timer NOR the `esc to interrupt` footer, which the dialog replaces with `Enter to select · ↑/↓ to navigate · Esc to cancel`. Anything else stays answerable, so an unreadable capture still keeps the alert. That second signal is reached by a delayed staleness pass (`STALE_CHECK_DELAY_MS`, 3s) scheduled alongside the re-capture, because a prompt answered BEFORE the hook lands creates an item whose FIRST capture already has no dialog in it: nothing ever parsed, `stop` may have fired already, and the alert then outlived reloads until the 12h TTL.
+
+⚠️ That pass must stay comfortably LATER than `RECAPTURE_DELAY_MS`, whose whole reason for existing is that the hook can beat Ink to the screen — resolving inside the paint window would clear the alert for a dialog that was about to appear. The frontend seeds from `GET /api/approvals` in `handleInit` **regardless of the setting**: the seed re-arms the tab-alert state machine (`setPendingHook`) unconditionally, and only populating `this.approvals` (the inbox surfaces) is gated — seeding used to be gated wholesale, which left a reloaded page with NO red tab while a permission dialog sat blocking a session (2026-08-15); `_onApprovalResolved` clears the pending-hook alert unconditionally for the same reason.
+
+⚠️ The red/yellow tab alert itself is a STEADY border/background/dot with a pulse on top: the original keyframes swung to transparent at 0%/100%, so half of every cycle looked like a normal tab. Push Approve/Deny buttons stay gated on the setting (`sendPushNotifications` strips `actions`/`approvalId` when OFF) and are answered from `sw.js` directly so they work with no tab open. Surfaces (all gated on the setting): header bell (marker-hidden until count > 0, phones never show it) + drawer (`approvals-ui.js`), phone overview NEEDS YOU answer strips (`mobile-overview.js`). Design: `docs/approvals-inbox-plan.md`.
+
+### Read My Mind intent profiles
+
+**Read My Mind intent profiles** (phase 1 of `docs/readmymind-plan.md`; `readMyMindEnabled`, SYNCED, default OFF): per-CASE profiles (user-stated `goals` + the user's recent real prompts), keyed by owner + realpath(workingDir) so they survive `/clear`/respawns and multi-user scoping is structural. Capture rides the transcript (`transcript:user_prompt` from `transcript-watcher.ts`), NOT the input paths: `POST /input` sees only programmatic prompts and the WS channel is raw keystrokes. The listener lives inside `startTranscriptWatcher()`'s `if (!watcher)` block (outside it would duplicate per hook event) and is claude-only + gated on the setting per event. Store: `src/intent-store.ts` singleton, `intents.json` written 0600 tmp+rename (prompts can contain secrets; never fed to `/api/search`). Endpoints: GET/PUT/DELETE `/api/sessions/:id/intent` + POST `/api/sessions/:id/readmymind` (`readmymind-routes.ts`, ownership via `findSessionOrFail` WITH `req`; registrations stay the bare `app.<method>('path')` shape, the endpoints.md drift scanner cannot see generics).
+
+**Phase 2 (predictor + 🧠 button)**: `readmymind-context.ts` is the PURE budgeted assembler (9 ranked sources, drop order siblings→away→workspace→tools, sections 1-4 truncate only); IO lives in `readmymind-collectors.ts` (transcript TAIL read — the live watcher keeps only a 500-char snippet — + git signals, skipped for remote-SSH cases) and the route; `readmymind-predictor.ts` reuses the AiCheckerBase spawn mechanics standalone (verdict-shaped base vs freeform JSON) as a mutable singleton routes call and tests stub. Claude-mode only (400), one in flight per session (409 CONFLICT), model = `readMyMindModel` setting defaulting to `AI_CHECK_MODEL` (opus, decided).
+
+Frontend `readmymind-ui.js`: header 🧠 marker-hidden (`btn-readmymind--hidden`) until the setting is ON; phones hide it in mobile.css and get a keyboard-accessory 🧠 key instead (ships in BOTH bar templates, revealed by the `rmm-enabled` class on the BAR element — setMode() rebuilds button innerHTML, so per-key state would be wiped; synced at init + every `applyHeaderVisibilitySettings()`). Alternate suggestions render as tappable rows that swap into the editable field without losing edits; Rethink rejects the whole shown set and carries the optional steer note (`#readMyMindSteer`, sent as `steer`, shown in ready + empty-result phases, cleared on each open). Suggestions render via value/`textContent` ONLY and Send/Insert go through `POST /input` (server-side, so the sendEnterKey/local-echo trap does not apply) — nothing auto-sends, ever. User guide: `docs/readmymind.md`.
+
+### Voice dictation via Claude
+
+**Voice dictation via Claude** (`claudeVoiceEnabled`, SYNCED, default OFF): the mic button can transcribe through this machine's Claude Code login instead of a Deepgram key, using the same speech-to-text service the CLI's own `/voice` mode uses.
+
+⚠️ **Claude Code's voice mode itself is unusable here**: it opens the HOST's microphone (`sox`/`arecord`), and the CLI runs in a headless tmux pane while the human is in a browser elsewhere. So Codeman captures in the browser and borrows only the backend. Audio goes browser → Codeman → Anthropic (`src/web/voice-stream.ts`): the OAuth token never reaches the page, and the browser only sends PCM and receives text.
+
+⚠️ Credentials are **read-only** (`src/claude-credentials.ts`) and Codeman never refreshes them — a refresh rotates the refresh token and could sign the user out of their own CLI; an elapsed token reports `expired` instead.
+
+⚠️ Capture MUST be linear16/16 kHz/mono, so it uses an **AudioWorklet**, not MediaRecorder (which cannot emit raw PCM); `voice-pcm-worklet.js` is fetched from JS, so it is invisible to `cacheBustAssets` and borrows voice-input.js's `?v=` token — **edit the two together**.
+
+⚠️ Transcript frames carry the WHOLE running transcript, not deltas: the Claude path replaces where the Deepgram path appends. Provider choice is `voiceSettings.provider` (`auto` prefers Claude → Deepgram → Web Speech). → `docs/claude-voice-plan.md`
+
+### Files panel search
+
+**Files panel search** (COD-236, the `q` param on `GET /api/sessions/:id/files`): `compileFileQuery()` (`utils/file-query.ts`, pure, no IO, so it unit-tests directly) compiles the query into a reusable predicate, which is what lets the server-side walk prune instead of streaming the whole tree.
+
+⚠️ **A query turns that endpoint into a FLAT match list rather than a nested tree**, and the walk deliberately recurses past non-matching directories, since the whole point of searching is to reach a file whose ancestors do not match. An empty or whitespace-only query compiles to `null`, which is what keeps the default tree response byte-identical when no search is requested.
+
+⚠️ **Globs are never compiled into a RegExp**: `*a*a*a…` translated to `^.*a.*a.*a…$` is a classic backtracking blowup evaluated synchronously against every walked path, so one pathological query would freeze the event loop for the whole server (the same reason `search-service.ts` is regex-free). `globMatch()` is a two-pointer wildcard walk instead, O(text · pattern) with both operands short by construction, and an overlong query (`MAX_QUERY_LENGTH`, 256) also compiles to `null` rather than running.
+
+Matching semantics: a query containing `/` matches the relative path, otherwise the bare entry name; globs match anchored and case-insensitively (`*` spans any run, slashes included, `?` exactly one character), everything else is a plain case-insensitive substring.
+
+### Raw file bodies: streamed and range-aware
+
+**Raw file bodies are streamed and range-aware**: `file-raw`, the attachments `/raw` route and `GET /api/download` always advertise `Accept-Ranges: bytes` and answer a `Range` header with `206` + `Content-Range` (single-range only; parser is pure + unit-tested in `src/web/http-range.ts`, a malformed spec is ignored → 200 while an out-of-bounds one is a 416).
+
+⚠️ **The size cap on all three is a sanity bound, not memory protection** (`MAX_FILE_DOWNLOAD_BYTES` in `config/buffer-limits.ts`, default 2GB, env `CODEMAN_MAX_DOWNLOAD_BYTES`, `0` = unlimited): the bodies stream, so size costs a read stream and not RSS (measured: a 600MB download moved peak RSS by ~37MB). Its predecessor was a hardcoded 50MB whose comment still said "prevent memory exhaustion" long after the `readFile()` it described was replaced by `sendFileBody()`, so all it did was refuse legitimate downloads of build artifacts, videos and archives. `/api/download` was the last route that really did buffer the whole file, and now shares `sendFileBody()` with the other two.
+
+⚠️ A 200-only response is what made the File Viewer's `<video>` unseekable: Chrome then reports `video.seekable` as `[0, 0]`, the scrub bar is inert and `currentTime = x` silently reverts (measured on an 18MB mp4), and Safari refuses to start the media at all.
+
+⚠️ These bodies go out through `reply.hijack()`, which bypasses Fastify's status handling — `sendRawStream` must copy the status onto `reply.raw` by hand or a partial body ships labelled `200` and the browser treats a slice as the whole file.
+
+⚠️ Closing the preview must **pause and unload** the media (`_stopFilePreviewMedia` in panels-ui.js): dropping the overlay's `visible` class is `display:none` and nothing else, and a DETACHED `HTMLMediaElement` keeps playing, which is how the X button used to leave a video audible with no player to pause.
+
 ## Frontend
 
 ### Command palette and shortcut registry
 
-**Command palette + shortcut registry** (COD-151/153/157/192, #146): `Ctrl/Cmd/Alt+K` opens the session palette (fuzzy search over live sessions; "Browse all sessions" → the Session Manager modal backed by `GET /api/sessions/unified`); the quick-start case `<select>` is fronted by a searchable picker (`buildCasePickerOptions`/`formatCasePickerLabel` — remote cases render `name @ hostId`). Shortcuts live in a rebindable registry (`DEFAULT_SHORTCUTS`/`getShortcutRegistry()`/`matchesShortcutEvent()` in app.js; overrides persist under `settings.shortcutOverrides` via `saveAppSettingsToStorage`); App Settings → Shortcuts renders capture/disable rows; `Ctrl+?` opens the registry-driven overlay (footer links to the full `#helpModal` reference). ⚠️ Palette-chord keys must ALSO be swallowed in `attachCustomKeyEventHandler` (terminal-ui.js) or xterm writes the control byte (0x0B) into the PTY. ⚠️ `saveAppSettings()` rebuilds settings from the DOM — keys edited elsewhere (`shortcutOverrides`, `showTokenCount`, `showCost`) need explicit `_prev` carry-over.
+**Command palette + shortcut registry** (COD-151/153/157/192, #146): `Ctrl/Cmd/Alt+K` opens the session palette (fuzzy search over live sessions; "Browse all sessions" → the Session Manager modal backed by `GET /api/sessions/unified`); the quick-start case `<select>` is fronted by a searchable picker (`buildCasePickerOptions`/`formatCasePickerLabel` — remote cases render `name @ hostId`). Shortcuts live in a rebindable registry (`DEFAULT_SHORTCUTS`/`getShortcutRegistry()`/`matchesShortcutEvent()` in app.js; overrides persist under `settings.shortcutOverrides` via `saveAppSettingsToStorage`); App Settings → Shortcuts renders capture/disable rows; `Ctrl+?` opens the registry-driven overlay (footer links to the full `#helpModal` reference). ⚠️ Palette-chord keys must ALSO be swallowed in `attachCustomKeyEventHandler` (terminal-ui.js) or xterm writes the control byte (0x0B) into the PTY. ⚠️ The global Escape handler (app.js) calls every overlay close method on every Escape, in the capture phase and so before the focused element's own Escape handler, which means a close method with side effects beyond hiding must return early when its overlay is not open: `closeCommandPalette()` and `closeSessionManager()` hand focus back on close (`_restoreOverlayFocus()`, panels-ui.js), and run unconditionally that restore stole focus from split Pane B and from any text field, and turned the inline tab rename's Escape into a commit. ⚠️ `saveAppSettings()` rebuilds settings from the DOM — keys edited elsewhere (`shortcutOverrides`, `showTokenCount`, `showCost`) need explicit `_prev` carry-over.
 
 **Terminal smart copy** (#211): `Ctrl+C` copies the selection when there is one and stays the interrupt when there isn't. Three rules keep that split honest, and breaking any of them silently costs the user their interrupt key:
 
@@ -308,11 +663,12 @@ Invariants:
 
 Copy goes through `_copyText()` (Clipboard API, then hidden-textarea + `execCommand`), not raw `navigator.clipboard`, because `install.sh`'s LAN option serves plain HTTP where `navigator.clipboard` is undefined; the fallback steals focus, so the terminal is refocused afterwards. Related: xterm registers its own `copy` listener on the terminal element gated on `hasSelection()`, which is why right-click → Copy has always worked. Selection itself is unavailable on touch devices by design (`user-select: none` on the terminal subtree), and in `shell`/`opencode`/`antigravity` tabs the TUI owns the mouse, so selecting there needs Shift+drag. Tests: `test/terminal-copy-selection.test.ts` (gate + wiring invariants), `test/terminal-copy-shortcut.test.ts` (browser, real key presses).
 
-**The main terminal's four copy paths clean the selection first** (`CodemanCopySelection.clean` in constants.js, pure; `cleanedTerminalSelection()` in terminal-ui.js is the half that reads the live terminal). Those four are the `Ctrl+C` chord, right-click, the phone selection button and Auto Copy. ⚠️ Three routes still copy the RAW padded rows, all of them predating the clean: the browser's own Edit → Copy, which xterm's own `copy` listener on the terminal element serves with `selectionText` directly; a `copy-selection` shortcut the user disabled in App Settings, where nothing calls `preventDefault()` and that native listener runs; and the subagent/teammate windows, which build their own `Terminal` in panels-ui.js with no copy wiring at all. xterm hands back whole screen ROWS and its own trim drops only cells that were never written to, so the real spaces a full-screen TUI paints across the unused part of a row count as content and reach the clipboard. Measured against Claude Code in a 282-column pane, single lines arrived carrying 138 trailing spaces on top of the two-space transcript indent. The clean drops each line's trailing run. Three rules keep it honest:
+**The main terminal's four copy paths clean the selection first** (`CodemanCopySelection.clean` in constants.js, pure; `cleanedTerminalSelection()` in terminal-ui.js is the half that reads the live terminal). Those four are the `Ctrl+C` chord, right-click, the phone selection button and Auto Copy. ⚠️ Three routes still copy the RAW padded rows, all of them predating the clean: the browser's own Edit → Copy, which xterm's own `copy` listener on the terminal element serves with `selectionText` directly; a `copy-selection` shortcut the user disabled in App Settings, where nothing calls `preventDefault()` and that native listener runs; and the subagent/teammate windows, which build their own `Terminal` in panels-ui.js with no copy wiring at all. xterm hands back whole screen ROWS and its own trim drops only cells that were never written to, so the real spaces a full-screen TUI paints across the unused part of a row count as content and reach the clipboard. Measured against Claude Code in a 282-column pane, single lines arrived carrying 138 trailing spaces on top of the two-space transcript indent. The clean drops each line's trailing run, and strips a LEADING margin when the session's CLI declares one. Four rules keep it honest:
 
-1. **Trailing padding only. A shared LEADING indent is deliberately NOT stripped**, and that is a decision rather than an omission: it was built, measured and dropped before #451 merged. It looks like the mirror image of the trailing trim and is not, because no native terminal does it and the transform cannot tell a TUI's margin from content that is genuinely indented. Measured over 401,445 three-row windows across 1,010 tracked files in this repo it fired on **73%** of them (92% inside a YAML workflow, 76% over `git log` output, 48% in a TypeScript source), and no width threshold separates the two because they are the same widths: a live Claude Code pane's own margins measure 2 and 5 columns while the most common non-TUI shared run is 4, sitting between them. The failure modes are what settle it. A wrong trailing trim costs nothing; a wrong dedent silently deletes information that was on screen, with no signal and nothing in the clipboard to hint at it, and it is wrong on `git log` bodies, on indented code read out of `cat` (semantic in Python), on `git diff` context rows where the leading space is the marker, and on stack traces. ⚠️ It also could not be made self-consistent cheaply: whether the first row joined the measurement depended on the mousedown COLUMN, which the user never sees, so one block of three rows produced three different clipboard results, and the flag read `getSelectionPosition().start`, which is the mousedown anchor xterm never normalises, so dragging UP through a block read it off the bottom row (the PR's test stub hardcoded a downward drag, so its suite could not express the case). If it is ever revisited, the one qualification that measured clean is **painted trailing padding** (a full-screen TUI writes real spaces across every row, while a shell pane leaves those cells never-written for xterm to trim): zero false positives over all 401,445 windows, no new plumbing. It still mangles a `git log` body sitting inside an agent's own gutter, which is why it was not taken.
+1. **A leading strip uses the width the CLI DECLARES, never one derived from the pane.** `capabilities.transcriptGutter` (CLI registry, a bounded integer) is the whole source: claude and codex each declare 2, no other stock entry declares any, and an entry that declares nothing never has a margin taken off a copy. ⚠️ The lookup keys on the session's LAUNCH mode, not on what is running in the pane: a claude-mode session whose pane has dropped to a plain shell (the CLI exited, or a shell was started inside it) still takes up to two columns off a copy, so a `cat`'d block indented four comes out at two. The ceiling rule below keeps its relative indentation intact and `copyStripMargin` (App Settings, "Trim the pane margin on copy") is the escape hatch, so this is a known limitation, not a guarantee the strip only ever fires on a transcript. The server publishes the map as `window.__codemanTranscriptGutter`, built by filtering `enabledClis()` on that capability rather than by listing ids, and `_cliGutterColumns()` (terminal-ui.js) looks that session's mode up in it, defaulting to the active session and taking an explicit id for Pane B of a split. ⚠️ **Three ways of deriving the width from the text were built and measured, and two of them shipped looking correct.** The selection's own shared indent fired on **73%** of 401,445 three-row windows across 1,010 tracked files, because a three-row window of nested YAML shares an indent for the same reason a margin does. **Painted trailing padding** — a full-screen TUI writes real spaces across the part of a row it is not using, while a shell leaves those cells never-written for xterm to trim — has no false positives and never over-stripped, and is nonetheless a function of pane WIDTH: the padding exists only while a rendered line stops short of the CLI's own layout width, and Claude Code's prose wraps to fill it. Dragging the same two prose rows of one live transcript at five window sizes, the share of rows carrying padding measured 44%, 6%, 6%, 7% and 87% at 123, 160, 198, 235 and 298 columns, so at every ordinary size the strip did nothing at all while every test and every 282-column measurement said it worked. The **narrowest indent on the surrounding rows** fires at every width and over-strips about 1% of selections, because a file listing inside the transcript can be the narrowest thing on screen. ⚠️ The declared width is a **CEILING, not the answer**: `clean()` strips the lesser of it and the run every selected line shares, so a block can only ever shift as a unit, the relative structure inside a selection survives by construction, and a selection reaching column 0 loses nothing. That is what keeps a `git log` body at its own four spaces inside an agent's two-column gutter. Measured over 1,392,281 selections — every 1, 2, 3, 5, 10 and 20-row window of real Claude screens replayed from live PTY streams at 100, 120, 160, 198, 235 and 282 columns — it over-strips none, breaks no relative indent and alters no text, at 100% of the selections whose own indent covers the gutter. ⚠️ Nothing reads the terminal buffer on this path; the old version scanned up to ~240 rows per `Ctrl+C` to measure a width the CLI can simply state. ⚠️ **The margin strip is not idempotent, so no caller may clean twice.** It takes the lesser of the declared width and the shared run, so a second pass takes up to `margin` columns more off whatever the first left. The trailing trim alone is a fixed point, and `copyTerminalSelection()` relied on that by re-cleaning whatever argument it was handed, which dedented every claude and codex copy twice on the `Ctrl+C` path — the most-used of the four, while right-click, the phone selection button and Auto Copy stayed correct because each hands over the raw selection or reads it live. The gate still tests the CLEANED string, so a padding-only selection still falls through to the PTY, and the RAW string is what travels on. A source-level test pins that branch, because it lives inside `initTerminal`'s `attachCustomKeyEventHandler` closure over a real xterm that the vm harness cannot build.
 2. **A COLUMN selection is returned untouched.** Alt+drag makes one (xterm's `shouldColumnSelect` keys on `altKey` alone, and neither `Terminal` Codeman builds passes the one option, `macOptionClickForcesSelection`, that would disable it), and a rectangle's rows lining up is the whole point of the gesture. xterm exposes the mode nowhere public, so the check reads `terminal._core._selectionService._activeSelectionMode` (`SelectionMode.COLUMN` is 3) and cleans normally if a future xterm renames it.
-3. **The emptiness gate is `trim()`, not truthiness, and it still clears the selection.** A multi-row drag across padding cleans to line breaks alone, which are truthy, and a bare newline pasted into a chat composer submits it. ⚠️ The clear is FEEDBACK, not protection for the interrupt, and the comments that said otherwise were describing the pre-clean code: the `Ctrl+C` gate above now tests the CLEANED selection, so a padding-only selection left set cleans to `''` on every later press and falls through to the PTY as `0x03` anyway. What the clear buys is that a highlight which copied nothing does not linger unexplained, which is also what the toast is for.
+3. **The mid-row flag reads an ORDERED range, and it governs one line.** ⚠️ `getSelectionPosition()` is reversal-aware on the pinned xterm and the review note that called it the raw mousedown anchor is out of date: `CoreBrowserTerminal.ts` reads `_selectionService.selectionStart`, whose getter returns `SelectionModel.finalSelectionStart`, and that swaps the pair when `areSelectionValuesReversed()` says so. Driving a real upward mouse drag through chromium against xterm 6.0 reports the same range as the downward drag of the same rows. `_normalisedSelectionRange()` orders the pair anyway, because the private model one layer down exposes unnormalised fields under the same two names, and a reversed pair would put the mid-row flag on the wrong end of the drag. `range.start.x > 0` then means the first selected line began mid-row and never carried the margin, so that line alone is left out of both the shared-indent ceiling and the strip. ⚠️ This is the ONE thing the mousedown column still decides and it decides it for that line only. In the dropped version it decided whether the first row joined the measurement, which changed what **every** row lost, so the same three rows produced three different clipboard results depending on where the click landed.
+4. **The emptiness gate is `trim()`, not truthiness, and it still clears the selection.** A multi-row drag across padding cleans to line breaks alone, which are truthy, and a bare newline pasted into a chat composer submits it. ⚠️ The clear is FEEDBACK, not protection for the interrupt, and the comments that said otherwise were describing the pre-clean code: the `Ctrl+C` gate above now tests the CLEANED selection, so a padding-only selection left set cleans to `''` on every later press and falls through to the PTY as `0x03` anyway. What the clear buys is that a highlight which copied nothing does not linger unexplained, which is also what the toast is for.
 
 Tests: `test/terminal-copy-clean.test.ts`.
 
@@ -378,6 +734,8 @@ Anatomy: `.set-shell` → `.set-shell-head` (title + `.set-head-actions`) + `.se
 
 `data-claude-only` lives on the **rail entries**, so external-CLI sessions lose Respawn and Ralph and open on Session (`switchOptionsTab('context')`, verified in the browser). `admin-ui.js` injects the multi-user Users entry as a `data-section="settings-users"` rail button plus a `#settings-users` section appended to `.set-rail-items` / `.set-doc`, so those two hooks must survive any restructure.
 
+Further detail: in the Settings section order, the version and the updater lead the document and the rest of the system settings tail it. ⚠️ Model cards (`#appSettingsModelCards`) and the effort segment are **views over hidden `<select>`s** that remain the source of truth; the cards hold the BASE model and the "1M context window" switch composes `base + [1m]` back into `claudeModel`, which is what retires the old "takes precedence over the toggle below" trap. Without the explicit chevron on the Add Case adapter's `<details>`, the five collapsed blocks render as plain headings nobody clicks.
+
 ### WebGL renderer toggle
 
 **WebGL renderer toggle** (#140, `webglRendererEnabled`): per-device (`displayKeys` set, stripped from the server payload — NOT in `SettingsUpdateSchema`, which is `.strict()`). The GPU-stall watchdog's sticky `codeman-webgl-disabled` marker survives page loads; it's cleared only by an explicit OFF→ON save transition or `?webgl=force` (`shouldSkipWebGL` in constants.js). `?nowebgl` still forces the DOM renderer per-load.
@@ -402,6 +760,28 @@ Anatomy: `.set-shell` → `.set-shell-head` (title + `.set-head-actions`) + `.se
 
 ⚠️ Collapsed means **different things per viewport**: at 1024px and up the sidebar keeps a 44px icon rail so the ambient signal (status dot, task/subagent/ultracode badges) survives — the Alt+N number, the name/folder and the `sh`/`oc`/`cx`/`gm` mode chip do NOT, because 44px minus paddings and borders is ~34px of content box and the chip lives inside `.tab-info`; below 1024px `mobile.css` turns the sidebar into an off-canvas overlay where collapsed == drawer closed (mirrored into an `.open` class plus `inert`/`aria-hidden`, since `translateX(-100%)` alone leaves every row in the Tab order), it defaults to CLOSED when the user has made no choice, and picking a session or web tab dismisses it. ⚠️ **That 1024px breakpoint is the only handheld test the sidebar may use** (`_isSessionSidebarOverlay()`, mirrored in the pre-paint script): `MobileDetection.getDeviceType()` calls everything from 768px up `'desktop'`, so using it gave 768-1023px the overlay CSS with docked-sidebar logic — drawer opening itself on load, immune to selection and Escape. The toggle chord (default Alt+B) also needs its gate in `terminal-ui.js`'s `attachCustomKeyEventHandler`, or `preventDefault()` in the capture handler still lets xterm write ESC b into the live PTY (same trap as COD-153). The sidebar filter only applies while its input is on screen — `applySidebarFilter()` strips the class in the header strip, the collapsed rail and the closed drawer, because a filter with no reachable control hides sessions permanently. Collapse state lives in its OWN `codeman-sidebar-collapsed` key, **not** in the settings blob — `saveAppSettings()` rebuilds that blob from DOM controls, so a key without a control is wiped on every Save. Solo (`/session/:id`) windows never get a sidebar (three guards: `getSessionListLayout()`, the pre-paint script, and `body.solo-mode`), because `#sessionTabs` parked in a `display:none` subtree measures 0/0 for tab overflow and inline rename. The sidebar CSS block sits at the END of `styles.css`, **after** the `html:not([data-skin="og"])` nesting block, and is layout-only — any colour on `.session-tab` there would render correctly on the `og` skin only. Same for the `mobile.css` block: it must stay at the end of the file or the earlier compact-strip rules clip the list to a 36px sliver. Two surfaces DEFER to the sidebar rather than adapt: **lineage arcs are skipped** in sidebar layout (`_appendLineageConnectionLines` early-returns — `computeLineagePath()`'s whole geometry hangs a U-bridge from the horizontal STRIP's bottom edge, so against a vertical list every arc would loop to the foot of the sidebar; a sideways lineage shape needs its own visual tuning, it is not a by-product of re-parenting), and the **desktop home tab rail** (`shouldShowHomeSessions()`) stays hidden while the sidebar is active, because both dock the session list flush left and the rail would render the same list next to it, z-ordered UNDER it. The subagent/ultracode connectors DO adapt (`_tabAnchor()`/`_tabConnectorPath()` in app.js: right-edge anchor, horizontal bezier), and the lineage strip-scroll listener redraws them on the sidebar's vertical scroll. `_scrollActiveTabIntoView()` owns active-row reveal on BOTH axes: sidebar mode branches to `scrollIntoView({block:'nearest'})` because the horizontal `computeTabScrollLeft` math no-ops against a vertical scroller, and `_fullRenderSessionTabs()` restores `scrollTop` alongside the #257 `scrollLeft` restore or ambient rebuilds yank a mid-scroll sidebar back to the top. Tests: `test/session-list-layout.test.ts`.
 
+Further detail: with many sessions the horizontal strip stops being scannable, which is why the list can move into the vertical `<aside>` with a filter box and a live count, collapsible to a 44px rail (`--sidebar-width` 260 / `--sidebar-width-collapsed` 44) via **Alt+B** (`toggleSessionSidebar`; Alt, not Ctrl+B, which must reach tmux/readline in the terminal). The setting lives in App Settings → Appearance → Tabs. There is a THIRD host for `#sessionTabs` besides `#sessionTabsHost` and `#sessionSidebarList`: `#tabRail`, the vertical rail. Exactly TWO functions reparent it and they must run in this order: `applySessionListLayout()` first (sidebar wins), then `applyTabOrientation()` (settings-ui.js), which moves the tabs into `#tabRail` only when the sidebar does not own them. ⚠️ `applySessionListLayout()` sets `data-session-list` / `data-sidebar` on `<html>` and must run BEFORE `applyTabWrapSettings()`, which is the one owner of `tabs-two-rows`/`tabs-show-folder` and reads those attributes.
+
+⚠️ **The vertical tab rail** (`tabOrientation`/`tabRailWidth`/`sessionSidebarFontSize`, all per-device display keys that ARE in the schema, like `sessionListLayout`) is a SECOND vertical list next to the sidebar: the orientation setting is silently ignored while the sidebar layout is chosen, desktop/tablet only (`resolveTabOrientation` forces horizontal on mobile), resizable via `tab-rail-resize.js` (which owns terminal refits during the drag). The pre-paint script stamps `data-tab-orientation` (+ `--tab-rail-width`) like it stamps the sidebar keys, or vertical mode flashes through the header strip; the name font size defaults to 12px, the sidebar's historical size, so untouched installs are never restyled.
+
+⚠️ **Detailed rows are a property of a vertical LIST, not of one surface** (`sessionListLayout: 'sidebar-rich'` for the sidebar, `tabRailDetail: 'rich'|'simple'` for the rail, rail default **rich**): both draw the home screen's per-session line (`created 3d ago · working 12m`) plus a status pill, from the SAME row model (`_sidebarRichRow`/`_sidebarRichMetaHTML` in app.js, classified by `_mobileOverviewState`/`_mobileOverviewSince`), and the render paths ask ONE gate, `isRichTabRows()` (= `isSessionSidebarRich() || isTabRailRich()`). ⚠️ Detail rides on its own attribute (`data-sidebar-detail` / `data-tab-rail-detail`) so every existing `[data-session-list="sidebar"]` / `[data-tab-orientation='vertical']` rule keeps matching both variants untouched; a flip of detail ALONE still needs a full render (the stamps line is emitted by the row template, not toggled by CSS) and must re-run `applyTabWrapSettings()`, which owns the folder line and is now rail-aware. ⚠️ The rich CSS rules carry a rail twin as a COMMA-GROUPED selector, never `:is()` (an `:is()` list takes its most specific argument, which would lift the sidebar arm from (0,3,1) to the rail's (0,5,1)).
+
+⚠️ Width is the whole reason there are thresholds: the rich sidebar is 300px (`--sidebar-width-rich`) and a rail that has never been sized defaults to **320** (`RICH_DEFAULT_WIDTH`, the existing Wide preset) instead of 256, because at 256 the stamps line ellipsizes mid-word; a user-narrowed rail drops the created stamp below 288 (`tab-rail-tight`, CSS only) and drops rich rows entirely below 240 (`tab-rail-compact`, which re-renders). A stored width is never overridden. ⚠️ Only detailed rows carry stamps that go stale with no event behind them, so `_startSidebarRichClock()` (20s, rewrites text in place — a re-render would restart every row's animation) must be armed and disarmed by BOTH `applySessionListLayout()` and `applyTabOrientation()`.
+
+⚠️ **Axis decisions must use `_isVerticalTabList()`** (sidebar OR rail), never `isSessionSidebarActive()` alone: the rail leaves `data-session-list` at `header`, and the sidebar-only predicate shipped four rail bugs at once (drag insertion side read from clientX, active tab never scrolled into view, floating windows anchored below tabs instead of beside them, connector redraws skipped on rail scroll).
+
+⚠️ Leaving sidebar mode **clears `_sidebarFilter`**: the filter box only exists in the aside, so a stale filter would hide sessions from the header strip with no reachable control to clear it. ⚠️ On handhelds the closed drawer keeps `display: flex`, so without `inert` + `aria-hidden` (`_isSessionSidebarOverlay()`) its filter box and ~4 tab stops per session stay in the tab order; the DOCKED desktop rail must never be inerted, its rows are still clickable.
+
+⚠️ **The detailed RAIL additionally wears the home rail's CARD, and the detailed SIDEBAR deliberately does not**: the rail is an occasional, resizable list you scan, the sidebar is a permanently-docked nav column where 20 stacked cards read as a wall — so the card rules are RAIL-SCOPED and were NOT added to the comma-grouped selectors above, which is the one-line change that would silently restyle the sidebar. Card state accents reuse `home-sessions-blink-red`/`-yellow` rather than declaring a second pair, and every state dot rule excludes `.tab-alert-action`/`.tab-alert-idle` by hand, because those alert rules are only (0,3,0) and the rail's are (0,5,1)+. There is no `.active` rule in that block on purpose: `.session-tab.active` already paints border/background/box-shadow `!important`.
+
+⚠️ **Row ORDER is a third rail attribute** (`tabRailSort: 'activity'|'manual'`, `data-tab-rail-sort`, default **activity**): a sorted rail answers the home screens' question with the home screens' answer, `CodemanSessionOrder` over rows classified by `_mobileOverviewState` (`_tabRailSortOrder` in app.js). ⚠️ **It is applied as the flex `order` property, never by reordering the DOM**: `#sessionTabs` stays in `sessionOrder`, so the Alt+N badge (`_tabIdx`, which therefore does NOT run 1,2,3 down a sorted rail — it names a shortcut, not a position), drag-and-drop, the arrow-key walk, the sidebar filter and `_scrollActiveTabIntoView()` all keep reading the list they always read, and a session changing state moves ONE inline style instead of forcing the full rebuild that would restart every card's animation on every SSE tick. The incremental render path therefore has to re-apply it (a state flip adds no tab, so the full rebuild is never reached) and an empty string is what clears it when sorting stops. ⚠️ Web tabs are pinned past the cards by a CSS `order: 9999` rather than an inline one, since `renderWebviewTabs()` emits the same markup for every layout; the flex default of 0 would interleave them among the sorted sessions. ⚠️ `setupTabDragHandlers()` sets `draggable="false"` and returns while sorting is on: the drop rewrites `sessionOrder` correctly and the sort then puts the card straight back, so the affordance would be a lie — `'manual'` is the way back to drag-reordering.
+
+⚠️ **The arrow-key walk is the one place that must follow the SORT rather than the DOM**: `_tabKeydownHandler` steps `querySelectorAll` order, which is `sessionOrder`, so on a sorted rail ArrowDown from the top card landed wherever that session sat in the tab order instead of on the card below it. It now sorts its node list by the COMPUTED `order` first (computed, not inline: web tabs get their `order: 9999` from CSS and would otherwise read as 0 and lead the walk). This is the exception that proves the DOM-stays-in-sessionOrder rule: the badge, drag model and Alt+N index all deliberately keep reading the DOM, and only the thing the user steps with their eyes follows the paint.
+
+### Split-pane sessions
+
+**Split-pane sessions** (`showSplitButton`, header button, default OFF, per-device like `showFileViewerButton` — not in `SettingsUpdateSchema`, `displayKeys` in settings-ui.js): shows two live sessions side-by-side in one Codeman window. Pane A is the untouched, existing singleton terminal (`this.terminal`/`this._ws` in terminal-ui.js); Pane B is a new, independent `SplitTerminalPane` (terminal-split.js) with its own xterm instance and its own `/ws/sessions/:id/terminal` WebSocket. ⚠️ **Pane B is deliberately plainer than Pane A** — no local-echo overlay, no CJK IME, no touch/mobile handlers, no keyboard accessory bar — since this is a desktop-only feature (a split view needs a wide viewport) and those features exist for mobile/touch input; `.btn-split` is hard-hidden below 1180px regardless of the setting by the `@media (max-width: 1179px)` rule in styles.css (mobile.css only carries a comment pointing at it: that file loads up to 1023px, so it cannot cover the 1024-1179px tablet range the feature also needs to stay off), and the per-device setting means turning it on at a desk can never sync it onto a phone in the first place. No persistence: closing the browser tab or reloading always returns to the normal single-pane view; there is no localStorage key for split state. ⚠️ Splitting a session against itself is disallowed (the picker excludes the active session), **as is splitting against a popped-out (detached) session** — `buildSplitPickerSessions()` excludes `detachedSessions` because a detached session's own window is already claiming its PTY size, and `MAX_WS_PER_SESSION` needs no change since Pane A/B are always two different sessions. ⚠️ Either pane's session ending (deleted locally or from another client) auto-collapses the split — Pane A's session ending promotes Pane B to the new single pane via `selectSession(id, { auto: true })` (an app-driven selection, so it must not spend the session's idle alert — see the Approvals Inbox note above), never by trying to hot-swap the lightweight `SplitTerminalPane` object into the primary singleton state. ⚠️ Pane B refits on every window/sidebar/tab-rail resize via the SAME trailing-edge `ResizeObserver` callback that resizes Pane A (`throttledResize` in terminal-ui.js) — it only ever measured Pane A's own container, so without an explicit `this._splitPane?.fit()` call there Pane B silently kept its stale PTY size through every resize that did not happen to be a divider drag. ⚠️ A dropped WebSocket leaves Pane B visibly dead (a message written into its own xterm buffer) rather than silently swallowing keystrokes with nothing on screen to explain why — there is no reconnect logic for v1, matching the "deliberately plainer than Pane A" design. Related but distinct: `detachSession()` already opens one session in a separate OS-level browser window (`isSoloWindow`) — that is prior art for "two sessions visible at once" but not for one window with a draggable in-page divider, which is what this feature adds. ⚠️ Pane B installs its own `attachCustomKeyEventHandler` gating the same app-level chords Pane A's own handler gates (command palette, Alt+1-9/[/] tab nav, Alt+B sidebar toggle, Ctrl+Z suspend, Shift/Ctrl+Enter newline, smart-copy Ctrl+C) — without it the document capture-phase handler's `preventDefault()` (which never stops xterm) let each chord ALSO write its raw byte/escape sequence into Pane B's live PTY on top of whatever the app action did to Pane A (COD-153). Ctrl+Z is swallowed unless Pane B's own session is `mode === 'shell'`, mirroring terminal-ui.js's reasoning: in a plain shell it is the user's own job-control tool, everywhere else it silently suspends an unattended agent loop. Shift/Ctrl+Enter POSTs to `/api/sessions/:id/send-key` (`{key:'S-Enter'|'C-Enter'}`, tmux `send-keys -H` for a real 0x0a) targeting THIS pane's own `sessionId` rather than the primary pane's `activeSessionId` — without it xterm's plain `\r` would submit an incomplete prompt instead of adding a line to it. Smart-copy Ctrl+C/Ctrl+Shift+C is re-implemented against `this.terminal` (Pane B's own) rather than reusing `app.copyTerminalSelection()`, which reads Pane A's terminal and would copy the wrong pane's selection; Ctrl+Shift+C never falls through even with nothing to copy, mirroring terminal-ui.js's own `ev.shiftKey` branch. ⚠️ **This is a UX-parity fix, not an interrupt-safety one** — verified live in a real browser: xterm's `evaluateKeyboardEvent` routes a shifted ctrl-letter into a branch that assigns `c.key` only for two special cases (`_`→US, `@`→NUL), so it emits no data for Ctrl+Shift+C at all regardless of any application gate; a synthetic keydown with the gate removed produces zero WS frames, proving no accidental interrupt reaches the PTY either way. What gating the whole copy block on `hasSelection()` (an earlier draft) actually cost: with no selection, a selection-less Ctrl+Shift+C fell straight to `return trLine truncated
+
 ### Gesture control: the setting
 
 **Gesture control** (the camera hand-tracking overlay) is **opt-in, default OFF**, under App Settings → Terminal & Input → Scrolling & rendering (`gestureControlEnabled`). `CODEMAN_GESTURE=1` makes the feature _available_ on the instance (CSP widening + `/gesture/` assets) and sets `window.__codemanGestureAvailable` (the Input section only shows when set); the overlay bundle is injected by `renderIndexHtml` **only when the setting is enabled**, so that method is `async` and reads `settings.json` via `readSettings(true)` — the `true` forces a **fresh** read (bypassing the 2s `_settingsCache`), because a post-save reload happens within that TTL and the cached value would otherwise render the pre-toggle state. Toggling the setting reloads the page (the bundle is render-injected).
@@ -436,6 +816,158 @@ Anatomy: `.set-shell` → `.set-shell-head` (title + `.set-head-actions`) + `.se
 
 **The hinge is a reserved region, and the CSS is inert by construction.** The CSS Viewport Segments media features report two segments only while a foldable is actually bent; `--fold-inline-end` / `--fold-block-end` (end of styles.css) measure the strip to keep clear from the LEADING segment (`env(viewport-segment-right 0 0)` and `env(viewport-segment-bottom 0 0)`, physical sides in every text direction) and are `0px` on everything else. The seven centred overlays are all `position: fixed; inset: 0` flex boxes; each shrinks its CONTENT box with padding rather than the box itself, so the backdrop still covers the far side of the fold and still swallows taps there. The cascade traps, each measured in headless Chromium against styles.css + mobile.css in index.html link order: (1) a later `padding-right` longhand beats the earlier `padding` shorthand it composes with, so each fold rule re-states the overlay's own gutter; (2) a base gutter that a LATER `@media` block overrides needs its own fold restatement in that block on a ZERO base, since the unconditional rules at the end of the file otherwise put the gutter back (the phone path picker and path preview drop to `padding: 0` under 600px and came back at 16px and 18px on every phone); (3) a compound rule written to outrank a mobile.css shorthand must be scoped to the band where that shorthand applies, because outside it there is no gutter to compose with (the palette's `.modal.command-palette-modal` added 0.75rem at 393, 900 and 1400px and pushed the shell 6px off centre, and inside the band it lost its bottom gutter to the shorthand until it restated that side too); (4) mobile.css loads AFTER styles.css, so a same-specificity rule there wins under its own breakpoint (the response viewer's `max-height: 92dvh` under 600px beat the tabletop cap, which now has a twin at the end of mobile.css). `test/foldable-layout.test.ts` DERIVES the overlay list from the stylesheet, simulates the cascade across both files at every breakpoint with and without the fold rules, and requires the two results to differ by exactly the fold strip, so each of the four fails there instead of on hardware nobody has.
 
+Further detail: the design follows Apple's [Designing for iPhone Duo](https://developer.apple.com/design/human-interface-guidelines/designing-for-iphone-duo). The sticky keyboard latch survived until the device was opened again, and rotating any phone hit it too. ⚠️ Physical sides, not logical ones: dialogs sit in the LEFT segment (the TOP one in tabletop pose) in every language, because the HIG keeps Duo's side controls on the same physical edge in RTL. The palette needs the compound `.modal.command-palette-modal` because mobile.css loads later and pads it with a shorthand under 768px; its compound rule lives INSIDE the 600-768px band whose mobile.css shorthand it composes with. The fold measurements were taken at 393 and 500px widths. Device profiles: `iPhone Duo (outer)` / `iPhone Duo (inner)` in `test/mobile/devices.ts`; unit coverage in `test/viewport-shape-change.test.ts`.
+
+### Terminal touch gestures: link taps and text selection
+
+**Terminal touch gestures: link taps and text selection**: on a touch device xterm's own handlers see neither — `touch-action: none` plus touchstart's preventDefault suppress the browser's compatibility mouse events, `_installMobileTapMouseGuard` drops the trusted ones that still arrive, and the synthetic `mousedown`/`mouseup` pair dispatched for mouse REPORTING goes to the `.xterm` root, an ANCESTOR of the screen element the linkifier and SelectionService listen on. So both gestures are driven explicitly.
+
+⚠️ **A tap activates the link under it** through the SAME provider that feeds the hover linkifier (`_terminalLinkAtPoint`, containment mirroring xterm's `_linkAtPosition`), synchronously inside `touchend` — that is what keeps the user gesture `window.open` needs — and BEFORE any mouse report, mirroring `_handleDesktopTerminalClick`'s skip for a hovered link. Two rows keep their meaning: the caret's logical line (`_tapIsOnCaretLine`, where a tap places the cursor in text the USER typed) and TUI-owned rows (`_isActionableMobileTerminalTap`, answering a dialog).
+
+⚠️ The caret line is the boundary rather than the tap INTENT, because a shell classifies every tap as `'input'` and gating on that would leave every URL in shell output inert.
+
+⚠️ **Long-press selects** by driving xterm's public `select()` (renderer-independent — under WebGL the glyphs are pixels and native selection cannot exist), drag or a further tap extends, and Copy goes through `copyTerminalSelection()` for its execCommand fallback on plain-HTTP installs. Three guards are load-bearing and each came from a real phone: the compat mouse pair after `touchend` (xterm focuses on mousedown and SelectionService resets the model there, so the keyboard sprang up and the selection vanished on lift), the platform's own ~500ms long-press (Android Chrome focuses the nearest editable element — the helper textarea — through no event a handler can preventDefault, so a bounded focus guard blurs it and `contextmenu` is suppressed for the gesture window), and `copyTerminalSelection()`'s closing `terminal.focus()` (right on desktop, wrong on a phone).
+
+Tests: `test/terminal-touch-tap.test.ts`.
+
+### Entrance animations
+
+**Entrance animations** (`entrance-animations.js`, all OFF by default): opt-in animations for the four things that appear when work starts, chosen per surface via `data-tab-anim` / `data-term-anim` / `data-win-anim` / `data-line-anim` on `<html>`. Defaults are the `legacy` theme, so an untouched install behaves exactly as before and every hook short-circuits on its first line. Persisted to its own `codeman:*Anim` localStorage keys (per-device, deliberately NOT in the `.strict()` `SettingsUpdateSchema`); picker in App Settings → Appearance, full per-surface lab at `?animlab=1`.
+
+⚠️ Tabs and connection lines are **destroyed mid-animation** on every re-render (`_fullRenderSessionTabs()` replaces the strip's innerHTML; `_updateConnectionLinesImmediate()` does `svg.innerHTML = ''`), so both are tracked by id and re-applied to the fresh element with a **negative `animation-delay`** to resume rather than restart.
+
+⚠️ The terminal-pane styles may animate **transform / opacity / clip-path only**, xterm's FitAddon derives rows+cols from `getComputedStyle(parent).width/height`, so animating width/height/padding there would resize the PTY; `test/entrance-animations.test.ts` pins that property allowlist, plus the rule→keyframes→theme-option chain a style silently does nothing without.
+
+⚠️ **`blur` is the ONE style that puts a `filter` on the terminal container**, against the standing rule, because every alternative was measured against a live xterm and does not work: a `backdrop-filter` veil on `::before` blurs perfectly while STATIC and Chrome silently drops the backdrop the moment ANY animation runs on that pseudo-element (the veil computes `blur(15.3px)` and the text behind it stays razor sharp), and driving the radius from rAF buys the same full-screen blur per frame plus main-thread work. The cost the rule exists to avoid is inherent to blurring a terminal, so the style buys it knowingly: opt-in, OFF by default, one ~520ms run per session open, class straight back off, `will-change` still unset. Worst-case price, headless SwiftShader with no GPU: frame deltas 16.7ms → 33.3ms for the run, against 16.7ms flat for `fade`. Do not generalise it — a second filtered terminal style needs its own measurement.
+
+⚠️ The `blur` connection line animates `filter` too, so both kinds of line hold their glow in **`--line-glow`** and both of its keyframes say `blur(N) var(--line-glow)`: the function lists then match and interpolate, instead of the glow vanishing for the run and popping back (a lineage line's glow is a different colour entirely, set per element). Its 100% frame deliberately omits `opacity` so the endpoint comes from the element's own resting value — 0.9 subagent, 0.72 lineage, 0.95 working — which is what `line-enter-fade`'s hardcoded 0.9 gets wrong.
+
+⚠️ Window styles other than `beam` transform the window, which moves the rect its connection line is aimed at; `beam` deliberately animates opacity/filter only so its line can draw toward a stable target.
+
+### Mobile tab strip scrolling
+
+**Mobile tab strip scrolling** (issue #257): under 768px the tab strip is a horizontal scroller (desktop wraps to a second row instead), so the active tab can sit off-screen. Three rules keep it reachable and they only work together: `_updateActiveTabImmediate()` scrolls the selected tab into view via `computeTabScrollLeft()` (pure, in constants.js) using **rect math on the strip's own `scrollLeft`**, never `scrollIntoView()`, which would also scroll the document under a fixed header; `_fullRenderSessionTabs()` **restores `scrollLeft`** across the `innerHTML` rebuild, since ambient rebuilds (a task badge appearing, a session created elsewhere) otherwise snap a mid-swipe strip back to 0; and it re-reveals the active tab **only when it changed** (`_lastRenderedActiveTabId`), so browsing the far end of the strip is not undone by background renders.
+
+⚠️ **The ACTIVE tab is the only one with action icons, and on a phone they can eat it**: `.session-tab.active .tab-name` reserves `min-width: 44px` in the phone block (under 600px), because a short session name rendered a 13px label against a 50px gear+close cluster, putting the tab's geometric CENTRE on the gear, so a thumb aiming at the tab opened Session Options instead of switching (measured at 360/393/430px; only long names cleared it).
+
+⚠️ **The floor is set by the 10th tab onward, not by the tabs you can see**: `.tab-number` renders only for `_tabIdx < 9`, so tab 10 loses 16px + a gap off its left and its centre sits 10px further right. The centre clears the icons when `reserved > icons + rightEdge - leftRunUp - gap` (= 50 + 9 - 17 - 4 = **38px**), hit-testing snaps to whole pixels so 39px still lands on the gear, and the practical floor is 40px — a NUMBERED tab clears it at 20px, which is exactly why reasoning from the tabs on screen would put the centre back on the gear. `test/mobile-tab-tap-zones.test.ts` recomputes that inequality from the stylesheet, so widening the gear or the padding fails there rather than on a phone. The guarantee is centre-off-the-ICONS, not centre-inside-the-label (on a numberless tab it lands in the gap between them, which still switches). Non-active tabs keep their icons hidden and stay tappable end to end.
+
+⚠️ Mobile no longer hoists the active session to the front of the strip: that reordering ran on full renders only, so tab order flipped depending on which render path fired, and it renumbered the Alt+N badges. Scroll-into-view replaces it; do not reintroduce it.
+
+### Phone overview home screen
+
+**Phone overview home screen** (`mobile-overview.js`, phones only, per-device `mobileOverviewEnabled`, default ON): under 600px the "C" logo shows a session overview (NEEDS YOU / CURRENT SESSIONS / PAST SESSIONS) instead of the welcome overlay; tablet and desktop are unchanged. The branch lives in `showWelcome()`/`hideWelcome()` (terminal-ui.js) behind `shouldUseMobileOverview()`, which is **width-driven** (`getDeviceType() === 'mobile'`) because this is a layout decision, unlike the settings namespace which stays handheld-based.
+
+⚠️ The container ships with the `hidden` attribute and only this module removes it: never give `.mobile-overview` a bare `display` rule, since desktop does not load `mobile.css` (`media="(max-width: 1023px)"`) and would then render it unstyled. Live re-renders ride on the tail of `_renderSessionTabsImmediate()` (every state change it needs already funnels there); PAST rows come from one `_fetchUnifiedSessions(60)` per home-screen visit and resume through the shared `resumeHistorySession()`, so they behave exactly like the welcome screen's Resume list.
+
+⚠️ Two things must stay in lockstep with surfaces outside this module, because divergence reads as a bug rather than a style: the split Run button carries the **toolbar's own classes** (`btn-toolbar btn-run mode-<backend>` / `btn-run-gear`) so the per-backend gradient and the light-skin overrides apply unchanged (mobile.css must therefore set no `background`/`color` on it), and row status uses the **session-tab language** (green dot when fine, `pulse` while working, yellow blinking row when waiting for input, red blinking row when a question is pending, mirroring `tab-alert-idle`/`tab-alert-action`). The picker mirrors the toolbar run-mode menu (`setRunMode()` + `run()`, `openWebviewFromMenu()` for saved dashboards) and deliberately omits its Recent-Sessions block, since PAST SESSIONS is that. Status pills carry `data-i18n-skip` (generic words like "idle" collide with state strings elsewhere).
+
+### Desktop home tab rail
+
+**Desktop home tab rail** (`home-sessions.js`, desktop only): the welcome overlay centers ~560px of content in a ~1400px window, so its left gutter is dead space; it carries the open tabs as a rail **docked flush to the left edge, full height** (a vertically centered card floating mid-gutter read as debris). Rows are in **overview order** (see Home-screen session order), and each carries a **created** stamp plus the **state duration** the order is computed from (`created 3d ago · working 12m`, word and anchor from `_mobileOverviewSince()` so both home screens say the same thing). A rail sorted by a number it does not show reads as arbitrarily shuffled, and a working row's plain last-active stamp always says "just now".
+
+⚠️ The number badge is the **Alt+1..9 index**, i.e. the position in the TAB STRIP, so on a sorted rail it deliberately does NOT run 1,2,3 downward: it names a shortcut, not a row position, and renumbering it to look tidy would make every badge lie. State classification is REUSED from mobile-overview.js (`_mobileOverviewState`/`_mobileOverviewCaseFor`), which is why the module loads after it.
+
+⚠️ The rail is `position: absolute` so the centered content never moves, which is exactly why it needs a **width gate in two places** — `HOME_SESSIONS_MIN_WIDTH` (1180) in the JS plus a `max-width: 1179px` media query as the backstop for a resize that outruns the matchMedia listener; drift between them means a rail overlapping the search panel, and `test/home-sessions.test.ts` pins them equal. ⚠️ `.home-sessions` is `display: flex`, so `[hidden]` must be re-asserted as `display: none` or the module's only visibility lever does nothing. ⚠️ Size scales with the viewport off **one knob**: `width: clamp(250px, 19vw, 430px)` plus a fluid `font-size` on `.home-sessions`, with every child sized in `em` — reintroducing `rem`/px type inside the block silently breaks the scaling, and widening the clamp past the gutter reintroduces the overlap the gate exists to prevent.
+
+The age stamps are refreshed **in place** by a 20s clock (`_tickHomeSessionsTimes()`, disarmed in `hideHomeSessions()`), never by re-rendering, which would restart every row's blink and working ring. Working state is deliberately byte-identical to the phone's: pulsing green dot + the `tab-load-spin` ring reused from the tab strip + the same green halo (added to `.mobile-overview-dot--working` at the same time), so "working" reads the same on every surface; **idle** is deliberately NOT that green — dot and pill mix toward `--text-muted` so a glance separates running from sitting. Live re-renders ride the tail of `_renderSessionTabsImmediate()` alongside the phone overview.
+
+### Home-screen session order
+
+**Home-screen session order** (`CodemanSessionOrder` in constants.js, pure + unit-tested in `test/session-overview-order.test.ts`): BOTH home screens (phone overview and desktop rail) order rows through this ONE comparator, because they list the same sessions and must answer "which of these wants me next?" the same way. Rank is `needs` → `error` → `waiting` → `working` → `idle` → `done`.
+
+⚠️ **The tiebreak flips direction halfway down**: states a session is still IN sort **oldest-first** (blocked longest / running longest = most urgent), states it has STOPPED in sort **newest-first** (the session that just went quiet is the one you came back for).
+
+⚠️ The running group keys off **`lastSubmitAt`** (the pane's last Enter), never `lastActivityAt`: a working Claude pane repaints about once a second, so its last-activity stamp is always "now" and would rank every running turn as freshly started. A working pane with no submit stamp falls back to last activity, which lands it at the SHORT end of the group rather than falsely leading it.
+
+⚠️ A **0 stamp means "unknown", not "the epoch"**, and it sorts last within its state either way, or a brand-new session would head every oldest-first group. Final tiebreak is the user's tab order (`orderIndex`), so the list is deterministic and cannot shuffle between renders. The tab strip itself is NOT sorted by this; it stays user-ordered and drag-reorderable.
+
+### Terminal font weight
+
+**Terminal font weight** (`terminalFontWeight` / `terminalFontWeightBold`, per-device, default = xterm's own `normal`/`bold`): bold text on the theme's default foreground carries exactly ONE cue, the weight step. Claude Code marks its markdown bold with a bare `ESC[1m` and no colour change, and xterm substitutes a bright colour for bold only when the foreground is a palette index 0-7, so the substitution never fires there. A two-face family keeps that step small and 400 stays 400 whatever family is chosen, which is why the NORMAL slot is settable at all. `CodemanTerminalFont.resolveWeights()` (constants.js, pure) resolves both slots, each against **its own** xterm default, so an unset bold weight can never inherit `normal`.
+
+⚠️ **The `@font-face` descriptor, not the file, is what the browser synthesizes from**: `fonts/jetbrains-mono-variable.woff2` carries a `wght` axis of 100-800, and while `styles.css` declared it `400 700` every weight below 400 rendered identically to 400 and 800 identically to 700 — measured — so the setting was a no-op for anyone without Fira Code or Cascadia Code installed, which is most installs. It is declared `100 800`; re-narrowing it silently guts the feature (`test/terminal-font-weight.test.ts` pins the range).
+
+⚠️ A live save must reach **both echo overlays** (`refreshFont()` — they cache `terminal.options.fontWeight` and paint it into their spans, so typed characters otherwise keep the old weight, most visible on a phone) **and open Agent Teams panes** (they read their options at construction, exactly like `applyTerminalSkin()` propagates).
+
+⚠️ `_awaitTerminalFont()` is deliberately untouched: `CharSizeService` measures through the CSS `font` shorthand, which RESETS the weight, so the measured face is always the 400 one and a weighted descriptor would ask for nothing new.
+
+### Shell keyboard accessory bar and one-shot Ctrl
+
+**Shell keyboard accessory bar + one-shot Ctrl** (issue #262, `keyboard-accessory.js`): a **shell**-mode session automatically swaps the mobile accessory bar for terminal controls (Ctrl, Esc, Tab, four arrows, paste, dismiss); every other mode keeps the agent bar. `setMode()` now records the user's `extendedKeyboardBar` preference as the **base** layout and `refreshForActiveSession()` (called from `selectSession`) resolves base-vs-shell, so a settings save during a shell session cannot yank the bar away and switching back restores the user's choice.
+
+⚠️ **Ctrl is a ONE-SHOT modifier applied in `terminal.onData`, not in a keydown handler**: a virtual keyboard emits no usable key events, so the character only exists as onData text. The hook sits AFTER `shouldSuppressTerminalQueryResponse` (xterm answers DA/CPR through onData too, and one of those would silently spend the modifier) and BEFORE every send path, so the control byte follows the normal control-char route.
+
+⚠️ **Not every onData chunk is a keystroke**, and the query filter is not enough on its own: xterm ALSO emits mouse and focus reports on its own initiative, so the hook skips them via `isTerminalFocusOrMouseReport()` (they still reach the PTY, they just don't count as the next key). The mouse half is live — a shell session keeps the NARROW strip, so mouse DECSETs reach the browser and one tap while vim/htop runs spent the armed modifier silently (measured). The focus half is defense in depth: `FOCUS_ESCAPE_FILTER` in `session.ts` strips `\x1b[?1004h` from every PTY read, so `sendFocusMode` never turns on today; if it ever did, the bar's own post-key refocus would emit `\x1b[I` and eat the modifier before the user typed.
+
+⚠️ It must disarm on ALL of: use, second tap, any other accessory key, session switch, keyboard dismissal, and a layout swap; a modifier left armed turns the next innocent keystroke into a control byte.
+
+⚠️ **onData is not the only input path** — with `cjkInputEnabled` on, the CJK textarea owns the keyboard (onData returns early for everything it swallows, and the focus router sends `terminal.focus()` there, which is where the bar refocuses after every key), so `_handleCjkInput()` applies the modifier too. It is that module's single choke point to the PTY, so one call covers typed characters, IME flushes, Enter, backspace and arrows. Without it an armed modifier could neither fire NOR be spent, and survived to a later keystroke.
+
+Mapping is `ctrlByteFor()` (`code & 0x1f` over @A-Z[\]^_ and a-z, plus Ctrl+Space=NUL / Ctrl+?=DEL); characters with no control equivalent pass through unchanged, like a hardware keyboard.
+
+⚠️ The armed style is `.accessory-btn.accessory-btn-ctrl.armed` (0,3,0) in BOTH stylesheets, and it cannot outrank mobile.css's light-skin repaint at **(0,3,1)** (`:is()` inherits its most specific argument, and that list holds `.btn-toolbar.btn-shell`) — so that rule excludes the state by hand as `.accessory-btn:not(.armed)`. Without the exclusion the armed button renders identically to a resting one on all four light skins, which is worse than no armed style at all.
+
+### Mobile prompt composer
+
+**Mobile prompt composer** (PR #444, the first slice of #359, `keyboard-accessory.js`): the agent bars' Paste key is now **Compose**, a dialog with a native multiline textarea (autocorrect, autocapitalize, spellcheck) where Enter adds a line and only **Send** submits; the shell bar keeps the direct Paste dialog, since shell input is not an agent prompt. Opening it ADOPTS the whole editable terminal prompt (`_takePendingLocalEcho`): the local-echo overlay's pending text has never reached the PTY, but the flushed prefix has, so that prefix is erased with backspaces counted in CODE POINTS (`Array.from(text).length`; measured on Claude Code 2.1.278, `a` + emoji + `b` takes three, and the UTF-16 count sent four and ate the neighbour; `clearTerminalInput()` in terminal-ui.js moved with it).
+
+⚠️ **Drafts are per-session and in memory only** (`_composerDrafts`, never persisted: prompts routinely carry secrets, and persisting them would need the 0600 treatment the intent store gets). Every non-Send exit (Cancel, backdrop, Escape, "Use terminal keyboard") leaves the taken text ONLY in the draft, with the dot on the key (`has-draft`, kept in step by `_syncComposerDraftIndicator`) as the signal that the terminal prompt is empty on purpose, and `_cleanupSessionData` discards the draft with the session.
+
+⚠️ **Delivery is a hand-built bracketed-paste frame** (`\x1b[200~` + the text with newlines mapped to `\r` + `\x1b[201~`, byte-identical to what `terminal.paste()` would emit) through `_sendInputAsync` WITHOUT `{ useMux: true }`, plus a SEPARATE Enter 120 ms later WITH it (codex drops keys that share a PTY read with a bracketed paste). Not `terminal.paste()`, for two reasons: xterm's `bracketedPasteMode` mirror is false for every session after a tab switch or reload (`terminal.reset()` in the replay re-clones the DEC modes, the tmux capture carries no `?2004h`, and tmux never forwards the pane's DECSET to a client after attach), so a paste through xterm would go out unbracketed and the CLI would submit at the first `\r`; and xterm's onData is where the local-echo paste branch flushes pending overlay text AHEAD of the block, text the composer has already taken and erased from the PTY, so the frame goes straight to the wire with the composer as the prompt's only owner. The unconditional frame is safe for a CLI that never enabled DECSET 2004 because tmux does the gating (measured against a live pane: markers stripped for a `cat -v` pane, forwarded intact to a process that had emitted `?2004h`).
+
+⚠️ The frame must never take the mux fallback: `TmuxManager.sendInput()` strips every `\r` and `\n`, which welds the lines together and submits them.
+
+⚠️ The size guard sits on the `MAX_INPUT_LENGTH` boundary (64 KiB of UTF-16 code units): `ws-routes.ts` drops a longer frame WITHOUT an ACK, which would wedge the durable queue, so `_composerMaxLength` is derived from that limit minus both markers and an oversized prompt stays a draft with a toast.
+
+⚠️ `.prompt-composer-overlay` is a `.paste-overlay` with a gutter of its own (a `padding` shorthand whose bottom is 12px plus the safe area), and the unconditional `.paste-overlay` fold rule at the end of styles.css is a later longhand at the same specificity, so it ERASED that gutter (measured at 393x852: `padding-bottom: 0px` flat, and the hinge strip REPLACING the gutter with the fold variables set): the composer has its own restatement after the fold rules, the dialog's `max-height` subtracts `--fold-block-end`, and `test/foldable-layout.test.ts` lists the composer in `ELEMENTS` by hand, because its derived overlay list keys on rules that declare `position: fixed; inset: 0` themselves.
+
+Tests: `test/mobile-prompt-composer.test.ts` (in the CI gate, deliberately not under `test/mobile/**`).
+
+### Dismissing the on-screen keyboard
+
+**Dismissing the on-screen keyboard** (PRs #279/#280, `terminal-ui.js`): the terminal parks focus on a hidden textarea that nothing used to release, so TWO gestures now blur it, and they own different regions.
+
+**(1)** `_installMobileKeyboardDismiss()` — a document-level `touchend` that fires only while the terminal input actually holds focus, **never inside `#terminalContainer`** (tap classification owns that) and **never on a control** (`MOBILE_KEYBOARD_DISMISS_EXEMPT_SELECTOR`, matched with `closest()` so an icon inside a button counts). Session tabs are covered by the selector's `[tabindex]:not([tabindex="-1"])` arm, which is what stops a tab tap from blurring and then being re-focused by `selectSession()`.
+
+**(2)** In `_handleMobileTerminalTap`, a second tap on **inert `content`** (`startedWithTerminalFocus`) blurs instead of re-focusing. ⚠️ Scoped to `content` on purpose: the prompt row (`input`) keeps focus-then-position so a second tap still places the caret, and actionable rows blur earlier via `_isActionableMobileTerminalTap`.
+
+⚠️ **A scroll ends in `touchend` too** — dismissing there closes the keyboard and drops the composer mid-read, so travel is tracked from `touchstart` and multi-touch is never a tap. Both classifiers MUST share one threshold: `initTerminal`'s `TAP_THRESHOLD` reads `MOBILE_KEYBOARD_DISMISS_TAP_SLOP`, since a gesture the terminal calls a scroll and the dismiss handler calls a tap is exactly that bug.
+
+⚠️ **The gate excludes `test/mobile/**`, so CI cannot see the only test covering (1)** — run `npm run test:mobile -- test/mobile/keyboard.test.ts` by hand and diff the FAIL list against master. (Not `npm test --`: the gate's config excludes that path, so a file filter pointing into it matches nothing and exits green having run zero tests.) That blind spot is why merging the two PRs, which conflicted semantically but not textually, produced a red suite with two green CI checks.
+
+### SSE staleness watchdog
+
+**SSE staleness watchdog** (`computeSseStale()` in constants.js, `_checkSseStale()` + a 5s interval in app.js): an `EventSource` that stops delivering does not always error, so `onerror` never fires, the header dot stays green, and every SSE-driven surface (tab status dots, sessions created on another device, renames) freezes until the user reloads.
+
+⚠️ The 15s server keepalive was an SSE **comment** (`:keepalive`), and comments are **invisible to `EventSource` by spec**, so there was nothing a client could observe: it is now the named `sse:heartbeat` event (`cleanupDeadClients()`, sse-stream-manager.ts), which is exactly why the frame had to change type.
+
+⚠️ Staleness is judged **only while the status is `connected`** and the device is online; that guard is the loop breaker, since a forced `connectSSE()` leaves `connected` immediately and cannot re-fire while a reconnect is in flight.
+
+⚠️ The liveness stamp is applied inside `addListener` itself, so every registered handler (the `_SSE_HANDLER_MAP` wrappers AND the directly-registered ones) feeds it from one place; the heartbeat's own listener is a no-op that exists **only** to be registered, since `EventSource` drops named events nobody listens for.
+
+⚠️ The watchdog interval is cleared at the top of `connectSSE()` and nowhere else (its only teardown path); clearing it elsewhere stacks intervals. Recovery needs no new sync path: the reconnect re-runs `handleInit` → `_resetAllAppState()`. The forced reconnect logs one diagnostic line, because a middlebox that strips heartbeats presents as "silently reconnects every 45s".
+
+### PTY and browser terminal geometry
+
+**The PTY and the browser terminal must never disagree about size** (issue #464, `syncTerminalGeometry()` in terminal-ui.js): Claude Code's TUI wraps its frame at the width the PTY reported and erases the previous frame by walking the cursor up the number of rows it BELIEVES that frame occupied. A browser terminal of a different width makes each logical line take more physical rows than Ink counted, so `eraseLines(n)` clears too few and the new frame paints over rows nothing erased — the doubled lines and half-overwritten prose in #464, **measured** against this repo's xterm (a 120-column PTY against a 62-column terminal renders every wrapped line twice; `test/terminal-pty-geometry.test.ts` pins it, and pins the clean render at matching widths so the assertion cannot pass against code that fixes nothing). ⚠️ **`fitAddon.fit()` is NOT the way to resize this terminal.** It resizes xterm to `proposeDimensions()` RAW while every server-facing path reports those floored at 40x10, so whenever the floor bit the two diverged silently — **measured in Chrome at 430px**: font size 44 proposed 13 columns, the server was told 40, and xterm stayed at 13. `syncTerminalGeometry()` fits, floors and applies as one step and is the ONE function that may change the size; `test/terminal-pty-geometry.test.ts` sweeps the seven modules that touch the main terminal (terminal-ui, mobile-handlers, app, ralph-panel, settings-ui, tab-rail-resize, notification-manager) for a bare fit; the split pane and teammate terminals own their own sizing and are out of scope. ⚠️ **Withhold the fit wherever you withhold the SIGWINCH.** `throttledResize` (virtual keyboard up) and `sendResize` (session detached into its own window) used to reflow locally and skip only the server write, which is the one combination that cannot be right. ⚠️ **A font change is a geometry change**: `setFontSize`/`setFontFamily`/`setFontWeight` move the cell size and told the server nothing, so raising the font on a phone left the CLI wrapping at the old column count (`_refitAfterCellSizeChange`). ⚠️ **Resize is no longer write-only.** `Session.resize` DECLINES a small-viewport request while a desktop connection holds an active sizing claim and says nothing, so both transports now answer with `Session.ptyGeometry` (`{"t":"zc"}` on the socket, the body of the resize POST) and `_onPtyGeometryReport` adopts it — a terminal that keeps a WIDTH the PTY refused renders GARBLED, not merely wrong-sized. ⚠️ While that refusal stands (`_paneWidthRefused`), a resize ASKS for the container's width without applying it (`_geometryForResizeRequest`: rows follow the container, columns stay at the PTY's): fitting first re-wrapped the whole buffer to the container and back on every 30s mobile retry, and ran the scrollback clear for a resize that brings no redraw. `selectSession` clears the flag, since it belongs to the previous pane. ⚠️ **`ptyGeometry` is null without a live pane**, never the field values: they are seeded at spawn (`_notePtySpawnGeometry`, so a reattached pane reports its tmux window's real size) and moved by `resize()`, but a dead-pane session still holds the constructor defaults of 120x40 or a gone pane's size — reporting those made a client adopt a size no process was ever told and claim another device owned the pane when none existed. ⚠️ **COLUMNS ONLY.** Adopting the PTY's ROWS was a regression: a phone taking a desktop's 43 rows into a viewport with room for 18 painted an `.xterm-screen` far taller than its container, xterm's own viewport then had nothing to scroll, and the CLI's input line sat below the container with no gesture able to reach it — output visible, typing invisible, for as long as the claim stayed hot. Width is the axis the wrap arithmetic depends on; rows only decide how much is on screen, and keeping the local count keeps the composer at the bottom of a viewport that scrolls. ⚠️ **`.term-overflows-x` keys on what does not FIT, not on a PTY mismatch**, because the 40-column floor widens the terminal past a narrow container with the PTY agreeing throughout (measured at 360px: font 18 paints 433px, font 24 paints 578px — 38% unreachable, and `increaseFontSize` reaches 24 in two taps). `_syncTerminalOverflowAffordance()` MEASURES `.xterm-screen` against the container on the next frame rather than deriving it from cell arithmetic. ⚠️ That rule sets **both** overflow axes — mobile.css loads later with `.terminal-container { overflow: visible }`, and a bare `overflow-x` would leave overflow-y computing to `auto`, handing the browser a vertical scroll container the terminal's touch handler does not know about — and sets **no `touch-action`**: the terminal's own touchmove handler pans it (`canPanHorizontally`), because `touchstart` preventDefault()s every 'content' tap and that cancels a native `pan-x` before it starts (measured: a 140px swipe reached scrollLeft 141 without that preventDefault and 0 with it).Line truncated
+
+### Terminal resilience: replay clears, renderer liveness, fetch deadlines
+
+**Terminal resilience: replay clears, renderer liveness, fetch deadlines**: three rules that each close a way the terminal silently stops being correct. ⚠️ **A replay clear MUST be in-stream, never `reset()`/`clear()`.** xterm's `write()` is asynchronously queued while `Terminal.reset()` is synchronous and, per upstream, "does not clear input buffers and does not reset the parser" — so bytes queued just before a reset are parsed AFTER it and fuse into the snapshot written next. **Measured** against the real xterm in this repo: `write('p8'); reset(); write('rmissions')` renders `p8rmissions`; the queued `\x1bc` renders `rmissions` and clears scrollback. `_resetTerminalForReplay()` (app.js) is the ONE clear, a single queued `\x1bc` (RIS), and all three replay paths go through it; RIS rather than `\x1b[3J\x1b[H\x1b[2J` because the erase leaves modes, charsets, scroll regions and SGR state alone. Callers may still chunk the content — ordering in the queue is what matters, not writing it in one call. ⚠️ **The renderer watchdog reads xterm privates and CANNOT be covered by the gate.** `_kickRenderer()` (terminal-ui.js) cancels a stale `_core._renderService._renderDebouncer._animationFrame` and forces a repaint. **Verified against xterm 6.0.0** (jsdom, after `open()`): the field path resolves, a forced stale handle genuinely makes `refreshRows` a no-op, and the kick schedules a fresh frame. **Reasoned, not reproduced here**: the premise that iOS discards scheduled rAF callbacks when a PWA backgrounds, which is what leaves the handle stale — that half wants a real-device pass. Codeman has exactly ONE xterm for the whole page load, so one backgrounding would wedge it until a reload. `_renderService` only exists after `open()`, which needs a real DOM, and the gate runs in node — so `test/xterm-private-api.test.ts` pins the RESOLVED lockfile version (not the `^6.0.0` range, which a real upgrade slips through) and a bump means re-verifying by hand. Every access is optional-chained on purpose: a renamed field must degrade to a no-op, never throw on a 2s timer. ⚠️ **Every terminal capture carries a deadline, and the helper reads the BODY** (`_fetchTerminalCapture`, app.js). `await fetch()` settles on response HEADERS, so clearing the timer there leaves the body — the multi-megabyte `?full=1` capture this exists for — unbounded: **measured** at 4026ms under a 1000ms deadline before the fix. The helper therefore returns `{json, headers, headersAt}` rather than a `Response`, and `_terminalCaptureInflight` is scoped the same way so a body still streaming counts toward a capture starting beside it. It degrades to a plain fetch where `AbortController` is missing — the deadline is a safety net, not a dependency. Tests: `test/terminal-resilience.test.ts` (pure decisions), `test/xterm-private-api.test.ts`.
+
+### WebSocket output-gap reconcile
+
+**WebSocket output-gap reconcile** (`_wsOutputGapSession`, app.js): terminal OUTPUT frames carry no sequence number (input frames do — `seq`+`cid`, at-most-once, ACKed), so a dropped socket leaves a hole nothing replays. ⚠️ **The gap is narrower than "the device went offline"**: if the network drops, SSE drops with it and `handleInit`'s keepTerminal branch already calls `_onSessionNeedsRefresh`. The uncovered case is the WS dying while SSE stays up (half-open socket, proxy idle-timeout, ping timeout), because `_onSSETerminal` discards every SSE terminal frame while `_wsReady` is true and `_wsReady` only flips in `ws.onclose`. Reaching `onclose` at all means the drop was unintentional (`_disconnectWs` nulls the handler first), so the session is marked and the next successful open reconciles. ⚠️ **The marker must be cleared by every path that repaints that session's buffer, and ONLY once one actually has.** `_markTerminalBufferReconciled()` is called from `selectSession` after its load, from `_cleanupSessionData`, and from `_onSessionNeedsRefresh` **at the repaint itself, not in its `finally`** — clearing on every exit meant a reconcile that threw, or hit the fetch deadline (the flaky link the marker exists for), dropped the gap with nothing to retry it. `ws.onopen` no longer clears it up front either, so a reconcile that is skipped or fails is tried again on the next open; re-entry is safe because `_terminalRefreshOwner` makes a second reconcile for the same session a no-op. `selectSession` loads the buffer and only THEN calls `_connectWs`, so without that clear the socket opening afterwards replays the whole buffer a second time on top of the one just written. Sequencing the output frames is the real fix and is not done. This is reasoned from the code path, not observed on a device.
+
+### Service worker precache and cache key
+
+**Service worker: precache and cache key are BUILD-GENERATED** (`sw.js` + `scripts/build.mjs`): the build content-hashes assets and rewrites two exact declarations in `sw.js` — `const BUILD_ID = 'dev';` and `const HASHED_ASSETS = [];`. ⚠️ **Each must appear exactly once or the build THROWS**, which is deliberate: the list used to be hand-maintained with PRE-hash names, so every entry 404'd in production and `cache.add().catch(() => {})` hid it (15 of 23 verified failing against a running instance). The dev literals are valid on their own, so dev serves an unrewritten worker with an empty precache. ⚠️ **`caches.match` must pass `ignoreSearch: true`**: `renderIndexHtml` runs `cacheBustAssets`, which appends `?v=<mtime>` to every same-origin `.js`/`.css` reference INCLUDING content-hashed names, so the page requests `/app.<hash>.js?v=<mtime>` while the cache holds `/app.<hash>.js`. Without it no precached entry is reachable and the install downloads ~1.3MB that can never be served — once per deploy, since `CACHE_NAME` now carries the build id. That per-build key is what makes `activate`'s cleanup actually delete anything; it used to be the constant `'codeman-v1'`, so assets from every past release accumulated forever. Contract pinned by `test/sw-precache-manifest.test.ts`, which PARSES the `HASHABLE` list out of `build.mjs` rather than copying it.
+
+### Z-index layers
+
+**Z-index layers**: subagent windows (1000), split picker menu (1000, `.split-picker-menu`), plan agents (1100), mobile/tablet fixed header (1200, `mobile.css`), modals on ≤768px (1300 — must beat the fixed header or the modal close button is buried), log viewers (2000), connection-loss overlay (2500, above the fixed header and modals), image popups (3000), response viewer (5000, backdrop 4999), file-preview overlay (5100 — must outrank the response viewer, which can launch it; at its old 2000 a path clicked in the chat opened BEHIND the chat), toasts/path picker (10000+, deliberately above the preview), the custom-model center-status banner (10001, `.center-status-banner` — `[hidden]` must re-assert `display: none` over its own `display: flex`, same trap as `.home-sessions[hidden]`, or `dismiss()` leaves an invisible click-blocker dead centre on screen), the swap-confirm and context-warning modals (10010, `#customModelSwapConfirmModal`/`#customModelContextWarningModal` — must clear both the plain `.modal` z-index of 1000 and the center-status banner it can appear over), terminal touch-selection bar (900 — above terminal content and the local-echo overlay, deliberately BELOW floating agent windows so it can never cover their controls), local echo overlay (7).
+
 ## Security layers
 
 ### Layer-by-layer detail
@@ -460,6 +992,16 @@ Anatomy: `.set-shell` → `.set-shell-head` (title + `.set-head-actions`) + `.se
 
 Target: 20 sessions, 50 agent windows at 60fps. Limits in `src/config/`: terminal 32MB (see below), text 1MB, messages 1000, max agents 500, max sessions 50, max SSE clients 100. **Terminal history** (`src/config/terminal-history.ts`, COD-80): tmux history-limit 100k lines, PTY buffer 32MB max / 24MB trim (env `CODEMAN_MAX_TERMINAL_BUFFER`/`CODEMAN_TRIM_TERMINAL_TO`; the env-derived trim is clamped ≤75% of max — trim ≥ max would disable `BufferAccumulator` trimming entirely = unbounded memory); browser xterm scrollback stays a separate hardcoded 50k (`DEFAULT_SCROLLBACK` in constants.js — 100k/tab is a mobile-memory hazard). tmux <3.7 allocates history at pane creation, so `createSession()` sets the global default in the same command queue immediately before `new-session`; tmux 3.7+ instead creates the session and targets only that pane, because changing the global option can resize and trim unrelated live panes. A settings change resizes tracked panes only on 3.7+ and otherwise affects future panes; no version can recover lines already evicted. Settings keys `terminalScrollbackLines`/`terminalBufferMaxBytes`/`terminalBufferTrimBytes` are schema-validated but inert (only `tmuxHistoryLimit` is wired); `buffer-limits.ts` re-exports the defaults. Text/message limits are env-overridable too (`CODEMAN_MAX_TEXT_OUTPUT`/`CODEMAN_TRIM_TEXT_TO`/`CODEMAN_MAX_MESSAGES`). **Image upload** (`image-input.js` / `config/buffer-limits.ts`): up to `_maxBatchImages` 20 images/batch (bounded concurrency 3), per-file `MAX_PASTE_IMAGE_BYTES` 50MB (env `CODEMAN_MAX_PASTE_IMAGE_BYTES`); the mobile camera-roll picker auto-downscales to fit before upload. **HEIC paste uploads** (#151): converted server-side to JPEG in a `worker_threads` worker (`web/heic-jpeg-worker.ts`, resourceLimits + 30s timeout) gated by `runWithConversionLimit()`; detection is magic-byte based (covers Android/MIUI HEIFs mislabeled as JPEG); headers declaring > 64MP are rejected 415 BEFORE decode (decompression-bomb guard). Deps: `heic-decode` + `jpeg-js`. Use `LRUMap` for bounded caches, `StaleExpirationMap` for TTL cleanup. Anti-flicker pipeline: `docs/terminal-anti-flicker.md`.
 
+### Process-tree walks are bounded
+
+**Process-tree walks are bounded** (`proc-tree.ts`, pure + unit tested): `collectDescendants(pid, byParent)` is the ONE descendant traversal, fed by a single cached `ps -eo pid=,ppid=` snapshot (`refreshProcSnapshot()` in tmux-manager.ts: in-flight-shared, async because `execSync`'s timeout cannot return at all while spawnSync waits on an unkillable child, and ANY error discards the result rather than caching a truncated `ps`, which would make whole subtrees invisible to the kill path).
+
+⚠️ **The unbounded version took a machine down** (2026-07-30): it ran `pgrep -P <pid>` once per node and recursed with no visited set, no depth limit and no node cap, so across ~28 adopted tmux trees the fan-out exploded while each `pgrep` blocked in the WSL kernel reading `/proc/<pid>/cgroup`, ending at ~13,000 `pgrep` processes in D-state, a load average above 13,000, and a machine recoverable only by restarting WSL, which cost every running session. Three properties make that impossible and each has a test: a cycle terminates (a real tree has none, a stale snapshot can still produce one), depth is capped (`PROC_WALK_MAX_DEPTH`), node count is capped (`PROC_WALK_MAX_NODES`). The fourth is structural: the function takes a snapshot and cannot spawn anything at all.
+
+⚠️ It lives in its own module because as a private method of `tmux-manager.ts` the regression test had to keep its own COPY of the algorithm, which is a test that passes while the shipped code rots.
+
+⚠️ Truncation is reported through `onTruncated` rather than silently, with BOTH caps named: a silent depth cap hides a deep tree exactly as effectively as a silent node cap hides a wide one.
+
 ## Local packages and build artifacts
 
 ### xterm-zerolag-input is single-source
@@ -481,3 +1023,35 @@ The repair is a **chmod, not a rebuild**: the prebuilt binary is fine. `scripts/
 ### Headless screenshot capture
 
 **Headless screenshots: `deviceScaleFactor` MUST be 1, and write unique filenames** — `scripts/capture-real-overview.mjs` (drives a live session in headless Chromium → overview PNG). Two traps, both observed 2026-06-14: **(1) DSF=2 doubles the console font.** xterm's WebGL renderer draws terminal glyphs at ~2× their nominal size under `deviceScaleFactor: 2`, while STILL reporting nominal cell dims (`terminal.cols`/`_renderService.dimensions.css.cell` say 8px/187cols — they lie), so it's invisible to any internal measurement and only the pixels reveal it. The HTML chrome (header/toolbar) is unaffected → ONLY the console font looks comically large. Default to **DSF=1** (script does); the image is 1× res but the font is true-to-browser. **(2) Stable filenames → stale renders.** Overwriting a fixed path (`claude-overview.png`) in place leaves OS image viewers (eog/feh) — and any HTTP client behind a long/`immutable` cache — showing the OLD render; the user reads it as "the fix didn't work". The script now mints a timestamped `claude-overview-<ts>.png` per run. ⚠️ This was a LOCAL image-viewer cache, NOT a Codeman serving bug: `file-routes` previews send `Cache-Control: no-cache` and `/api/screenshots/:name` sends none. The one real Codeman-side footgun: `server.ts` serves non-content-hashed static assets `public, max-age=31536000, immutable`, and `cacheBustAssets()` only rewrites `.js`/`.css` refs — a stable-named **image** referenced from public/ would go stale on overwrite. Reflect the per-device UI to match a real device when capturing: seed `localStorage` `codeman:skin`, `codeman-font-size`, and the desktop `codeman-app-settings` blob (the plan-usage chip is a per-device display key deleted from the server payload — a fresh browser hides it unless seeded; close side panels for a full-width terminal).
+
+### Test isolation: tmux, docker and HOME
+
+**Tmux safety**: under vitest (`VITEST` env var, set automatically), `TmuxManager` no-ops ALL shell commands and becomes a pure in-memory mock — tests physically cannot create/kill/attach real tmux sessions (`IS_TEST_MODE` in `src/tmux-manager.ts`). Every docker IO path is no-op'd the same way. `Session` is test-gated too: instead of attaching a real tmux client, it spawns a raw-mode echo PTY (`TEST_PTY_SCRIPT` in `src/session.ts`), so integration tests get a live input/output loop that echoes each byte exactly once.
+
+`test/setup.ts` gives every test file a temporary `HOME`/`USERPROFILE` (all `homedir()`-derived state, `~/.codeman` and `~/codeman-cases` included, resolves into a per-file fixture; the Playwright browser cache path is preserved), and additionally strips `CODEMAN_PASSWORD`/`CODEMAN_USERNAME` (so auth state from the running instance can't leak into tests) and `CODEMAN_GESTURE` (a shell-exported gesture flag would flip render-injection assertions), and strips the three instance-selection vars `CODEMAN_INSTANCE`/`CODEMAN_DATA_DIR`/`CODEMAN_TMUX_SOCKET` (#356/#371; `test/test-env-isolation.test.ts` pins the list, and its STATIC half reads setup.ts so a dropped `delete` fails everywhere rather than only on a box that exports the var).
+
+⚠️ `CODEMAN_DATA_DIR` is the one that matters: `getDataDir()` reads it as an ABSOLUTE override before it ever looks at `homedir()`, so one inherited from the shell (a second instance, a beta run, a shell left over from `codeman web -d`) bypasses the temp HOME entirely, and a bare suite run once overwrote the real `remote-hosts.json` with a route test's fixture. `os.homedir()` itself DOES follow `$HOME`, so the temp HOME is what redirects everything else; `CODEMAN_INSTANCE` must be stripped in the setup file and never in a hook, because `config/instance.ts` captures it into a module-level const on first import.
+
+Tests that delete case trees go through `safeRmHomeTree()` (`test/mocks`), which refuses any path outside the temp HOME, so a wrong anchor leaves a temp dir behind instead of deleting `~/codeman-cases`.
+
+⚠️ Raw `npx vitest` without `--config` skips `setup.ts` and with it the temp-HOME isolation.
+
+### install.sh: the public installer
+
+**`install.sh`** (repo root) is the public entry point: `curl -fsSL <raw url> | bash` installs Node/tmux/git/build tools if missing, clones to `~/.codeman/app`, builds, and offers a systemd/launchd service. Since installer v2 (2026-09-20) it is **look, ask, work, done**: `preflight_detect` prints what is on the machine, every human step runs BEFORE the build (one consent for all missing packages, ONE sudo prompt kept warm by `sudo_session_start`, the AI CLI menu, the Tailscale login/operator/HTTPS-toggle preflight), then the clone/`npm install`/build/service/serve run unattended behind `run_step` spinners (output in `~/.codeman/install.log`, tail shown on failure), and `print_done_screen` ends on the URL with a terminal QR code (the `qrcode` package Codeman already ships). Design + verification record: `docs/installer-v2-plan.md`.
+
+The network-access question is 3-way: **Tailscale** (loopback bind + `tailscale serve`, curl-verified end-to-end), **LAN** (0.0.0.0 + password prompt), or **local-only**; it preserves the existing binding on re-runs via `read_existing_binding()`, which also reads back `CODEMAN_BASE_URL`/`CODEMAN_PORT` from the unit, and the flag/env PRESET paths keep an existing password too (`${CODEMAN_PASSWORD:-$EXISTING_PASSWORD}`: `--lan --service` on a password-protected unit used to rewrite it open with the unauthenticated ack, found in review 2026-09-21); `--password`/`--port` flip `RECONFIGURE` so they reach the unit instead of taking the quiet update path.
+
+⚠️ The env a hand-started `codeman web` needs (host, password, ack, base URL, port) is composed in ONE place, `start_command_hint` for the done screen's Start line and `export_bind_env` for main()'s `exec` branch, so the two cannot disagree; `stop_background_helpers` runs right before that `exec`, because exec skips the EXIT trap and the sudo keepalive (keyed on `$$`, which becomes the server's pid) would otherwise refresh the sudo timestamp for the server's whole life. Ctrl+C in the HTTPS-toggle poll is trapped for the poll only and skips Tailscale for the run rather than killing the installer.
+
+⚠️ **Tailscale is two halves on purpose**: `tailscale_prepare` (question phase: preflight, the opt-in rename, the serve SHAPE) and `tailscale_apply` (after the build: the one serve command). The shape is decided up front because it can change the service unit: when `:443` root already belongs to another app, the default is a **sub-path** (`tailscale serve --bg --set-path /codeman <port>` + `CODEMAN_BASE_URL=/codeman` in the unit; measured 2026-09-20: serve STRIPS the mount prefix before proxying, Codeman's `stripBasePath` tolerates unprefixed requests, and `--base-url` is what makes the emitted URLs carry it, verified live through the maintainer's tailnet incl. hashed assets and SSE), else a second port (8443+), replace, or skip. `detect_tailscale_serve_url` recognises all three shapes (`ts_serve_find_port_mapping`).
+
+⚠️ **Rename is opt-in and defaults to NO everywhere** (owner decision 2026-09-20: the tailnet name is the machine's SSH identity); `--name`/`install.sh name` do it, `--yes` and non-interactive never do. Serve config is keyed by the DNS name it was written under, so `tailscale_rename_node` takes OUR mapping down first (`tailscale_remove_our_mapping`, `TS_MAPPING_REMOVED_BY_RENAME`) and it is re-added under the new name; the previous name is recorded in `~/.codeman/tailscale-rename` so uninstall can offer it back. Tailscale state is detected dynamically from `tailscale serve status --json` (no marker files); the installer must NEVER `tailscale serve reset`, touch a mapping it did not create, run `tailscale funnel` or advertise a Tailscale Service (a Service needs a TAGGED node + admin approval, so it is a docs hint only); `test/install-sh-invariants.test.ts` pins all of those plus the rename-before-shape order and the flag/header parity.
+
+A foreign `/Library/LaunchDaemons/com.codeman.web.plist` (the Mac mini's headless setup) is now LEFT ALONE rather than replaced by a LaunchAgent. Subcommands: `update`, `uninstall`, `tailscale` (retrofit), `name [<n>]`, `status` (the done screen again), `cloudflared` (the tunnel client, no longer a question in the main flow); flags `--tailscale|--lan|--local`, `--name|--no-rename`, `--service|--run|--no-start`, `--yes`, `--password`, `--port` pipe through `bash -s --` and set the same variables as their env twins (`CODEMAN_NONINTERACTIVE=1` approves system changes for automation and never installs Tailscale, renames or starts a service; `CODEMAN_TAILSCALE=1` presets the Tailscale choice).
+
+Its CLI knowledge is a GENERATED block (`npm run generate:cli-catalog`, markers in the file), not a hand-written list: detection, the install menu and the closing reminder all read it, which is what stops the class of bug upstream `b6d0f1fa` fixed by hand (a user with only omp installed being told no AI CLI was found).
+
+⚠️ It must stay **bash 3.2** clean — macOS ships it and the documented install is `curl | bash` under `set -euo pipefail`, so `declare -A`, `mapfile`, namerefs, `${x,,}` and here-strings are all fatal there; CI runs `bash -n` plus a real `bash:3.2` container, since expanding an EMPTY array under `set -u` is a runtime abort `bash -n` cannot see.
+
+⚠️ It executes ONLY commands from the embedded block (`CLI_INSTALL_CMD_TRUSTED`) — there is no network fetch of the catalogue at install time to worry about at all.

docs/cli-enable-disable-plan.md

@@ -0,0 +1,314 @@
+# CLI management Settings UI + write API — plan
+
+> Tracked separately from `DEPLOYMENT_PLAN.md` (PR B2, merged) and `docs/copilot-integration-plan.md`
+> (parked). This is "PR C" from the original #343 review: *"settings UI + write endpoints +
+> auto-install, once we've settled the trust model... I want to make that call on its own, not
+> inside a 100-file diff."*
+>
+> **Phase 0 is CLOSED as of 2026-09-21** — all three original pieces are IN SCOPE (expanded from
+> this plan's first draft, which recommended #2/#3 as separate/out-of-scope; the user chose full
+> scope instead, with the risk called out explicitly for #3 before confirming). See "Decisions"
+> below for the full record.
+
+## Status as of 2026-09-22
+
+**Phases 1–6 are ALL IMPLEMENTED** (commits `da07b38c` "add cliManagementEnabled flag and GET
+/api/clis" and `db4557d9` "Phases 3-6 - write API + custom entries + Settings UI", both on this
+branch, `feat/cli-management`). Confirmed present in the tree: `cliManagementEnabled` in
+`SettingsUpdateSchema`; `GET /api/clis`, `PUT /api/clis/:id`, `POST /api/clis/:id/install`,
+`POST /api/clis`, `PUT /api/clis/custom/:id`, `DELETE /api/clis/:id` in
+`src/web/routes/cli-registry-routes.ts`; the `shell`/`claude` `UNDISABLEABLE_IDS` backend guard;
+`isAdmin(req)` gating on both the list and write routes; `appendAdminAudit` wired into the install
+route; tmp+rename+`0o600` writes in `registry-writer.ts`; the full Settings UI (row list, toggle,
+Install button, custom-entry create/edit/delete form) in `settings-ui.js` + `index.html`.
+`test/routes/cli-registry-routes.test.ts` (425 lines) and `test/cli-registry-no-id-branching.test.ts`
+cover it. This status section, plus the fix and gap below, is the one piece of that work done in
+a *different* session from the one that wrote Phases 1–6 — reviewed by reading the diff and
+verifying each claim against the actual routes/tests, not by re-implementing anything.
+
+### Gotcha found and fixed (commit `0c77dd0a`)
+
+**Toggling a CLI off in Settings had no effect anywhere except the Settings row itself.**
+`window.__codemanCliAvailable` — the flag `isCliAvailable()` reads client-side to gate the
+welcome-screen buttons, the Run-menu dropdown and the mobile overview — is injected **once**, at
+initial page render (`server.ts`), built purely from each CLI's own installed-on-PATH resolver
+(`isClaudeAvailable()` etc.), with **no reference to the registry's `enabled` flag at all**. So
+disabling a CLI here updated its own row and nothing else — every launch surface kept offering it,
+both live and after a full page reload, since even a *fresh* render never consulted the registry.
+Root-caused and reported by the user testing the live feature ("toggle those off, they still
+appear in that menu and on the front main screen").
+
+Fixed two places:
+- `server.ts`: after building `available`, intersect the nine real `SessionMode` ids against
+  `enabledClis()`. `git`/`cloudflared` (utility binaries, not CLI registry entries) and
+  `deepseekBinary` (a secondary installed-only flag for the "add a profile" affordance) are
+  deliberately left alone — they were never registry-gated to begin with.
+- `settings-ui.js`: `toggleCliEnabled()` now patches `window.__codemanCliAvailable` in place and
+  refreshes the welcome screen, the mobile overview and an already-open Run menu, mirroring the
+  existing `installDeepSeekProfile()` pattern for the same "injected once, needs an explicit
+  patch" reason — the server-side fix alone still left every surface stale until the next reload.
+
+New test in `test/render-index-html.test.ts`: an installed-but-disabled CLI (codex, forced via
+`clis.json` + `reloadCliRegistry()`) reads as unavailable, while an installed-and-enabled one
+(claude) is unaffected by the override.
+
+**Verified on the Debian devbox** (`codeman-devbox`, real tmux — this sandbox has none and
+`WebServer`'s constructor hard-requires it): typecheck clean, the new test passes (17/17 in
+`render-index-html.test.ts`), the CLI-registry suites pass (86/86), and the **full CI gate is
+green — 415 test files, 7855 tests, 0 failures**.
+
+### Launch-surface registry integration — completed
+
+The welcome screen, desktop Run menu and mobile Run picker now use the same injected CLI catalog.
+Every enabled registry entry is rendered; unavailable binaries remain hidden as before. Settings
+updates the catalog and availability flags in place after enable/disable, create, edit or delete,
+so the launch surfaces update without a page reload. A custom entry uses the generic quick-start
+path, while stock entries retain their existing per-CLI launch settings.
+
+Not otherwise re-verified line-by-line against every Phase 1–6 checklist item below (e.g. the
+exact wording of toasts, the "same PR" sequencing notes) — the checklists are left as originally
+written; treat the **Status** section above as authoritative for what exists.
+
+---
+
+## Background
+
+`src/config/cli-registry/registry.ts` is READ-ONLY today, and says so in its own header comment:
+
+> "⚠️ READ-ONLY. Nothing in this module writes, creates or migrates the file... there is no
+> settings UI and no write API yet... A `seededStockIds` ratchet belongs with the write API that
+> needs it."
+
+Confirmed on `master` (2026-09-21): no `/api/clis` route exists at all (read or write);
+`~/.codeman/clis.json` is hand-edit-only; `resolveInstallCommandForPlatform()` is documented
+"Display text only — never executed" — nothing runs an install command server-side today. The
+original #343 review flagged the opposite (`spawn(command, {shell: true})`, `env.allowedPrefixes`
+contributed from a write) as needing its own trust-model decision; that decision was never made
+after the split, just dropped. This plan makes it.
+
+**Closest existing precedent, and the template this plan follows for the read/write API**:
+`src/web/routes/custom-model-routes.ts` + `src/custom-model-hosts.ts` (#393/#430/#459) — a small
+per-item JSON store, Settings-UI-driven, admin-gated in multi-user mode, tmp+rename+0600 writes.
+
+**Precedent for the new master feature flag (Phase 1)**: `customModelEndpointsEnabled` —
+`z.boolean().optional()` in `SettingsUpdateSchema` (`schemas.ts:1319`), a checkbox read/written by
+id in `openAppSettings()`/`saveAppSettings()` (`settings-ui.js:401`/`:2120`). SYNCED, not
+per-device (present in the schema, absent from `displayKeys`), default OFF.
+
+**Spec refs for the whole plan:**
+- `src/config/cli-registry/registry.ts` — the read path; `resolveRegistry()`'s merge semantics
+  (`deepMerge`, `UNMERGEABLE_KEYS`) apply unchanged to whatever this plan writes
+- `docs/cli-registry.md` — registry shape, "The override file", "Arg-template safety" (the four
+  layers Phase 5's custom-entry validation must not weaken), "Adding a CLI" (the 5-step recipe a
+  custom entry does NOT get to skip just because it arrives via UI instead of a stock.ts edit)
+- `src/web/routes/custom-model-routes.ts` + `src/custom-model-hosts.ts` — read/write API template
+- `docs/multi-user-plan.md`, `docs/security-architecture.md` — admin-gating conventions
+- `CLAUDE.md` §Multi-user mode, §"Settings surface", §"Per-device vs synced settings"
+
+---
+
+## Decisions (Phase 0, closed 2026-09-21)
+
+1. **Enable/disable a stock CLI's `enabled` flag** — IN SCOPE. Plus a **master feature flag**
+   (`cliManagementEnabled`, synced, default OFF) gating the whole Settings UI section's visibility,
+   matching this codebase's standing convention for new admin-facing surfaces.
+2. **Auto-install** (stock CLIs' already-shipped, already-vetted install commands) — IN SCOPE,
+   same PR.
+3. **Custom CLI entries via the UI** — IN SCOPE, **typed-argv only**: a custom entry goes through
+   the exact same schema/argv-safety path stock entries do (named token patterns, no raw shell-text
+   field). Its install command stays **display-only text**, same as every stock entry today — Phase
+   4's auto-install NEVER executes a custom entry's install command, only a stock one's. This is
+   the one place scope was deliberately narrowed relative to what was agreed in principle, because
+   `docs/cli-registry.md`'s arg-template-safety section exists specifically to keep config free of
+   shell text, and a free-text install command for a user-defined entry would reopen exactly that.
+4. **`shell`/`claude` un-disableable** — enforced at the **backend**, not just the UI (a
+   frontend-only guard is bypassable with curl).
+5. **Non-admin visibility in multi-user mode** — the CLI-management Settings section is **hidden
+   entirely** for a non-admin, not shown-empty.
+6. **`seededStockIds` ratchet** — not needed. `deepMerge()` only overrides a key the file actually
+   sets, so a CLI absent from `clis.json.clis` always falls through to its stock `enabled` value
+   with no special-casing. (Carried over from the first draft, not re-litigated.)
+
+---
+
+## Phase 1 — Master feature flag: `cliManagementEnabled`
+
+**Status:** DONE (commit `da07b38c`) — verified present in `SettingsUpdateSchema`, `index.html`,
+`openAppSettings()`/`saveAppSettings()`.
+
+**Spec refs:**
+- `schemas.ts:1319` (`customModelEndpointsEnabled`) — the exact pattern to mirror: `z.boolean().optional()`
+  in `SettingsUpdateSchema`
+- `settings-ui.js:401`/`:2120` — checkbox read/write by id in `openAppSettings()`/`saveAppSettings()`
+- `CLAUDE.md` §"Adding Features" → "App setting" — decide per-device vs synced FIRST (this one is
+  synced: a feature toggle, not a display preference) and add to `displayKeys` NEVER for a synced
+  setting
+
+**Checklist:**
+- [x] Add `cliManagementEnabled: z.boolean().optional()` to `SettingsUpdateSchema`
+- [x] Add the checkbox to `index.html`'s `#settings-clis` section, above where Phase 6's per-CLI
+      list will render — reads/writes via `openAppSettings()`/`saveAppSettings()` by id, same as
+      `customModelEndpointsEnabled`
+- [x] `readCliManagementEnabled()` helper (mirrors `readCustomModelEndpointsEnabled()` in
+      `custom-model-routes.ts:609`) for the route file(s) in Phases 2-5 to gate on
+- [x] When OFF: `GET /api/clis` still exists but the Settings UI section stays hidden
+      (`applyCliManagementVisibility()`); the write endpoints reject (see Phase 3)
+
+**Verify:** `npm run typecheck` passes; a unit test confirms `SettingsUpdateSchema` accepts/rejects
+the field correctly; toggling it in a fresh browser profile shows/hides the Settings section with
+no server restart.
+
+---
+
+## Phase 2 — Read endpoint: `GET /api/clis`
+
+**Status:** DONE (commit `da07b38c`) — verified present in `src/web/routes/cli-registry-routes.ts`.
+
+**Spec refs:**
+- `src/web/routes/custom-model-routes.ts:730` (`GET /api/model-endpoints`) — multi-user read
+  gating: empty list for a non-admin, never a 403
+- `src/config/cli-registry/registry.ts` — `listClis()` (every entry, including disabled stock
+  ones — this is an admin/settings surface, unlike `enabledClis()`)
+- `window.__codemanCliAvailable`'s resolvers (`isClaudeAvailable()` etc.) — candidate `installed`
+  source; confirm whether to reuse directly or the response needs its own probe (Open Question 4,
+  carried from the first draft — still genuinely open, decide during this phase not before)
+
+**Checklist:**
+- [x] New route file `cli-registry-routes.ts`
+- [x] Response excludes `launch`/`env`/`capabilities`/`overlays`/`discovery`
+- [x] `isMultiUserMode() && !isAdmin(req)` → `[]`
+- [x] Unit tests in `test/routes/cli-registry-routes.test.ts` (admin/non-admin/single-user,
+      disabled stock CLI still present)
+
+**Verify:** `npm test -- test/routes/cli-registry-routes.test.ts` passes; `curl localhost:3000/api/clis | jq`
+shows every stock CLI including disabled ones.
+
+---
+
+## Phase 3 — Write endpoint: `PUT /api/clis/:id` (stock enable/disable)
+
+**Status:** DONE (commit `db4557d9`) — `UNDISABLEABLE_IDS`, admin gate, tmp+rename+0600 all
+confirmed present.
+
+**Spec refs:**
+- `src/web/routes/custom-model-routes.ts:753` + `src/custom-model-hosts.ts:91` — write-path
+  template: `adminOnly` gate, read-modify-write the WHOLE file, tmp+rename+0600
+- `registry.ts:47` (`filePath()` = `dataPath(...)`) and `reloadCliRegistry()` — write to the same
+  resolved path, invalidate the cache on every successful write or the change is invisible until
+  restart
+
+**Checklist:**
+- [x] Body: `{ enabled: boolean }`. Zod schema in `schemas.ts`
+- [x] Gate order: `cliManagementEnabled` → `adminOnly` → shell/claude guard → stock-only guard
+- [x] Rejects disabling `shell` or `claude` (`UNDISABLEABLE_IDS`)
+- [x] Rejects a write for an id that isn't a stock CLI
+- [x] Deep-merges `{ clis: { [id]: { enabled } } }`, preserving other override keys
+- [x] tmp+rename+0600 write, `reloadCliRegistry()` on success
+- [x] Unit tests (`test/routes/cli-registry-routes.test.ts`)
+
+**Verify:** `npm test` full gate green; `curl -X PUT localhost:3000/api/clis/grok -d '{"enabled":false}'`
+then `GET /api/clis` shows the change with no restart; same against `shell`/`claude` returns an
+error and changes nothing; `ls -la ~/.codeman/clis.json` shows mode 0600.
+
+---
+
+## Phase 4 — Auto-install: `POST /api/clis/:id/install` (stock CLIs only)
+
+**Status:** DONE (commit `db4557d9`) — route present, `appendAdminAudit` wired in.
+
+**Spec refs:**
+- `registry.ts:231` (`resolveInstallCommandForPlatform`) — currently "Display text only — never
+  executed"; this phase is what changes that, for stock entries only, with Decision 2's sign-off
+- Original #343 review's exact concern re: `env.allowedPrefixes` contributed from a write — stays
+  out of scope; this phase only ever runs a command, never touches the env allowlist
+
+**Checklist:**
+- [x] Separate endpoint from Phase 3's toggle
+- [x] Gate order: `cliManagementEnabled` → `adminOnly` → stock-entry-only guard
+- [x] `resolveInstallCommandForPlatform(entry)` for the target
+- [x] Bounded execution (timeout, captured stdout/stderr)
+- [x] Does NOT auto-enable on successful install
+- [x] Audit-logged via `appendAdminAudit`
+- [x] Unit tests
+
+**Verify:** a real install triggered via the endpoint against a CLI not currently installed,
+`GET /api/clis`'s `installed` field flips true with no restart; audit log entry present; attempting
+install against a custom entry's id fails with a clear error; full CI gate green.
+
+---
+
+## Phase 5 — Custom CLI entries: create / update / delete via API
+
+**Status:** DONE (commit `db4557d9`) — `POST /api/clis`, `PUT /api/clis/custom/:id`,
+`DELETE /api/clis/:id` all present. Open Question 2 resolved: a **separate** endpoint
+(`PUT /api/clis/custom/:id`), not Phase 3's `PUT /api/clis/:id` widened.
+
+**Spec refs:**
+- `docs/cli-registry.md` §"Arg-template safety" (all four layers), §"Adding a CLI" (the 5-step
+  recipe) — a custom entry created via this API must satisfy the SAME schema (`CliEntrySchema`)
+  every stock entry does; there is no relaxed path for UI-originated entries
+- `registry.ts`'s `resolveRegistry()` — the custom-entry branch (`stock: false`, dropped with a
+  warning on validation failure, never falls back silently) already exists and is unchanged by
+  this phase; this phase only adds a way to WRITE what that branch reads
+
+**Checklist:**
+- [x] `POST /api/clis` (create), full `CliEntrySchema` validation
+- [x] `PUT /api/clis/custom/:id` (update) — separate endpoint from Phase 3's stock toggle
+- [x] `DELETE /api/clis/:id` refuses for any stock id
+- [x] `id` collision check against existing stock ids
+- [x] `discovery.install.command` on a custom entry stays DISPLAY-ONLY
+- [x] Same tmp+rename+0600 write pattern, `reloadCliRegistry()` on every successful mutation
+- [x] Unit tests
+
+**Verify:** `npm test` full gate green; create a custom entry via curl, confirm it appears in
+`GET /api/clis` — **confirm it appears in the Run menu is UNVERIFIED and currently FALSE, see
+"Outstanding" above**; delete it, confirm it's gone and `clis.json` no longer references it.
+
+---
+
+## Phase 6 — Settings UI
+
+**Status:** DONE (commit `db4557d9`) — `#cliListGroup`, row rendering, toggle, Install button,
+custom-entry create/edit/delete form all present in `settings-ui.js`/`index.html`. Manual browser
+verification per the phase's own "Verify" step (flag on/off, non-admin hidden, toggle stops the
+Run menu offering a CLI, create/enable/launch a custom entry, delete it, shell/claude undisableable)
+has **not** been re-run in this session — the toggle→Run-menu leg specifically was BROKEN until the
+gotcha fix above, and the create→launch leg for a custom entry is the confirmed gap in
+"Outstanding".
+
+**Spec refs:**
+- `index.html:2357` (`#settings-clis`) — the existing home; Phase 1's master toggle at the top,
+  then the per-CLI list, then (if `cliManagementEnabled`) a "custom CLI" creation form, all above
+  the existing Codex-only groups
+- `CLAUDE.md` §"Settings surface" — App Settings scrolls, it does not tab-switch
+- `admin-ui.js` — pattern for an admin-only-VISIBLE section (not just admin-only-writable),
+  needed here per Decision 5
+
+**Checklist:**
+- [x] Whole section hidden when `cliManagementEnabled` is OFF, and separately hidden for a
+      non-admin in multi-user mode (`_applyCliManagementAdminGate`)
+- [x] Fetches `GET /api/clis` when the section becomes visible; renders one row per CLI
+- [x] Stock rows: enabled toggle only; `shell`/`claude` rows show the toggle disabled/greyed
+- [x] Custom rows: enabled toggle plus edit/delete affordances
+- [x] "Add custom CLI" form (id/label/badge/binary/argv)
+- [x] Toggle/edit/delete update the row in place
+
+**Verify:** manual browser test per `CLAUDE.md`'s "Always Test Before Deploying" rule — **not yet
+re-run end-to-end in this session**; do this before considering the feature ready to ship, and
+expect the custom-entry-launch step to fail until the Outstanding gap above is closed.
+
+---
+
+## Remaining Open Questions
+
+1. **Phase 2's `installed` source** — resolved: reuses `window.__codemanCliAvailable`'s existing
+   resolvers via `GET /api/clis`'s own probe (confirmed by reading the route).
+2. **Phase 5's `PUT` endpoint shape** — resolved: a **separate** endpoint
+   (`PUT /api/clis/custom/:id`), not Phase 3's toggle route widened.
+3. **Sequencing against the parked Copilot plan** — unchanged, still not blocking.
+4. **NEW: custom-CLI Run-menu integration** — see "Outstanding" above. Not decided or started.
+
+---
+
+Implementation is underway (see Status above); this line is left for history rather than removed —
+the plan was originally approved before Phases 1–6 landed.

docs/cli-registry.md

@@ -18,7 +18,17 @@ Every run mode Codeman can launch — Claude Code, Terminal/Shell, OpenCode, Cod
 
 ## The override file
 
-`~/.codeman/clis.json` (instance-scoped through `dataPath()`) holds overrides and custom entries only, never a copy of the stock catalog: `{ "clis": { "<id>": { ...partial entry... } } }`. Objects merge key-wise onto the stock entry, arrays replace wholesale. **The file must be mode 0600**; the loader refuses any group/world permission bit, read bits included, so a file created with a normal umask (0644) is ignored until you `chmod 600` it. Every reason a file was ignored or an entry dropped is logged once, prefixed `[cli-registry]`, on the first load. A stock entry whose override fails validation falls back to the shipped definition; a custom entry that fails is dropped. The file is read once per process and re-read only on restart.
+`~/.codeman/clis.json` (instance-scoped through `dataPath()`) holds overrides and custom entries only, never a copy of the stock catalog: `{ "clis": { "<id>": { ...partial entry... } } }`. Objects merge key-wise onto the stock entry, arrays replace wholesale. **The file must be mode 0600**; the loader refuses any group/world permission bit, read bits included, so a file created with a normal umask (0644) is ignored until you `chmod 600` it. Every reason a file was ignored or an entry dropped is logged once, prefixed `[cli-registry]`, on the first load. A stock entry whose override fails validation falls back to the shipped definition; a custom entry that fails is dropped. The file is read once per process and re-read after a change made through CLI management (below).
+
+## Managing CLIs from Settings
+
+App Settings → Agents & CLIs → **CLI management** (`cliManagementEnabled`, default OFF; admin-only in multi-user mode) lists every entry with an installed/not-installed badge and:
+
+- toggles any entry on or off. A `kind: 'shell'` entry cannot be disabled, and the row shows no switch for it. A disabled CLI disappears from the Run menu, the welcome screen and the phone overview, and new session requests for it are rejected.
+- installs a missing **stock** CLI by running its shipped install command, after a confirm that names the exact command. Only one install per CLI runs at a time, and the command runs without any `CODEMAN_*` variable in its environment. A custom entry's install command is never executed.
+- adds, edits and deletes **custom** entries (id, label, badge, binaries, launch argv). The server re-validates the whole assembled entry through `CliEntrySchema`, so the form cannot bypass the load-time rules.
+
+These are the only writes to `clis.json`. They are serialized, and a file that does not parse or has unsafe permissions is refused rather than overwritten; fix it (or `chmod 600` it) and retry. The HTTP routes are listed in `docs/api-reference.md` under *CLI management*.
 
 ## The shape of an entry
 
@@ -36,7 +46,9 @@ interface CliEntry {
   launch: CliLaunch; // the structured argv template
   env: CliEnv; // exports, tmux setenv keys, the env-override allowlist
   capabilities: CliCapabilities; // what every call site reads instead of the id
-  //   .workDetect?: { promptGlyph, workingLine } — how this CLI's pane shows work
+  //   .workDetect?: { promptGlyph, workingLine, watchingLine?, watchingLines?, awaitingLine? }
+  //   — how this CLI's pane shows work, work it started in the background, and a turn
+  //   that ended waiting for workers it will resume from
   overlays: CliOverlays; // remote-SSH / Docker pane commands, credential store
 }
 ```
@@ -45,10 +57,61 @@ interface CliEntry {
 
 ### Regexes that come from config
 
-Two capability fields carry a regular expression an override file can set: `discovery.version.regex` and `capabilities.workDetect.workingLine`. Both go through `compileVersionRegex()`, which caps the source at 200 characters, refuses the nested-quantifier shapes that cause catastrophic backtracking, and returns `null` rather than throwing so every caller degrades instead of crashing.
+Four capability fields carry a regular expression an override file can set: `discovery.version.regex`, `capabilities.workDetect.workingLine`, `capabilities.workDetect.watchingLine` and `capabilities.workDetect.awaitingLine`. All four go through `compileVersionRegex()`, which caps the source at 200 characters, refuses the nested-quantifier shapes that cause catastrophic backtracking, and returns `null` rather than throwing so every caller degrades instead of crashing.
 
 `workingLine` is the one that matters most, because it is compiled once per session and then run against every accumulated PTY chunk and every pane capture. A nested quantifier there is a ReDoS against the event loop for the whole server, not just that session. The guard therefore runs in two places, and neither is redundant: `schema.ts` rejects the entry at LOAD time so a bad pattern never reaches a session, and `_workingLinePattern()` in `session.ts` compiles through the same helper so the runtime cannot end up with a pattern the schema would have refused.
 
+`watchingLine` reads a different row of the same screen. A CLI draws it while work the agent
+itself started is still running — Claude prints `⏵⏵ bypass permissions on · 1 monitor · ← for
+agents` while a monitor, a backgrounded shell or a cloud session is live. Codeman turns that
+into `Session.watching`, and an idle prompt from such a session opens already acknowledged,
+so a pane waiting for its own background work never raises an alert a human cannot answer.
+Group 1 is the label, and a CLI that declares no pattern reports no background work.
+Claude's Artifact comment monitor is the one chip that does not count. It waits for a human
+to comment on a page the agent published, so Claude's pattern refuses any footer that
+carries it, and the idle alert goes out as usual.
+
+Two CLIs declare such a row today, and they put it in different places. Claude writes its
+chip on the last row of the screen, so it keeps the default one-row window and anchors on
+the `·` its footer joins items with. Codex pins
+`1 background terminal running · /ps to view · /stop to close` ABOVE its composer, which
+puts the row third from the bottom once the status line and the composer are counted, so its
+entry declares `watchingLines: 3` and matches that row end to end. Both were measured
+against live panes rather than read out of a binary, which is the standard for adding a
+third.
+
+`awaitingLine` covers the quiet pane that is neither idle nor watching: a turn that ENDED
+to wait for workers the CLI will resume from by itself. When background agents or an
+ultracode workflow are still running at turn end, Claude closes the turn with
+`✻ Waiting for 1 dynamic workflow to finish` instead of `✻ Brewed for 1m 18s`, and a pane
+showing that row counts as working. ⚠️ Claude renders the row once and never redraws it, so
+the words are still on screen after the workers report back and the follow-up turn ends.
+The pattern is therefore never run over the whole pane: `isAwaitingWorkers()`
+(`session-activity.ts`) walks up from the composer past blank, framed and indented rows and
+tests only the first row that starts in column 0, which is the newest transcript row. Claude
+starts its own rows in column 0 and the agent's prose never does, so the anchor also keeps an
+agent from holding its own session busy.
+
+That label is the one value in the registry that an AGENT can influence, because it comes off
+the agent's own screen. Two things keep it honest, and both belong to whoever adds a pattern
+for a new CLI. `watchingLabel()` in `session-activity.ts` searches only the last few
+non-blank rows, which should be the part of the screen the CLI draws rather than the agent,
+and the pattern should anchor on chrome only that CLI can produce. Keep the window as small
+as the layout allows, since every row it adds is another row the agent may be able to write.
+The label is also ANSI-stripped and length-capped at the source, and every interpolation of
+it into markup goes through `escapeHtml()`, since it ends up on a badge and in an approval
+card.
+
+The two shipped entries do not sit equally well behind that rule, and the difference decides
+what a pattern is allowed to do. Claude's chip is the last row, so its one-row window holds
+nothing the agent can write — not even the status line above it, whose command a session
+running with permissions bypassed can write into its own `.claude/settings.json`. Codex's row
+shares its slot with the last row of the transcript whenever no terminal is running, so a
+message ending in that exact line is matched. What keeps that harmless is `hooks: 'none'`: no
+hook event from a codex session reaches the approvals inbox, so a forged label costs a wrong
+badge and cannot silence an alert. Before giving a CLI both hook signals and a pattern, make
+sure its row is one the agent cannot write.
+
 ### Three capabilities that must stay independent
 
 `external`, `hooks` and `altScreen` describe three different, deliberately unequal sets, and deriving any one from another has already shipped a bug. `shell` has no hooks but is **not** an external CLI, so a hooks predicate written as `!isExternalCliMode()` accepted `until=stop` on a shell session and then blocked the caller for their entire timeout. `deepseek` is the mirror image: it IS external and it DOES have hooks.
@@ -102,6 +165,8 @@ It matches four shapes, not one: `mode === '<id>'`, `mode !== '<id>'`, `case '<i
 
 The allowlist is not a formality. If a branch is about what a CLI can DO it belongs in `CliCapabilities`; the entries that remain are things that are not CLI-behaviour branches at all — chiefly the legacy per-mode `<Mode>Config` objects on `POST /api/sessions`, which are a fact about the public HTTP API rather than about any CLI, plus a few documented cases where `mode === 'claude'` is genuinely the right question (Read My Mind reads Claude's _own_ transcript, so a capability there would be actively wrong).
 
+`test/frontend-cli-no-id-branching.test.ts` is the same guard for the two frontend files the CLI registry's Run-menu consolidation touches, `session-ui.js` and `mobile-overview.js` — deliberately not the rest of `src/web/public/`, whose per-CLI rules stay out of scope for now (see "Fields declared for later" below). Its allowlist keys on `<file>::<expression>` with no line number, since a single unrelated edit to a contended file would otherwise shift every subsequent line and make every entry go stale at once, and each entry additionally carries the exact number of approved call sites — a bare key would let a brand-new branch reusing an already-approved expression land unreviewed. Its comparison shape differs from the backend guard's in one respect: the left-hand side may be any identifier, not only one named `mode`, `id` or `agentType`, because the review of #458 found `const m = this._runMode; if (m === 'codex')` slipping past the named form while the scanned file already filters with `(m) => m !== 'shell'`.
+
 ## Two namespaces called `param`
 
 `launch.params` keys, `env.configSetenv[].fromParam` and `capabilities.privilegedParams[].param` all name a **launch param**. The **legacy wire field** a param arrives as is a separate namespace, and `launch.legacyConfigAliases` is the only bridge between the two.
@@ -110,9 +175,9 @@ This matters because it is invisible when it is wrong. `capabilities.privilegedP
 
 ## Fields declared for later
 
-`shortBadge`, `accent`, `capabilities.echo`, `capabilities.wheelForward`, `capabilities.keyboardAccessory` and `capabilities.maxFrameBytes` are **declared but not yet read**. They all describe frontend behaviour, and the frontend is deliberately untouched here: `app.js`, `terminal-ui.js` and `styles.css` keep their own hand-authored per-CLI rules, and moving them is its own piece of work verified by a browser/mobile suite the CI gate cannot see.
+`accent`, `capabilities.echo`, `capabilities.wheelForward`, `capabilities.keyboardAccessory` and `capabilities.maxFrameBytes` are **declared but not yet read**. (`shortBadge` was on this list until the CLI management list in Settings started showing it.) They all describe frontend behaviour, and the frontend is deliberately untouched here: `app.js`, `terminal-ui.js` and `styles.css` keep their own hand-authored per-CLI rules, and moving them is its own piece of work verified by a browser/mobile suite the CI gate cannot see.
 
-Treat those values as **transcribed, not authoritative** — nothing enforces that `echo.policy` matches `_updateLocalEchoState`'s fallthrough, or that `accent` matches the gradient CSS paints, so re-measure before wiring one up. A field that is both wrong and unread is worse than an absent one, because the next reader trusts it; `test/cli-registry-no-id-branching.test.ts` pins the list so it cannot quietly grow, and wiring one up makes its line there fail, which is the direction you want.
+Treat those values as **transcribed, not authoritative** — nothing enforces that `echo.policy` matches `_updateLocalEchoState`'s fallthrough, so re-measure before wiring one up. `accent` is the one exception: it was measured against styles.css on 2026-09-21 (method in the comment above `CLAUDE` in `stock.ts`), though nothing keeps it in step with the CSS either. A field that is both wrong and unread is worse than an absent one, because the next reader trusts it; `test/cli-registry-no-id-branching.test.ts` pins the list so it cannot quietly grow, and wiring one up makes its line there fail, which is the direction you want.
 
 `overlays.credStore` is in the same category, for a sharper reason: the Docker credential-seeding path still reads its own `CRED_STORES` table, because this shape allows ONE store per CLI and the live table needs two for gemini (`.gemini` for the CLI's own auth plus `.config/gcloud` for Vertex), while deepseek declares none here even though `.dsh` is seeded. Wiring it means making the field an array and correcting those two entries — a change to credential seeding, which is simultaneously the worst thing here to get wrong and the least covered by tests, since every docker IO path is no-op'd under vitest.
 

docs/custom-model-endpoints.md

@@ -183,6 +183,34 @@ launch, with the endpoint's `defaultModelId` marked but not auto-chosen —
 the point of asking is letting one launch deliberately differ from the
 saved default, not just confirming it.
 
+The modal promotes exactly one row to the top of the list rather than
+always showing raw discovery order, so the zero-wait choice is the one
+under your thumb:
+
+- **"Currently loaded"** — a model from this host's own list that
+  llama-swap reports `ready` right now, queried via
+  `GET /api/model-endpoints/:id/running-status`. Bounded client-side to
+  ~800ms (`Promise.race`), on top of the route's own 5s server-side
+  timeout, so an endpoint that is asleep or firewalled cannot leave the
+  modal invisible for the full 5s after the Run menu has already closed.
+- **"Last used"** — shown only when nothing is currently loaded: the model
+  actually launched last for this exact (harness, endpoint) pair, read
+  from the per-device `codeman:customModelLastUsed:<mode>:<endpointId>`
+  localStorage key. Written by `_runCustomModelEntryViaRestart` (claude)
+  and `_quickStartWithCustomModelConfirm` (every one-shot launch; the
+  `runCustomModelEntry` entry point itself only dispatches between the
+  two) only once the model is actually applied, never on the mere click —
+  declining the context-window warning means this exact model cannot work
+  with this CLI at all, so promoting it next time would be actively wrong,
+  not just premature.
+
+Neither tag reorders anything past that one promoted row. The "Default"
+pill is a separate span, not a third value of the same slot: a promoted
+row that is also the endpoint's `defaultModelId` shows both tags (on a
+single-purpose GPU box that is the common case, and an exclusive slot
+silently dropped the Default marking for exactly that row), and a row
+with neither promotion nor default shows no tag at all.
+
 **How the launch itself applies the endpoint depends on the harness.** For
 opencode, Codex, Gemini, Pi, Grok, DeepSeek and OMP (`runCustomModelEntry` →
 `_runCustomModelEntryOneShot`), the endpoint/model is folded into the SAME

docs/deepseek-integration.md

@@ -53,7 +53,9 @@ that spawns a literal `pnpm` with no npm fallback, so without one it exits 127 w
 surfaces that same line as the install error. `npm install -g pnpm` (or
 `corepack enable pnpm`) is the fix. This is what broke the Docker agent image in
 [#352](https://github.com/Ark0N/Codeman/issues/352); the image now installs pnpm
-alongside `dsh`.
+alongside `dsh`. The Compose server image (`docker/server.Dockerfile`) does not
+ship `dsh`, since it is installed at runtime, but it does ship pnpm so the UI
+button works there too.
 
 Codeman's default is `@deepseek-harness-tui/dsh-tui` because it is by a wide
 margin the most used community TUI, it is MIT, and it implements the status

docs/docker-cases.md

@@ -81,6 +81,10 @@ Antigravity (`agy`) and Grok (`grok`) are the two CLIs not installed from npm (G
 
 Pi's credentials are seeded per-FILE rather than as a whole directory (`auth.json`, `settings.json`, `trust.json`, `models.json`, `models-store.json` out of `~/.pi/agent`), because that directory also holds `sessions/`, `extensions/`, `skills/` and the installed package trees — gigabytes on an active host. Consequence: in-container pi sessions are invisible host-side, so `pi -c` inside a Docker case only sees that container's own history. See [`pi-integration.md`](./pi-integration.md). Grok is seeded per-file for the same reason (`auth.json`, `config.toml`, `pager.toml` out of `~/.grok`, which also holds `sessions/`, `memory/` and the ~160MB binary under `downloads/`), with the same consequence for `grok -c`. See [`grok-integration.md`](./grok-integration.md). OMP is the one CLI in this family where `sessions/` is the EXCEPTION rather than the rule: `~/.omp/agent/{config.yml,mcp.json,models.yml,settings.yml}` are seeded per-file (the dir also holds SQLite caches and `terminal-sessions/`), but `~/.omp/agent/sessions/` is shared RW like codex's, not seeded, because Codeman reads it host-side for history recovery and `--resume` pinning. See [`omp-integration.md`](./omp-integration.md).
 
+The image can also carry the GitHub CLI (`gh`) and the Azure CLI (`az` + the `azure-devops` extension, in `AZURE_EXTENSION_DIR=/opt/az-extensions` so it stays out of the seeded HOME), wired into the system git config as credential helpers for github.com and dev.azure.com / *.visualstudio.com, exactly as in `docker/server.Dockerfile`. Their sign-ins are seeded per-FILE like pi's: `~/.config/gh/{hosts.yml,config.yml}` and `~/.azure/{azureProfile.json,msal_token_cache.json,service_principal_entries.json,clouds.config,config}`, never `~/.azure`'s logs, command index or extensions. A token kept in a desktop keyring, or in the encrypted MSAL cache az uses on Windows/macOS, is not in those files and does not carry. None of the three is version-pinned; the `--no-cache` rebuild recommended above is also what refreshes them. Both CLIs are opt-in and OFF by default: `CODEMAN_AGENT_IMAGE_INSTALL_GH=1` / `CODEMAN_AGENT_IMAGE_INSTALL_AZ=1` in the environment of `scripts/build-agent-image.mjs`, or of the Codeman server for its own auto-build (in the Compose deployment, `environment:` in `docker-compose.override.yml`), become the `CODEMAN_INSTALL_GH` / `CODEMAN_INSTALL_AZ` build args and put that CLI, its extension and its helper entry into the image. Unset passes nothing, so a default build's argv is unchanged and the image has neither. The sign-in seeds follow the same switches, read when a case container is created: `.config/gh` only with `CODEMAN_AGENT_IMAGE_INSTALL_GH=1`, `.azure` only with `CODEMAN_AGENT_IMAGE_INSTALL_AZ=1` (`enabledByEnv` in `CRED_STORES`), never merely because the files exist. Seeds are create-time mounts and deliberately not part of the config hash (hashing them would trip the drift gate for every case), so an existing case container picks them up only when it is recreated.
+
+Set `CODEMAN_AGENT_IMAGE_GIT_USER_NAME` and `CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL` together to configure the agent image's Git identity. Rebuild an existing `codeman/agent:base` with `node scripts/build-agent-image.mjs --no-cache`, then recreate Docker-case containers so they use the rebuilt image.
+
 ## Quickest path: one-click "Run in Docker"
 
 On the **New case → Create New** tab there's a **🐳 Run in an isolated Docker container** checkbox. Checking it alone is enough: Codeman creates the case folder in `~/codeman-cases/<name>`, spins up a hardened container with sensible defaults (auto-provisioning a shared `default` host), and starts the session inside it. No host/image/network fields to fill in.

docs/docker-compose.md

@@ -6,6 +6,10 @@ For the Compose configuration, environment settings, storage migration, and macv
 
 The image includes Claude Code, Codex, Gemini CLI, and OpenCode. Authenticate a CLI from its Codeman session; credentials are never baked into the image.
 
+CLIs installed from **App Settings → Agents & CLIs → CLI management** (DeepSeek Harness, Pi, and the other npm-based ones) go to `~/.local` on the `CODEMAN_APPDATA_PATH` mount, so they survive an image rebuild and a container recreate. Releases up to 1.33.1 installed them into the image instead, so a CLI installed from Settings on one of those has to be installed again once after the rebuild. The same applies to a hand-run `npm install -g` inside a session: it writes to the image prefix (`/opt/codeman-cli`) and is lost on the next rebuild, so use `npm install -g --prefix ~/.local <package>` instead.
+
+It can also include the GitHub CLI (`gh`) and the Azure CLI (`az`) with the `azure-devops` extension, wired in as Git credential helpers, so Clone Repo and `git clone` reach private GitHub and Azure DevOps repositories once they are signed in. Both are off by default; [Turning them on](../docker/README.md#turning-them-on) shows the `docker-compose.override.yml` settings.
+
 ## Prerequisites
 
 - Docker Engine or Docker Desktop with Docker Compose v2
@@ -67,7 +71,7 @@ If that directory was created by an earlier root-running image, change its owner
 
 Codeman updates itself from **App Settings → Updates**, as it does on a bare host. The checkout mounted at `/opt/codeman` is the same directory Compose builds from, so the update's `git checkout` and rebuild land on the host and survive container recreation; the restart is the server exiting, which `restart: unless-stopped` turns into a relaunch on the new build.
 
-That applies application code only. A release that changes `docker/server.Dockerfile`, `docker/docker-compose.yaml`, or adds a key to `docker/.env.example` needs the image rebuilt or the container recreated, which a container cannot do to itself. The updater detects each case and refuses with a message naming what changed; run `docker/Start-Codeman.sh` on the host to apply those.
+That applies application code only. A release that changes `docker/server.Dockerfile`, `docker/docker-compose.yaml`, or adds a key to `docker/.env.example` needs the image rebuilt or the container recreated, which a container cannot do to itself. The updater detects each case and refuses with a message naming what changed; run `docker/Start-Codeman.sh` on the host to apply those. For a major update, or a base-image change `Start-Codeman.sh` does not fully pick up, `docker/Update-Codeman.sh` rebuilds with no layer cache and clears the two build-artefact volumes before handing off to it (see "Major updates" in `docker/README.md`).
 
 `CODEMAN_REPO_PATH` overrides which checkout is mounted. It defaults to the compose project's parent directory, so it normally needs no setting. Point it at a directory that is not a git checkout and in-app updates are reported as unavailable.
 

docs/docker-self-update.md

@@ -10,15 +10,18 @@ this file covers only what the container changes.
 
 ## The short version
 
-| Change in the release            | Applied by                                       |
-| -------------------------------- | ------------------------------------------------ |
-| Application code                 | The in-app updater                               |
-| `docker/server.Dockerfile`       | `docker/Start-Codeman.sh` on the host            |
-| `docker/docker-compose.yaml`     | `docker/Start-Codeman.sh` on the host            |
-| New key in `docker/.env.example` | Add it to `docker/.env`, then `Start-Codeman.sh` |
+| Change in the release                     | Applied by                                                                      |
+| ----------------------------------------- | ------------------------------------------------------------------------------- |
+| Application code                          | The in-app updater                                                              |
+| `docker/server.Dockerfile`                | `docker/Start-Codeman.sh` on the host                                           |
+| `docker/docker-compose.yaml`              | `docker/Start-Codeman.sh` on the host                                           |
+| New key in `docker/.env.example`          | Add it to `docker/.env`, then `Start-Codeman.sh`                                |
+| A major update, or a Node base-image bump | `docker/Update-Codeman.sh` on the host (no-cache rebuild + fresh build volumes) |
 
-The in-app updater detects all three of the bottom rows itself and refuses with a
+The in-app updater detects the three middle rows itself and refuses with a
 message naming what changed, so you never have to work out which case you are in.
+`Update-Codeman.sh` is the heavier option for when `Start-Codeman.sh` is not
+enough: see "Major updates" in `docker/README.md`.
 
 ## Why the container needs its own path
 
@@ -224,7 +227,10 @@ the host and the in-app path works from then on.
 
 **Resetting the build artefacts** — `docker compose down -v`, then
 `Start-Codeman.sh`. This discards the named volumes and re-seeds them from a fresh
-image.
+image. `docker/Update-Codeman.sh` scripts the same reset by default for the two
+build-artefact volumes (`codeman-node-modules`, `codeman-dist`) only, plus an
+unconditional `--no-cache` rebuild, which a plain `Start-Codeman.sh` run does not
+force on its own. See "Major updates" in `docker/README.md`.
 
 ## Disabling it
 

docs/extending-codeman.md

@@ -338,6 +338,42 @@ codeman ralph start|stop|status|reset    codeman users add|passwd|list
 codeman status | list | attach <path>    codeman doctor
 ```
 
+### Opening a session from your own page
+
+To send someone from your page to one session, link to the dashboard with the
+session id in the fragment, as in `http://127.0.0.1:3000/#session=<id>`. The
+dashboard selects that tab when it loads. It also removes the fragment from its
+own URL, so a later link to the same session still counts as a change.
+
+Keep reusing one named window to make later links fast:
+
+```js
+window.open(`${codeman}/#session=${encodeURIComponent(id)}`, 'codeman');
+```
+
+When that window already shows the dashboard, only the fragment differs. The
+browser therefore keeps the page loaded, and the dashboard switches tabs without
+reloading it. A session the window has shown before appears at once. A session
+your page has only just created may not be listed yet, so the dashboard waits
+for its `session:created` event and selects it then. That wait lasts at most 30
+seconds: a link whose session never appears (a closed session, a typo, or in
+multi-user mode another user's session) is dropped with a "Session not found"
+notice. Clicking another tab, going Home or opening a web tab also ends the
+wait, so a session that turns up later never takes the screen from the person.
+
+When your page holds the window reference (`const win = window.open(...)`),
+prefer `win.location.replace(url)` for later links: it still fires `hashchange`
+without a reload, but adds no history entry, so Back in the dashboard window
+does not turn into a silent no-op.
+
+Following a link does not count as someone looking at the session, so it
+leaves the session's idle alert in place. The alert clears when the person
+clicks the tab or types into the session. A link to a session that is popped
+out into its own window asks that window to come forward, as clicking its tab does.
+
+A link to `/session/<id>` opens a page showing that session alone, and that
+page loads from scratch for every link.
+
 ## Seam 4: Hooks
 
 Claude Code hooks post to `POST /api/v1/hook-event` from inside an agent session.

docs/installer-v2-plan.md

@@ -0,0 +1,380 @@
+# Installer v2: three questions, then a URL you can open on your phone (Plan)
+
+Status: **Phase 1 IMPLEMENTED (2026-09-20)**, phases 2 and 3 open. It builds on
+`docs/tailscale-installer-plan.md` (implemented 2026-08-04), which made Tailscale a
+guided option; this round makes it the thing the install ENDS on, and makes the whole
+installer shorter to sit through. Owner decisions taken before implementation: rename
+is opt-in and **defaults to no everywhere** (the machine name is used for other things);
+the URL keeps the node name unless asked; `codeman-<hostname>` is the suggested name;
+sub-path is the default for an occupied `:443`.
+
+Verification record for phase 1 (all on the maintainer's box, 2026-09-20):
+
+- `test/install-sh-invariants.test.ts` (28 tests, incl. the new Tailscale safety pins)
+  and the detection-parity test pass; `bash -n` passes.
+- Every new decision function driven with stubbed tailscale state under **bash 5.2 and
+  bash 3.2** (the `bash:3.2` container CI uses): flags, the launch default, the serve
+  shape for free / ours / occupied `:443` (all four answers plus the non-interactive
+  default), the three serve commands, the rename question (Enter keeps the name; `--yes`
+  and non-interactive never rename; `codeman-*` nodes are skipped; `--name` is
+  sanitized), `run_step` success/failure/stdin, the unit round-trip of
+  `CODEMAN_BASE_URL`/`CODEMAN_PORT`/an escaped password, and the done screen.
+- A full non-interactive install into a sandboxed `HOME` with `CODEMAN_TAILSCALE=1`:
+  preflight summary, kept the existing prod mapping (no serve mutation), clone 2 s,
+  `npm install` 18 s, build 23 s, symlink, done screen; `install.sh status` on a pty
+  renders the QR code. Nothing on the real system changed.
+- **Sub-path mode end to end over the real tailnet**: an isolated Codeman
+  (`CODEMAN_INSTANCE`, port 3999, `--base-url /codeman`) behind
+  `tailscale serve --https=8445 --set-path /codeman 3999` answered `/codeman/api/status`,
+  `/codeman/` (with `<base href="/codeman/">` and `__CODEMAN_BASE__="/codeman"`), the
+  hashed CSS/JS, `/codeman` without a slash, and the SSE stream; mapping and server
+  removed afterwards. **Correction to section 2**: serve STRIPS the mount prefix
+  before proxying (a direct `/codeman/api/status` on the server is 404 while the same
+  path through serve is 200). That is fine because Codeman's ingress tolerates
+  unprefixed requests; `--base-url` is needed for the URLs Codeman EMITS, not for
+  what it receives.
+- Not yet exercised on a fresh machine (unchanged from the previous plan): Tailscale
+  absent / logged out / HTTPS toggle off, the rename against a real node (the
+  off-rename-re-add order is implemented but only unit-driven), macOS, uninstall. The
+  Mac mini and a throwaway VM are the venues; see section 8.
+- **Review fixes (2026-09-21)**, from the two reviews on PR #460 (DeepSeek Harness, then
+  Claude): the done screen's Start line is composed from every non-default value
+  (`start_command_hint`, shared with the exec branch as `export_bind_env`), so "do not
+  start" under a sub-path or a custom port no longer prints a bare `codeman web`; the
+  `--lan`/`--tailscale`/env preset paths keep an existing password instead of rewriting
+  the unit open; `--password`/`--port` flip `RECONFIGURE` so they reach the unit;
+  `install.sh name` re-syncs the unit's base URL after a rename; the sudo keepalive is
+  ended before the `exec` into the foreground server; Ctrl+C in the HTTPS-toggle poll
+  skips Tailscale instead of killing the run; `uninstall` asks before removing a
+  LaunchDaemon it never wrote; a foreign LaunchDaemon gets a restart hint and the done
+  screen stops claiming the new build is running; the preflight summary reads the
+  Tailscale state without node; the LAN security notice uses the configured port; a
+  bare re-run ends on the done screen; a build failure after a rename names the
+  `install.sh tailscale` recovery; `TS_JOINED_HERE` is gone.
+
+Goal, in one sentence: a user runs the one-liner, answers at most three questions, walks
+away during the build, and comes back to `https://<name>.<tailnet>.ts.net` printed with a
+QR code, already answering, on every device in their tailnet. That is exactly the
+maintainer's own production setup (`tnode.tailf80371.ts.net` fronting `127.0.0.1:3000`),
+and the installer should produce it without the user knowing what `tailscale serve` is.
+
+## 1. Where the installer is today
+
+Facts from reading `install.sh` (2886 lines, 19 `prompt_yes_no` sites) and the live
+Tailscale state on the maintainer's box (tailscale 1.102.2, user-owned node, MagicDNS +
+HTTPS certs on, serve mapping `443 -> https+insecure://localhost:3000`).
+
+**The order is backwards for a human.** The flow is: detect -> ask about git -> ask about
+node -> ask about tmux -> ask about build tools -> AI CLI menu -> ask about cloudflared ->
+clone -> `npm install` -> build (minutes) -> **then** the network-access question -> the
+Tailscale sub-steps (install? login URL, sudo for operator, admin-console toggle loop) ->
+the launch menu (no default; a bare Enter re-prompts) -> tunnel-service question. A fresh
+Ubuntu server taking the Tailscale route answers roughly ten prompts plus two to four sudo
+password prompts, split around a multi-minute build. The user cannot walk away at any
+point, and the question that matters most (how do I reach it) comes last.
+
+**The Tailscale flow works but was never exercised on a fresh machine.** The previous
+plan's manual matrix still lists items 1-4, 7 and 10-12 (Tailscale absent, logged out,
+HTTPS toggle off, port 443 occupied, macOS, uninstall, phone PWA) as untested. The
+maintainer's own verification was the idempotent "kept as-is" path.
+
+**The URL is the machine's name, full stop.** `setup_tailscale_serve` derives it from
+`.Self.DNSName`, and nothing lets the user influence it. A second Codeman on the same
+tailnet is `macminis-mac-mini.tailf80371.ts.net`, which tells you nothing about Codeman.
+
+**Port 443 taken means give up or clobber.** If another app already owns the root of
+`:443`, the only offer is "replace it?" (default no), and declining falls back to
+local-only. Codeman already supports running under a sub-path (`--base-url`), and
+Tailscale serve supports mounting a path (`--set-path`), so there is a third answer nobody
+is offered.
+
+**The result is invisible afterwards.** Once the terminal scrolls away, nothing in the app
+or the CLI tells the user their Tailscale URL again. `codeman doctor` does not probe
+Tailscale; App Settings -> Remote access shows only the Cloudflare tunnel.
+
+**Two service writers exist.** `install.sh` carries its own plist/unit generator (~180
+lines) next to `codeman service install` (`src/service-installer.ts`). They agree on the
+job name by design, but the bash copy is the one that writes `CODEMAN_PASSWORD` into the
+unit, so they cannot simply be merged. Left as-is in this plan (see section 9).
+
+## 2. What Tailscale makes possible for the name (researched 2026-09-20)
+
+| Option | Resulting URL | What it needs | Side effects | Verdict |
+| ------ | ------------- | ------------- | ------------ | ------- |
+| **A. Node name** (today) | `https://tnode.tailf80371.ts.net` | `tailscale serve --bg 3000` | none | **Default.** Zero admin-console work, matches the maintainer's prod. |
+| **B. Rename the node** | `https://codeman-tnode.tailf80371.ts.net` | `tailscale set --hostname codeman-<host>` (operator or root) | Renames the machine tailnet-wide: ssh targets, other serve URLs, the admin console entry. Tailscale de-dups a clash as `-1`. The cert follows the new name. | **Opt-in, default NO everywhere** (owner decision 2026-09-20: the machine is used for other things, so a bare Enter never renames it). The proposal was YES when the installer itself had just joined the tailnet; rejected. |
+| **C. Tailscale Service** | `https://codeman.tailf80371.ts.net` | tailscale >= 1.86 on the host; the host must have a **tag-based identity** ("You cannot use a device authenticated with a user account as a Service host"); the service is defined in the admin console first; the host is then approved there (or via `autoApprovers.services`). Public beta since 2025-10-28, all plans. | Re-authenticating a personal machine as a tagged node changes its identity (SSH ACLs, user attribution). Known daemon quirk: approval is not picked up until `serve clear` + re-advertise (tailscale/tailscale#18821). | **Detect and hint only** in this round. The maintainer's own node has `Self.Tags: null`, so it could not host one without re-tagging. Worth a real flow once someone with a tagged fleet asks. |
+| **D. Sub-path** | `https://tnode.tailf80371.ts.net/codeman` | `tailscale serve --bg --set-path /codeman 3000` plus `--base-url /codeman` on the server | Codeman runs under a prefix. Hooks are unaffected (they hit the raw port with no prefix, which `rewriteUrl` already tolerates). Serve forwards the prefix unchanged, which is exactly the shape `--base-url` was built for. | **The answer when `:443` root is already taken.** Replaces today's replace-or-nothing prompt. |
+| **E. Second port** | `https://tnode.tailf80371.ts.net:8443` | `tailscale serve --bg --https=8443 3000` | Port in the URL; the beta-preview recipe already uses this. | Fallback when the user rejects D. |
+| Funnel (public internet) | `https://tnode.tailf80371.ts.net` from anywhere | `tailscale funnel` | Public exposure; different risk class. | **Out of scope**, as before. Docs only, with the password warning. |
+
+Sources: Tailscale Services docs (`tailscale.com/docs/features/tailscale-services`), the
+Services beta announcement (`tailscale.com/blog/services-beta`), machine names
+(`tailscale.com/kb/1098/machine-names`), the serve CLI reference
+(`tailscale.com/docs/reference/tailscale-cli/serve`), the macOS variants page
+(`tailscale.com/docs/concepts/macos-variants`), and `tailscale serve --help` on 1.102.2
+(which lists `--service`, `--set-path`, `--yes`, `advertise`, `get-config`/`set-config`).
+
+**Trap for option B (verify on the Mac mini before shipping):** the serve config is keyed
+by `host:port` using the DNS name at configuration time (`"Web": {"tnode.tailf80371.ts.net:443": ...}`
+in `serve status --json`). Renaming a node after serve is configured most likely orphans that
+entry: the handler lookup uses the current name and never matches the old key, and the only
+tool that removes a stale key is `serve reset`, which this installer must never run. So the
+order is **rename first, then configure serve** on a fresh install, and on a retrofit
+(`install.sh name`) **turn our mapping off, rename, wait for `.Self.DNSName` to change,
+re-add**.
+
+## 3. Target UX
+
+### 3.1 Three questions, then walk away
+
+```
+  Codeman installer
+
+  Found:      git, Node 22.14, tmux 3.4, build tools     Missing: nothing
+  AI CLIs:    Claude Code (~/.local/bin/claude)
+  Tailscale:  connected as tnode (tailf80371.ts.net)
+  Existing:   none
+
+  1/3  How should the dashboard be reachable?
+         1) Tailscale  https://tnode.tailf80371.ts.net  (recommended, already connected)
+         2) Any device on your network (0.0.0.0, password required)
+         3) This machine only (127.0.0.1)
+       Choose [1/2/3] (default 1):
+
+  2/3  Name this machine "codeman-tnode" on your tailnet? [y/N]
+       (only shown for option 1; default no, always)
+
+  3/3  Run Codeman as a background service that starts on boot? [Y/n]
+
+  Installing… this takes a few minutes. You can leave this running.
+    ✓ dependencies    ✓ clone    ✓ build (2m 41s)    ✓ service    ✓ tailscale serve
+```
+
+Rules that make this work:
+
+- **Every step that needs a human runs BEFORE the build.** The dependency consent, the
+  AI CLI menu, the Tailscale install consent, the `tailscale up` login URL, the operator
+  grant, and the tailnet HTTPS toggle all move into the question phase. The build, the
+  service, `tailscale serve` and the verification are unattended.
+- **One consent for all missing system packages.** "Install git, Node 22 and build tools
+  now? [Y/n]" replaces four separate prompts. Each package still runs its own
+  distro-specific installer.
+- **One sudo prompt.** When anything needs root (packages, the Tailscale installer,
+  `tailscale up`, the operator grant), the installer says so once, runs `sudo -v`, and keeps
+  the timestamp alive in a background loop until it exits. macOS needs no sudo for the
+  Tailscale GUI-app CLI and the pattern still holds for Homebrew packages.
+- **Service is the default.** Enter on the last question installs the service; "run in
+  this terminal" and "don't start" stay reachable by answering, and by flag.
+- **The cloudflared question is gone from the main flow.** It is optional, defaults to
+  no, and has an in-app toggle (App Settings -> Remote access). The done screen mentions it
+  only when `cloudflared` is already installed. The Linux tunnel-service prompt goes with it.
+- **The HTTPS-certificates toggle no longer asks "re-check now?"** The installer prints the
+  admin URL, opens it in a browser when one is available (`xdg-open` / `open`, never on a
+  headless box), and polls `tailscale status --json` every 5 s for up to 5 minutes. Ctrl+C or
+  the timeout falls back exactly as today.
+- **Progress, not silence.** `npm install` and `npm run build` run behind one line each
+  with elapsed time; their output goes to `~/.codeman/install.log` and is printed only on
+  failure, with the exact retry command.
+
+### 3.2 The done screen
+
+One block, the URL first, a QR code the phone can scan, and nothing the user does not need
+right now.
+
+```
+  ✓ Codeman 1.31.0 is running
+
+    Your tailnet:    https://codeman-tnode.tailf80371.ts.net    (HTTPS, any of your devices)
+    This machine:    http://localhost:3000
+
+    ▄▄▄▄▄▄▄ ▄ ▄▄  ▄▄▄▄▄▄▄
+    █ ▄▄▄ █ ▄▄▀ ▄ █ ▄▄▄ █      scan with your phone
+    █ ███ █ ███▀▀ █ ███ █
+    █▄▄▄▄▄█ █ ▄ █ █▄▄▄▄▄█
+
+    Manage   systemctl --user restart codeman-web  ·  journalctl --user -u codeman-web -f
+    Update   re-run the install line, or App Settings → System → Updates
+    Docs     https://github.com/Ark0N/Codeman/wiki
+
+  Security: Codeman binds 127.0.0.1. Tailscale authenticates every device before a
+  packet reaches it. Details: docs/security-architecture.md
+```
+
+The QR comes from the `qrcode` package Codeman already depends on
+(`node -e "require('qrcode').toString(url, {type:'terminal', small:true}, …)"` from
+`$INSTALL_DIR`, verified locally: 17 rows by 45 columns). Skipped when the terminal has no
+color support or fewer than 50 columns. The QR encodes the plain URL, not an auth token:
+the tailnet is the login.
+
+### 3.3 Express mode and flags
+
+Env vars stay (`CODEMAN_TAILSCALE=1`, `CODEMAN_HOST`, `CODEMAN_PASSWORD`,
+`CODEMAN_NONINTERACTIVE=1`, `CODEMAN_PORT`). Flags are added because they are
+discoverable from the one-liner and pipe through `bash -s --`:
+
+```bash
+curl -fsSL https://getcodeman.com/install | bash -s -- --tailscale --service
+curl -fsSL https://getcodeman.com/install | bash -s -- --lan --password 'x' --service
+curl -fsSL https://getcodeman.com/install | bash -s -- --local --run
+curl -fsSL https://getcodeman.com/install | bash -s -- --tailscale --name codeman-build --yes
+```
+
+| Flag | Meaning |
+| ---- | ------- |
+| `--tailscale` / `--lan` / `--local` | Answer 1/3 (same semantics as `CODEMAN_TAILSCALE=1`, `CODEMAN_HOST=0.0.0.0`, `CODEMAN_HOST=127.0.0.1`) |
+| `--name <n>` / `--no-rename` | Answer 2/3: rename the node to `<n>`, or never ask |
+| `--service` / `--run` / `--no-start` | Answer 3/3 |
+| `--yes` | Accept every default, still prompt for a login URL (a human must open it) |
+| `--password <p>` | Same as `CODEMAN_PASSWORD` |
+| `--port <n>` | Same as `CODEMAN_PORT`; the serve target follows it |
+
+`--yes` differs from `CODEMAN_NONINTERACTIVE=1`: it is the interactive user saying "I trust
+the defaults", so it may install software and may wait on a login URL. Non-interactive stays
+the CI contract and never installs Tailscale.
+
+## 4. The Tailscale flow, v2
+
+The state machine from the previous plan stays; these are the changes.
+
+1. **Preflight, before the build** (`tailscale_preflight`): installed? -> install
+   (Linux: official script; macOS: brew cask, else download link and wait). Logged in? ->
+   `tailscale up` with the URL printed prominently and a 5-minute poll. Operator (Linux):
+   grant once under the single sudo session. HTTPS certs: poll instead of ask (Ctrl+C
+   during the poll skips Tailscale for this run rather than ending the installer). The
+   rename default does not depend on whether this run performed the login (decided NO
+   everywhere), so nothing records it.
+2. **Name** (`tailscale_choose_name`, question 2/3): shown only on the Tailscale route.
+   Default `codeman-<oshostname>` sanitized to `[a-z0-9-]`, max 63. Applied with
+   `ts_cmd_serve set --hostname`, then poll `.Self.DNSName` until it carries the new name
+   (up to 60 s). Order matters: this runs before any serve mutation (section 2 trap).
+   Declining keeps the node name. On a re-run against a node already named `codeman-*`,
+   the question is skipped.
+3. **Serve, after the service is up** (`setup_tailscale_serve`): unchanged idempotent
+   "kept as-is" path first. When `:443` root belongs to another target, the new prompt is:
+
+   ```
+   tailscale serve already sends https://tnode.tailf80371.ts.net to port 8080.
+     1) Add Codeman under a path:  https://tnode.tailf80371.ts.net/codeman   (default)
+     2) Use another port:          https://tnode.tailf80371.ts.net:8443
+     3) Replace the existing mapping with Codeman
+     4) Skip Tailscale for now
+   ```
+
+   Option 1 writes `--base-url /codeman` into the service unit (it is a `WebLaunchOptions`
+   field already, and `buildWebArgs` carries it) and runs
+   `tailscale serve --bg --set-path /codeman <port>`. Option 2 runs `--https=8443`.
+   `detect_tailscale_serve_url` learns to recognize all three shapes (root, path, port) so
+   uninstall, the security notice and the re-run default keep working.
+4. **Warm the certificate.** Right after serve is configured, fire one background
+   `curl -sk https://<url>/api/status` so Let's Encrypt issuance overlaps the rest of the
+   install instead of adding 30 s to the verify step.
+5. **Verify** as today (200 or 401 on `/api/status`), with the path-aware URL.
+6. **Services hint** (option C): when `.Self.Tags` is non-empty and `serve --help`
+   lists `--service`, the done screen adds one line: "This is a tagged node, so it can also
+   host `https://codeman.<tailnet>.ts.net` as a Tailscale Service: see Remote Access in the
+   wiki." No flow, no prompt.
+7. **macOS**: the App Store and Standalone variants cannot run before login, so a
+   LaunchAgent plus serve only comes back after someone logs in. The done screen says so on
+   macOS. The Mac mini (`arbbot`, headless, system LaunchDaemon) is the reference for the
+   "headless Mac" caveat, and `install.sh` must keep refusing to replace a LaunchDaemon it
+   did not write (today it removes one; that is a bug for the Mac mini and is fixed here:
+   detect `UserName` in the daemon plist and leave it alone with a message).
+8. **Uninstall** additionally offers to restore the original node name when this installer
+   renamed it (the original is recorded in `~/.codeman/install.json`, the one marker file
+   this feature adds, because tailscaled does not remember previous names).
+9. **Subcommands**: `install.sh tailscale` (unchanged purpose, now runs the v2 flow),
+   `install.sh name [<n>]` (rename with the off/rename/re-add dance), `install.sh status`
+   (prints the done screen again, URL and QR included, for the "what was my URL" moment).
+
+## 5. In-app: the URL stays discoverable
+
+Small, read-only, and the first server-side code this feature has ever needed.
+
+- **`GET /api/system/remote-access`** returns
+  `{ tailscale: { installed, connected, dnsName, url, mode: 'root'|'path'|'port'|null } }`
+  by running `tailscale status --json` and `tailscale serve status --json` through
+  `execFile` with the existing exec timeout, cached 30 s, resolved through the same
+  `get_tailscale_path` search as the installer (PATH, then the macOS app bundle), and a
+  no-op under `VITEST` like every other IO probe. Never mutates serve config.
+- **App Settings -> Remote access** gains a **Tailscale** row above the Cloudflare toggle:
+  the URL as a copy chip, a QR button reusing `showTunnelQR`'s modal, and when nothing is
+  configured a one-line hint with `bash ~/.codeman/app/install.sh tailscale`. The welcome
+  screen's "open on your phone" affordance shows the same QR.
+- **`codeman doctor`** grows a `tailscale` entry under `other` in
+  `config/dependency-registry.ts`: installed, connected, serving Codeman (URL). Pure
+  engine, injectable probe host, like the existing rows.
+- No new SSE event, no settings key, no state.json change.
+
+## 6. Security posture
+
+Nothing widens. The bind stays loopback; the tailnet is the authentication boundary;
+`.ts.net` is already in `DEFAULT_TRUSTED_HOST_SUFFIXES`. New surfaces are read-only
+probes. `install.sh` still never runs `tailscale serve reset`, still touches only the
+mapping it created, and gains one more never: it never advertises a Tailscale Service or
+runs `tailscale funnel`. The sudo keep-alive loop is killed by the existing `cleanup` trap.
+The rename records the previous name locally and offers the reversal at uninstall.
+
+## 7. Implementation inventory
+
+| File | Change |
+| ---- | ------ |
+| `install.sh` | New `parse_flags`, `preflight_summary`, `ask_everything` (the three questions), `sudo_session`, `run_step` (spinner + log), `tailscale_preflight`, `tailscale_choose_name`, `tailscale_rename_node`, `print_done_screen`, `print_qr`, `status` subcommand, `name` subcommand. Modified: `main` (reordered into ask -> work -> done), `choose_network_binding` (question 1/3, same defaults), `setup_tailscale_serve` (path/port options), `detect_tailscale_serve_url` (three shapes), `setup_systemd_service`/`setup_launchd_service` (`--base-url`, LaunchDaemon guard), `uninstall` (rename reversal), header docs (flags). Removed from the main flow: the cloudflared prompt, the tunnel-service prompt. bash 3.2 rules unchanged. |
+| `src/web/routes/system-routes.ts` | `GET /api/system/remote-access` |
+| `src/tailscale-status.ts` (new) | Pure parser for the two JSON shapes + the IO wrapper; unit-tested against captured `serve status --json` fixtures (root, path, port, foreign target, none) |
+| `src/config/dependency-registry.ts`, `src/utils/dependency-checker.ts` | `tailscale` doctor row |
+| `src/web/public/index.html`, `settings-ui.js`, `panels-ui.js` | Tailscale row + QR, welcome-screen QR |
+| `test/install-sh-invariants.test.ts` | Extend: flags documented in the header, no `serve reset`, no `funnel`, no `--service` advertise, every serve mutation goes through `ts_cmd_serve`, rename happens before serve in `main` (static order check) |
+| `.github/workflows/ci.yml` | The bash 3.2 step additionally sources the script with stubbed `ts_cmd`/`ts_cmd_serve`/`read_reply` and drives `ask_everything` through all three answers and the 443-occupied menu |
+| `test/tailscale-status.test.ts`, `test/routes/system-routes-remote-access.test.ts` | Parser + route |
+| Docs | README install + remote-access sections, `docs/wiki/Installation.md`, `Remote-Access.md` (naming options table, Services caveat, path/port variants), `Mobile-Guide.md`, `Running-As-A-Service.md` (macOS login caveat), `FAQ.md`, `docs/security-architecture.md` §A, CLAUDE.md Scripts & Tunnel paragraph, `docs/tailscale-installer-plan.md` gets a pointer here. getcodeman.com copy lives outside the repo (maintainer handbook). |
+
+Changeset: `minor` (new flags, new subcommands, new API route).
+
+## 8. Test plan
+
+Automated (the gate): the static invariants above, the bash 3.2 container drive of the
+question phase, the JSON parser fixtures, the route test.
+
+Manual matrix, on a fresh Ubuntu 24 VM and on the Mac mini, since the previous plan's
+items never ran on a fresh machine:
+
+1. Tailscale absent, declined -> local-only, done screen shows the retrofit command.
+2. Tailscale absent, accepted -> install, login URL, operator, certs toggle polled, rename
+   question shown (default no), service, serve, URL verified, QR scans on a phone, PWA installs.
+3. Tailscale present and logged in on a pre-existing node -> rename default NO, URL is the
+   node name, `serve status` gains exactly one entry.
+4. `:443` root occupied -> path option -> `https://<node>/codeman` answers, hooks still
+   fire (raw port), `install.sh status` prints the path URL.
+5. Rename on a node that already has our serve mapping (`install.sh name`) -> off, rename,
+   re-add, `serve status` has no stale key.
+6. Re-run the one-liner -> quiet update, binding and name preserved, no prompts.
+7. `--yes` end to end; `CODEMAN_NONINTERACTIVE=1` end to end (no software installed).
+8. Uninstall -> mapping removed, other mappings intact, rename reversal offered.
+9. Mac mini: LaunchDaemon left alone with the message; done screen carries the login caveat.
+
+## 9. Phasing and open decisions
+
+**Phase 1 (this round):** the reorder, the three questions, one consent + one sudo, flags,
+the done screen with QR, Tailscale preflight-before-build, the path/port answer for an
+occupied 443, the rename step, `status` and `name` subcommands, docs.
+
+**Phase 2:** the in-app Tailscale row + QR, `codeman doctor` row, the `remote-access`
+route. Independent of phase 1 and useful on its own for existing installs.
+
+**Phase 3 (optional):** replace the bash service writers with `codeman service install`
+once that command can carry `CODEMAN_PASSWORD` behind an explicit flag; and a Tailscale
+Services flow if a tagged-fleet user asks for `codeman.<tailnet>.ts.net`.
+
+Decisions for the maintainer:
+
+1. **Rename default.** Decided 2026-09-20: always NO; the yes answer, `--name` and
+   `install.sh name` are the ways in. (The proposal was YES only when this run had joined
+   the tailnet, NO otherwise; rejected because the host is used for other things.)
+2. **Name pattern.** `codeman-<hostname>` (proposed; unique per machine, and two Codemans
+   on one tailnet stay distinguishable) versus plain `codeman` (nicer once, collides on the
+   second install, Tailscale silently appends `-1`).
+3. **Path versus port** as the default answer for an occupied 443. Proposed: path, because
+   the URL has no port and `--base-url` already exists for exactly this proxy shape.
+4. **Whether Phase 2 ships in the same release.** It is the part that helps people who
+   installed months ago.

docs/reliable-input-delivery.md

@@ -66,6 +66,31 @@ each `(clientId, seq)` at most once, so a resend can't type the prompt twice.
   (the 200 is the client's ACK). `curl`/legacy callers omit the fields and always
   apply.
 
+## Oversized input (issue #484)
+
+Delivery has a third outcome besides "applied" and "retry": **refused for good**.
+Both transports refuse a frame longer than `MAX_INPUT_LENGTH` (64 KiB,
+`src/config/terminal-limits.ts`; the POST schema uses the same constant). Before
+#484 the client treated that like a transient failure, so an oversized paste sat
+at the head of the queue, was re-sent every 2 s forever, blocked every later
+input for the session, and came back from localStorage on each reload.
+
+- `_sendInputAsync()` splits a paste over the frame limit into in-limit frames
+  (`CodemanInputLimit.split`, constants.js, never cutting a surrogate pair). They
+  go out in seq order, so the PTY sees one contiguous stream. A paste over
+  `PASTE_MAX_CHARS` (1 MiB), or an oversized `useMux` write (line-oriented, never
+  split), is refused with a toast and never queued.
+- The WebSocket answers an oversized sequenced frame with
+  `{t:'ia', seq, err:'too_large', max}`; the client drops it with a toast. A
+  client that predates `err` reads it as a plain ACK and drops it too.
+- The POST drain drops a frame answered `400`/`413` (`401`/`403` stay transient:
+  an expired login delivers once the user signs in again).
+- `_loadReliableState()` prunes persisted frames over the limit, so a queue
+  poisoned by an older build heals on the first load after upgrading.
+- ⚠️ The frontend limit (`INPUT_FRAME_MAX_CHARS`) and the composer's
+  `COMPOSER_INPUT_FRAME_LIMIT` must equal `MAX_INPUT_LENGTH`; pinned by
+  `test/input-size-limit.test.ts`.
+
 ## Known limitation
 
 Dedup state is in-memory on the server. A **server restart** between a write and
@@ -79,3 +104,5 @@ across the narrow restart window.
   semantics (monotonic, per-client, gap-tolerant, eviction-safe).
 - `test/routes/session-routes.test.ts` — POST `/input` applies a tagged
   `(clientId, seq)` once on redelivery; untagged input always applies.
+- `test/input-size-limit.test.ts`: one input limit on both sides, frame
+  splitting, and dropping (never retrying) a frame refused for good (#484).

docs/security-architecture.md

@@ -270,9 +270,15 @@ tailscale serve --bg 3000      # HTTPS at https://<node>.<tailnet>.ts.net
 Only devices on your tailnet can reach it; Tailscale handles identity and
 terminates TLS with a real Let's Encrypt certificate (so PWA install and web
 push work). No app password and no `0.0.0.0` bind required. (This is the
-maintainer's production setup.) `CODEMAN_TAILSCALE=1` presets the choice for
-automation; the installer never runs `tailscale serve reset` and never touches
-serve mappings other than `443 -> Codeman's port`.
+maintainer's production setup.) `CODEMAN_TAILSCALE=1` or `--tailscale` presets
+the choice for automation. When `:443` on the node already belongs to another
+app, the installer mounts Codeman under `/codeman` (`tailscale serve --set-path`
+plus `--base-url`, which keeps the loopback bind and the same host guard) or on a
+second port rather than replacing it. The installer never runs `tailscale serve
+reset`, never touches serve mappings other than the one it created, never opens a
+`tailscale funnel` (public internet, a different risk class) and never advertises
+a Tailscale Service. Renaming the node (`--name`, `install.sh name`) is opt-in
+and defaults to no, because the tailnet name is also the machine's SSH identity.
 
 ### B. Authenticated cloudflared tunnel + password
 
@@ -491,7 +497,7 @@ production layout (`~/.codeman`, `-L codeman`, port 3000).
 Docker cases (1.4.0) run a session inside a per‑case container instead of on the host. The security posture:
 
 - **Hardened create flags, always** — `--cap-drop ALL`, `--security-opt no-new-privileges`, `--pids-limit` (fork‑bomb guard), `--memory` == `--memory-swap` (a real OOM cap), `--init`, and non‑root: `--user <hostUid>:0` on Linux (host uid → workspace files stay host‑owned; GID 0 keeps `$HOME` writable), `--userns=keep-id` on rootless Podman. **Never** `--privileged`, and **never** the docker socket — the pure builder in `docker-hosts.ts` cannot emit them and the schema cannot represent them.
-- **Credentials never enter an image** — the convenient default bind‑mounts host cred dirs (`~/.claude`, `~/.codex`, `~/.gemini` — which also carries Antigravity's `antigravity-cli/` state — `~/.config/{gcloud,opencode}`, five seeded files from `~/.pi/agent`, and three from `~/.grok`) read‑write. Bind mounts are physically excluded from `docker commit`, so exported images are secret‑free. API‑key CLIs get their key as an exec‑time NAME‑ONLY `--env OPENAI_API_KEY` (no `=value`, no `ps` leak, never committed); a create‑time `-e` for a secret is never used. The **sealed** profile (`mountCredentials:false` + `network:none`) drops the host mounts; full‑image export is then refused (an in‑container login would ride the committed layer) unless a pre‑commit scrub is opted into.
+- **Credentials never enter an image** — the convenient default bind‑mounts host cred dirs (`~/.claude`, `~/.codex`, `~/.gemini` — which also carries Antigravity's `antigravity-cli/` state — `~/.config/{gcloud,opencode}`, five seeded files from `~/.pi/agent`, three from `~/.grok`, and, only when their opt-in switches `CODEMAN_AGENT_IMAGE_INSTALL_GH` / `_AZ` are `1`, `~/.config/gh/{hosts.yml,config.yml}` and the sign-in files from `~/.azure`) read‑write. Bind mounts are physically excluded from `docker commit`, so exported images are secret‑free. API‑key CLIs get their key as an exec‑time NAME‑ONLY `--env OPENAI_API_KEY` (no `=value`, no `ps` leak, never committed); a create‑time `-e` for a secret is never used. The **sealed** profile (`mountCredentials:false` + `network:none`) drops the host mounts; full‑image export is then refused (an in‑container login would ride the committed layer) unless a pre‑commit scrub is opted into.
 - **Blast radius — accept it explicitly** — the convenient profile mounts an arbitrary host workspace RW plus the host credential dirs RW into a network‑enabled container, so container‑run agent code can read/modify those host trees and reach the network at once. Still a net improvement over today's on‑host `--dangerously-skip-permissions` execution; use the sealed profile for genuinely untrusted work.
 - **Import is untrusted‑bundle‑safe** — `/api/docker-cases/import` validates the manifest + per‑member SHA‑256 before extraction, rejects absolute / `..` tar members (traversal guard), and re‑tags the loaded image into a quarantined namespace so it can never overwrite `codeman/agent:base` or a pre‑existing tag.
 - **Host guard & the bridge‑hooks listener** — in‑container hook callbacks carry `Host: host.docker.internal` / `host.containers.internal`; both are on the always‑on host‑header allowlist (`DOCKER_HOST_GATEWAY_ALIASES`) and resolve to the host only from inside a container netns, so they are not a browser DNS‑rebinding surface. On a loopback‑only server, in‑container hooks are opt‑in via `CODEMAN_DOCKER_BRIDGE_HOOKS=1`, which binds a SECOND listener on the docker bridge gateway serving **only** the hook endpoints (every other path → `403`) into the same hook‑secret‑gated pipeline. The bridge is host‑internal (containers + host), not the LAN, so it does not widen network exposure; the hook secret is bind‑mounted read‑only and referenced by path.
@@ -510,6 +516,7 @@ Full feature guide: [`docker-cases.md`](docker-cases.md).
 - **Auth is a parallel branch** (`middleware/auth.ts`) that leaves the single‑user path untouched: per‑user scrypt verify (`timingSafeEqual`, timing‑equalized against user enumeration), identity‑carrying cookies, a per‑username failure bucket (a botnet can't brute one account across IPs; one NATed user can't lock out the rest), and a `mustChangePassword` lockbox. The hook‑secret loopback bypass, host guard, and Origin/CSRF guard are unchanged (hooks authenticate the INSTANCE, not a user).
 - **Ownership is enforced server‑side only** and fails closed: `req.authUser` (a synthetic admin in single‑user), `findSessionOrFail` returns NOT_FOUND (never 403) for a foreign session, list/SSE/WS/file‑preview/search all filter by `session.owner`, and SSE routing defaults session‑scoped events to their owner (unresolved owner → withheld). The load‑bearing rule is **non‑admin `workingDir` confinement**: a non‑admin's session/one‑shot working dir must realpath‑resolve inside `~/codeman-users/<name>/cases`, checked BEFORE any disk write.
 - **Privileged actions are a one‑bit grant** (`canBypassPermissions`, default off): only granted users (and admins) get `--dangerously-skip-permissions` (others are silently downgraded to `--permission-mode auto`), shell‑mode sessions, cron `launchCommand`, and other CLIs' bypass flags. Machine‑level resources (remote/Docker host definitions, tunnel, self‑update, settings writes) are admin‑only.
+- **Clone Repo does not lend the server's git sign-in to non-admins.** A clone writes only inside the caller's own case space, so it is not admin-gated, but the server account's git credential helpers (the Docker image's opt-in `gh`/`az` helpers, or any `gh auth setup-git`) are shared by every user. A non-admin's clone and preflight therefore run with `git -c credential.helper=`, which empties the helper list including the URL-scoped entries (`cloneWithoutCredentialHelpers` in `case-routes.ts`, argv pinned in `test/git-clone.test.ts`). This closes the Clone Repo path only: the account's SSH keys still apply to an `ssh://` URL, and a non-admin's agent sessions run as the same account, consistent with the first bullet above. Docker cases are a second route to the same sign-in: with `CODEMAN_AGENT_IMAGE_INSTALL_GH`/`_AZ` on, a non-admin's Docker case with credential seeding on (the default) receives a copy of the server account's `gh`/`az` sign-in, exactly as it receives the Claude and Codex credentials.
 - **Admin actions are audited** append‑only to `~/.codeman/admin-audit.jsonl` (acting admin, action, target, IP). Passwords set by an admin create/reset are one‑time (returned once, force change). Under Basic auth, `logout` only truly ends QR‑issued sessions — to lock someone out, disable the account or reset the password (a proper login form is a deferred Phase 6).
 
 ---

docs/split-pane-sessions-plan.md

@@ -0,0 +1,198 @@
+# Split-Pane Sessions — Design Spec
+
+**Status**: Implemented (v1)
+**Author**: Claude (session with Tim), 2026-09-15
+**Scope**: v1 only. v2 items are named and explicitly deferred, not designed.
+
+## Problem
+
+Codeman's terminal area shows exactly one active session (pane) at a time —
+switching panes re-binds the single xterm instance and the single WebSocket
+to a different session. Multi-monitor spanning (`scripts/span-codeman.sh` /
+`span-codeman.ps1`) turned out to solve a different problem: it makes one
+browser window bigger, but that window still shows one session; floating
+subagent windows are draggable overlays on top of it, not tiled panes. There
+is no way today to see two live sessions (e.g. `w1-codeman` and
+`w1-mcp-memory`) side-by-side in one window, even on a monitor wide enough to
+fit both.
+
+## Goal (v1)
+
+From the active session, open a **second, independent, fully live session**
+in a pane beside it — draggable divider, side-by-side only. Closing the
+second pane collapses back to today's normal single-pane view. No
+persistence: a page reload always returns to single-pane. Floating
+subagent/Ultracode windows keep their current behavior unchanged (global,
+unconstrained across the whole viewport, split or not).
+
+Explicitly out of scope for v1 (v2 candidates, not designed here):
+- More than 2 panes / grid layouts
+- Vertical (stacked) splits
+- Drag-a-tab-to-split as a trigger (v1 trigger is an explicit button + picker)
+- Persisting the split layout across reload or across devices
+- Mobile/tablet layouts (viewport is too narrow for this to make sense; gated
+  to desktop widths the same way `home-sessions.js`'s rail is)
+- Feature parity between the two panes (see "Pane B is deliberately plainer"
+  below)
+
+## Current architecture (why this isn't a CSS change)
+
+`terminal-ui.js` is built entirely around **singleton** state: `this.terminal`
+(one xterm instance), `this._ws`/`this._wsSessionId` (one WebSocket, rebound
+on every pane switch via `_disconnectWs()` + `_connectWs(newId)`), a
+`this._xtermSnapshots` map used only to restore scrollback into that one
+terminal when switching back to a session. Roughly 280 references to this
+singleton state exist across the file (input handling, resize/fit, sizing-
+token claims, mobile touch gestures, CJK IME, local-echo overlay wiring,
+keyboard accessory bar, link providers, etc.).
+
+Showing two sessions at once therefore requires a second, independently
+alive xterm + WebSocket pair running concurrently — not a layout change to
+one shared instance.
+
+**Related prior art**: `detachSession(id)` (app.js) already opens one session
+in a genuinely separate browser window (`isSoloWindow` mode) with its own
+independent WebSocket, and two of those can already be snapped side-by-side
+today with zero new code. That covers "two sessions visible at once" but not
+what this spec is for: one Codeman window with two panes and a divider you
+can drag without leaving your seat, each still a full participant in that
+window's floating subagent windows, header, and settings. This spec builds
+past detach, not a duplicate of it.
+
+**Server-side check (done, not just assumed)**: `MAX_WS_PER_SESSION = 5`
+(`src/web/routes/ws-routes.ts`), scoped by `clientId:tabNonce`
+(`ws-connection-registry.ts`). Splitting always opens a *different* session
+in the second pane (self-splitting is disallowed, see below), so this is two
+sessions each getting their normal one connection — the existing cap is
+irrelevant here and needs no server change.
+
+## Key design decision: Pane B is deliberately plainer than Pane A
+
+Porting all ~280 singleton behaviors to a second, symmetric pane is not
+worth it for v1 — most of that code is input-quality-of-life for **mobile/
+touch** (local-echo overlay, CJK IME textarea, touch gesture handling,
+keyboard accessory bar), and this feature is desktop-only by nature (a split
+view needs a wide viewport). So:
+
+- **Pane A** (the session that was already active when you opened the split)
+  stays exactly what it is today — `this.terminal`, `this._ws`, unchanged
+  code path, zero regression risk.
+- **Pane B** is a new, smaller `SplitTerminalPane` object: its own xterm
+  instance + fit addon, its own WebSocket to `/ws/sessions/:id/terminal`,
+  resize-on-divider-drag, and plain keyboard input. It does **not** get the
+  local-echo overlay, CJK IME composition, touch/mobile handlers, or the
+  keyboard accessory bar. On a desktop, typing directly into an xterm
+  instance with no overlay is exactly how Codeman behaved before the local-
+  echo overlay existed for touch devices — normal, not degraded, for a
+  keyboard-and-mouse user.
+
+If this asymmetry actually bothers you in daily use, promoting Pane B to full
+parity is a scoped v2 (extract the shared logic already once you have two
+call sites to compare, rather than guessing the right abstraction now).
+
+One more asymmetry worth naming here rather than discovering by surprise:
+while both panes accept keyboard input, the global capture-phase shortcut
+handler (`app.js`) always resolves against Pane A — it has no notion of
+which pane currently has focus. So Ctrl+L or Ctrl+W typed while Pane B has
+focus clears or closes Pane A, not the session you were actually typing
+into. Not fixed for v1, same reasoning as the rest of this section.
+
+## Components
+
+### 1. `SplitTerminalPane` (new, `terminal-split.js`)
+
+A small class, one instance per secondary pane:
+- `constructor(sessionId, mountEl)`
+- `connect()` — creates the xterm instance (same theme/font config as the
+  primary, read from the same settings so it doesn't visually clash), opens
+  `/ws/sessions/:id/terminal`, wires input → WS, WS → terminal write
+- `fit()` — calls the fit addon; called on divider drag (rAF-throttled) and
+  on window resize
+- `destroy()` — disposes the xterm instance, closes the WS cleanly
+
+No snapshot/scrollback-restore map is needed the way `_xtermSnapshots` exists
+for Pane A — Pane B is destroyed on close, not hidden-and-restored, since
+there's no persistence requirement.
+
+### 2. Split container (layout)
+
+```
+.terminal-split-container         (flex row, only rendered when split is active)
+├── .terminal-wrap                (existing element, Pane A — untouched)
+├── .split-divider                (new, draggable seam)
+└── .terminal-pane-b              (new, hosts SplitTerminalPane's xterm + a
+                                    small header: session name + × close button)
+```
+
+When not split, `.terminal-wrap` renders exactly as it does today (no
+wrapping container at all, to keep the no-split path byte-identical to
+current behavior). Splitting inserts the container and reparents
+`.terminal-wrap` into it as the first child — same reparenting pattern
+already used by `applySessionListLayout()` for `#sessionTabs`, so this isn't
+a new pattern for the codebase.
+
+Default split is 50/50 (`flex-basis: 50%` each). Divider drag updates both
+panes' `flex-basis` live (rAF-throttled) and calls `fit()` on **both**
+terminals per tick, clamped to 20%/80% so neither pane can be dragged into an
+unusably thin sliver.
+
+### 3. Trigger UI
+
+A **"Split"** button (header, opt-in like the other header buttons —
+`showSplitButton`, default off, same pattern as `showMultiMonitorButton`)
+opens a small picker listing your other open sessions (reuses
+`this.sessions`/`sessionOrder`, filtered to exclude the currently active
+session — you cannot split a session against itself). Picking one:
+1. Creates the split container, reparents `.terminal-wrap`
+2. Instantiates `SplitTerminalPane` for the chosen session in `.terminal-pane-b`
+3. Button state flips to "close split" (or Pane B's own header × does it)
+
+Closing (via Pane B's × or the header button toggling off):
+1. `SplitTerminalPane.destroy()`
+2. Removes `.terminal-split-container`, reparents `.terminal-wrap` back to
+   its original location at 100% width
+3. Fires a resize/fit on Pane A (same `ResizeObserver`-driven fit already in
+   place today — no new code needed here, it fires naturally once the
+   container's size changes)
+
+v2 note (not designed): dragging a session tab onto the active pane as an
+alternate trigger. You confirmed right-click doesn't work today (Codeman
+doesn't intercept it) and declined a keybind, so v1 is button+picker only.
+
+### 4. Failure / edge cases
+
+- **The Pane B session ends or is deleted while split is active** → treat
+  identically to the user closing Pane B manually: destroy the pane, collapse
+  to Pane A at full width.
+- **The Pane A session ends while split is active** → Pane B is promoted:
+  it becomes the new single full-width pane (reusing today's normal
+  single-pane code path means Pane B's `SplitTerminalPane` must hand off to
+  a real `this.terminal`/`this._ws` binding — simplest correct approach is
+  to just collapse the split and let normal session-select logic reopen
+  Pane B's session as the new primary, rather than trying to promote the
+  lightweight pane object in place).
+- **Both end** → falls through to today's normal "no active session" /
+  welcome-screen state.
+- **Subagent/Ultracode floating windows** → no design work needed; they're
+  already positioned independent of `.terminal-wrap`'s layout, so they
+  continue to float over whichever pane(s) are on screen, unconstrained,
+  exactly as today.
+
+## Testing
+
+- Unit: `SplitTerminalPane` connect/fit/destroy lifecycle (mock WS, like
+  existing terminal tests use `TEST_PTY_SCRIPT`).
+- Route/integration: opening two WS connections to two different sessions
+  from one simulated client concurrently — confirms the existing per-session
+  cap and connection registry need no changes.
+- Browser (Playwright, `test/browser` since this is desktop-viewport-gated
+  UI): open split via button+picker, verify both panes render live output
+  independently, drag divider and confirm both refit, close Pane B and
+  confirm Pane A returns to full width, kill the Pane B session externally
+  and confirm auto-collapse.
+
+## Open questions for review
+
+None blocking — the scope-narrowing decisions above (Pane B feature parity,
+no persistence, side-by-side only, button+picker trigger) came directly from
+your answers during brainstorming. Flag anything here you want reconsidered.

docs/tailscale-installer-plan.md

@@ -1,5 +1,10 @@
 # Tailscale Setup in the Installer (Plan)
 
+> Superseded in part by [`installer-v2-plan.md`](installer-v2-plan.md) (2026-09-20), which
+> moved every human step before the build, added the sub-path / second-port answer for an
+> occupied `:443`, the opt-in rename, flags, and the done screen with a QR code. The
+> state machine and safety rules below still hold.
+
 Goal: make "Codeman over Tailscale, with real HTTPS" a first-class, guided path in
 `install.sh`, instead of a one-line hint pointing at the docs. Today the safest
 recommended deployment (loopback bind + `tailscale serve`) is exactly what the

docs/versioning-policy.md

@@ -40,6 +40,10 @@ A **MAJOR** bump is required to break any of these after 1.0:
    optional fields, new error codes, new SSE events) are non-breaking; breaking
    changes ship under a new prefix (`/api/v2`). The unversioned `/api/...` alias
    is kept working for the bundled UI.
+5. **The dashboard's `#session=<id>` link.** Opening the dashboard URL with a
+   `#session=<id>` fragment selects that session if this client can see it. The
+   fragment name and that meaning are stable; see
+   [Opening a session from your own page](extending-codeman.md#opening-a-session-from-your-own-page).
 
 ## What SemVer does NOT cover (internal surfaces — may change in any release)
 

docs/wiki/Agent-CLIs.md

@@ -76,7 +76,7 @@ output. The other CLIs expose no equivalent.
 | Read My Mind                                      | Yes    | No                                                   |
 | Ralph loop and its task tracker                   | Yes    | No                                                   |
 | Subagent and team windows                         | Yes    | No                                                   |
-| Model, effort, and ultracode controls             | Yes    | No                                                   |
+| Model, effort, advisor, and ultracode controls    | Yes    | No                                                   |
 | `stop` and `blocked` wait signals                 | Yes    | DeepSeek yes; elsewhere 400 if you ask for them explicitly |
 | The bundled agent skill                           | Yes    | No                                                   |
 
@@ -96,6 +96,9 @@ The defaults you will care about, all under **App Settings**:
 - **Effort** (`low` through `max`) or **ultracode** for dynamic multi-agent workflows. Also
   a soft default: `/effort` overrides it any time. Effort is deliberately not passed as an
   environment variable, because that would hard-lock it and block in-session switching.
+- **Advisor** (Sonnet, Opus or Fable): a stronger model Claude consults at decision points,
+  via Claude Code's [advisor tool](https://code.claude.com/docs/en/advisor). Also a soft
+  default: `/advisor` switches it or turns it off inside the session.
 - **Startup permission mode** (Agents & CLIs section). The default is
   `--dangerously-skip-permissions`, which is why the security model matters. You can switch
   new sessions to Anthropic's classifier-guarded `auto` mode, normal prompting, or an

docs/wiki/Contributing.md

@@ -42,10 +42,17 @@ npm run typecheck
 npm run lint
 npm run format:check
 npm run check:frontend-syntax
+npm run check:browser-excludes
 npm test -- test/<file>.test.ts   # one file, the normal way
 npm run test:ci                    # the full CI sweep
 ```
 
+`npm install` installs a `pre-push` git hook that runs the static checks above (about 10-40s,
+machine-dependent) and blocks a push that would fail them. It skips itself when you push
+something other than the checked-out HEAD, or when the tree has uncommitted changes the
+checks would read. Skip it once with `CODEMAN_SKIP_PREPUSH=1 git push`; a
+`pre-push` hook of your own is never overwritten.
+
 **Never run bare `npm test`.** The default configuration includes browser-driven Playwright
 suites that need a live server, Chromium, and environment-specific baselines; they hang or
 fail on a normal machine. `test:ci` is the honest "run everything".

docs/wiki/Core-Concepts.md

@@ -20,12 +20,19 @@ Three ways to get one, all under **+** next to the case picker:
 | How               | Result                                                                                                 |
 | ----------------- | ------------------------------------------------------------------------------------------------------ |
 | **Create New**    | A fresh `~/codeman-cases/<name>` with a scaffolded `CLAUDE.md`.                                          |
-| **Clone Repo**    | A public repo cloned into `~/codeman-cases/<name>` and registered as a case.                            |
+| **Clone Repo**    | A repo cloned into `~/codeman-cases/<name>` and registered as a case. Private repos need this machine's own git credentials (see below). |
 | **Link Existing** | An existing folder anywhere on disk, registered in place. Nothing is copied or moved.                    |
 
 Linked cases keep living where they are. Deleting a case in Codeman removes the
 registration, and for a linked case that is all it removes.
 
+**Clone Repo never asks for credentials.** It uses whatever the server's own git already has:
+an ssh key, or a credential helper such as `gh auth setup-git`. The Docker image can include
+helpers for GitHub (`gh`) and Azure DevOps (`az`), turned on in `docker-compose.override.yml`;
+then signing those CLIs in once from a shell session is enough. See the private repositories
+section of `docker/README.md`. Without credentials a private repo fails straight away with an
+authentication error.
+
 **Cases created from scratch are the only copy of that code.** Uninstalling Codeman does not
 delete `~/codeman-cases/`, but treat that directory as real work, not scratch space.
 

docs/wiki/Custom-Model-Endpoints.md

@@ -50,7 +50,13 @@ pointed at.
 the session launches straight away on that model — nothing to choose. With two or more, a
 small dialog asks which one to use for this launch before starting the session; the
 endpoint's default model, if set, is marked but not auto-picked, so a launch can deliberately
-use a different one without changing the saved default.
+use a different one without changing the saved default. The list is not raw discovery order
+either: the model llama-swap reports loaded and ready is moved to the top and tagged
+**Currently loaded**, and when nothing is loaded, the model you last launched on this harness
+and endpoint pair is moved up instead and tagged **Last used** (a per-device browser value, so
+another device starts from its own history). The default model keeps its own **Default** pill
+in both cases, and nothing is ever auto-chosen: the promoted row is simply the one under your
+thumb.
 
 **For opencode, Codex, Gemini, Pi, Grok, DeepSeek and OMP, picking an entry launches
 straight onto the endpoint** — no restart, because the endpoint is applied before the

docs/wiki/Docker-Cases.md

@@ -118,6 +118,41 @@ invisible from the host (`pi -c` and `grok -c` inside a docker case see only tha
 container's history). OMP's `sessions/` is the exception and is shared read-write, because
 Codeman reads it host-side for history and resume.
 
+**Git hosts.** The agent image can also include the GitHub CLI (`gh`) and the Azure CLI (`az`,
+with the `azure-devops` extension), off by default, and its git then uses them as credential
+helpers for github.com and Azure DevOps. When the matching switch is on, their sign-ins are
+seeded like everything else, file by file: `~/.config/gh/hosts.yml` and `config.yml`, and the
+sign-in files from `~/.azure` (not its logs or extensions). With a switch off they are never
+copied in, even if the files exist. So once a switch is on and `gh auth login` / `az login`
+have been run where Codeman runs, agents in a Docker case can clone and push private repos on
+those hosts. Two limits:
+
+- A token held in a desktop keyring or an encrypted token cache (Windows, macOS) is not
+  inside those files and does not carry in. Sign in inside the container instead. The Docker
+  server image and a headless Linux host keep it in the files, so they carry.
+- The sign-ins are mounted when a case container is **created**, so an existing container
+  never picks them up. After turning a switch on, signing in, or rebuilding the agent image,
+  **recreate the case container**: remove it, and the next session in that case creates a
+  fresh one. (Or sign in inside the existing container instead.)
+
+This hands a GitHub token and an Azure sign-in to every agent in a seeded Docker case, the
+same trust you already give it with Claude, Codex or gcloud. Turn seeding off for a case that
+should not have them.
+
+Both CLIs are opt-in. To build the agent image with them, set
+`CODEMAN_AGENT_IMAGE_INSTALL_GH=1` and/or `CODEMAN_AGENT_IMAGE_INSTALL_AZ=1` where the image
+is built: in front of `node scripts/build-agent-image.mjs`, or in the Codeman server's
+environment for the image it builds automatically (in the Docker deployment, `environment:`
+in `docker-compose.override.yml`), then rebuild the image with `--no-cache`.
+`docker/README.md` ("Private repositories") has the details and the matching switches for
+the server image.
+
+To give agents a fixed Git commit identity, set `CODEMAN_AGENT_IMAGE_GIT_USER_NAME` and
+`CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL` together in that same environment (in the Docker
+deployment, set `GIT_USER_NAME` and `GIT_USER_EMAIL` in `docker/.env` instead, which feeds
+both images). An existing `codeman/agent:base` only picks it up after a `--no-cache` rebuild
+and recreated case containers; `docker/README.md` ("Git commit identity") has the details.
+
 ## Isolation
 
 Every container runs hardened by default:

docs/wiki/Installation.md

@@ -24,16 +24,22 @@ This installs Node.js, tmux and a build toolchain if they are missing (node-pty
 Linux prebuild, so it compiles from source), clones Codeman into `~/.codeman/app`, and
 builds it.
 
-What it asks you:
+It starts by printing what it found (git, Node, tmux, build tools, agent CLIs, Tailscale,
+an existing install), then asks everything it needs up front, then does the work
+unattended. You can leave while it builds. What it asks you:
 
-1. **Permission for every system change.** Package installs and agent CLI downloads are
-   prompted individually. Nothing is installed silently. If no agent CLI is found, a menu
-   offers to install any of them (DeepSeek excepted: its npm package installs only a
-   launcher with no runnable profile), or you skip and install one yourself later.
+1. **One consent for the missing packages.** Git, Node.js, tmux and (on Linux) the build
+   toolchain are installed after a single yes, and sudo asks for your password once for
+   the whole run. Nothing is installed silently. If no agent CLI is found, a menu offers
+   to install any of them (DeepSeek excepted: its npm package installs only a launcher
+   with no runnable profile), or you skip and install one yourself later.
 2. **How the dashboard should be reachable.** Three choices:
-   - **Tailscale** (recommended for phone access): keeps the loopback bind and walks you
-     through `tailscale serve`, including the tailnet HTTPS toggle, then verifies the result
-     end to end.
+   - **Tailscale** (recommended for phone access): keeps the loopback bind, installs
+     Tailscale if needed, logs in, enables the tailnet HTTPS toggle (it opens the admin
+     page for you and waits; Ctrl+C there skips Tailscale for this run), then configures `tailscale serve` after the build and
+     verifies the result end to end. If another app already owns `:443` on your node,
+     you choose between a sub-path (`https://<machine>.<tailnet>.ts.net/codeman`, the
+     default), a second port, replacing the other mapping, or skipping.
    - **Your local network** (`0.0.0.0`): prompts for a password. Skipping the password takes
      an explicit confirmation and ends on a loud warning.
    - **This machine only** (`127.0.0.1`): the safest option, and the default for a bare
@@ -44,26 +50,54 @@ What it asks you:
    Tailscale. An existing loopback install defaults to keeping loopback, or to Tailscale when
    a serve mapping for Codeman is already there. A bare Enter never pulls in new software,
    and a non-interactive run always keeps the safe loopback default.
-3. **What to do when it finishes.** Run in this terminal, install as a background service
-   that starts on boot, or do nothing yet.
+3. **What to call this machine on your tailnet** (Tailscale route only). By default the URL
+   uses the machine's existing name. Answer yes to rename it `codeman-<hostname>`; the
+   default is no, because the tailnet name is also what SSH and everything else on that
+   machine are reached by.
+4. **Whether to run Codeman in the background.** Enter installs a systemd user service or a
+   macOS LaunchAgent that starts on boot; answering no offers to start it in this terminal
+   instead, or not at all.
+
+It ends on a screen with the URL (your tailnet, your network, or this machine), a QR code to
+scan with your phone, and the two commands you need to manage the service.
 
 Re-running the same one-liner **updates an existing install in place**. Local changes in
 `~/.codeman/app` are stashed rather than discarded, a running service is restarted and
 verified, and your existing network binding is preserved. An interrupted first install
 resumes instead of restarting.
 
-Two other entry points exist:
+Other entry points:
 
 ```bash
+install.sh status       # print the URLs, the QR code and the manage commands again
 install.sh update       # update only
-install.sh uninstall    # remove
+install.sh uninstall    # remove (offers to undo a rename it performed)
 install.sh tailscale    # retrofit Tailscale access onto an existing install
+install.sh name [<n>]   # rename this machine on your tailnet (default codeman-<hostname>)
+install.sh cloudflared  # install cloudflared for the in-app Cloudflare tunnel
 ```
 
+**Flags** answer the questions from the command line and pipe through `bash -s --`:
+
+```bash
+curl -fsSL https://getcodeman.com/install | bash -s -- --tailscale --service
+curl -fsSL https://getcodeman.com/install | bash -s -- --lan --password 'x' --service
+curl -fsSL https://getcodeman.com/install | bash -s -- --local --run
+```
+
+`--tailscale` / `--lan` / `--local` answer the access question, `--name <n>` / `--no-rename`
+the name, `--service` / `--run` / `--no-start` the last one. `--yes` takes every default
+(it still waits on a Tailscale login URL, and a network bind still asks for a password).
+`--port <n>` moves Codeman off 3000; the service file and the serve mapping follow it. On an
+existing install, `--port` and `--password` re-run the setup so the service file picks them up,
+and a re-run with `--lan` or `--tailscale` keeps the password the service already has.
+
 **Automation and CI**: with no terminal attached, any step that would change the system
 aborts with instructions instead of running silently. Set `CODEMAN_NONINTERACTIVE=1` to
 approve those steps. `CODEMAN_TAILSCALE=1` preselects the Tailscale answer, and never
-installs Tailscale itself non-interactively.
+installs Tailscale itself non-interactively; a non-interactive run never renames the
+machine and never starts a service. Everything the unattended steps print goes to
+`~/.codeman/install.log`, and the last lines of it are shown when a step fails.
 
 ## Route B: npm
 

docs/wiki/Mobile-Guide.md

@@ -60,14 +60,20 @@ On by default; it can be turned off in settings.
 
 A row of keys above the virtual keyboard, and what it contains depends on the session.
 
-**Agent sessions** get quick actions: `/init`, `/clear`, `/compact`, a clipboard key, `Esc`,
-a path picker, an image key, and 🧠 when Read My Mind is on. Destructive commands need a
-double press, so you cannot fire `/clear` with a stray thumb. On Codex sessions the bar also
-shows `⇧←` and `⇧→`, the Shift-modified arrows Codex binds to editing the last queued
-message and walking the prompt stack.
+**Agent sessions** get quick actions: `/init`, `/clear`, `/compact`, a Compose key, `Esc`,
+a path picker, and 🧠 when Read My Mind is on. Compose opens a multiline editor with
+autocorrect: Enter adds a new line, and only Send delivers the text, as one paste followed
+by Enter, so your line breaks reach the agent intact. Anything already typed on the terminal
+prompt moves into the editor when it opens. Drafts are kept per session and in memory only,
+so switching tabs keeps them and a page reload forgets them; a dot on the key shows a draft
+is parked. The editor's Image button attaches photos and puts their paths into the draft.
+Destructive commands need a double press, so you cannot fire `/clear` with a stray thumb. On
+Codex sessions the bar also shows `⇧←` and `⇧→`, the Shift-modified arrows Codex binds to
+editing the last queued message and walking the prompt stack.
 
 **Shell sessions** automatically swap it for terminal controls: `Ctrl`, `Esc`, `Tab`, four
-arrows, paste, and dismiss. Your normal preference is remembered and restored when you
+arrows, a direct Paste key (shell input is not an agent prompt, so there is no Compose
+there), and dismiss. Your normal preference is remembered and restored when you
 switch back to an agent session, so a settings change during a shell session cannot strip
 the bar away permanently.
 

docs/wiki/Notifications-And-Approvals.md

@@ -103,6 +103,34 @@ locked phone and the agent continues.
 With the inbox off, the buttons are stripped from the notification payload entirely rather
 than being shown and failing.
 
+## When a session is watching its own work
+
+An agent that starts a monitor, puts a shell in the background or hands a task to a cloud
+session is told by its CLI to end the turn and wait to be notified. The pane then goes
+quiet, and the CLI's idle notification arrives about a minute later — for a session that
+wants nothing from you.
+
+Codeman reads what the CLI prints about its own background work and treats that prompt
+differently. It raises no tab alert, no desktop notification and no push, the session stays
+out of NEEDS YOU on every surface, and the row wears a blue **watching** badge instead. Hover
+it, or read it on a phone through your screen reader, and it says what is running: "1
+monitor", "2 shells", "1 background terminal".
+
+The prompt itself is not thrown away. It sits in the Approvals drawer as an ordinary card,
+still answerable, with a line reading "quiet, watching 1 monitor" where a card you had
+already looked at would say nothing. The next time that session goes quiet for an ordinary
+reason, it alerts you exactly as before.
+
+Two limits are worth knowing. A permission prompt or a question dialog still goes red
+whatever else the agent started, because that one blocks it outright. A question asked in
+plain prose is not a dialog, so an agent that starts a monitor and then writes "which branch
+should I target?" is quiet along with the rest — check a watching session yourself if it has
+been quiet longer than the work it is waiting for should take.
+
+An agent waiting for your comments on an artifact it published never counts as watching.
+Claude shows that as "1 Artifact comment monitor", but the agent hears nothing until you
+comment, so the session alerts you like any other quiet session.
+
 ## The phone overview
 
 On phones, tapping the "C" logo gives a session overview with **NEEDS YOU** first, then

docs/wiki/Quick-Start.md

@@ -43,7 +43,7 @@ To make a new one, click **+** next to the picker. The Add Case dialog has three
 | Tab               | Use it when                                                                                                        |
 | ----------------- | ------------------------------------------------------------------------------------------------------------------ |
 | **Create New**    | Starting a fresh project. Creates `~/codeman-cases/<name>` and scaffolds a `CLAUDE.md` into it.                     |
-| **Clone Repo**    | Working on an existing public repo. Paste the URL; Codeman preflights it as you type, offers the repo's real branches and tags, and fills in the case name. |
+| **Clone Repo**    | Working on an existing repo: public, or private once this machine's git can authenticate (the Docker image can include `gh`/`az` helpers for this). Paste the URL; Codeman preflights it as you type, offers the repo's real branches and tags, and fills in the case name. |
 | **Link Existing** | The code is already on disk. Point at the folder, with **Browse** if you would rather click than type.               |
 
 The gear next to the picker holds two per-case toggles: **Agent Teams** and

docs/wiki/Remote-Access.md

@@ -33,11 +33,12 @@ Your devices join a private network, and Codeman stays bound to loopback. Nothin
 published to the internet, and you get real HTTPS with a real certificate.
 
 The installer sets this up for you, including installing Tailscale, logging in, enabling
-tailnet HTTPS, and verifying the result end to end. To retrofit it onto an existing
-install:
+tailnet HTTPS, and verifying the result end to end. It ends on the URL with a QR code to
+scan. To retrofit it onto an existing install, or to see the URL and QR code again:
 
 ```bash
 install.sh tailscale
+install.sh status
 ```
 
 By hand:
@@ -49,6 +50,22 @@ tailscale serve status
 
 Then open `https://<machine>.<tailnet>.ts.net` from any device on your tailnet.
 
+### The name in the URL
+
+The URL is the machine's MagicDNS name, so on a machine called `tnode` it is
+`https://tnode.<tailnet>.ts.net`. Three ways to influence that, from least to most work:
+
+| You want                                   | How                                                                                                   |
+| ------------------------------------------ | ----------------------------------------------------------------------------------------------------- |
+| The machine's existing name (default)      | Nothing. This is what the installer does unless you say otherwise.                                     |
+| `https://codeman-<hostname>.<tailnet>.ts.net` | Answer yes to the installer's name question, pass `--name codeman-<hostname>`, or run `install.sh name`. This renames the machine tailnet-wide (SSH included), which is why the installer defaults to no. `install.sh uninstall` offers to rename it back. |
+| `https://codeman.<tailnet>.ts.net`         | A [Tailscale Service](https://tailscale.com/docs/features/tailscale-services). Only a **tagged** node can host one (a device signed in with a user account cannot), the service is defined and approved in the admin console, and the feature is in beta. The installer does not set this up; it is a `tailscale serve --service=svc:codeman --https=443 127.0.0.1:3000` on a tagged host once the service exists. |
+
+If `:443` on your node already belongs to another app, the installer offers Codeman under
+`https://<machine>.<tailnet>.ts.net/codeman` (the default, via `tailscale serve --set-path`
+plus Codeman's `--base-url`), on a second port (`https://<machine>.<tailnet>.ts.net:8443`),
+or replacing the other mapping. It never replaces anything without asking.
+
 Notes:
 
 - Keep the loopback bind. `tailscale serve` connects to `127.0.0.1:3000` locally, so
@@ -58,7 +75,11 @@ Notes:
 - Codeman's Host-header allowlist already accepts `.ts.net`, so no extra configuration is
   needed.
 - The installer never resets or rewrites `serve` mappings other than the one pointing at
-  Codeman's port, so unrelated serve configuration is left alone.
+  Codeman's port, so unrelated serve configuration is left alone. It also never opens a
+  `tailscale funnel` (that is the public internet) and never advertises a Tailscale Service.
+- On macOS, the App Store and standalone Tailscale apps only run once someone is logged in,
+  so a headless Mac needs the open-source `tailscaled` for the URL to come back after a
+  reboot on its own.
 
 ## Cloudflare tunnel
 

docs/wiki/Running-As-A-Service.md

@@ -67,6 +67,14 @@ On Linux, if you want the service running while you are not logged in:
 loginctl enable-linger $USER
 ```
 
+On macOS, a LaunchAgent starts when you log in, not at boot. A headless Mac (no GUI login)
+needs a system LaunchDaemon instead, written by hand as root. The installer recognises an
+existing `/Library/LaunchDaemons/com.codeman.web.plist` and leaves it alone rather than
+installing a LaunchAgent next to it, since the two would fight over the port; remove the
+daemon first if you want to switch. The same login caveat applies to the App Store and
+standalone Tailscale apps, so on a headless Mac the Tailscale URL only comes back after a
+reboot if the open-source `tailscaled` is used.
+
 ### Writing the unit by hand
 
 **Linux (systemd user unit):**

docs/wiki/Settings-Reference.md

@@ -46,6 +46,7 @@ supervised by systemd or launchd; npm installs report as non-updatable. See
 | Extended Keyboard Bar         | Per device           | Which accessory bar phones get. Shell sessions override it while they are active. |
 | Wheel Scrolls Local History   | Off                  | Keeps the wheel on the local buffer instead of forwarding it to the CLI. |
 | Auto Copy Selection           | Off                  | Copies highlighted terminal text to the clipboard the moment you finish selecting it. Ctrl+C still copies on demand. |
+| Trim The Pane Margin On Copy  | On                   | Takes the left margin a full-screen agent CLI paints down its own edge off a copy, so the text pastes flush. Each CLI declares its own width, and the strip never exceeds the indent every selected line shares, so nesting is kept. Claude Code and Codex declare a margin; a shell does not. |
 | Normal / Bold font weight     | xterm defaults       | Per device, each slot from 100 to 900. The bundled JetBrains Mono renders every step, so a lighter normal weight makes Claude's bold headings stand out. Applies live to the terminal, both echo overlays and open team panes. |
 | WebGL Renderer                | On                   | With a GPU-stall watchdog that falls back to DOM rendering.            |
 | Gesture Control               | Off                  | Camera hand tracking. Also needs `CODEMAN_GESTURE=1` on the server.    |
@@ -55,12 +56,14 @@ supervised by systemd or launchd; npm installs report as non-updatable. See
 Chips for every optional header control, with a live preview of the resulting header:
 
 Run, Font Size, System Stats, Redraw Terminal, Response Viewer, Away Digest, Session
-Manager, Attachments, File Viewer, Multi-monitor, Plan Usage, Lifecycle Log, Monitor,
+Manager, Attachments, File Viewer, Multi-monitor, Split, Plan Usage, Lifecycle Log, Monitor,
 Project Insights, File Browser, Subagents, Approvals Inbox, Read My Mind, Ultracode Agents,
 Ultracode Windows, Cron.
 
 Most default to off. The stock desktop header is system stats, File Viewer, and the gear.
-New header controls never appear on phones.
+New header controls never appear on phones. Split is desktop-only regardless of this
+setting — the button and the feature both stay off below a ~1180px viewport, where two
+resizable panes plus their divider have nowhere to go.
 
 This section also holds background-agent tracking, including whether to track agents for
 every session or only the active tab.
@@ -84,13 +87,22 @@ every session or only the active tab.
 
 ### Models
 
-Claude model cards, the 1M context window switch, and the thinking effort segment. The cards
-and the switch compose into one model choice, so there is no separate "which one wins"
-question.
+Claude model cards, the 1M context window switch, the thinking effort segment and the
+advisor segment. The cards and the switch compose into one model choice, so there is no
+separate "which one wins" question.
 
-Model and effort are both **soft defaults**: the model is written into the case's
-`.claude/settings.local.json` and effort is passed at start, so `/model` and `/effort`
-inside a session override them at any time.
+Model, effort and advisor are all **soft defaults**: the model is written into the case's
+`.claude/settings.local.json` and effort and advisor are passed at start, so `/model`,
+`/effort` and `/advisor` inside a session override them at any time.
+
+**Advisor** gives new Claude sessions Claude Code's
+[advisor tool](https://code.claude.com/docs/en/advisor): a second, stronger model that Claude
+consults before committing to an approach, when an error keeps coming back, and before it
+calls a task done. A common pairing is a Sonnet main model with an Opus or Fable advisor,
+which costs less than running the stronger model all the time. **Default** leaves it to
+whatever you picked with `/advisor` yourself. The advisor needs the Anthropic API (not
+Bedrock or Vertex), and an advisor that ranks below the session's model is simply not
+attached.
 
 **Custom model endpoints** (off by default) adds a saved-endpoint list plus a matching
 section to the Run dropdown, for pointing a harness at your own OpenAI-compatible server

docs/wiki/The-Dashboard.md

@@ -48,6 +48,7 @@ One tab per session, in your order, and that order syncs across your devices.
 | Yellow tab, blinking          | The agent is waiting for input from you.                                 |
 | Red tab, blinking             | A question or permission prompt is blocking the session.                 |
 | No dot                        | The session is not running.                                              |
+| Muted grey dot plus an `exited (137)` badge | The agent inside the pane has exited, with that exit code (or `exited (signal 9)`). A bare `exited` means tmux saw the pane die but did not report how, which is not the same as a clean `exited (0)`. Detailed sidebar and rail rows read `exited` in their pill. |
 
 ![Tab alerts](https://raw.githubusercontent.com/Ark0N/Codeman/master/docs/images/tab-alerts-20260815.png)
 
@@ -116,6 +117,7 @@ The right side of the header. Almost all of these are off until you enable them
 | Lifecycle Log          | Off                | Session start, exit, and kill audit trail.                                       |
 | Cron ⏰                | Off                | Scheduled jobs.                                                                   |
 | Multi-monitor          | Off, macOS         | Opens a window spanning every display.                                            |
+| Split                  | Off, desktop only  | View a second session beside the active one, with a draggable divider.           |
 | Tunnel indicator       | When a tunnel runs | Cloudflare tunnel status.                                                        |
 | Admin panel            | Multi-user only    | User administration.                                                              |
 
@@ -149,10 +151,13 @@ Worth knowing:
 
 - **Scrollback.** Agent/TUI sessions pull their entire tmux scrollback on first open.
   Shell sessions open from a bounded recent tail so a large transcript cannot stall tab
-  switching; press **Load full history** to pull the rest explicitly. Ordinary Shell scrolling
-  and automatic output recovery stay within the bounded browser buffer.
-- **Wheel and touch scrolling** are forwarded into Claude's own transcript on recent Claude
-  versions, so the wheel scrolls the conversation rather than the terminal. `Shift+Wheel` is
+  switching. Scrolling to the top of a Shell pane pulls the most recent 1 MiB of its tmux
+  history; press **Load full history** to pull the rest explicitly. Automatic output
+  recovery stays within the bounded browser buffer.
+- **Wheel and touch scrolling** are forwarded into Claude's own transcript when a recent
+  Claude runs fullscreen (`CLAUDE_CODE_NO_FLICKER=1`, or `"tui": "fullscreen"` in
+  `~/.claude/settings.json`), so the wheel scrolls the conversation rather than the terminal.
+  Claude's default inline view keeps its history in the terminal and scrolls locally. `Shift+Wheel` is
   always local scrollback. Other CLIs scroll locally.
 - **Selection copy.** `Ctrl+C` copies when text is selected and interrupts when it is not.
   `Ctrl+Shift+C` always copies.

docs/wiki/Troubleshooting.md

@@ -164,8 +164,11 @@ Scrollback behaviour depends on the CLI, and Codeman adjusts what it strips per
 Things to try:
 
 - `Shift+Wheel` always scrolls the local buffer, whatever else is going on.
-- On Claude sessions with a recent CLI, the wheel is forwarded into Claude's own transcript,
-  so it scrolls the conversation rather than the terminal buffer. That is intended.
+- On Claude sessions running fullscreen (recent CLI with mouse tracking on), the wheel is
+  forwarded into Claude's own transcript, so it scrolls the conversation rather than the
+  terminal buffer. That is intended. Claude's default inline view scrolls locally; turn
+  fullscreen on with `CLAUDE_CODE_NO_FLICKER=1` or `"tui": "fullscreen"` in
+  `~/.claude/settings.json`.
 - Scrolling to the very top pulls the full tmux scrollback again on demand.
 
 ### The wheel does nothing in a Codex session

docs/wiki/Working-With-Files.md

@@ -13,7 +13,8 @@ It renders what it can:
 
 | Kind                     | Behaviour                                                                 |
 | ------------------------ | ------------------------------------------------------------------------- |
-| Text and code            | Syntax-aware preview. Long files are truncated in plain preview.           |
+| Text and code            | Plain preview with Lines (line numbers) and Wrap toggles in the header. Long files are truncated in plain preview. |
+| Markdown                 | Rendered by default: headings, tables, code blocks with copy buttons, images and links relative to the file (root-relative ones resolve from the workspace root, as on GitHub). Opened from an attachment card, where the file's folder is unknown, relative images show their alt text and relative links show as plain text. The MD pill in the header flips to source. |
 | Images                   | Inline.                                                                    |
 | Audio and video          | Inline with a working scrub bar, because range requests are supported.     |
 | PDF and Office documents | Converted for preview when a converter is available.                       |
@@ -85,8 +86,9 @@ File paths in a session are links. That works in two places:
   render as underlined monospace links.
 
 Clicking one opens it in the preview: images and PDFs render, video and audio play with a
-working scrub bar, documents convert, text and Markdown show inline. Log-shaped files open in
-the tail viewer instead, which follows a file that is still being written.
+working scrub bar, documents convert, text shows inline and Markdown renders. The exception is
+a text or Markdown file inside the workspace clicked in the terminal: that opens in the tail
+viewer instead, which follows a file that is still being written.
 
 Paths **outside** the session's workspace work too, which matters because that is where most
 of an agent's output lands: a screenshot in `/tmp`, a capture in its own scratchpad, a file in

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "aicodeman",
-  "version": "1.31.0",
+  "version": "1.33.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "aicodeman",
-      "version": "1.31.0",
+      "version": "1.33.3",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [
@@ -55,6 +55,7 @@
         "@types/web-push": "^3.6.4",
         "@types/ws": "^8.18.1",
         "@vitest/coverage-v8": "^4.1.8",
+        "@xterm/headless": "^6.0.0",
         "agent-browser": "^0.6.0",
         "esbuild": "^0.27.3",
         "eslint": "^9.0.0",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "aicodeman",
-  "version": "1.31.0",
+  "version": "1.33.3",
   "description": "Mission control for AI coding agents - run 20 autonomous agents with real-time monitoring and session persistence",
   "type": "module",
   "main": "dist/index.js",
@@ -28,6 +28,7 @@
     "pretest:mobile": "node scripts/prepare-test-vendor.mjs",
     "test:mobile": "vitest run --config test/mobile/vitest.config.ts",
     "check:frontend-syntax": "node scripts/check-frontend-syntax.mjs",
+    "check:browser-excludes": "node scripts/check-browser-test-excludes.mjs",
     "fix:node-pty": "node scripts/fix-node-pty.mjs",
     "typecheck": "tsc --noEmit && tsc -p config/tsconfig.scripts.json",
     "lint": "eslint --config config/eslint.config.js 'src/**/*.ts'",
@@ -123,6 +124,7 @@
     "@types/web-push": "^3.6.4",
     "@types/ws": "^8.18.1",
     "@vitest/coverage-v8": "^4.1.8",
+    "@xterm/headless": "^6.0.0",
     "agent-browser": "^0.6.0",
     "esbuild": "^0.27.3",
     "eslint": "^9.0.0",

plugins/codeman/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "codeman",
   "description": "Drive Codeman, the self-hosted session manager for AI coding agents, from inside a Claude Code session: spawn worker sessions, prompt them, wait for them, read their answers, clean up. Acts only inside a Codeman-managed session.",
-  "version": "1.31.0",
+  "version": "1.33.3",
   "author": {
     "name": "Ark0N",
     "url": "https://github.com/Ark0N"

plugins/codeman/skills/codeman/SKILL.md

@@ -47,7 +47,7 @@ later call opens with, and your first REAL call performs them anyway:
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
 ```
 
 ⚠️ **Never spend a Bash call on this check alone.** §1's block opens with this same
@@ -75,8 +75,8 @@ PRE="${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh"
 mkdir -p "$(dirname "$PRE")"
 # Rewrite unless the file already ends with THIS version's stamp, so a stale or a
 # half-written file self-heals here instead of costing you a round trip to rm it.
-grep -qs '^CODEMAN_PREAMBLE=1.30.1$' "$PRE" || (umask 077; cat > "$PRE" <<'PREAMBLE'
-# ---- Codeman agent preamble 1.30.1 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
+grep -qs '^CODEMAN_PREAMBLE=1.33.4$' "$PRE" || (umask 077; cat > "$PRE" <<'PREAMBLE'
+# ---- Codeman agent preamble 1.33.4 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
 API="${CODEMAN_API_URL:?CODEMAN_API_URL not set; refusing to guess}"
 SELF="${CODEMAN_SESSION_ID:?CODEMAN_SESSION_ID not set}"
 # Credentials, cheapest first. Your session has usually INHERITED the server's
@@ -196,6 +196,11 @@ _accept_trust() {  # <sid> -> 0 once it has answered the dialog, 1 if it could n
 # rather than handed back, because a worker that never drew its composer would eat the
 # task prompt with its trust dialog. There is deliberately no pid poll: wait-output
 # already blocks until the composer draws, and pid!=null proved startup, never readiness.
+# CODEMAN_WORKER_ADVISOR=opus (or fable / sonnet) gives every CLAUDE worker spawned while
+# it is set Claude Code's advisor tool: a stronger model the worker consults before
+# committing to an approach, on a recurring error and before declaring the task done.
+# Other modes ignore it. A value the server refuses fails the spawn (INVALID_INPUT); an
+# advisor that ranks below the worker's model is accepted but never attached by claude.
 spawn_worker() {
   local name="${1:?spawn_worker needs a case name}" mode="${2:-claude}" q sid cp r
   # parentSessionId doubles the CURL header, so a spawn_worker copied off the shared
@@ -207,12 +212,19 @@ spawn_worker() {
   # server clamps this back to `workspace-write` for an owner without the grant.
   # Spawn by hand (§5.1) when you want a worker that asks.
   q=$("${CURL[@]}" -X POST "$API/api/v1/quick-start" -H 'Content-Type: application/json' \
-      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" \
+      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" --arg a "${CODEMAN_WORKER_ADVISOR:-}" \
         '{caseName:$n,mode:$m,parentSessionId:$p}
-         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)')")
+         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)
+         + (if $m == "claude" and $a != "" then {advisorModel:$a} else {} end)')")
   sid=$(jq -r 'if .success then .data.sessionId else empty end' <<<"$q")
   # NOT retryable in a loop: every quick-start failure code is terminal (§5.1).
   [ -n "$sid" ] || { jq -c '{error,errorCode}' <<<"$q" >&2; return 1; }
+  # A server without advisor support DROPS the field instead of refusing it, so read it
+  # back: a worker silently missing the advisor it was asked for is worth one line.
+  if [ "$mode" = claude ] && [ -n "${CODEMAN_WORKER_ADVISOR:-}" ] &&
+     [ "$("${CURL[@]}" "$API/api/v1/sessions/$sid" | jq -r '.data.advisorModel // empty')" != "$CODEMAN_WORKER_ADVISOR" ]; then
+    echo "worker $sid: this Codeman server ignored CODEMAN_WORKER_ADVISOR (no advisor support); it runs without one" >&2
+  fi
   if [ "$mode" = deepseek ]; then
     # The one non-claude mode with REAL end-of-turn signals: its TUI reports
     # idle/working/blocked to Codeman, so sendwait, until=stop and the Approvals
@@ -372,10 +384,10 @@ last_text() {
 # The stamp is the LAST line on purpose (a truncated write leaves it unset) and is kept
 # bare on purpose: the write condition above anchors on it with $, so an inline comment
 # here would fail that match and rewrite this file on every single bootstrap.
-CODEMAN_PREAMBLE=1.30.1
+CODEMAN_PREAMBLE=1.33.4
 PREAMBLE
 )
-. "$PRE"; [ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble at $PRE is stale or truncated: rm it and re-run this block"; exit 1; }
+. "$PRE"; [ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble at $PRE is stale or truncated: rm it and re-run this block"; exit 1; }
 ```
 
 Every later Bash call that touches the API starts with the same two loader lines from
@@ -426,7 +438,7 @@ and no per-call body to hand-build.
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null   # §0 loader
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
 N=(alpha beta)                    # INVENT one fresh case name per worker; never list cases first
                                   # (a name may carry a mode: `beta:deepseek`, see below)
 T=('reply with one line: the absolute path of your working directory'
@@ -493,6 +505,12 @@ Four things this block leans on, each one link away, no detour needed to run it:
   `sendwait` reads the composer and keeps pressing Enter until the prompt has left it.
   All three are reasons to let `sendwait` build the call rather than hand-rolling it.
 - Each `sendwait` costs that worker one billed turn, as does every prompt you send it.
+- For long or high-stakes worker tasks, `CODEMAN_WORKER_ADVISOR=opus spawn_workers "${N[@]}"`
+  (`fable`, `opus` or `sonnet`) gives each claude worker Claude Code's advisor tool: a
+  stronger model it consults before committing to an approach, on a recurring error and
+  before declaring the task done. Advisor calls bill extra tokens, and an advisor ranked
+  below the worker's own model is never attached (on an Opus worker only `opus` and
+  `fable` do anything).
 - Deleting the sessions does **not** remove the case directories. They are marked as
   agent-created, so `GET /api/v1/cases/agent-created` lists them for cleanup: §5.14.
 

plugins/codeman/skills/codeman/preamble.sh

@@ -1,4 +1,4 @@
-# ---- Codeman agent preamble 1.30.1 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
+# ---- Codeman agent preamble 1.33.4 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
 API="${CODEMAN_API_URL:?CODEMAN_API_URL not set; refusing to guess}"
 SELF="${CODEMAN_SESSION_ID:?CODEMAN_SESSION_ID not set}"
 # Credentials, cheapest first. Your session has usually INHERITED the server's
@@ -118,6 +118,11 @@ _accept_trust() {  # <sid> -> 0 once it has answered the dialog, 1 if it could n
 # rather than handed back, because a worker that never drew its composer would eat the
 # task prompt with its trust dialog. There is deliberately no pid poll: wait-output
 # already blocks until the composer draws, and pid!=null proved startup, never readiness.
+# CODEMAN_WORKER_ADVISOR=opus (or fable / sonnet) gives every CLAUDE worker spawned while
+# it is set Claude Code's advisor tool: a stronger model the worker consults before
+# committing to an approach, on a recurring error and before declaring the task done.
+# Other modes ignore it. A value the server refuses fails the spawn (INVALID_INPUT); an
+# advisor that ranks below the worker's model is accepted but never attached by claude.
 spawn_worker() {
   local name="${1:?spawn_worker needs a case name}" mode="${2:-claude}" q sid cp r
   # parentSessionId doubles the CURL header, so a spawn_worker copied off the shared
@@ -129,12 +134,19 @@ spawn_worker() {
   # server clamps this back to `workspace-write` for an owner without the grant.
   # Spawn by hand (§5.1) when you want a worker that asks.
   q=$("${CURL[@]}" -X POST "$API/api/v1/quick-start" -H 'Content-Type: application/json' \
-      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" \
+      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" --arg a "${CODEMAN_WORKER_ADVISOR:-}" \
         '{caseName:$n,mode:$m,parentSessionId:$p}
-         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)')")
+         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)
+         + (if $m == "claude" and $a != "" then {advisorModel:$a} else {} end)')")
   sid=$(jq -r 'if .success then .data.sessionId else empty end' <<<"$q")
   # NOT retryable in a loop: every quick-start failure code is terminal (§5.1).
   [ -n "$sid" ] || { jq -c '{error,errorCode}' <<<"$q" >&2; return 1; }
+  # A server without advisor support DROPS the field instead of refusing it, so read it
+  # back: a worker silently missing the advisor it was asked for is worth one line.
+  if [ "$mode" = claude ] && [ -n "${CODEMAN_WORKER_ADVISOR:-}" ] &&
+     [ "$("${CURL[@]}" "$API/api/v1/sessions/$sid" | jq -r '.data.advisorModel // empty')" != "$CODEMAN_WORKER_ADVISOR" ]; then
+    echo "worker $sid: this Codeman server ignored CODEMAN_WORKER_ADVISOR (no advisor support); it runs without one" >&2
+  fi
   if [ "$mode" = deepseek ]; then
     # The one non-claude mode with REAL end-of-turn signals: its TUI reports
     # idle/working/blocked to Codeman, so sendwait, until=stop and the Approvals
@@ -294,4 +306,4 @@ last_text() {
 # The stamp is the LAST line on purpose (a truncated write leaves it unset) and is kept
 # bare on purpose: the write condition above anchors on it with $, so an inline comment
 # here would fail that match and rewrite this file on every single bootstrap.
-CODEMAN_PREAMBLE=1.30.1
+CODEMAN_PREAMBLE=1.33.4

plugins/codeman/skills/codeman/reference/endpoints.md

@@ -340,11 +340,18 @@ ESC=$(printf '\033')
 ### Starting a worker
 
 `POST /api/v1/quick-start` body (all optional):
-`{"caseName":"worker-1","mode":"claude","sessionName":"w9-worker","effort":"high"}`
+`{"caseName":"worker-1","mode":"claude","sessionName":"auth-worker","effort":"high"}`
 ,  `mode` ∈ `claude|shell|opencode|codex|gemini|antigravity|pi|grok|deepseek|omp`; response is
 `.data.{sessionId, caseName, casePath}`. Creates the case directory (a real directory
 on the user's disk) if missing, do not retry it in a loop, and remember the name.
 
+A claude worker also takes `"advisorModel":"opus"` (`fable`, `opus`, `sonnet` or a full
+model id): Claude Code's advisor tool, a stronger model the worker consults before
+committing to an approach, on a recurring error and before declaring the task done. It is
+a soft default the worker can change with `/advisor`. Remote and docker cases refuse it
+(400), as they refuse `effort`. `spawn_worker` and `spawn_workers` send it for you when
+`CODEMAN_WORKER_ADVISOR` is set.
+
 ⚠️ A `mode` whose CLI is **not installed on the server** fails the spawn with
 `OPERATION_FAILED`; it never falls back to claude. Probe first whenever you did not pick
 the mode yourself: `GET /api/v1/claude/status`, `GET /api/v1/opencode/status`,
@@ -384,7 +391,7 @@ every claude create path installs them, so a linked case and a raw path both get
 
 **The two-step alternative, `POST /api/v1/sessions`.** Use it when you need a session in
 a directory that is not a case (body takes `workingDir`, `mode`, `name`, `effort`,
-`envOverrides`). Three differences that break copied code:
+`advisorModel`, `envOverrides`). Three differences that break copied code:
 
 - The id is at **`.data.session.id`**, not quick-start's `.data.sessionId`
   (`session-routes.ts:878` returns `{ session: lightState }`).

plugins/codeman/skills/codeman/reference/messaging.md

@@ -101,11 +101,16 @@ the case name, read it from the listing.
 From Codeman 1.16 a LOCAL claude spawn passes `--name <session name>` when the local
 CLI is 2.1.224+ (`buildNameCliArgs`, `session-cli-builder.ts:97-101`, wired in at
 `tmux-manager.ts:797`), so a worker's peer name usually IS its Codeman session name
-(verified live: quick-start with `sessionName: "w9-msgtest"` listed as `w9-msgtest`,
-and its messages arrive tagged `from-name="w9-msgtest"`; a derived-name worker's
+(verified live: a quick-start `sessionName` is listed as that exact peer name, and
+the worker's messages arrive tagged `from-name="<that name>"`; a derived-name worker's
 messages carry no `from-name`). Name your workers: a quick-start WITHOUT
 `sessionName` leaves the Codeman name empty, so there is nothing to pass and the
-peer name stays derived. The flag is fail-closed (older/unknown CLI omits it, because an
+peer name stays derived. ⚠️ Give them a DESCRIPTIVE name: only a name the user chose
+is pinned (`Session.cliPinnedName`), because `--name` is also the conversation's
+`/resume` title and terminal title and suppresses Claude's own generated title. A
+placeholder-shaped name (`w9-msgtest`, anything matching `isGeneratedSessionName`)
+and an auto name are NOT passed, so such a worker's peer name is derived; use
+`msgtest-worker` rather than `w9-msgtest`. The flag is fail-closed (older/unknown CLI omits it, because an
 unknown flag aborts startup and would kill every spawn) and allowlist-sanitized (a name of
 only unsafe characters is dropped), and the docker/remote builders never see it at all
 (`tmux-manager.ts:782-789`), which is why the `tmux` column stays the canonical join key
@@ -196,8 +201,8 @@ idle:
 The contract an orchestrator follows for any fleet of two or more messaging workers.
 Every topology in the next section is this protocol plus a wiring diagram.
 
-1. **Spawn with a name, and confirm hooks.** Use `quick-start` with `sessionName` (the
-   `--name` gate above). Session create installs the hooks block into the workspace
+1. **Spawn with a name, and confirm hooks.** Use `quick-start` with a descriptive,
+   non-`w<N>-` `sessionName` (the `--name` gate above). Session create installs the hooks block into the workspace
    whatever kind it is, so a linked case and a raw `POST /api/sessions` path both get
    `stop`/`blocked` by default. ⚠️ Not unconditionally: the operator can turn
    `workspaceHooksEnabled` off, remote SSH sessions never get hooks, and a session from

plugins/codeman/skills/codeman/reference/recipes.md

@@ -21,7 +21,7 @@ by sourcing the preamble file the §0 bootstrap wrote, and checking its version
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; re-run the §0 bootstrap"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; re-run the §0 bootstrap"; exit 1; }
 ```
 
 Do **not** re-paste the preamble body into each call. Sourcing it is what retires the

plugins/codeman/skills/codeman/reference/verbs.md

@@ -692,8 +692,9 @@ The shape, each step verified live (probes, failure modes and safety detail in
    [§5.2](#52-readiness)).
 2. `ListAgents`: find the worker's row by its `tmux codeman-<first 8 of session id>`
    column; the row's `name [ref]` is the address. On Codeman 1.16+ with claude
-   2.1.224+ a worker's peer name is its Codeman session name, so pass `sessionName`
-   in quick-start to pick it; older setups list a name derived from the case folder.
+   2.1.224+ a worker's peer name is its Codeman session name, so pass a DESCRIPTIVE
+   `sessionName` in quick-start to pick it (a `w<N>-` placeholder-shaped name is not
+   pinned, so it lists derived); older setups list a name derived from the case folder.
    No row = messaging is off for that worker (it is feature-flagged even on matching
    CLI versions, observed live): fall back to the HTTP recipes without complaint.
 3. `SendMessage` the task; first contact must use the `name [ref]` form copied from

scripts/build.mjs

@@ -146,10 +146,44 @@ console.log('\n[build] content-hash cache busting');
     html = html.replaceAll(`"${original}"`, `"${hashed}"`);
   }
   writeFileSync(join(distPublic, 'index.html'), html);
+
+  // Rewrite sw.js from the SAME manifest that just renamed the files.
+  //
+  // The service worker's precache list used to be maintained by hand with the
+  // pre-hash names, so after this step every entry in it pointed at a file that
+  // no longer existed and `cache.add(...).catch(() => {})` hid it. Deriving it
+  // here is the only way the two cannot drift.
+  //
+  // The cache key gets the build hash for the same reason: `activate` deletes
+  // every cache that is not the current one, so a constant key meant that
+  // cleanup never ran and hashed assets from every past release piled up.
+  const swPath = join(distPublic, 'sw.js');
+  let sw = readFileSync(swPath, 'utf8');
+  const hashedAssets = Object.values(manifest);
+  const buildId = createHash('md5').update(hashedAssets.join('|')).digest('hex').slice(0, 12);
+  // Rewrite the two declarations. Anchored on the full `const … = …;` text so
+  // each pattern occurs exactly once and cannot collide with prose in sw.js's
+  // own comments — an earlier cut used bare `__BUILD_ID__` sentinels and the
+  // first match landed in the comment that documented them, leaving the real
+  // constant untouched and still producing a plausible-looking cache key.
+  const swEdits = [
+    ["const BUILD_ID = 'dev';", `const BUILD_ID = '${buildId}';`],
+    ['const HASHED_ASSETS = [];', `const HASHED_ASSETS = [${hashedAssets.map((p) => JSON.stringify(p)).join(', ')}];`],
+  ];
+  for (const [from, to] of swEdits) {
+    const hits = sw.split(from).length - 1;
+    if (hits !== 1) {
+      throw new Error(`sw.js: expected exactly one \`${from}\`, found ${hits} — precache would ship stale`);
+    }
+    sw = sw.replace(from, to);
+  }
+  writeFileSync(swPath, sw);
+
   console.log('  Hashed files:');
   for (const [orig, hashed] of Object.entries(manifest)) {
     console.log(`    ${orig} -> ${hashed}`);
   }
+  console.log(`  sw.js: cache bucket codeman-${buildId}, ${hashedAssets.length} precached assets`);
 }
 
 // 6. Compress with gzip + brotli

scripts/check-browser-test-excludes.mjs

@@ -0,0 +1,185 @@
+#!/usr/bin/env node
+/**
+ * Browser-test exclusion check.
+ *
+ * `npm run test:ci` must never try to drive a real browser: CI runners (and any
+ * clean checkout) have no chromium, so such a file dies with
+ * `browserType.launch: Executable doesn't exist` and takes the whole suite with
+ * it. `config/vitest.ci.config.ts` therefore excludes every browser-driven test
+ * via `BROWSER_TEST_GLOBS` in `config/test-suites.ts`. That list is maintained
+ * BY HAND, and a new browser test simply does not appear in it unless someone
+ * remembers. The omission is invisible on a developer machine that has run
+ * `npx playwright install`, where the test passes, and only shows up on a clean
+ * runner.
+ *
+ * Two deliberate design choices:
+ *
+ * 1. **Detection is by CONTENT, not filename.** Matching `*.browser.test.ts`
+ *    would miss the browser tests that predate that convention
+ *    (`inline-rename`, `opencode-resize`, `webgl-fallback`,
+ *    `terminal-copy-shortcut`, `codex-predictive-echo`). What actually makes a
+ *    file dangerous is importing a browser driver, so that is what is tested.
+ *    ⚠️ Only a DIRECT import is seen: a test that reaches playwright through a
+ *    helper module (e.g. `test/mobile/helpers/browser.ts`) is not detected, so
+ *    such a test still has to be added to `BROWSER_TEST_GLOBS` by hand.
+ *
+ * 2. **The exclusion side is answered by vitest itself**, via
+ *    `vitest list --filesOnly`, rather than by re-implementing glob matching
+ *    against the config's `exclude` array. Patterns there include `test/mobile/**`
+ *    and `perf-*`; a hand-rolled matcher that disagreed with vitest by even one
+ *    edge case would report a gap that does not exist, or miss one that does.
+ *    Asking the real resolver cannot drift from the real behaviour.
+ *
+ * The pure pieces are exported for test/check-browser-test-excludes.test.ts; the
+ * check itself only runs when this file is executed directly.
+ */
+import { readdirSync, readFileSync } from 'node:fs';
+import { join, dirname, relative, sep, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { execFileSync } from 'node:child_process';
+
+const ROOT = join(dirname(fileURLToPath(import.meta.url)), '..');
+const CI_CONFIG = join('config', 'vitest.ci.config.ts');
+const SUITES_FILE = join('config', 'test-suites.ts');
+
+/** Importing any one of these means the test needs a real browser binary. */
+const BROWSER_DRIVER =
+  /\bfrom\s+['"](?:playwright|playwright-core|@playwright\/test|puppeteer|puppeteer-core)['"]|\b(?:require|import)\(\s*['"](?:playwright|playwright-core|@playwright\/test|puppeteer|puppeteer-core)['"]\s*\)/;
+
+/** @param {string} source */
+export function importsBrowserDriver(source) {
+  return BROWSER_DRIVER.test(source);
+}
+
+/** @param {string} dir @returns {string[]} */
+function walk(dir) {
+  const out = [];
+  for (const entry of readdirSync(dir, { withFileTypes: true })) {
+    const path = join(dir, entry.name);
+    if (entry.isDirectory()) out.push(...walk(path));
+    else if (entry.isFile() && entry.name.endsWith('.test.ts')) out.push(path);
+  }
+  return out;
+}
+
+/**
+ * Every `*.test.ts` under `<root>/test`, as sorted repo-relative POSIX paths (the form
+ * `vitest list` prints).
+ *
+ * @param {string} root
+ * @returns {string[]}
+ */
+export function findTestFiles(root) {
+  return walk(join(root, 'test'))
+    .map((file) => relative(root, file).split(sep).join('/'))
+    .sort();
+}
+
+/**
+ * The subset of {@link findTestFiles} that imports a browser driver.
+ *
+ * @param {string} root
+ * @returns {string[]}
+ */
+export function findBrowserTests(root) {
+  return findTestFiles(root).filter((file) => importsBrowserDriver(readFileSync(join(root, file), 'utf8')));
+}
+
+/**
+ * Parse `vitest list --filesOnly` output into a set of repo-relative paths. Stray
+ * blank or decorative lines are ignored rather than assuming the format is pristine.
+ *
+ * @param {string} output
+ * @returns {Set<string>}
+ */
+export function parseVitestFileList(output) {
+  return new Set(
+    output
+      .split('\n')
+      .map((line) => line.trim())
+      .filter((line) => line.endsWith('.test.ts'))
+      .map((line) => line.replace(/^\.\//, ''))
+  );
+}
+
+/**
+ * Whether the `vitest list` paths and the walked tree name at least one file in common.
+ * False means the two sides are not speaking the same path format (absolute paths, backslashes
+ * or a new prefix after a vitest upgrade), and then {@link findLeaks} would find nothing
+ * against a perfectly non-empty listing.
+ *
+ * @param {Set<string>} ciFiles
+ * @param {string[]} testFiles
+ */
+export function listingMatchesTree(ciFiles, testFiles) {
+  return testFiles.some((file) => ciFiles.has(file));
+}
+
+/**
+ * @param {string[]} browserTests
+ * @param {Set<string>} ciFiles
+ * @returns {string[]} browser-driven files that the CI config would still collect
+ */
+export function findLeaks(browserTests, ciFiles) {
+  return browserTests.filter((file) => ciFiles.has(file));
+}
+
+function main() {
+  const testFiles = findTestFiles(ROOT);
+  const browserTests = findBrowserTests(ROOT);
+
+  let collected;
+  try {
+    collected = execFileSync('npx', ['vitest', 'list', '--config', CI_CONFIG, '--filesOnly'], {
+      cwd: ROOT,
+      encoding: 'utf8',
+      stdio: ['ignore', 'pipe', 'pipe'],
+    });
+  } catch (err) {
+    console.error('✗ could not enumerate the CI test set via `vitest list`.');
+    console.error(err.stderr ? err.stderr.toString() : String(err));
+    process.exit(1);
+  }
+
+  const ciFiles = parseVitestFileList(collected);
+  if (ciFiles.size === 0) {
+    // An empty list would make every browser test look excluded: fail rather than pass vacuously.
+    console.error('✗ `vitest list` reported no test files; refusing to pass on an empty CI set.');
+    process.exit(1);
+  }
+  // Same vacuous pass, one step removed: a listing whose paths never match the tree. This guard,
+  // not `vitest list --json`, is the answer to format drift: the JSON form prints absolute paths
+  // that would need canonicalizing against ROOT (symlinked checkouts), and its shape can drift too.
+  if (!listingMatchesTree(ciFiles, testFiles)) {
+    const sample = [...ciFiles].slice(0, 3).join(', ');
+    console.error(
+      `✗ none of the ${ciFiles.size} paths \`vitest list\` reported (e.g. ${sample}) is one of the ${testFiles.length} test/**/*.test.ts files; its output format has probably changed.`
+    );
+    process.exit(1);
+  }
+
+  const leaked = findLeaks(browserTests, ciFiles);
+
+  if (leaked.length > 0) {
+    console.error(`✗ ${leaked.length} browser-driven test file(s) are NOT excluded from ${CI_CONFIG}:\n`);
+    for (const file of leaked) console.error(`    ${file}`);
+    console.error(`
+These import a browser driver, so on a runner with no chromium they fail with
+"browserType.launch: Executable doesn't exist" and take the suite down. Add each
+to BROWSER_TEST_GLOBS in ${SUITES_FILE} (${CI_CONFIG} derives its excludes from
+it, and \`npm run test:browser\` its includes).
+
+They may well pass on this machine; that is the trap. To reproduce a clean
+runner locally:
+  PLAYWRIGHT_BROWSERS_PATH=\$(mktemp -d) PUPPETEER_CACHE_DIR=\$(mktemp -d) npm run test:ci`);
+    process.exit(1);
+  }
+
+  console.log(
+    `✓ all ${browserTests.length} browser-driven test files are excluded from the CI suite (${ciFiles.size} files collected)`
+  );
+}
+
+if (process.argv[1] && resolve(process.argv[1]) === fileURLToPath(import.meta.url)) {
+  main();
+}

scripts/git-hooks.mjs

@@ -0,0 +1,253 @@
+/**
+ * @fileoverview Git hook bodies + install policy, shared by scripts/postinstall.js and
+ * pinned by test/git-hooks.test.ts.
+ *
+ * Why a pre-push hook: the static CI job (lockfile, typecheck, lint, format, frontend
+ * syntax, ...) fails often on things a contributor could have caught locally in seconds,
+ * and finding out after a push costs a full CI round-trip plus a fix-up commit. Running
+ * the same checks before the push surfaces those failures in ~10-40s instead (12s on a fast
+ * workstation, ~35s measured elsewhere; typecheck, format:check and lint dominate).
+ *
+ * Why pre-PUSH and not pre-commit: a commit is cheap and local, a push is what CI and
+ * reviewers pick up. And why the STATIC tier only: the unit/integration suite takes
+ * minutes, which nobody tolerates per push, so a hook that ran it would be bypassed
+ * within a day. The checks below mirror the static CI job.
+ *
+ * ⚠️ The checks read the WORKING TREE, not the commits being pushed. So the hook skips
+ * (with a one-line notice) whenever the two can differ: when HEAD is not the commit being
+ * pushed, and when `git status` shows uncommitted or untracked changes in a path a check
+ * reads ({@link PRE_PUSH_WATCHED_PATHS}). In a checkout shared by several agent sessions
+ * the second case is usually another session's WIP, which must not block this push.
+ *
+ * ⚠️ This installer is deliberately MARKER-OWNED, unlike the older pre-commit installer in
+ * postinstall.js which overwrites whatever it finds. A developer's own pre-push hook must
+ * survive `npm install`.
+ */
+
+import { execFileSync } from 'node:child_process';
+import { chmodSync, existsSync, mkdirSync, readFileSync, realpathSync, writeFileSync } from 'node:fs';
+import { basename, dirname, join, resolve } from 'node:path';
+
+/**
+ * Ownership marker. ⚠️ Never bump the version suffix: ownership is matched on this exact
+ * string, so a `v2` would read every installed `v1` hook as foreign and never refresh it.
+ * A changed body still reaches installed hooks, because the refresh compares the whole file.
+ */
+export const PRE_PUSH_MARKER = '# codeman-managed-hook: pre-push v1';
+
+/**
+ * Checks that make up the fast tier, cheapest first so failures surface sooner. Each entry
+ * is the argument list for `npm run`, and each is a step of the static job in
+ * .github/workflows/ci.yml (test/git-hooks.test.ts pins that every script exists).
+ */
+export const PRE_PUSH_CHECKS = [
+  ['check:lockfile'],
+  ['generate:cli-catalog', '--', '--check'],
+  ['check:browser-excludes'],
+  ['check:frontend-syntax'],
+  ['format:check'],
+  ['lint'],
+  ['typecheck'],
+];
+
+/**
+ * Paths whose uncommitted state would leak into a check, so a dirty one makes the hook skip.
+ * Derived from what each check reads: src/ (format:check, lint, typecheck,
+ * check:frontend-syntax), config/ (eslint + vitest configs, test-suites.ts, the CLI
+ * catalogue), scripts/ (every check is a script there, and typecheck's second pass compiles
+ * one), test/ (check:browser-excludes scans it and runs `vitest list` over it),
+ * package.json + package-lock.json (check:lockfile), install.sh (generate:cli-catalog
+ * --check diffs its generated block), tsconfig.json (typecheck, and
+ * config/tsconfig.scripts.json extends it) and .prettierignore + .editorconfig
+ * (format:check; the Prettier CLI honours .editorconfig by default).
+ */
+export const PRE_PUSH_WATCHED_PATHS = [
+  'src',
+  'config',
+  'scripts',
+  'test',
+  'package.json',
+  'package-lock.json',
+  'install.sh',
+  'tsconfig.json',
+  '.prettierignore',
+  '.editorconfig',
+];
+
+/**
+ * Render the pre-push hook script.
+ *
+ * POSIX sh, not bash: this ships to whatever shell the contributor's git uses.
+ */
+export function renderPrePushHook() {
+  const runs = PRE_PUSH_CHECKS.map((args) => `run_check ${args.join(' ')}`).join('\n');
+  const watched = PRE_PUSH_WATCHED_PATHS.join(' ');
+
+  return `#!/bin/sh
+${PRE_PUSH_MARKER}
+# Installed by scripts/postinstall.js. Edit scripts/git-hooks.mjs, not this file:
+# it is regenerated on npm install. Delete the marker line above to take ownership
+# and the installer will leave your version alone.
+#
+# Skip once:   CODEMAN_SKIP_PREPUSH=1 git push
+# Skip always: remove this file.
+
+[ "$CODEMAN_SKIP_PREPUSH" = "1" ] && exit 0
+
+repo_root=$(git rev-parse --show-toplevel 2>/dev/null) || exit 0
+cd "$repo_root" || exit 0
+
+# Nothing to check without dependencies (fresh clone, or a worktree that never ran
+# npm install). Warn rather than blocking the push on a setup detail.
+if [ ! -d node_modules ]; then
+  echo "pre-push: node_modules missing, skipping checks (run 'npm install' to enable them)."
+  exit 0
+fi
+
+# GUI git clients and IDEs often run hooks with a minimal PATH that lacks an nvm or
+# Homebrew Node. Every check would then fail with "npm: not found", so skip instead.
+command -v npm >/dev/null 2>&1 || { echo "pre-push: npm not on PATH, skipping checks."; exit 0; }
+
+# git feeds us "<localref> <localsha> <remoteref> <remotesha>" per ref. A deletion has an
+# all-zero local sha and no tree worth checking; if every ref is a deletion, skip.
+# The checks below read the working tree, so they only say something about a pushed commit
+# that IS the checked-out HEAD (tags are peeled to their commit first).
+head=$(git rev-parse -q --verify HEAD 2>/dev/null)
+has_content=0
+not_head=''
+while read -r localref localsha _remoteref _remotesha; do
+  [ -z "$localsha" ] && continue
+  case "$localsha" in
+    0000000000000000000000000000000000000000) ;;
+    *)
+      has_content=1
+      commit=$(git rev-parse -q --verify "$localsha^{commit}" 2>/dev/null)
+      [ -n "$head" ] && [ "$commit" = "$head" ] || not_head="$localref"
+      ;;
+  esac
+done
+[ "$has_content" = "0" ] && exit 0
+
+if [ -n "$not_head" ]; then
+  echo "pre-push: skipping static checks: $not_head is not the checked-out HEAD, and the checks read the working tree."
+  exit 0
+fi
+
+# Uncommitted or untracked changes in a path a check reads would be judged instead of the
+# pushed commit. In a checkout shared by several sessions that is usually someone else's WIP.
+if [ -n "$(git --no-optional-locks status --porcelain -- ${watched} 2>/dev/null)" ]; then
+  echo "pre-push: skipping static checks: uncommitted changes under ${watched} would be checked instead of the pushed commit."
+  exit 0
+fi
+
+log=$(mktemp "\${TMPDIR:-/tmp}/codeman-prepush.XXXXXX") || exit 0
+trap 'rm -f "$log"' EXIT
+
+failed=''
+run_check() {
+  if ! npm run --silent "$@" >"$log" 2>&1; then
+    echo ""
+    echo "pre-push: FAILED  npm run $*"
+    tail -n 25 "$log"
+    failed="$failed $1"
+  fi
+}
+
+echo "pre-push: running static checks (~10-40s)..."
+${runs}
+
+if [ -n "$failed" ]; then
+  echo ""
+  echo "pre-push: blocked by:$failed"
+  echo "Fix, or push anyway with:  CODEMAN_SKIP_PREPUSH=1 git push"
+  exit 1
+fi
+
+echo "pre-push: static checks passed."
+exit 0
+`;
+}
+
+/**
+ * Decide what to do with an existing hook file.
+ *
+ * @param {{ existing: string | null | undefined, next: string }} args
+ * @returns {'write' | 'up-to-date' | 'skip-foreign'}
+ */
+export function planHookInstall({ existing, next }) {
+  if (existing === null || existing === undefined || existing.trim() === '') return 'write';
+  if (!existing.includes(PRE_PUSH_MARKER)) return 'skip-foreign';
+  return existing === next ? 'up-to-date' : 'write';
+}
+
+/** @param {string} cwd @param {string[]} args */
+function git(cwd, args) {
+  return execFileSync('git', args, { cwd, encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'] }).trim();
+}
+
+/**
+ * realpath() that tolerates a missing leaf: a fresh `.git` may have no `hooks/` yet, so
+ * canonicalize the parent and re-append the name. Throws if the parent is missing too.
+ *
+ * @param {string} path
+ */
+function canonicalPath(path) {
+  return existsSync(path) ? realpathSync(path) : join(realpathSync(dirname(path)), basename(path));
+}
+
+/**
+ * Resolve the hooks directory for the checkout rooted at `repoRoot`, or null when there
+ * is nothing to install into.
+ *
+ * Asks git (`--git-path hooks`) rather than assuming `<root>/.git/hooks`: in a worktree
+ * `.git` is a FILE pointing at the parent repo, so the hooks live under
+ * `--git-common-dir`.
+ *
+ * ⚠️ Returns a directory ONLY when it is this repository's own `<git-common-dir>/hooks`.
+ * `--git-path hooks` also reports `core.hooksPath`, and that setting is often GLOBAL (a
+ * shared hooks directory used by every repo on the machine); installing there would
+ * overwrite the user's own hooks and run Codeman's checks on unrelated repos. A
+ * `core.hooksPath` that points back at the repo's own hooks dir still resolves, because
+ * the comparison is on canonical paths rather than on whether the setting exists.
+ *
+ * Also returns null unless `repoRoot` is itself the top of a work tree. Without that guard,
+ * a copy of this package sitting inside SOMEONE ELSE's repository (e.g. under their
+ * node_modules) would resolve to their hooks directory and install Codeman's hook there.
+ *
+ * @param {string} repoRoot
+ * @returns {string | null}
+ */
+export function resolveGitHooksDir(repoRoot) {
+  try {
+    const top = git(repoRoot, ['rev-parse', '--show-toplevel']);
+    if (!top || realpathSync(top) !== realpathSync(repoRoot)) return null;
+    // Both are printed relative to the cwd (repoRoot) unless already absolute.
+    const hooks = git(repoRoot, ['rev-parse', '--git-path', 'hooks']);
+    const common = git(repoRoot, ['rev-parse', '--git-common-dir']);
+    if (!hooks || !common) return null;
+    const own = join(realpathSync(resolve(repoRoot, common)), 'hooks');
+    return canonicalPath(resolve(repoRoot, hooks)) === own ? own : null;
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * Install (or refresh) the managed pre-push hook in `hooksDir`, honouring
+ * {@link planHookInstall}: a hook without the marker is never touched.
+ *
+ * @param {string} hooksDir
+ * @returns {'write' | 'up-to-date' | 'skip-foreign'}
+ */
+export function installPrePushHook(hooksDir) {
+  const path = join(hooksDir, 'pre-push');
+  const next = renderPrePushHook();
+  const existing = existsSync(path) ? readFileSync(path, 'utf8') : null;
+  const action = planHookInstall({ existing, next });
+  if (action === 'write') {
+    mkdirSync(hooksDir, { recursive: true });
+    writeFileSync(path, next, { mode: 0o755 });
+    chmodSync(path, 0o755); // `mode` only applies when the file is created
+  }
+  return action;
+}

scripts/lib/cli-catalog.mjs

@@ -55,9 +55,61 @@ export function agentImageNpmPackages(catalog) {
   return packages;
 }
 
-/** The `--build-arg` pairs the agent image takes. PURE. */
-export function agentImageBuildArgPairs(catalog) {
-  return [['CLI_NPM_PACKAGES', agentImageNpmPackages(catalog).join(' ')]];
+/**
+ * Environment variable → agent.Dockerfile ARG for the optional git-host CLIs (gh, az).
+ * ⚠️ Mirrored by `GIT_HOST_CLI_BUILD_ARGS` in `src/docker-hosts.ts`; the parity test pins them.
+ */
+export const GIT_HOST_CLI_BUILD_ARGS = [
+  ['CODEMAN_AGENT_IMAGE_INSTALL_GH', 'CODEMAN_INSTALL_GH'],
+  ['CODEMAN_AGENT_IMAGE_INSTALL_AZ', 'CODEMAN_INSTALL_AZ'],
+];
+
+/**
+ * Environment variable → Dockerfile ARG for the image's system Git identity.
+ * ⚠️ Mirrored by `GIT_IDENTITY_BUILD_ARGS` in `src/docker-hosts.ts`; the parity test pins them.
+ */
+export const GIT_IDENTITY_BUILD_ARGS = [
+  ['CODEMAN_AGENT_IMAGE_GIT_USER_NAME', 'GIT_USER_NAME'],
+  ['CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL', 'GIT_USER_EMAIL'],
+];
+
+/**
+ * The `--build-arg` pairs for the optional git-host CLIs. PURE. An unset or empty variable
+ * contributes NOTHING, so the Dockerfile's own default (off) applies and the argv is the same
+ * as before these existed; anything other than 0/1 is refused rather than guessed at.
+ */
+export function gitHostCliBuildArgPairs(env) {
+  const pairs = [];
+  for (const [envName, argName] of GIT_HOST_CLI_BUILD_ARGS) {
+    const value = env[envName];
+    if (value === undefined || value === '') continue;
+    if (value !== '0' && value !== '1') {
+      throw new Error(`${envName} must be 0 or 1, got ${JSON.stringify(value)}`);
+    }
+    pairs.push([argName, value]);
+  }
+  return pairs;
+}
+
+/** The `--build-arg` pairs for Git identity, requiring either both values or neither. */
+export function gitIdentityBuildArgPairs(env) {
+  const pairs = GIT_IDENTITY_BUILD_ARGS.map(([envName, argName]) => [argName, env[envName] ?? '']);
+  const configured = pairs.filter(([, value]) => value !== '');
+  if (configured.length === 0) return [];
+  if (configured.length !== pairs.length) {
+    const names = GIT_IDENTITY_BUILD_ARGS.map(([envName]) => envName).join(' and ');
+    throw new Error(`${names} must both be set when configuring Git identity`);
+  }
+  return pairs;
+}
+
+/** The `--build-arg` pairs the agent image takes. PURE given `env`. */
+export function agentImageBuildArgPairs(catalog, env = process.env) {
+  return [
+    ['CLI_NPM_PACKAGES', agentImageNpmPackages(catalog).join(' ')],
+    ...gitHostCliBuildArgPairs(env),
+    ...gitIdentityBuildArgPairs(env),
+  ];
 }
 
 /** Read the committed catalogue. IO. */

scripts/postinstall.js

@@ -356,14 +356,17 @@ if (!isGlobalInstall) {
 }
 
 // ----------------------------------------------------------------------------
-// 5. Install git pre-commit hook (format check)
+// 5. Install git hooks (pre-commit format check, pre-push static checks)
 // ----------------------------------------------------------------------------
 
 if (!isGlobalInstall) {
     try {
         const { writeFileSync, mkdirSync } = await import('fs');
-        const gitHooksDir = join(import.meta.dirname, '..', '.git', 'hooks');
-        if (existsSync(join(import.meta.dirname, '..', '.git'))) {
+        const { resolveGitHooksDir, installPrePushHook } = await import('./git-hooks.mjs');
+        // Resolved through git, not `../.git/hooks`: in a worktree `.git` is a file.
+        // null when this directory is not the top of a git checkout.
+        const gitHooksDir = resolveGitHooksDir(join(import.meta.dirname, '..'));
+        if (gitHooksDir) {
             mkdirSync(gitHooksDir, { recursive: true });
             const hook = `#!/bin/bash
 # Auto-installed by postinstall — prevents CI format failures
@@ -379,9 +382,18 @@ fi
             const hookPath = join(gitHooksDir, 'pre-commit');
             writeFileSync(hookPath, hook, { mode: 0o755 });
             console.log(colors.green('✓ Git pre-commit hook installed (prettier check)'));
+
+            // Unlike the pre-commit hook above, this one is marker-owned: a pre-push
+            // hook the developer wrote themselves is left alone.
+            const action = installPrePushHook(gitHooksDir);
+            if (action === 'write') {
+                console.log(colors.green('✓ Git pre-push hook installed') + colors.dim(' (static CI checks, ~10-40s)'));
+            } else if (action === 'skip-foreign') {
+                console.log(colors.dim('  Existing pre-push hook left untouched (not Codeman-managed)'));
+            }
         }
     } catch {
-        // Non-critical — git hook is a convenience
+        // Non-critical — git hooks are a convenience
     }
 }
 

scripts/self-update.sh

@@ -74,6 +74,15 @@ echo "[self-update] $(date) start tag=$TAG supervisor=$SUPERVISOR repo=$REPO"
 export PATH="$(dirname "$NODE"):$HOME/.local/bin:$HOME/.npm-global/bin:/usr/local/bin:/opt/homebrew/bin:$PATH"
 export GIT_TERMINAL_PROMPT=0
 
+# --node is the server's process.execPath, a VERSIONED path (Homebrew resolves it
+# into Cellar/node/<ver>/). A `brew upgrade node` under a long-running server
+# deletes it, and every status write then failed, so the status stayed "queued"
+# forever. Fall back to whatever node is on PATH.
+if [ ! -x "$NODE" ]; then
+  echo "[self-update] WARN: $NODE is not executable, falling back to node on PATH"
+  NODE="$(command -v node || echo node)"
+fi
+
 TO_VERSION="${TAG##*@}"   # codeman@0.9.4 → 0.9.4 (tag is validated upstream)
 STASH_REF=""
 MANUAL_CMD=""
@@ -276,7 +285,17 @@ case "$SUPERVISOR" in
     # domain needs root, but we don't need it — kill the server and launchd
     # respawns it on the new dist/ within ThrottleInterval seconds.
     if [[ -n "$SERVER_PID" ]] && kill "$SERVER_PID" 2>/dev/null; then
-      : # respawn is launchd's job from here
+      # Respawn is launchd's job, but only once the old process EXITS. A graceful
+      # shutdown that hangs leaves the port closed and the service down, so
+      # escalate to SIGKILL (tmux sessions live outside the server and survive).
+      for _ in $(seq 1 30); do
+        kill -0 "$SERVER_PID" 2>/dev/null || break
+        sleep 1
+      done
+      if kill -0 "$SERVER_PID" 2>/dev/null; then
+        echo "[self-update] server pid $SERVER_PID still alive 30s after SIGTERM, sending SIGKILL"
+        kill -9 "$SERVER_PID" 2>/dev/null || true
+      fi
     else
       MANUAL_CMD="sudo launchctl kickstart -k system/com.codeman.web"
       write_status "completed-needs-manual-restart" "Update staged — restart Codeman to apply v$TO_VERSION."

skills/codeman/SKILL.md

@@ -47,7 +47,7 @@ later call opens with, and your first REAL call performs them anyway:
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
 ```
 
 ⚠️ **Never spend a Bash call on this check alone.** §1's block opens with this same
@@ -75,8 +75,8 @@ PRE="${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh"
 mkdir -p "$(dirname "$PRE")"
 # Rewrite unless the file already ends with THIS version's stamp, so a stale or a
 # half-written file self-heals here instead of costing you a round trip to rm it.
-grep -qs '^CODEMAN_PREAMBLE=1.30.1$' "$PRE" || (umask 077; cat > "$PRE" <<'PREAMBLE'
-# ---- Codeman agent preamble 1.30.1 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
+grep -qs '^CODEMAN_PREAMBLE=1.33.4$' "$PRE" || (umask 077; cat > "$PRE" <<'PREAMBLE'
+# ---- Codeman agent preamble 1.33.4 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
 API="${CODEMAN_API_URL:?CODEMAN_API_URL not set; refusing to guess}"
 SELF="${CODEMAN_SESSION_ID:?CODEMAN_SESSION_ID not set}"
 # Credentials, cheapest first. Your session has usually INHERITED the server's
@@ -196,6 +196,11 @@ _accept_trust() {  # <sid> -> 0 once it has answered the dialog, 1 if it could n
 # rather than handed back, because a worker that never drew its composer would eat the
 # task prompt with its trust dialog. There is deliberately no pid poll: wait-output
 # already blocks until the composer draws, and pid!=null proved startup, never readiness.
+# CODEMAN_WORKER_ADVISOR=opus (or fable / sonnet) gives every CLAUDE worker spawned while
+# it is set Claude Code's advisor tool: a stronger model the worker consults before
+# committing to an approach, on a recurring error and before declaring the task done.
+# Other modes ignore it. A value the server refuses fails the spawn (INVALID_INPUT); an
+# advisor that ranks below the worker's model is accepted but never attached by claude.
 spawn_worker() {
   local name="${1:?spawn_worker needs a case name}" mode="${2:-claude}" q sid cp r
   # parentSessionId doubles the CURL header, so a spawn_worker copied off the shared
@@ -207,12 +212,19 @@ spawn_worker() {
   # server clamps this back to `workspace-write` for an owner without the grant.
   # Spawn by hand (§5.1) when you want a worker that asks.
   q=$("${CURL[@]}" -X POST "$API/api/v1/quick-start" -H 'Content-Type: application/json' \
-      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" \
+      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" --arg a "${CODEMAN_WORKER_ADVISOR:-}" \
         '{caseName:$n,mode:$m,parentSessionId:$p}
-         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)')")
+         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)
+         + (if $m == "claude" and $a != "" then {advisorModel:$a} else {} end)')")
   sid=$(jq -r 'if .success then .data.sessionId else empty end' <<<"$q")
   # NOT retryable in a loop: every quick-start failure code is terminal (§5.1).
   [ -n "$sid" ] || { jq -c '{error,errorCode}' <<<"$q" >&2; return 1; }
+  # A server without advisor support DROPS the field instead of refusing it, so read it
+  # back: a worker silently missing the advisor it was asked for is worth one line.
+  if [ "$mode" = claude ] && [ -n "${CODEMAN_WORKER_ADVISOR:-}" ] &&
+     [ "$("${CURL[@]}" "$API/api/v1/sessions/$sid" | jq -r '.data.advisorModel // empty')" != "$CODEMAN_WORKER_ADVISOR" ]; then
+    echo "worker $sid: this Codeman server ignored CODEMAN_WORKER_ADVISOR (no advisor support); it runs without one" >&2
+  fi
   if [ "$mode" = deepseek ]; then
     # The one non-claude mode with REAL end-of-turn signals: its TUI reports
     # idle/working/blocked to Codeman, so sendwait, until=stop and the Approvals
@@ -372,10 +384,10 @@ last_text() {
 # The stamp is the LAST line on purpose (a truncated write leaves it unset) and is kept
 # bare on purpose: the write condition above anchors on it with $, so an inline comment
 # here would fail that match and rewrite this file on every single bootstrap.
-CODEMAN_PREAMBLE=1.30.1
+CODEMAN_PREAMBLE=1.33.4
 PREAMBLE
 )
-. "$PRE"; [ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble at $PRE is stale or truncated: rm it and re-run this block"; exit 1; }
+. "$PRE"; [ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble at $PRE is stale or truncated: rm it and re-run this block"; exit 1; }
 ```
 
 Every later Bash call that touches the API starts with the same two loader lines from
@@ -426,7 +438,7 @@ and no per-call body to hand-build.
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null   # §0 loader
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; run the full §0 block"; exit 1; }
 N=(alpha beta)                    # INVENT one fresh case name per worker; never list cases first
                                   # (a name may carry a mode: `beta:deepseek`, see below)
 T=('reply with one line: the absolute path of your working directory'
@@ -493,6 +505,12 @@ Four things this block leans on, each one link away, no detour needed to run it:
   `sendwait` reads the composer and keeps pressing Enter until the prompt has left it.
   All three are reasons to let `sendwait` build the call rather than hand-rolling it.
 - Each `sendwait` costs that worker one billed turn, as does every prompt you send it.
+- For long or high-stakes worker tasks, `CODEMAN_WORKER_ADVISOR=opus spawn_workers "${N[@]}"`
+  (`fable`, `opus` or `sonnet`) gives each claude worker Claude Code's advisor tool: a
+  stronger model it consults before committing to an approach, on a recurring error and
+  before declaring the task done. Advisor calls bill extra tokens, and an advisor ranked
+  below the worker's own model is never attached (on an Opus worker only `opus` and
+  `fable` do anything).
 - Deleting the sessions does **not** remove the case directories. They are marked as
   agent-created, so `GET /api/v1/cases/agent-created` lists them for cleanup: §5.14.
 

skills/codeman/preamble.sh

@@ -1,4 +1,4 @@
-# ---- Codeman agent preamble 1.30.1 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
+# ---- Codeman agent preamble 1.33.4 (seeded by Codeman at session spawn; the SKILL.md §0 bootstrap rewrites it when missing or stale) ----
 API="${CODEMAN_API_URL:?CODEMAN_API_URL not set; refusing to guess}"
 SELF="${CODEMAN_SESSION_ID:?CODEMAN_SESSION_ID not set}"
 # Credentials, cheapest first. Your session has usually INHERITED the server's
@@ -118,6 +118,11 @@ _accept_trust() {  # <sid> -> 0 once it has answered the dialog, 1 if it could n
 # rather than handed back, because a worker that never drew its composer would eat the
 # task prompt with its trust dialog. There is deliberately no pid poll: wait-output
 # already blocks until the composer draws, and pid!=null proved startup, never readiness.
+# CODEMAN_WORKER_ADVISOR=opus (or fable / sonnet) gives every CLAUDE worker spawned while
+# it is set Claude Code's advisor tool: a stronger model the worker consults before
+# committing to an approach, on a recurring error and before declaring the task done.
+# Other modes ignore it. A value the server refuses fails the spawn (INVALID_INPUT); an
+# advisor that ranks below the worker's model is accepted but never attached by claude.
 spawn_worker() {
   local name="${1:?spawn_worker needs a case name}" mode="${2:-claude}" q sid cp r
   # parentSessionId doubles the CURL header, so a spawn_worker copied off the shared
@@ -129,12 +134,19 @@ spawn_worker() {
   # server clamps this back to `workspace-write` for an owner without the grant.
   # Spawn by hand (§5.1) when you want a worker that asks.
   q=$("${CURL[@]}" -X POST "$API/api/v1/quick-start" -H 'Content-Type: application/json' \
-      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" \
+      -d "$(jq -nc --arg n "$name" --arg m "$mode" --arg p "$SELF" --arg a "${CODEMAN_WORKER_ADVISOR:-}" \
         '{caseName:$n,mode:$m,parentSessionId:$p}
-         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)')")
+         + (if $m == "deepseek" then {deepSeekConfig:{permissionMode:"danger-full-access"}} else {} end)
+         + (if $m == "claude" and $a != "" then {advisorModel:$a} else {} end)')")
   sid=$(jq -r 'if .success then .data.sessionId else empty end' <<<"$q")
   # NOT retryable in a loop: every quick-start failure code is terminal (§5.1).
   [ -n "$sid" ] || { jq -c '{error,errorCode}' <<<"$q" >&2; return 1; }
+  # A server without advisor support DROPS the field instead of refusing it, so read it
+  # back: a worker silently missing the advisor it was asked for is worth one line.
+  if [ "$mode" = claude ] && [ -n "${CODEMAN_WORKER_ADVISOR:-}" ] &&
+     [ "$("${CURL[@]}" "$API/api/v1/sessions/$sid" | jq -r '.data.advisorModel // empty')" != "$CODEMAN_WORKER_ADVISOR" ]; then
+    echo "worker $sid: this Codeman server ignored CODEMAN_WORKER_ADVISOR (no advisor support); it runs without one" >&2
+  fi
   if [ "$mode" = deepseek ]; then
     # The one non-claude mode with REAL end-of-turn signals: its TUI reports
     # idle/working/blocked to Codeman, so sendwait, until=stop and the Approvals
@@ -294,4 +306,4 @@ last_text() {
 # The stamp is the LAST line on purpose (a truncated write leaves it unset) and is kept
 # bare on purpose: the write condition above anchors on it with $, so an inline comment
 # here would fail that match and rewrite this file on every single bootstrap.
-CODEMAN_PREAMBLE=1.30.1
+CODEMAN_PREAMBLE=1.33.4

skills/codeman/reference/endpoints.md

@@ -340,11 +340,18 @@ ESC=$(printf '\033')
 ### Starting a worker
 
 `POST /api/v1/quick-start` body (all optional):
-`{"caseName":"worker-1","mode":"claude","sessionName":"w9-worker","effort":"high"}`
+`{"caseName":"worker-1","mode":"claude","sessionName":"auth-worker","effort":"high"}`
 ,  `mode` ∈ `claude|shell|opencode|codex|gemini|antigravity|pi|grok|deepseek|omp`; response is
 `.data.{sessionId, caseName, casePath}`. Creates the case directory (a real directory
 on the user's disk) if missing, do not retry it in a loop, and remember the name.
 
+A claude worker also takes `"advisorModel":"opus"` (`fable`, `opus`, `sonnet` or a full
+model id): Claude Code's advisor tool, a stronger model the worker consults before
+committing to an approach, on a recurring error and before declaring the task done. It is
+a soft default the worker can change with `/advisor`. Remote and docker cases refuse it
+(400), as they refuse `effort`. `spawn_worker` and `spawn_workers` send it for you when
+`CODEMAN_WORKER_ADVISOR` is set.
+
 ⚠️ A `mode` whose CLI is **not installed on the server** fails the spawn with
 `OPERATION_FAILED`; it never falls back to claude. Probe first whenever you did not pick
 the mode yourself: `GET /api/v1/claude/status`, `GET /api/v1/opencode/status`,
@@ -384,7 +391,7 @@ every claude create path installs them, so a linked case and a raw path both get
 
 **The two-step alternative, `POST /api/v1/sessions`.** Use it when you need a session in
 a directory that is not a case (body takes `workingDir`, `mode`, `name`, `effort`,
-`envOverrides`). Three differences that break copied code:
+`advisorModel`, `envOverrides`). Three differences that break copied code:
 
 - The id is at **`.data.session.id`**, not quick-start's `.data.sessionId`
   (`session-routes.ts:878` returns `{ session: lightState }`).

skills/codeman/reference/messaging.md

@@ -101,11 +101,16 @@ the case name, read it from the listing.
 From Codeman 1.16 a LOCAL claude spawn passes `--name <session name>` when the local
 CLI is 2.1.224+ (`buildNameCliArgs`, `session-cli-builder.ts:97-101`, wired in at
 `tmux-manager.ts:797`), so a worker's peer name usually IS its Codeman session name
-(verified live: quick-start with `sessionName: "w9-msgtest"` listed as `w9-msgtest`,
-and its messages arrive tagged `from-name="w9-msgtest"`; a derived-name worker's
+(verified live: a quick-start `sessionName` is listed as that exact peer name, and
+the worker's messages arrive tagged `from-name="<that name>"`; a derived-name worker's
 messages carry no `from-name`). Name your workers: a quick-start WITHOUT
 `sessionName` leaves the Codeman name empty, so there is nothing to pass and the
-peer name stays derived. The flag is fail-closed (older/unknown CLI omits it, because an
+peer name stays derived. ⚠️ Give them a DESCRIPTIVE name: only a name the user chose
+is pinned (`Session.cliPinnedName`), because `--name` is also the conversation's
+`/resume` title and terminal title and suppresses Claude's own generated title. A
+placeholder-shaped name (`w9-msgtest`, anything matching `isGeneratedSessionName`)
+and an auto name are NOT passed, so such a worker's peer name is derived; use
+`msgtest-worker` rather than `w9-msgtest`. The flag is fail-closed (older/unknown CLI omits it, because an
 unknown flag aborts startup and would kill every spawn) and allowlist-sanitized (a name of
 only unsafe characters is dropped), and the docker/remote builders never see it at all
 (`tmux-manager.ts:782-789`), which is why the `tmux` column stays the canonical join key
@@ -196,8 +201,8 @@ idle:
 The contract an orchestrator follows for any fleet of two or more messaging workers.
 Every topology in the next section is this protocol plus a wiring diagram.
 
-1. **Spawn with a name, and confirm hooks.** Use `quick-start` with `sessionName` (the
-   `--name` gate above). Session create installs the hooks block into the workspace
+1. **Spawn with a name, and confirm hooks.** Use `quick-start` with a descriptive,
+   non-`w<N>-` `sessionName` (the `--name` gate above). Session create installs the hooks block into the workspace
    whatever kind it is, so a linked case and a raw `POST /api/sessions` path both get
    `stop`/`blocked` by default. ⚠️ Not unconditionally: the operator can turn
    `workspaceHooksEnabled` off, remote SSH sessions never get hooks, and a session from

skills/codeman/reference/recipes.md

@@ -21,7 +21,7 @@ by sourcing the preamble file the §0 bootstrap wrote, and checking its version
 
 ```bash
 . "${XDG_CACHE_HOME:-$HOME/.cache}/codeman-agent-$CODEMAN_SESSION_ID.sh" 2>/dev/null
-[ "${CODEMAN_PREAMBLE:-}" = 1.30.1 ] || { echo "preamble missing or stale; re-run the §0 bootstrap"; exit 1; }
+[ "${CODEMAN_PREAMBLE:-}" = 1.33.4 ] || { echo "preamble missing or stale; re-run the §0 bootstrap"; exit 1; }
 ```
 
 Do **not** re-paste the preamble body into each call. Sourcing it is what retires the

skills/codeman/reference/verbs.md

@@ -692,8 +692,9 @@ The shape, each step verified live (probes, failure modes and safety detail in
    [§5.2](#52-readiness)).
 2. `ListAgents`: find the worker's row by its `tmux codeman-<first 8 of session id>`
    column; the row's `name [ref]` is the address. On Codeman 1.16+ with claude
-   2.1.224+ a worker's peer name is its Codeman session name, so pass `sessionName`
-   in quick-start to pick it; older setups list a name derived from the case folder.
+   2.1.224+ a worker's peer name is its Codeman session name, so pass a DESCRIPTIVE
+   `sessionName` in quick-start to pick it (a `w<N>-` placeholder-shaped name is not
+   pinned, so it lists derived); older setups list a name derived from the case folder.
    No row = messaging is off for that worker (it is feature-flagged even on matching
    CLI versions, observed live): fall back to the HTTP recipes without complaint.
 3. `SendMessage` the task; first contact must use the `name [ref]` form copied from

src/claude-session-title.ts

@@ -0,0 +1,45 @@
+/**
+ * @fileoverview Carry a Codeman rename into Claude Code's own session title.
+ *
+ * Claude Code keeps a conversation's title in its transcript as a
+ * `{"type":"custom-title"}` row (what `/rename` writes), last row wins, and the
+ * `/resume` picker shows `customTitle ?? aiTitle`. Renaming a tab in Codeman
+ * used to change only the tab, so `/resume` kept listing the old name.
+ *
+ * Appending the row is enough for a pane that was spawned WITHOUT `--name`
+ * (every placeholder- or auto-named tab, see `Session.cliPinnedName`): that
+ * process holds no title of its own and never writes one back. A process that
+ * WAS spawned with `--name` re-appends its in-memory title after each turn, so
+ * there the new title holds from the next spawn, which pins the new name.
+ *
+ * @module claude-session-title
+ */
+
+import fs from 'node:fs/promises';
+
+/**
+ * Append a `custom-title` row for `conversationId` to an existing transcript.
+ * Never creates the file: a missing transcript means the conversation has not
+ * been written yet, and a file of only a title row would show up in `/resume`
+ * as an empty conversation. Returns whether a row was written.
+ */
+export async function appendClaudeCustomTitle(
+  transcriptPath: string,
+  conversationId: string,
+  title: string
+): Promise<boolean> {
+  const customTitle = title.trim();
+  // Claude reads the row through `customTitle ?? aiTitle`, so an empty string
+  // would blank the picker entry rather than fall back to the generated title.
+  if (!customTitle) return false;
+  try {
+    if (!(await fs.stat(transcriptPath)).isFile()) return false;
+  } catch {
+    return false;
+  }
+  // One O_APPEND write of one line, the same way Claude appends its own rows,
+  // so it cannot interleave with a row the live process is writing.
+  const row = JSON.stringify({ type: 'custom-title', customTitle, sessionId: conversationId });
+  await fs.appendFile(transcriptPath, `${row}\n`);
+  return true;
+}

src/cli.ts

@@ -129,6 +129,8 @@ program
 
 /** Same registry the server resolves case names through (mirrors `case-routes.ts`). */
 const LINKED_CASES_FILE = dataPath('linked-cases.json');
+/** Graceful shutdown budget before the process force-exits (see the SIGTERM handler). */
+const SHUTDOWN_FORCE_EXIT_MS = 10_000;
 
 /**
  * Case name to directory, checking `linked-cases.json` FIRST and falling back to the
@@ -1002,6 +1004,14 @@ webCmd.action(async (options) => {
       if (shuttingDown) return;
       shuttingDown = true;
       console.log(palette.warn(`\n${signal} received, shutting down gracefully...`));
+      // A hung stop() must not keep the process alive: the listener is already
+      // closed by then, and a KeepAlive LaunchDaemon only respawns the server once
+      // it EXITS (systemd would SIGKILL after TimeoutStopSec; launchd does not).
+      // Seen after a self-update on macOS: port closed, process alive, service down.
+      setTimeout(() => {
+        console.error(palette.err(`Shutdown did not finish in ${SHUTDOWN_FORCE_EXIT_MS / 1000}s, forcing exit`));
+        process.exit(1);
+      }, SHUTDOWN_FORCE_EXIT_MS).unref();
       try {
         await server.stop();
       } catch (err) {

src/config/cli-registry/registry-writer.ts

@@ -0,0 +1,115 @@
+/**
+ * @fileoverview Write side of the CLI registry (docs/cli-enable-disable-plan.md, Phases 3/5).
+ *
+ * Kept deliberately SEPARATE from `registry.ts`, whose reading path does no writes on import
+ * (`schemas.ts` imports it, transitively). Only `cli-registry-routes.ts` imports this module,
+ * so that property still holds for every OTHER importer of the registry.
+ *
+ * Every mutation goes through `mutateRegistryFile()`, which does three things the #476 review
+ * found missing:
+ *
+ * - **Serialized.** Mutations run one at a time on a single promise chain, and each one
+ *   reads, changes, writes and reloads before the next starts. Unserialized read-modify-write
+ *   lost toggles when three `PUT /api/clis/:id` calls ran in parallel.
+ * - **Refuses a file it must not trust.** The reader ignores a `clis.json` with any
+ *   group/world permission bit and quarantines one that does not parse. The writer used to
+ *   treat both as "start fresh", so one Settings click replaced a hand-edited file with a
+ *   one-key file, or rewrote a refused file as 0600 and so trusted it. It now starts fresh
+ *   ONLY on ENOENT and otherwise throws `RegistryWriteRefusedError`, leaving the file alone.
+ * - **Unique temp file.** Every write gets its own tmp name before the rename, so two writes
+ *   can never rename each other's temp file away (the ENOENT-on-rename 500s).
+ *
+ * Same tmp+rename+0600 shape as `custom-model-hosts.ts`. The file is hand-editable, so a
+ * write must never leave it half-written, and 0600 is the mode `isUnsafePermissions()`
+ * requires on the next read.
+ */
+
+import { randomUUID } from 'node:crypto';
+import { existsSync, mkdirSync } from 'node:fs';
+import fs from 'node:fs/promises';
+import { dirname } from 'node:path';
+import { isUnsafePermissions, registryFilePath, reloadCliRegistry } from './registry.js';
+import type { CliRegistryFile } from './types.js';
+
+/** A write refused because the existing `clis.json` must not be overwritten. The message is user-facing. */
+export class RegistryWriteRefusedError extends Error {
+  constructor(message: string) {
+    super(message);
+    this.name = 'RegistryWriteRefusedError';
+  }
+}
+
+/**
+ * Read the raw override file for mutation. Only a MISSING file starts fresh. A file with
+ * unsafe permissions, one that cannot be read, or one that does not parse is refused rather
+ * than overwritten, because the user's hand-edit is worth more than one toggle.
+ */
+export async function readRegistryFileForWrite(): Promise<CliRegistryFile> {
+  const path = registryFilePath();
+  let raw: string;
+  try {
+    raw = await fs.readFile(path, 'utf-8');
+  } catch (err) {
+    if ((err as NodeJS.ErrnoException).code === 'ENOENT') return { schemaVersion: 1, clis: {} };
+    throw new RegistryWriteRefusedError(`Cannot read ${path} (${(err as Error).message}); not changing it.`);
+  }
+  if (isUnsafePermissions(path)) {
+    throw new RegistryWriteRefusedError(
+      `${path} has group/world permission bits, so Codeman ignores it. Run \`chmod 600 ${path}\` and check its contents before changing CLIs here.`
+    );
+  }
+  let parsed: unknown;
+  try {
+    parsed = JSON.parse(raw);
+  } catch (err) {
+    throw new RegistryWriteRefusedError(
+      `${path} is not valid JSON (${(err as Error).message}). Fix or remove it before changing CLIs here.`
+    );
+  }
+  const clis = (parsed as { clis?: unknown } | null)?.clis;
+  if (typeof parsed !== 'object' || parsed === null || typeof clis !== 'object' || clis === null) {
+    throw new RegistryWriteRefusedError(`${path} has no "clis" object. Fix or remove it before changing CLIs here.`);
+  }
+  return parsed as CliRegistryFile;
+}
+
+export async function writeRegistryFile(file: CliRegistryFile): Promise<void> {
+  const target = registryFilePath();
+  const dir = dirname(target);
+  if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
+  const tmp = `${target}.${process.pid}.${randomUUID()}.tmp`;
+  try {
+    await fs.writeFile(tmp, JSON.stringify(file, null, 2), { mode: 0o600 });
+    await fs.rename(tmp, target);
+  } catch (err) {
+    await fs.rm(tmp, { force: true }).catch(() => {});
+    throw err;
+  }
+}
+
+let mutationChain: Promise<unknown> = Promise.resolve();
+
+/**
+ * Run one registry mutation. The chain holds exactly one at a time: `fn` receives the
+ * current file and returns `{ file, result }`. If `file` is set it is written and the
+ * registry reloaded before the next mutation starts; if not, nothing is written, which is
+ * how a validation failure returns early. Checks made inside `fn` (does this id exist,
+ * is it a duplicate) therefore see every earlier mutation's result.
+ *
+ * A failed mutation rejects its own caller only. The chain keeps going.
+ */
+export function mutateRegistryFile<T>(
+  fn: (file: CliRegistryFile) => Promise<{ file?: CliRegistryFile; result: T }> | { file?: CliRegistryFile; result: T }
+): Promise<T> {
+  const run = mutationChain.then(async () => {
+    const current = await readRegistryFileForWrite();
+    const { file, result } = await fn(current);
+    if (file) {
+      await writeRegistryFile(file);
+      reloadCliRegistry();
+    }
+    return result;
+  });
+  mutationChain = run.catch(() => {});
+  return run;
+}

src/config/cli-registry/registry.ts

@@ -48,6 +48,16 @@ function filePath(): string {
   return dataPath('clis.json');
 }
 
+/**
+ * The resolved path of `~/.codeman/clis.json`, exported for the write API
+ * (`cli-registry-writer.ts`, docs/cli-enable-disable-plan.md Phases 3/5) so both the read and
+ * write sides resolve the SAME path through the SAME instance-scoped helper — never a second
+ * `dataPath('clis.json')` call that could drift from this one under a future `dataPath()` change.
+ */
+export function registryFilePath(): string {
+  return filePath();
+}
+
 /**
  * Keys that must never be merged out of a hand-editable JSON file.
  *
@@ -90,8 +100,11 @@ export interface LoadResult {
  * as mode 0o666 there regardless of its actual ACL), so this check would flag every file on
  * Windows and silently ignore all user config. `win32` relies on NTFS ACLs instead, which
  * this check cannot see and does not attempt to.
+ *
+ * Exported for `registry-writer.ts`, which must refuse the same files: rewriting a refused
+ * file as 0600 would silently turn it into trusted config.
  */
-function isUnsafePermissions(path: string): boolean {
+export function isUnsafePermissions(path: string): boolean {
   if (process.platform === 'win32') return false;
   try {
     const mode = statSync(path).mode & 0o777;

src/config/cli-registry/schema.ts

@@ -294,6 +294,23 @@ const capabilitiesSchema = z
     effort: z.boolean(),
     agentSkillInjection: z.boolean(),
     statusLineTelemetry: z.boolean(),
+    // How many columns this CLI indents its transcript body by, so a copy can take
+    // that much off the clipboard. Bounded, because it is the whole strip: a copy
+    // never removes more than this, nor more than every selected line shares.
+    //
+    // ⚠ DECLARED, not measured off the pane, and two measured attempts are why.
+    // Asking whether the pane painted spaces across the unused part of each row
+    // separates a TUI from a shell perfectly where it fires and never
+    // over-stripped, but it is a function of pane WIDTH: that padding exists
+    // only while a rendered line stops short of the CLI's own layout width, and
+    // Claude Code's prose wraps to fill it — the share of padded rows on one
+    // live transcript ran 44%, 6%, 6%, 7% and 87% at 123, 160, 198, 235 and 298
+    // columns, so the strip did nothing at any ordinary size. Taking the
+    // narrowest indent on screen instead fires everywhere and over-strips, since
+    // a file listing inside the transcript can be the narrowest thing on it.
+    // A declared width cannot do either. Absent means no strip, so a CLI whose
+    // transcript layout nobody has measured is never touched.
+    transcriptGutter: z.number().int().min(1).max(8).optional(),
     workDetect: z
       .object({
         promptGlyph: z.string().min(1).max(8),
@@ -308,8 +325,38 @@ const capabilitiesSchema = z
             (src) => compileVersionRegex(src) !== null,
             'workingLine must be a regex compileVersionRegex() accepts: at most 200 characters, no nested quantifiers'
           ),
+        // Same guard, same reasons: this one runs over the foot of a pane capture every
+        // time a session settles, and ~/.codeman/clis.json can set it.
+        watchingLine: z
+          .string()
+          .min(1)
+          .refine(
+            (src) => compileVersionRegex(src) !== null,
+            'watchingLine must be a regex compileVersionRegex() accepts: at most 200 characters, no nested quantifiers'
+          )
+          .optional(),
+        // Bounded hard: this is how far up the screen a config file may push the search,
+        // and every row it adds is one more row the agent itself may be able to write.
+        watchingLines: z.number().int().min(1).max(8).optional(),
+        // Same guard again: tested against a pane row every time a session settles.
+        awaitingLine: z
+          .string()
+          .min(1)
+          .refine(
+            (src) => compileVersionRegex(src) !== null,
+            'awaitingLine must be a regex compileVersionRegex() accepts: at most 200 characters, no nested quantifiers'
+          )
+          .optional(),
       })
       .strict()
+      // A window with nothing to search is a typo, not a configuration. Refused at LOAD
+      // time for the same reason `privilegedParams[].param` is checked against the params
+      // the entry declares: the failure is otherwise silent and looks like a feature that
+      // simply never fires.
+      .refine(
+        (v) => v.watchingLines === undefined || v.watchingLine !== undefined,
+        'watchingLines has nothing to bound without a watchingLine'
+      )
       .optional(),
     model: z
       .object({ source: z.enum(['flag', 'claude-settings-file', 'none']), param: z.string().optional() })

src/config/cli-registry/stock.ts

@@ -75,11 +75,24 @@ function agentDefaults(): Pick<
   };
 }
 
+// `accent` on every entry below (except SHELL, which the frontend renders no
+// distinct color for) is measured from the actual `.btn-toolbar.btn-run.mode-<id>`
+// CSS rule's `border-color` on the OG skin (styles.css) — the single cleanest
+// representative hex each entry's own multi-stop gradient resolves around.
+// Corrected 2026-09-21 after PR #458's review found several were simply wrong
+// (e.g. claude was registered as Anthropic's brand orange, `#d97757`, but the
+// button renders blue): `docs/cli-registry.md`'s own "transcribed, not
+// authoritative, re-measure before wiring one up" warning for this
+// DECLARED-FOR-LATER field, taken literally. The one exception is GEMINI, whose
+// run-button border (#60a5fa) is the only one that disagrees with its own tab badge
+// and run-mode dot (#8ab4f8); it takes the badge colour, so every accent names the
+// same hex the frontend uses as that CLI's flat identity. This is a data-accuracy fix only —
+// `accent` still has no reader, so nothing rendered changes because of it.
 const CLAUDE: CliEntry = {
   id: 'claude' as CliEntry['id'],
-  label: 'Claude',
+  label: 'Claude Code',
   shortBadge: 'CC',
-  accent: '#d97757',
+  accent: '#3b82f6',
   enabled: true,
   stock: true,
   order: 0,
@@ -200,12 +213,48 @@ const CLAUDE: CliEntry = {
   },
   capabilities: {
     external: false,
+    // Claude indents its transcript body two columns and puts its own ●/✻/❯ markers
+    // in them, so a copy can drop two and paste flush. Claude and codex are the only
+    // entries that declare this, because theirs are the only gutters that have been measured.
+    transcriptGutter: 2,
     // The historical hard-coded pair, now stated as data. `workingLine` matches both the
     // `✻ Actualizing… (39s · ↓ 2.0k tokens)` status line and the bare `esc to interrupt`
     // footer, because tmux repaints partially and only one of the two may land in a chunk.
     workDetect: {
       promptGlyph: '❯',
       workingLine: String.raw`…\s*\((?:\d+h\s+)?(?:\d+m\s+)?\d+s\b|esc to interrupt`,
+      // Claude prints what it started in the background on the footer row beneath its
+      // composer, as `⏵⏵ bypass permissions on · 1 monitor · ← for agents`. The labels are
+      // the CLI's own words for each kind of background task, and group 1 is the one
+      // Codeman badges the session with. Verified against a live 2.1.278 pane on
+      // 2026-09-21.
+      // ⚠️ Two things keep an agent from writing its own label here, and both matter.
+      // The footer is the LAST row, so the default one-row window (`WATCHING_TAIL_LINES`)
+      // holds nothing but Ink's own chrome — in particular it leaves out the status line
+      // directly above, whose content comes from a `statusLine` command a bypassed
+      // session can write into its own `.claude/settings.json`. And the leading `·` keeps
+      // the match on the footer's own item list rather than on any text that happens to
+      // carry a count. A footer that ever drew the chip as its only item would report no
+      // watching rather than open that door. See `watchingLabel()` in
+      // `session-activity.ts`.
+      // ⚠️ An Artifact comment monitor is the one chip that waits on the user. The agent
+      // has published a page and hears nothing until somebody comments on it, so the
+      // lookahead refuses the whole row while that chip is on it, whatever else is
+      // running beside it. The `^` is what makes the lookahead judge the row once:
+      // without it the engine retries from each later position, and a start past the
+      // chip reports the shell beside it. The lookahead keys on "Artifact" alone, so a
+      // footer cut off mid-chip (`· 1 Artifact…`, `· 1 Artifact comm…`) is still refused;
+      // no other chip on this row says "Artifact". Counting the chip as watching kept the
+      // idle alert quiet for a session that was waiting for a human.
+      watchingLine: String.raw`^(?!.*Artifact).*?·\s*(\d+ (?:monitors?|shells?|teams?|local agents?|cloud sessions?|MCP tasks?|background tasks?|(?:background|remote) dynamic workflows?))`,
+      // When a turn ends while background agents or an ultracode workflow are still
+      // running, Claude swaps its `✻ Brewed for 1m 18s` closing row for
+      // `✻ Waiting for 2 background agents and 1 dynamic workflow to finish` and resumes
+      // by itself when they report back. Read from the 2.1.283 bundle (the turn-duration
+      // renderer) and a live pane on 2026-09-28. The row is a snapshot taken at turn end
+      // and never redrawn, which is why only the newest row above the composer counts.
+      // Anchored on column 0: Claude's own rows start there, the agent's prose never does.
+      awaitingLine: String.raw`^✻ Waiting for \d+ (?:background agents?|dynamic workflows?)\b`,
     },
     requiresMux: false,
     // Claude installs Codeman's own hooks block into every workspace it runs in, so its
@@ -214,6 +263,8 @@ const CLAUDE: CliEntry = {
     transcript: 'claude-jsonl',
     altScreen: 'strip-full',
     echo: { policy: 'buffer', anchor: { kind: 'glyph', glyph: '❯', offset: 2 } },
+    // Declared-for-later: the live rule (`_shouldForwardWheelToApp`, terminal-ui.js) is this version
+    // AND the server-published `cliMouseTracking` flag (#498), so wiring this field up needs both.
     wheelForward: { mode: 'version-gated', minVersion: '2.1.187' },
     keyboardAccessory: 'agent',
     privilegedCommandGate: false,
@@ -368,7 +419,7 @@ const OPENCODE: CliEntry = {
   id: 'opencode' as CliEntry['id'],
   label: 'OpenCode',
   shortBadge: 'OC',
-  accent: '#f59e0b',
+  accent: '#10b981',
   enabled: true,
   stock: true,
   order: 10,
@@ -454,7 +505,7 @@ const CODEX: CliEntry = {
   id: 'codex' as CliEntry['id'],
   label: 'Codex',
   shortBadge: 'CX',
-  accent: '#6b7fd7',
+  accent: '#a855f7',
   enabled: true,
   stock: true,
   order: 20,
@@ -518,7 +569,43 @@ const CODEX: CliEntry = {
     // `Working (2m 49s • esc to interrupt)` above it while a turn runs. It animates no
     // braille spinner, and it never prints `esc to interrupt` at rest, so that phrase
     // alone separates a running turn from an idle one.
-    workDetect: { promptGlyph: '›', workingLine: '[Ee]sc to interrupt' },
+    // Codex pins a row of its own while a background terminal it started is still
+    // running: `  1 background terminal running · /ps to view · /stop to close`. Unlike
+    // Claude's footer chip that row sits ABOVE the composer, which puts it third from the
+    // bottom once the status line and the composer are counted, hence `watchingLines`.
+    // Measured against a live codex-cli 0.154.0 pane on 2026-09-22: the row appears when
+    // the terminal starts, follows the composer down as the conversation grows, and is
+    // gone after `/stop`.
+    // ⚠️ This entry CANNOT promise what Claude's does, and the difference is Codex's
+    // layout rather than its pattern. The third row from the bottom is the chip only
+    // while a terminal runs; with none running it is the last row of the transcript,
+    // which the agent writes. Matching the complete row raises the bar — an assistant
+    // message has to end with this exact line, to the character — but nothing here makes
+    // forging it impossible, so do not read the Claude comment above as applying here.
+    // What contains it is that codex declares `hooks: 'none'`: no hook event from a codex
+    // session ever reaches `notePrompt()`, so there is no idle item to pre-acknowledge
+    // and a forged label costs a wrong badge and nothing else. A CLI that gains hook
+    // signals must not keep a pattern this soft.
+    // ⚠️ Background TERMINALS are the only background work codex advertises on screen.
+    // A sub-agent started without waiting outlives the turn just as a terminal does —
+    // measured 2026-09-22, the sandboxed process was still running — and the pane shows
+    // nothing at all for it: the last rows are the composer and the status line, and
+    // `Sub-agents running` lives in the on-demand `/subagents` panel, not above the
+    // composer. So a codex session waiting on a sub-agent reads as plainly idle here.
+    // Nothing is misfiled by that (codex raises no idle prompts), and there is no row to
+    // match until codex pins one.
+    workDetect: {
+      promptGlyph: '›',
+      workingLine: '[Ee]sc to interrupt',
+      watchingLine: String.raw`^\s{0,4}(\d+ background terminals?) running · /ps to view · /stop to close$`,
+      watchingLines: 3,
+    },
+    // Two columns, like claude's, measured on a live 0.154.0 answer: the `•`/`›`/`⚠`
+    // markers sit in the gutter, prose continuations sit at 2, and a nested YAML block
+    // the model wrote rendered at 2/4/6/8 for its own 0/2/4/6. Replayed at 100, 120,
+    // 160, 198, 235 and 282 columns the indents were 0, 2, 4, 6 and 8 at every one,
+    // never 1, so the width is not a function of the pane.
+    transcriptGutter: 2,
     transcript: 'codex-rollout',
     altScreen: 'strip-full',
     echo: { policy: 'predict', anchor: { kind: 'cursor' }, predictProfile: 'codex' },
@@ -565,7 +652,8 @@ const GEMINI: CliEntry = {
   id: 'gemini' as CliEntry['id'],
   label: 'Gemini',
   shortBadge: 'GM',
-  accent: '#4285f4',
+  // The tab badge / run-mode-dot colour, not the run-button border (see the note above CLAUDE).
+  accent: '#8ab4f8',
   enabled: true,
   stock: true,
   order: 30,
@@ -657,7 +745,7 @@ const ANTIGRAVITY: CliEntry = {
   id: 'antigravity' as CliEntry['id'],
   label: 'Antigravity',
   shortBadge: 'AG',
-  accent: '#8b5cf6',
+  accent: '#22d3ee',
   enabled: true,
   stock: true,
   order: 40,
@@ -727,7 +815,7 @@ const PI: CliEntry = {
   id: 'pi' as CliEntry['id'],
   label: 'Pi',
   shortBadge: 'PI',
-  accent: '#10b981',
+  accent: '#f472b6',
   enabled: true,
   stock: true,
   order: 50,
@@ -851,10 +939,10 @@ const GROK: CliEntry = {
   shortBadge: 'GK',
   // Upstream hand-authored a charcoal GRADIENT across 4+ CSS spots (welcome button, tab
   // badge, run-mode dot, mobile skin overrides) rather than one flat colour; our registry's
-  // `accent` is a single hex, so this is the closest single value (the run-mode-dot colour,
-  // zinc-400). Nothing reads `accent` yet — the frontend is untouched in this change and
-  // keeps its own hand-authored CSS; the field is here so the entry is complete.
-  accent: '#a1a1aa',
+  // `accent` is a single hex, so this is the closest single value (zinc-300, the run-button
+  // border and tab-badge colour). Nothing reads `accent` yet: the frontend keeps its own
+  // hand-authored CSS; the field is here so the entry is complete.
+  accent: '#d4d4d8',
   enabled: true,
   stock: true,
   order: 70,
@@ -986,7 +1074,7 @@ const DEEPSEEK: CliEntry = {
   id: 'deepseek' as CliEntry['id'],
   label: 'DeepSeek',
   shortBadge: 'DS',
-  accent: '#4d6bfe',
+  accent: '#7c93ff',
   enabled: true,
   stock: true,
   order: 80,
@@ -1151,7 +1239,7 @@ const OMP: CliEntry = {
   id: 'omp' as CliEntry['id'],
   label: 'OMP',
   shortBadge: 'OM',
-  accent: '#7c9cf5',
+  accent: '#818cf8',
   enabled: true,
   stock: true,
   order: 90,

src/config/cli-registry/types.ts

@@ -344,7 +344,61 @@ export interface CliCapabilities {
     promptGlyph: string;
     /** Source of a regex matching the status line this CLI draws while a turn runs. */
     workingLine: string;
+    /**
+     * Source of a regex matching the row this CLI draws while work it started in the
+     * background is still running, e.g. Claude's `· 1 monitor ·` footer chip or Codex's
+     * `1 background terminal running · /ps to view`. Capture group 1 is the label Codeman
+     * shows, and the whole match stands in when the pattern declares no group. A CLI that
+     * omits this reports no background work, which is what every CLI did before the field
+     * existed.
+     */
+    watchingLine?: string;
+    /**
+     * How many rows at the FOOT of the screen that row can appear in, counting non-blank
+     * rows only. Claude writes its chip on the last row and keeps the default; Codex pins
+     * its own above the composer, which puts it third from the bottom, so it declares
+     * more. Keep each number as small as that CLI's layout allows: every extra row is
+     * another row an agent might be able to write, and the label is what silences an
+     * alert. See `watchingLabel()` in `session-activity.ts`.
+     */
+    watchingLines?: number;
+    /**
+     * Source of a regex matching the row this CLI closes a turn with when it ended that
+     * turn to WAIT for workers it started and will resume on its own once they finish,
+     * e.g. Claude's `✻ Waiting for 1 dynamic workflow to finish`. A pane showing it counts
+     * as working, not idle: nothing is being asked of the user, and the next turn starts
+     * without them.
+     *
+     * Unlike `workingLine` this is never searched across the pane. The CLI prints the row
+     * once and never updates it, so the copy from an earlier turn is still on screen after
+     * the workers are done. Only the newest transcript row directly above the composer is
+     * tested. See `isAwaitingWorkers()` in `session-activity.ts`.
+     */
+    awaitingLine?: string;
   };
+  /**
+   * How many columns this CLI indents its transcript body by, so a copy taken from its
+   * pane can drop that much and paste flush. Claude Code indents two and puts its own
+   * markers in those columns.
+   *
+   * ⚠ DECLARED rather than measured off the pane, and two measured attempts are why.
+   * Asking whether the pane painted real spaces across the unused part of each row
+   * separates a TUI from a shell perfectly where it fires and never over-stripped; it
+   * is also a function of pane WIDTH, because that padding exists only while a
+   * rendered line stops short of the CLI's own layout width and Claude Code's prose
+   * wraps to fill it. On one live transcript the share of padded rows ran 44%, 6%, 6%,
+   * 7% and 87% at 123, 160, 198, 235 and 298 columns, so at any ordinary window size
+   * the strip silently did nothing. Taking the narrowest indent on the surrounding
+   * rows instead fires at every width and over-strips on roughly 1% of selections,
+   * because a file listing inside the transcript can be the narrowest thing on screen.
+   *
+   * A declared width can do neither. The strip is the lesser of this and what every
+   * selected line shares, so a block can only ever shift as a unit, and it can never
+   * shift further than the CLI itself says its gutter is.
+   *
+   * Absent means no strip at all, the same fail-safe direction `workDetect` takes.
+   */
+  transcriptGutter?: number;
   /** No direct-PTY fallback: the CLI must run inside tmux (secrets ride tmux setenv). */
   requiresMux: boolean;
   /**
@@ -629,12 +683,14 @@ export interface CliOverlays {
 /**
  * ⚠️ DECLARED-FOR-LATER: fields no code reads yet.
  *
- * `shortBadge`, `accent`, `overlays.credStore`, `capabilities.echo`, `capabilities.wheelForward`,
+ * `accent`, `overlays.credStore`, `capabilities.echo`, `capabilities.wheelForward`,
  * `capabilities.keyboardAccessory` and `capabilities.maxFrameBytes` all describe FRONTEND
- * behaviour, and the frontend is deliberately untouched by the change that introduced this
- * registry — `app.js`, `terminal-ui.js`, `styles.css` and friends keep their own
+ * behaviour, and most of the frontend is deliberately untouched by the change that introduced
+ * this registry — `app.js`, `terminal-ui.js`, `styles.css` and friends keep their own
  * hand-authored per-CLI rules, and moving them is its own piece of work with its own way of
- * being verified (a mobile/browser suite the CI gate cannot see).
+ * being verified (a mobile/browser suite the CI gate cannot see). `shortBadge` graduated out of
+ * this list (docs/cli-enable-disable-plan.md, Phase 2): `GET /api/clis` reads it for the
+ * CLI-management Settings list.
  *
  * They are declared now because each entry should describe its CLI completely, and because
  * transcribing them while the hand-written source is still on screen is when the values are
@@ -651,7 +707,13 @@ export interface CliEntry {
   label: string;
   /** Two-ish character tab badge, e.g. 'OC'. */
   shortBadge: string;
-  /** Single hex colour. CSS derives every per-CLI gradient from it via --cli-accent. */
+  /**
+   * Single hex colour, measured from the CLI's actual `.btn-toolbar.btn-run.mode-<id>`
+   * gradient in styles.css (see stock.ts's comment above `CLAUDE` for the exact
+   * methodology). DECLARED-FOR-LATER (above) — no code reads this yet; styles.css's
+   * gradients are still hand-authored per id, not derived from this field via any
+   * CSS custom property. There is no `--cli-accent` variable in the codebase.
+   */
   accent: string;
   enabled: boolean;
   /** Set by the loader from the shipped catalog; a user entry can never claim it. */

src/config/dependency-registry.ts

@@ -69,7 +69,9 @@ const ALL: ProbeEnvironment[] = ['linux', 'darwin', 'wsl', 'win32'];
  * shown to the user and claude's does not follow the pattern.
  */
 const DOCTOR_ROW_OVERRIDES: Record<string, { id?: string; label?: string; usedBy: string[] }> = {
-  claude: { usedBy: ['Claude Code sessions (default backend)'] },
+  // The label override keeps the doctor row's historical "Claude CLI" spelling now that
+  // the registry label is the product name, "Claude Code".
+  claude: { label: 'Claude CLI', usedBy: ['Claude Code sessions (default backend)'] },
   opencode: { usedBy: ['OpenCode sessions'] },
   codex: { usedBy: ['Codex sessions'] },
   gemini: { usedBy: ['Gemini sessions'] },

src/config/server-timing.ts

@@ -99,3 +99,11 @@ export const STALE_DATA_MAX_AGE_MS = 60 * 60 * 1000;
 
 /** Standard 5-minute inactivity timeout for streams and caches (ms) */
 export const INACTIVITY_TIMEOUT_MS = 5 * 60 * 1000;
+
+/**
+ * Gap between a paste-mode cron prompt's text and its Enter (ms). The two must be
+ * separate writes: Claude Code takes a raw `<text>\r` burst of about a hundred
+ * characters as a paste and turns its `\r` into a newline. A separate `\r` 80 ms
+ * after the text was measured to submit; this leaves room for a longer prompt.
+ */
+export const CRON_PASTE_ENTER_DELAY_MS = 300;

src/cron/cron-service.ts

@@ -20,7 +20,7 @@ import { getErrorMessage, createErrorResponse, ApiErrorCode } from '../types/api
 import { MAX_CONCURRENT_SESSIONS, MAX_CRON_JOBS, MAX_CRON_RUN_HISTORY } from '../config/map-limits.js';
 import { canUsernameRunPrivilegedCommands, resolveClaudeModeForUsername } from '../user-store.js';
 import { sessionCapacityState, isWorkingDirAllowedForUsername } from '../web/route-helpers.js';
-import { CRON_READY_MAX_ATTEMPTS, CRON_READY_SETTLE_MS } from '../config/server-timing.js';
+import { CRON_PASTE_ENTER_DELAY_MS, CRON_READY_MAX_ATTEMPTS, CRON_READY_SETTLE_MS } from '../config/server-timing.js';
 import {
   DEFAULT_BLOCKED_TREES,
   isBlockedAttachmentPath,
@@ -100,6 +100,41 @@ const CRON_WORKING_DIR_BLOCKED_TREES: readonly string[] = [...DEFAULT_BLOCKED_TR
 /** Prompt delivery is single-line only (writeViaMux/Ink constraint). */
 const HAS_NEWLINE = /[\r\n]/;
 
+/** The three session calls prompt delivery needs, so it can be tested without a PTY. */
+type CronPromptTarget = Pick<Session, 'write' | 'writeViaMux' | 'verifySubmitted'>;
+
+/**
+ * Send a cron job's (single-line) prompt into its session and press Enter.
+ *
+ * `typed` goes through the mux: the text is typed, Enter is its own key, and the
+ * session re-presses it while the prompt is still on the composer.
+ *
+ * `paste` writes the text straight into the PTY, and must send its Enter as a
+ * SEPARATE write. It used to send `<text>\r` in one piece, and Claude Code (measured
+ * on 2.1.283) takes a burst of about a hundred characters as a paste, so the `\r`
+ * landed as a newline and the prompt sat unsent while the run reported
+ * `prompt_sent`. The Enter goes down the same PTY as the text, so it cannot overtake
+ * it, and the same composer check then covers a CLI that was not taking Enter yet.
+ *
+ * @returns false when the session had no PTY or mux to write to
+ */
+export async function deliverCronPrompt(
+  target: CronPromptTarget,
+  prompt: string,
+  inputMode: CronJob['inputMode'],
+  wait: (ms: number) => Promise<void> = delay
+): Promise<boolean> {
+  if (inputMode !== 'paste') {
+    return target.writeViaMux(prompt.endsWith('\r') ? prompt : `${prompt}\r`);
+  }
+  const text = prompt.replace(/[\r\n]+$/, '');
+  if (!target.write(text)) return false;
+  await wait(CRON_PASTE_ENTER_DELAY_MS);
+  if (!target.write('\r')) return false;
+  target.verifySubmitted(text);
+  return true;
+}
+
 /** Order-insensitive equality for the weekly-days arrays. */
 function sameDays(a: number[] | undefined, b: number[] | undefined): boolean {
   const x = [...(a ?? [])].sort((p, q) => p - q);
@@ -623,15 +658,9 @@ export class CronService {
         const s = this.deps.sessions.get(sessionId);
         if (!s) return;
         try {
-          const payload = prompt.endsWith('\r') ? prompt : `${prompt}\r`;
-          let delivered = true;
-          if (job.inputMode === 'paste') {
-            s.write(payload);
-          } else {
-            delivered = await s.writeViaMux(payload);
-          }
+          const delivered = await deliverCronPrompt(s, prompt, job.inputMode);
           if (!delivered) {
-            this.failRun(job, run, 'Failed to send prompt: mux write failed');
+            this.failRun(job, run, 'Failed to send prompt: the session could not be written to');
             return;
           }
           run.status = 'prompt_sent';

src/docker-hosts.ts

@@ -606,9 +606,65 @@ export function agentImageNpmPackages(): string[] {
   return packages;
 }
 
-/** The `--build-arg` pairs the agent image takes. */
-export function agentImageBuildArgPairs(): Array<[string, string]> {
-  return [['CLI_NPM_PACKAGES', agentImageNpmPackages().join(' ')]];
+/**
+ * Environment variable → agent.Dockerfile ARG for the optional git-host CLIs (gh, az).
+ * ⚠️ Mirrors `GIT_HOST_CLI_BUILD_ARGS` in `scripts/lib/cli-catalog.mjs`; the parity test pins them.
+ */
+export const GIT_HOST_CLI_BUILD_ARGS: ReadonlyArray<readonly [string, string]> = [
+  ['CODEMAN_AGENT_IMAGE_INSTALL_GH', 'CODEMAN_INSTALL_GH'],
+  ['CODEMAN_AGENT_IMAGE_INSTALL_AZ', 'CODEMAN_INSTALL_AZ'],
+];
+
+/**
+ * Environment variable → Dockerfile ARG for the image's system Git identity.
+ * ⚠️ Mirrors `GIT_IDENTITY_BUILD_ARGS` in `scripts/lib/cli-catalog.mjs`; the parity test pins them.
+ */
+export const GIT_IDENTITY_BUILD_ARGS: ReadonlyArray<readonly [string, string]> = [
+  ['CODEMAN_AGENT_IMAGE_GIT_USER_NAME', 'GIT_USER_NAME'],
+  ['CODEMAN_AGENT_IMAGE_GIT_USER_EMAIL', 'GIT_USER_EMAIL'],
+];
+
+/**
+ * The `--build-arg` pairs for the optional git-host CLIs. PURE. An unset or empty variable
+ * contributes NOTHING, so the Dockerfile's own default (off) applies and the argv is the same
+ * as before these existed; anything other than 0/1 is refused rather than guessed at.
+ */
+export function gitHostCliBuildArgPairs(env: NodeJS.ProcessEnv): Array<[string, string]> {
+  const pairs: Array<[string, string]> = [];
+  for (const [envName, argName] of GIT_HOST_CLI_BUILD_ARGS) {
+    const value = env[envName];
+    if (value === undefined || value === '') continue;
+    if (value !== '0' && value !== '1') {
+      throw new Error(`${envName} must be 0 or 1, got ${JSON.stringify(value)}`);
+    }
+    pairs.push([argName, value]);
+  }
+  return pairs;
+}
+
+/**
+ * The `--build-arg` pairs for a configured Git identity. An absent pair leaves
+ * Git unconfigured, preserving existing deployments; a partial pair is refused.
+ * ⚠️ Mirrors `gitIdentityBuildArgPairs()` in `scripts/lib/cli-catalog.mjs`; the parity test pins them.
+ */
+export function gitIdentityBuildArgPairs(env: NodeJS.ProcessEnv): Array<[string, string]> {
+  const pairs = GIT_IDENTITY_BUILD_ARGS.map(([envName, argName]) => [argName, env[envName] ?? ''] as [string, string]);
+  const configured = pairs.filter(([, value]) => value !== '');
+  if (configured.length === 0) return [];
+  if (configured.length !== pairs.length) {
+    const names = GIT_IDENTITY_BUILD_ARGS.map(([envName]) => envName).join(' and ');
+    throw new Error(`${names} must both be set when configuring Git identity`);
+  }
+  return pairs;
+}
+
+/** The `--build-arg` pairs the agent image takes. PURE given `env`. */
+export function agentImageBuildArgPairs(env: NodeJS.ProcessEnv = process.env): Array<[string, string]> {
+  return [
+    ['CLI_NPM_PACKAGES', agentImageNpmPackages().join(' ')],
+    ...gitHostCliBuildArgPairs(env),
+    ...gitIdentityBuildArgPairs(env),
+  ];
 }
 
 // ========== Credential mount resolution (IO) ==========
@@ -785,6 +841,14 @@ interface CredStorePolicy {
   seedFiles?: string[];
   /** Seed the WHOLE dir (RO mount → cp -a) — for stores with no shared/host-read state. */
   seedWhole?: boolean;
+  /**
+   * Seed this store ONLY when this environment variable is exactly `1`, read when
+   * the container is created. For credentials that belong to an opt-in tool rather
+   * than to an agent CLI every case already trusts: they are not inert just because
+   * the image lacks the tool (a gh `hosts.yml` token or an Azure refresh token is
+   * usable by anything in the container, and the agent in it is prompt-injectable).
+   */
+  enabledByEnv?: string;
 }
 
 const CRED_STORES: CredStorePolicy[] = [
@@ -829,6 +893,31 @@ const CRED_STORES: CredStorePolicy[] = [
   },
   { rel: '.config/gcloud', seedWhole: true },
   { rel: '.config/opencode', seedWhole: true },
+  // GitHub CLI: `hosts.yml` holds the token wherever no system keyring exists (the
+  // Docker server image, a headless Linux host), `config.yml` the preferences. An
+  // agent image built with CODEMAN_INSTALL_GH=1 routes github.com git credentials
+  // through `gh`, so this seed is what lets an agent clone/push a private repo. A
+  // token that lives in a desktop keyring is not in `hosts.yml` and does not carry
+  // in; sign `gh` in inside the container. OPT-IN: seeded only when the same switch
+  // that builds gh into the agent image is on, never merely because the file exists.
+  { rel: '.config/gh', seedFiles: ['hosts.yml', 'config.yml'], enabledByEnv: 'CODEMAN_AGENT_IMAGE_INSTALL_GH' },
+  // Azure CLI: only the sign-in state. `~/.azure` also accumulates `logs/`,
+  // `commands/`, telemetry and (on a bare host) `cliextensions/`, none of which is
+  // needed to authenticate; the agent image carries its own extensions outside HOME.
+  // `msal_token_cache.json` is plaintext only on Linux (Windows/macOS encrypt it), so
+  // this carries a sign-in from the Docker server image or a Linux host.
+  // OPT-IN like gh: the MSAL cache holds refresh tokens for the whole Azure account.
+  {
+    rel: '.azure',
+    enabledByEnv: 'CODEMAN_AGENT_IMAGE_INSTALL_AZ',
+    seedFiles: [
+      'azureProfile.json',
+      'msal_token_cache.json',
+      'service_principal_entries.json',
+      'clouds.config',
+      'config',
+    ],
+  },
   // OMP keeps its config in `~/.omp/agent` (config.yml/mcp.json/models.yml/
   // settings.yml — small, no bigger than grok's config.toml/pager.toml), but
   // that dir ALSO holds agent.db/history.db/models.db (SQLite caches) and
@@ -853,10 +942,14 @@ const CRED_STORES: CredStorePolicy[] = [
  * session state back into the host). Every path is existsSync-gated (on most hosts
  * only a subset exists). Pure-ish IO (no writes; just existence checks + mount specs).
  */
-export function resolveDockerCredentialArtifacts(home: string = homedir()): DockerClaudeArtifacts {
+export function resolveDockerCredentialArtifacts(
+  home: string = homedir(),
+  env: NodeJS.ProcessEnv = process.env
+): DockerClaudeArtifacts {
   const mounts: DockerMount[] = [];
   const seedCopies: DockerSeedCopy[] = [];
   for (const store of CRED_STORES) {
+    if (store.enabledByEnv && env[store.enabledByEnv] !== '1') continue;
     const hostBase = join(home, store.rel);
     if (!existsSync(hostBase)) continue;
     const containerBase = `${CONTAINER_HOME}/${store.rel}`;
@@ -1136,10 +1229,17 @@ function buildAgentImage(
       error: `docker/agent.Dockerfile not found in this install; clone the repo or build ${image} manually`,
     });
   }
+  let buildArgPairs: Array<[string, string]>;
+  try {
+    buildArgPairs = agentImageBuildArgPairs();
+  } catch (err) {
+    // A malformed CODEMAN_AGENT_IMAGE_* value: report it like any other build failure.
+    return Promise.resolve({ ok: false, built: false, alreadyPresent: false, error: String((err as Error).message) });
+  }
   const argv = dockerEngineArgv(docker);
   const args = [
     ...argv.slice(1),
-    ...agentImageBuildArgs(resolved.dockerfile, image, resolved.contextDir, opts.noCache, agentImageBuildArgPairs()),
+    ...agentImageBuildArgs(resolved.dockerfile, image, resolved.contextDir, opts.noCache, buildArgPairs),
   ];
   return new Promise<EnsureImageResult>((resolve) => {
     // async spawn (NEVER spawnSync) so a multi-minute build never wedges the event loop.

src/git-clone.ts

@@ -195,6 +195,8 @@ export interface CloneOptions {
   /** `--depth 1`: history-less but much faster on large repos. */
   shallow?: boolean;
   timeoutMs?: number;
+  /** Clear every git credential helper for this run (see `GIT_NO_CREDENTIAL_HELPERS`). */
+  withoutCredentialHelpers?: boolean;
 }
 
 export type CloneResult = { ok: true; stderr: string } | { ok: false; failure: GitFailure };
@@ -436,12 +438,27 @@ export function isSafeGitRef(ref: string): boolean {
 
 // ─── Pure: argv + env ────────────────────────────────────────────────────────
 
+/**
+ * Global git options that empty the credential-helper list for one run.
+ *
+ * Every Codeman user in multi-user mode runs git as the SAME OS account, so a
+ * helper that account has (the Docker image's opt-in `gh`/`az` helpers, or a
+ * user's own `gh auth setup-git`) would read private repositories on the
+ * signed-in admin's behalf for anyone who can reach Clone Repo. An empty
+ * `credential.helper` resets the helper list, and a command-line `-c` is read
+ * last, so it also drops the URL-scoped `credential.<url>.helper` entries the
+ * image configures (verified against a real private repo: refs with the helper,
+ * `could not read Username` with it cleared). Public repositories are
+ * unaffected. It must precede the subcommand.
+ */
+export const GIT_NO_CREDENTIAL_HELPERS: readonly string[] = ['-c', 'credential.helper='];
+
 /**
  * argv for the clone. `--` separates flags from operands so neither the
  * repository nor the destination can ever be read as an option.
  */
 export function buildCloneArgs(opts: CloneOptions): string[] {
-  const args = ['clone'];
+  const args = [...(opts.withoutCredentialHelpers ? GIT_NO_CREDENTIAL_HELPERS : []), 'clone'];
   // `--single-branch` is what makes "just this tag/branch" cheap on a big repo.
   if (opts.ref) args.push('--single-branch', '--branch', opts.ref);
   if (opts.shallow) args.push('--depth', '1');
@@ -450,8 +467,14 @@ export function buildCloneArgs(opts: CloneOptions): string[] {
 }
 
 /** argv for the preflight. `--symref` is what reveals the remote's default branch. */
-export function buildLsRemoteArgs(repository: string): string[] {
-  return ['ls-remote', '--symref', '--', repository];
+export function buildLsRemoteArgs(repository: string, opts: { withoutCredentialHelpers?: boolean } = {}): string[] {
+  return [
+    ...(opts.withoutCredentialHelpers ? GIT_NO_CREDENTIAL_HELPERS : []),
+    'ls-remote',
+    '--symref',
+    '--',
+    repository,
+  ];
 }
 
 /**
@@ -579,7 +602,7 @@ export function classifyGitFailure(stderr: string, timedOut: boolean, spawnError
     return {
       code: 'AUTH_REQUIRED',
       message:
-        'That repository needs authentication. Codeman clones without credentials, so private repositories have to be cloned outside Codeman and added with Link Existing.',
+        "That repository needs authentication. Codeman never asks for credentials, so sign this server's git in first (for example `gh auth login` or `az login` from a shell session; the Docker image can include both, see docker/README.md), or clone it outside Codeman and add it with Link Existing.",
       stderr: clean,
     };
   }
@@ -790,7 +813,8 @@ export function isGitAvailable(): boolean {
  */
 export async function probeGitRemote(
   repository: string,
-  timeoutMs = GIT_LS_REMOTE_TIMEOUT_MS
+  timeoutMs = GIT_LS_REMOTE_TIMEOUT_MS,
+  opts: { withoutCredentialHelpers?: boolean } = {}
 ): Promise<GitRemoteProbe> {
   if (!isGitAvailable()) {
     return {
@@ -800,7 +824,7 @@ export async function probeGitRemote(
       failure: classifyGitFailure('', false, 'ENOENT: git not found'),
     };
   }
-  const run = await runGit(buildLsRemoteArgs(repository), timeoutMs, MAX_LS_REMOTE_BYTES);
+  const run = await runGit(buildLsRemoteArgs(repository, opts), timeoutMs, MAX_LS_REMOTE_BYTES);
   if (run.code !== 0 || run.spawnError) {
     return {
       reachable: false,

src/mux-interface.ts

@@ -24,6 +24,7 @@ import type {
   OmpConfig,
   SessionRemote,
   SessionDocker,
+  PaneExit,
 } from './types.js';
 
 /**
@@ -56,6 +57,23 @@ export interface MuxSession {
   respawnConfig?: PersistedRespawnConfig;
   /** Whether Ralph / Todo tracking is enabled */
   ralphEnabled?: boolean;
+  /**
+   * This record was rebuilt from the tmux socket rather than from Codeman's own
+   * bookkeeping, so everything on it but the name and the pid is a guess. Its
+   * synthetic `restored-<fragment>` id cannot find the session's `state.json`
+   * entry either, which means a remote or docker session rediscovered this way
+   * arrives with no `remote`/`docker` metadata and looks local. Anything that
+   * would be WRONG about such a session rather than merely vague must fail
+   * closed on this flag.
+   *
+   * ⚠ It is PERMANENT, not merely true for the boot that rediscovered the
+   * session: `saveSessions()` serializes the whole record to
+   * `mux-sessions.json` and `loadSessions()` restores it, so a genuinely local
+   * session rediscovered once stays opted out of everything keyed on this for
+   * the life of that record. That is the safe direction to fail, and it costs
+   * only the guess Codeman is declining to make.
+   */
+  discovered?: boolean;
 }
 
 /**
@@ -72,6 +90,13 @@ export interface CreateSessionOptions {
   workingDir: string;
   mode: SessionMode;
   name?: string;
+  /**
+   * Name pinned on a claude spawn as `--name` (version-gated, sanitized, local only).
+   * Deliberately NOT `name`: `--name` owns the prompt-box label, the `/resume` picker
+   * entry and the terminal title, and a pinned title stops Claude generating its own,
+   * so only a user-chosen name belongs here (see `Session.cliPinnedName`).
+   */
+  cliName?: string;
   niceConfig?: NiceConfig;
   model?: string;
   claudeMode?: ClaudeMode;
@@ -90,6 +115,8 @@ export interface CreateSessionOptions {
   envOverrides?: Record<string, string>;
   /** Claude CLI effort level, injected as a `--settings` soft default (overridable via /effort in-session) */
   effort?: EffortLevel;
+  /** Claude advisor model, merged into the same `--settings` JSON (overridable via /advisor in-session) */
+  advisorModel?: string;
   /** tmux history-limit (scrollback lines) allocated when this session is created. */
   historyLimit?: number;
   /** Remote execution metadata for local tmux sessions wrapping SSH */
@@ -105,8 +132,15 @@ export interface RespawnPaneOptions {
   sessionId: string;
   workingDir: string;
   mode: SessionMode;
-  /** Session display name; a respawned claude keeps its `--name` peer name (version-gated, local only). */
+  /** Session display name (tab name). */
   name?: string;
+  /**
+   * Name pinned on a respawned claude as `--name` (version-gated, sanitized, local only).
+   * Deliberately NOT `name`: `--name` owns the prompt-box label, the `/resume` picker
+   * entry and the terminal title, and a pinned title stops Claude generating its own,
+   * so only a user-chosen name belongs here (see `Session.cliPinnedName`).
+   */
+  cliName?: string;
   niceConfig?: NiceConfig;
   model?: string;
   claudeMode?: ClaudeMode;
@@ -132,6 +166,8 @@ export interface RespawnPaneOptions {
   unsetEnvKeys?: string[];
   /** Claude CLI effort level (preserved across respawns, injected via `--settings`) */
   effort?: EffortLevel;
+  /** Claude advisor model (preserved across respawns, merged into the same `--settings` JSON) */
+  advisorModel?: string;
   /** Original tmux history-limit retained for config parity; respawn cannot resize the existing pane. */
   historyLimit?: number;
   /** Remote execution metadata for local tmux sessions wrapping SSH */
@@ -180,6 +216,7 @@ export interface PaneCaptureOptions {
  * - `sessionKilled` (data: { sessionId: string }) - Session terminated
  * - `sessionDied` (data: { sessionId: string }) - Session died unexpectedly
  * - `statsUpdated` (sessions: MuxSessionWithStats[]) - Stats refreshed
+ * - `paneExitsUpdated` () - A pane read finished; ask `getPaneExit()` per session
  */
 export interface TerminalMultiplexer extends EventEmitter {
   /** Which backend this instance uses */
@@ -294,6 +331,32 @@ export interface TerminalMultiplexer extends EventEmitter {
   /** Check if the pane in a session is dead (command exited but remain-on-exit keeps it alive) */
   isPaneDead(muxName: string): boolean;
 
+  /**
+   * What the last pane read saw of this session's agent, or `undefined` for
+   * UNKNOWN (Ark0N/Codeman#446). Unlike `isPaneDead()` this costs nothing: it
+   * reads a map the batched watcher fills, so it answers no fresher than that
+   * watcher's interval and the three synchronous `isPaneDead()` callers still
+   * need their own probe. See {@link PaneExit}.
+   */
+  getPaneExit?(muxName: string): PaneExit | undefined;
+
+  /**
+   * How many authoritative pane reads have agreed on the exit `getPaneExit()`
+   * reports, or 0 when it reports none. The exited-agent sweep closes a session
+   * only once this reaches `CLEAN_EXIT_CONFIRMING_READS` (`pane-exit-sweep.ts`),
+   * and a multiplexer without this method never has a session closed by it.
+   */
+  getPaneExitReadCount?(muxName: string): number;
+
+  /** Forget a session's exit observation, e.g. once its pane has been respawned. */
+  clearPaneExit?(muxName: string): void;
+
+  /** Start polling every pane on the socket for an exited agent. */
+  startPaneExitWatcher?(intervalMs?: number): void;
+
+  /** Stop the pane-exit watcher. */
+  stopPaneExitWatcher?(): void;
+
   /** Respawn a dead pane with a fresh command. Returns the new PID or null on failure. */
   respawnPane(options: RespawnPaneOptions): Promise<number | null>;
 

src/pane-exit-sweep.ts

@@ -0,0 +1,99 @@
+/**
+ * @fileoverview The exited-agent sweep's decision rule (Ark0N/Codeman#446).
+ *
+ * Codeman creates every tmux pane with `remain-on-exit on`, so `/exit` ends the
+ * CLI while the pane, the tmux session and the `tmux attach-session` process
+ * all live on. Part 1 of #446 records that as `SessionState.paneExit`. This
+ * module decides when such a session is closed, the way the X button closes
+ * it, so finished sessions stop piling up on the board.
+ *
+ * The rule closes a session only on a POSITIVE observation of a clean exit:
+ *
+ * - The exit status must be an explicit numeric 0 with no signal. An absent
+ *   status is UNKNOWN, never 0: on tmux 3.2a a SIGKILLed pane reports neither a
+ *   status nor a signal, so reading absence as clean would sweep an agent the
+ *   OOM killer took. A non-zero status or any signal keeps the row, marked with
+ *   the exit, as the crash evidence #210 was filed to keep.
+ * - At least {@link CLEAN_EXIT_CONFIRMING_READS} authoritative pane reads must
+ *   have agreed on that exit. A failed, empty or skipped read counts for
+ *   nothing, because unknown never closes anything.
+ * - No start, attach or relaunch may be in flight for the session. The
+ *   dead-pane branch of `Session._setupOrAttachMuxSession()` respawns an exited
+ *   pane on purpose, and for a few seconds that pane still reads as dead.
+ * - The exit must land at least {@link CLEAN_EXIT_MIN_PANE_LIFETIME_MS} after
+ *   the last start, attach or relaunch finished. A CLI that prints a startup
+ *   error ("not logged in", a bad profile, a config error) and exits 0 would
+ *   otherwise lose its tab, and the error with it, seconds after launch. Its
+ *   row stays, marked `exited (0)`, for the user to read and close.
+ *
+ * Scoping to local mux-backed sessions happens before this rule runs:
+ * `Session.setPaneExit()` forces the field to UNKNOWN for direct-PTY, remote,
+ * docker and discovered sessions, so their `paneExit` never reaches here.
+ *
+ * Pure, so the rule is unit-tested without a server (test/pane-exit-sweep.test.ts).
+ */
+import type { PaneExit } from './types/index.js';
+
+/**
+ * How many authoritative pane reads must agree on a clean exit before the
+ * session is closed. At the watcher's 2 s cadence two reads mean a finished
+ * session disappears within about four seconds of its agent exiting.
+ */
+export const CLEAN_EXIT_CONFIRMING_READS = 2;
+
+/**
+ * How long a pane must have been up before a clean exit closes its session.
+ * An exit sooner than this after the last pane start is read as a startup
+ * failure rather than a user ending the agent, and the row is kept.
+ */
+export const CLEAN_EXIT_MIN_PANE_LIFETIME_MS = 10_000;
+
+/** The lifecycle-log reason recorded when the sweep closes a session. */
+export const CLEAN_EXIT_CLOSE_REASON = 'agent exited cleanly (status 0)';
+
+/**
+ * Is this exit a clean one? True only for an explicit numeric status of 0 with
+ * no signal reported.
+ *
+ * ⚠ Never widen this to `(exit.status ?? 0) === 0` or to "no signal, so it was
+ * clean". An absent status is how a signal death presents on tmux 3.2a, and
+ * that shortcut would close crashed agents with nothing failing to warn you.
+ */
+export function isCleanPaneExit(exit: PaneExit | undefined): boolean {
+  if (!exit) return false;
+  if (exit.signal !== undefined) return false;
+  return exit.status === 0;
+}
+
+/** Everything the sweep needs to know about one session. */
+export interface CleanExitSweepCandidate {
+  /** The session's published exit, already scoped by `Session.setPaneExit()`. */
+  paneExit: PaneExit | undefined;
+  /** Authoritative pane reads that agreed on that exit (`getPaneExitReadCount()`). */
+  confirmingReads: number;
+  /** A start, attach or relaunch is running for this session's pane. */
+  paneLifecycleInFlight: boolean;
+  /** The session is already being closed or detached. */
+  closing: boolean;
+  /**
+   * When the last start, attach or relaunch of this pane finished
+   * (`Session.paneStartedAt`), or 0 when none has run in this process.
+   */
+  paneStartedAt: number;
+}
+
+/** Should the sweep close this session now? See the file overview for the rule. */
+export function shouldCloseCleanlyExitedSession(candidate: CleanExitSweepCandidate): boolean {
+  if (candidate.closing) return false;
+  if (candidate.paneLifecycleInFlight) return false;
+  if (!isCleanPaneExit(candidate.paneExit)) return false;
+  // `at` is when this server first read the pane dead, so an exit during the
+  // start itself lands BEFORE `paneStartedAt` and is kept too.
+  if (
+    candidate.paneStartedAt > 0 &&
+    candidate.paneExit!.at - candidate.paneStartedAt < CLEAN_EXIT_MIN_PANE_LIFETIME_MS
+  ) {
+    return false;
+  }
+  return candidate.confirmingReads >= CLEAN_EXIT_CONFIRMING_READS;
+}

src/reboot-restore.ts

@@ -19,19 +19,22 @@
  * touching its status, so a pinned session a reboot killed still reads `idle` or
  * `busy` and stays eligible.
  *
- * ⚠️ Ending the AGENT rather than the session is a shape this module CANNOT
- * recognise today, and a reboot restores it. `/exit` ends the CLI inside the
- * pane, `remain-on-exit` keeps the pane, and the PTY Codeman owns is the
- * `tmux attach-session` process, which stays alive throughout — so no exit
- * handler runs, no lifecycle `exit` is logged, and the record keeps both its pid
- * and `status: 'idle'`. Nothing durable distinguishes it from a session that was
- * simply idle when the power went. Ark0N/Codeman#446 covers making Codeman
- * notice the dead pane; until a record can say the agent is gone, this pass will
- * offer those sessions back, and the user dismisses or closes them.
+ * ⚠️ Ending the AGENT rather than the session leaves no trace in `status` or
+ * `pid`. `/exit` ends the CLI inside the pane, `remain-on-exit` keeps the pane,
+ * and the PTY Codeman owns is the `tmux attach-session` process, which stays
+ * alive throughout — so no exit handler runs, no lifecycle `exit` is logged,
+ * and the record keeps both its pid and `status: 'idle'`. Ark0N/Codeman#446
+ * handles it in two steps. The pane-exit watcher persists `paneExit`, and the
+ * clean-exit sweep (`pane-exit-sweep.ts`) closes a session whose agent exited
+ * with status 0 through `cleanupSession()`, which leaves the durable record
+ * described above. This module also refuses a record whose persisted
+ * `paneExit` is a clean exit, which covers a session that exited moments
+ * before the power went, before the sweep reached it. A crashed agent's record
+ * stays eligible, like the row the sweep leaves on the board for it.
  *
- * The `pid` check below is therefore NOT that rule. It refuses a record whose
- * attach process was already gone, which is a session that never started or
- * whose pane died outright.
+ * The `pid` check below is NOT that rule. It refuses a record whose attach
+ * process was already gone, which is a session that never started or whose
+ * pane died outright.
  *
  * @dependencies types (SessionState), config/cli-registry
  * @consumedby web/server (plan build at boot), web/routes/reboot-restore-routes
@@ -41,6 +44,7 @@
 
 import type { SessionState } from './types.js';
 import { getCli } from './config/cli-registry/registry.js';
+import { isCleanPaneExit } from './pane-exit-sweep.js';
 
 /** Session statuses a reboot restore may rebuild. `stopped` is the kill marker. */
 const RESTORABLE_STATUSES: ReadonlySet<string> = new Set(['idle', 'busy', 'error']);
@@ -109,7 +113,7 @@ export function resolveResumeConversationId(state: SessionState): string {
 /**
  * Why one session was passed over. Reported for logging and shown to the user.
  *
- * The first seven are decided before anything is built. `capacity-reached` and
+ * All but the last two are decided before anything is built. `capacity-reached` and
  * `rebuild-failed` can only happen once a click is spending the plan, and they
  * are the two the banner must not confuse with a missing workspace: one means
  * "try again after closing something", the other means the CLI would not start.
@@ -120,6 +124,7 @@ export interface RebootRestoreRejection {
     | 'no-persisted-record'
     | 'intentionally-ended'
     | 'not-running'
+    | 'agent-exited'
     | 'respawn-blocked'
     | 'remote-or-docker'
     | 'unsupported-mode'
@@ -191,7 +196,8 @@ export function planRebootRestore(
       //
       // ⚠️ This does NOT catch a session the user ended with `/exit`. See the
       // module header: that leaves the pid in place, because the pid is the tmux
-      // attach process and `remain-on-exit` keeps it alive.
+      // attach process and `remain-on-exit` keeps it alive. The `paneExit` check
+      // below catches it instead.
       //
       // Conservative on purpose. A session that somehow persisted no pid while
       // genuinely running is not offered, and its conversation stays reachable
@@ -200,6 +206,13 @@ export function planRebootRestore(
       skipped.push({ sessionId, reason: 'not-running' });
       continue;
     }
+    if (isCleanPaneExit(state.paneExit)) {
+      // The user ended the agent, and the clean-exit sweep would have closed the
+      // session had the power not gone first (Ark0N/Codeman#446). The same
+      // explicit-0 rule applies: an absent status is unknown, not clean.
+      skipped.push({ sessionId, reason: 'agent-exited' });
+      continue;
+    }
     if (state.respawnBlocked === true) {
       // The crash-loop breaker tripped on this pane. Re-creating it restarts the loop.
       skipped.push({ sessionId, reason: 'respawn-blocked' });

src/session-activity.ts

@@ -21,6 +21,8 @@
  * in 12/12 windows and the four idle ones in 0/12.
  */
 
+import { stripAnsi } from './utils/regex-patterns.js';
+
 /**
  * A gap longer than this ends a run of continuous output. Claude repaints at
  * least once a second while working, so this leaves generous headroom.
@@ -91,3 +93,124 @@ export function isSustainedActivity(streak: ActivityStreak | null, streakMs: num
 export function isPaneQuiet(lastActivityAt: number, now: number, silenceMs: number = IDLE_SILENCE_MS): boolean {
   return now - lastActivityAt >= silenceMs;
 }
+
+/**
+ * How many rows at the foot of a pane capture may hold the background-work row, for a
+ * CLI that declares no number of its own (`capabilities.workDetect.watchingLines`).
+ *
+ * One, because the tightest window is the right default and Claude Code needs no more:
+ * it draws its chip on the LAST row of the screen. Blank rows are dropped before the
+ * window is taken, so a trailing blank costs nothing, and a CLI that ever prints a row
+ * BELOW its chip loses the badge rather than gaining a hole.
+ *
+ * ⚠️ The size of this window is a trust boundary, not a tidiness measure, and the row
+ * it excludes first is the one that taught us so: Claude's status line sits directly
+ * above the footer, its content comes from a `statusLine` command, and a session running
+ * with permissions bypassed can write that command into `.claude/settings.json` in its
+ * own workspace. A window of two therefore let an agent print `· 1 monitor ·` onto a row
+ * of its own and silence its own idle alert. Every row added here is another row
+ * somebody may be able to write, so widen this only for a CLI whose layout forces it,
+ * and never to a whole-pane search.
+ */
+export const WATCHING_TAIL_LINES = 1;
+
+/** Longest label a badge will carry. A footer chip is a handful of words. */
+export const MAX_WATCHING_LABEL_CHARS = 40;
+
+/**
+ * What a pane says is still running in the background, e.g. `1 monitor` or `2 shells`.
+ *
+ * The CLI writes that chip while a monitor, a backgrounded shell or a cloud session it
+ * started is still going, which is exactly the case where the agent has ended its turn
+ * without wanting anything from the user. `pattern` comes from the CLI's own registry
+ * entry (`capabilities.workDetect.watchingLine`); group 1 is the label when the pattern
+ * declares one, and the whole match stands in when it does not.
+ *
+ * Each candidate row is tested on its own, bottom row first, so a pattern can anchor
+ * itself with `^` or `$` against a single row rather than against a joined block. Blank
+ * rows are dropped before the window is taken, because a CLI that leaves a blank line
+ * between its chrome rows would otherwise spend the window on nothing. The answer is
+ * stripped of ANSI and capped, because it ends up on a badge and in an approval card.
+ *
+ * @param tailLines how many non-blank rows from the bottom to look at, defaulting to
+ *   `WATCHING_TAIL_LINES`; a CLI declares its own when its row is not the last one
+ * @returns the label, or null when the pane shows no background work
+ */
+export function watchingLabel(
+  paneText: string | null | undefined,
+  pattern: RegExp,
+  tailLines: number = WATCHING_TAIL_LINES
+): string | null {
+  if (!paneText) return null;
+  const lines = stripAnsi(paneText)
+    .split('\n')
+    .map((line) => line.trimEnd())
+    .filter((line) => line !== '');
+  for (const line of lines.slice(-Math.max(1, tailLines)).reverse()) {
+    // A pattern compiled by compileVersionRegex() never carries the `g` flag, but a
+    // caller reaching in from a test or a config reload might, and a stale lastIndex
+    // would make the same screen match every other call.
+    pattern.lastIndex = 0;
+    const match = pattern.exec(line);
+    if (!match) continue;
+    const label = (match[1] ?? match[0]).trim().slice(0, MAX_WATCHING_LABEL_CHARS);
+    if (label) return label;
+  }
+  return null;
+}
+
+/**
+ * How many rows above the composer the turn's closing row may sit. Between the two Claude
+ * draws only its composer border and, sometimes, a right-aligned hint
+ * (`new task? /clear to save 169.1k tokens`), so this leaves room for a blank row or two
+ * and no more. A bound, not a tuning knob: the walk must never reach far enough up the
+ * transcript to find an old turn's row.
+ */
+export const AWAITING_SEARCH_ROWS = 6;
+
+/** A row that opens with a box-drawing character is the composer's frame, not transcript. */
+const COMPOSER_FRAME_ROW = /^[─-╿]/;
+
+/**
+ * Whether the pane's newest turn ended by handing off to workers the CLI will wait for,
+ * e.g. Claude's `✻ Waiting for 1 dynamic workflow to finish`.
+ *
+ * Such a pane is quiet and shows its composer, so every other signal calls it idle, yet
+ * nothing is being asked of the user: the CLI resumes by itself when the workers report
+ * back. That is why a session in this state counts as working.
+ *
+ * ⚠️ The row is a snapshot. Claude renders it once, at the end of the turn, and never
+ * updates it, so after the workers finish the same words are still on screen above the
+ * follow-up turn. Matching them anywhere on the pane would pin the session busy for as
+ * long as they stay visible. Only the newest transcript row counts: the walk starts at
+ * the composer (the LAST row carrying `promptGlyph`), steps up past blank rows, the
+ * composer's frame and anything indented (a right-aligned hint, a wrapped continuation),
+ * and tests the first row that starts in column 0. A follow-up turn always puts rows of
+ * its own there, so the stale copy is never the one tested.
+ *
+ * @param promptGlyph the CLI's composer glyph (`capabilities.workDetect.promptGlyph`)
+ * @returns false when the screen shows no composer, which is no evidence either way
+ */
+export function isAwaitingWorkers(paneText: string | null | undefined, pattern: RegExp, promptGlyph: string): boolean {
+  if (!paneText) return false;
+  const rows = stripAnsi(paneText)
+    .split('\n')
+    .map((row) => row.trimEnd());
+  let composer = -1;
+  for (let i = rows.length - 1; i >= 0; i--) {
+    // Claude has drawn its composer both bare (`❯ …` between rules) and boxed (`│ ❯ … │`).
+    if (rows[i].replace(/^[\s│]+/, '').startsWith(promptGlyph)) {
+      composer = i;
+      break;
+    }
+  }
+  if (composer < 0) return false;
+  for (let i = composer - 1; i >= Math.max(0, composer - AWAITING_SEARCH_ROWS); i--) {
+    const row = rows[i];
+    if (row === '' || /^\s/.test(row) || COMPOSER_FRAME_ROW.test(row)) continue;
+    // Same reasoning as watchingLabel(): a caller's `g` flag must not make this flap.
+    pattern.lastIndex = 0;
+    return pattern.test(row);
+  }
+  return false;
+}

src/session-cli-builder.ts

@@ -9,7 +9,7 @@
  */
 
 import type { ClaudeMode, EffortLevel } from './types.js';
-import { isEffortLevel } from './types.js';
+import { isAdvisorModel, isEffortLevel } from './types.js';
 import { getAugmentedPath } from './utils/index.js';
 import { compareVersions } from './utils/dependency-checker.js';
 import { dataPath } from './config/instance.js';
@@ -54,6 +54,25 @@ export function buildEffortCliArgs(effort?: EffortLevel): string[] {
   return effort === 'ultracode' ? ['--settings', '{"ultracode":true}'] : ['--effort', effort];
 }
 
+/**
+ * The `--settings` keys that switch on Claude Code's advisor tool for one session: a
+ * stronger model the main model consults at decision points (code.claude.com/docs/en/advisor).
+ * Returns `{}` for an absent or non-allowlisted value, so callers can spread it unconditionally.
+ *
+ * ⚠️ Carried as the `advisorModel` SETTINGS key, never the `--advisor` flag. The flag EXITS at
+ * launch on any pairing the CLI refuses (`claude --advisor haiku` prints "cannot be used as an
+ * advisor" and exits 1, as does a Fable advisor still awaiting usage-credit consent), which
+ * would leave a dead pane on every spawn and respawn. The settings key degrades instead: the
+ * CLI simply does not attach an advisor it cannot use. It is a SOFT default either way:
+ * `/advisor` still switches or turns it off inside the running session.
+ *
+ * ⚠️ Claude Code reads only ONE `--settings` flag per invocation, so this must be merged into
+ * the same JSON object as ultracode and the statusLine exporter, never rendered on its own.
+ */
+export function buildAdvisorSettings(advisorModel?: string): { advisorModel?: string } {
+  return isAdvisorModel(advisorModel) ? { advisorModel } : {};
+}
+
 /**
  * Minimum Claude CLI version for passing `--name` at spawn. 2.1.224 is the release
  * that ships cross-session messaging (the feature that makes the peer name matter),
@@ -111,6 +130,7 @@ export function buildNameCliArgs(sessionName: string | undefined, cliVersion: st
  * @param effort - Optional effort level, injected via --settings (overridable in-session)
  * @param sessionName - Optional Codeman session name, passed as `--name` (version-gated)
  * @param cliVersion - Installed Claude CLI version for the `--name` gate (null = omit the flag)
+ * @param advisorModel - Optional advisor model, merged into the one `--settings` JSON (see buildAdvisorSettings)
  * @returns Array of CLI arguments
  */
 export function buildInteractiveArgs(
@@ -120,11 +140,21 @@ export function buildInteractiveArgs(
   allowedTools?: string,
   effort?: EffortLevel,
   sessionName?: string,
-  cliVersion?: string | null
+  cliVersion?: string | null,
+  advisorModel?: string
 ): string[] {
   const args = [...buildPermissionArgs(claudeMode, allowedTools), '--session-id', sessionId];
   if (model) args.push('--model', model);
-  args.push(...buildEffortCliArgs(effort));
+  const effortArgs = buildEffortCliArgs(effort);
+  const advisor = buildAdvisorSettings(advisorModel);
+  if (advisor.advisorModel === undefined) {
+    args.push(...effortArgs);
+  } else if (effortArgs[0] === '--settings') {
+    // One --settings flag only: fold the advisor into ultracode's JSON object.
+    args.push('--settings', JSON.stringify({ ...JSON.parse(effortArgs[1]), ...advisor }));
+  } else {
+    args.push(...effortArgs, '--settings', JSON.stringify(advisor));
+  }
   args.push(...buildNameCliArgs(sessionName, cliVersion));
   return args;
 }

src/session-cli-registry-bridge.ts

@@ -20,7 +20,7 @@
 import type { CliEntry } from './config/cli-registry/types.js';
 import { renderLaunch, type EngineValues, type ParamValues } from './config/cli-registry/argv.js';
 import { matchesPattern } from './config/cli-registry/patterns.js';
-import { buildEffortCliArgs, sanitizeCliSessionName } from './session-cli-builder.js';
+import { buildAdvisorSettings, buildEffortCliArgs, sanitizeCliSessionName } from './session-cli-builder.js';
 import { compareVersions } from './utils/dependency-checker.js';
 import { getClaudeCliVersion } from './utils/claude-cli-resolver.js';
 import { launcherDefaultTarget } from './utils/cli-launcher.js';
@@ -54,6 +54,8 @@ export interface SpawnBridgeOptions {
   ompConfig?: OmpConfig;
   resumeSessionId?: string;
   effort?: EffortLevel;
+  /** Claude advisor model; rides the same `--settings` JSON as ultracode (see buildAdvisorSettings). */
+  advisorModel?: string;
   sessionName?: string;
   claudeCliVersion?: string | null;
   /**
@@ -198,14 +200,20 @@ export function buildSpawnCommandFromRegistry(entry: CliEntry, options: SpawnBri
     engineValues.effortLevel = effortValue;
   }
 
-  // Fold the ephemeral plan-usage statusLine exporter (see resolveStatusLineCliCommand in
-  // hooks-config.ts) into the SAME `--settings` JSON object as ultracode/ effort, since Claude
-  // Code accepts only one `--settings` flag per invocation — rendering them as two independent
-  // params would let the second one silently win. Claude-only in practice (statusLineCommand
-  // is resolved claude-mode-only upstream), but this merge is mode-agnostic.
-  if ((effortFlag === '--settings' && effortValue) || options.statusLineCommand) {
-    const settingsObj: Record<string, unknown> =
-      effortFlag === '--settings' && effortValue ? JSON.parse(effortValue) : {};
+  // Fold the advisor model and the ephemeral plan-usage statusLine exporter (see
+  // resolveStatusLineCliCommand in hooks-config.ts) into the SAME `--settings` JSON object as
+  // ultracode/ effort, since Claude Code accepts only one `--settings` flag per invocation:
+  // rendering them as independent params would let the last one silently win. Claude-only in
+  // practice: only claude's launch template renders this engine value, so another CLI's
+  // session carrying an advisorModel launches exactly as before.
+  // Key order (ultracode, advisorModel, statusLine) keeps a launch without an advisor
+  // byte-identical to one from before the advisor existed.
+  const advisorSettings = buildAdvisorSettings(options.advisorModel);
+  if ((effortFlag === '--settings' && effortValue) || advisorSettings.advisorModel || options.statusLineCommand) {
+    const settingsObj: Record<string, unknown> = {
+      ...(effortFlag === '--settings' && effortValue ? JSON.parse(effortValue) : {}),
+      ...advisorSettings,
+    };
     if (options.statusLineCommand) {
       settingsObj.statusLine = { type: 'command', command: options.statusLineCommand };
     }

src/session.ts

@@ -42,6 +42,7 @@ import {
   NiceConfig,
   DEFAULT_NICE_CONFIG,
   getErrorMessage,
+  isAdvisorModel,
   isEffortLevel,
   type ClaudeMode,
   type SessionMode,
@@ -60,8 +61,11 @@ import {
   type SessionDocker,
   type SessionNameSource,
   type SessionWriteOptions,
+  type PaneExit,
 } from './types.js';
 import { resolveAndClaimOmpSessionId } from './utils/omp-session-resolver.js';
+import { claudeTranscriptExists } from './utils/claude-transcript.js';
+import { matchesPattern } from './config/cli-registry/patterns.js';
 import { probeDockerCliVersion } from './docker-hosts.js';
 import { probeRemoteCliVersion } from './remote-hosts.js';
 import type { TerminalMultiplexer, MuxSession } from './mux-interface.js';
@@ -81,6 +85,9 @@ import {
   trackActivityStreak,
   isSustainedActivity,
   isPaneQuiet,
+  watchingLabel,
+  isAwaitingWorkers,
+  WATCHING_TAIL_LINES,
   IDLE_RECHECK_MS,
   PANE_PROBE_MIN_INTERVAL_MS,
   PANE_PROBE_RECHECK_MS,
@@ -497,8 +504,37 @@ export class Session extends EventEmitter {
   private _activityStreak: ActivityStreak | null = null; // Unbroken run of PTY repaints (working detection)
   private _lastPaneProbeAt = 0; // Throttle for the tmux screen probe
   private _lastPaneProbeWorking: boolean | null = null; // Its last verdict (null = could not read)
+  /**
+   * Background work the pane's own footer reports, e.g. `1 monitor`; null for none.
+   *
+   * Cached BESIDE `_lastPaneProbeWorking` and refreshed only by a capture that really
+   * happened, so it goes stale exactly as that verdict does. The probe returns its
+   * cached boolean without re-capturing inside `PANE_PROBE_MIN_INTERVAL_MS`, and a
+   * label derived from a capture nobody took would be a guess wearing a fact's clothes.
+   *
+   * ⚠️ It then FREEZES once `_confirmIdle()` concludes: `activityTimeout` is null from
+   * there, and nothing looks at the pane again until it produces output. That is
+   * correct rather than merely tolerable, because work ending repaints the pane either
+   * way — a monitor firing wakes the agent, and codex drops its background-terminal row
+   * on its own. Do not add a timer to keep this fresh; it would spend a `capture-pane`
+   * per idle session per tick to learn nothing.
+   *
+   * A server restart is not a hole in that either, though it looks like one: this field
+   * is live state and starts empty. Reconciliation re-attaches the pane, the attach
+   * repaint carries the composer glyph, and the idle confirmation that arms on it probes
+   * and re-reads the label with no input from anyone — measured 2026-09-23 on a restarted
+   * instance, back within ~20 s for a session whose background terminal was still
+   * running. A session that comes back with no label has no chip on its screen.
+   */
+  private _watching: string | null = null;
   /** Lazily compiled `capabilities.workDetect.workingLine`. See _workingLinePattern(). */
   private _workingLineRe: RegExp | undefined = undefined;
+  /** Lazily compiled `capabilities.workDetect.watchingLine`. See _watchingLinePattern(). */
+  private _watchingLineRe: RegExp | null | undefined = undefined;
+  /** Resolved with the pattern above: how many rows at the foot of the screen to search. */
+  private _watchingWindow = WATCHING_TAIL_LINES;
+  /** Lazily compiled `capabilities.workDetect.awaitingLine`. See _awaitingLinePattern(). */
+  private _awaitingLineRe: RegExp | null | undefined = undefined;
   private _trustDialogAccepted: boolean = false; // Stops the trust-dialog scan (answered, or given up)
   private _trustDialogAttempts = 0; // Keystrokes sent at the trust dialog
   private _lastTrustDialogScanAt = 0; // Throttle for the trust-dialog screen read
@@ -542,6 +578,35 @@ export class Session extends EventEmitter {
   private _mux: TerminalMultiplexer | null = null;
   private _muxSession: MuxSession | null = null;
   private _useMux: boolean = false;
+  /**
+   * The agent in this session's local tmux pane has exited (Ark0N/Codeman#446).
+   * `null` is the UNKNOWN arm of the tri-state and is what {@link setPaneExit}
+   * stores for every session shape the field does not apply to. See
+   * {@link PaneExit} for the shapes and for why an unknown answer must never be
+   * rendered as "alive".
+   */
+  private _paneExit: PaneExit | null = null;
+  /**
+   * How many starts, attaches or relaunches are running for this session's
+   * pane. While one is, a dead-pane reading may describe a pane that is being
+   * revived on purpose, so the exited-agent sweep leaves the session alone
+   * (Ark0N/Codeman#446). A counter rather than a flag, so two overlapping
+   * operations cannot clear each other's mark.
+   */
+  private _paneLifecycleOps = 0;
+  /** When the last pane start, attach or relaunch finished (ms), 0 when none has run. */
+  private _paneStartedAt = 0;
+  /**
+   * The server has started closing this session, so no start or attach may
+   * begin (see {@link markClosing}).
+   */
+  private _closing = false;
+  /**
+   * This session was rebuilt from the tmux socket rather than from Codeman's
+   * own records, so its `remote`/`docker` metadata is missing rather than known
+   * to be absent. See {@link MuxSession.discovered}.
+   */
+  private _discoveredMuxSession = false;
   // Flag to prevent new timers after session is stopped
   private _isStopped: boolean = false;
 
@@ -594,6 +659,11 @@ export class Session extends EventEmitter {
   // the CLAUDE_CODE_EFFORT_LEVEL env var, which would hard-lock the session.
   private _effort: EffortLevel | undefined;
 
+  // Claude advisor model (code.claude.com/docs/en/advisor), merged into the same launch
+  // `--settings` JSON as ultracode, never the `--advisor` flag (which exits on a refused
+  // pairing). A soft default: /advisor still switches or disables it in-session.
+  private _advisorModel: string | undefined;
+
   // Custom Model Endpoint Profiles (docs/custom-model-endpoints-plan.md). `envKeys`,
   // `configDir` and `launchModel` are internal bookkeeping ONLY (never surfaced via
   // toState()/the customModel getter): they are what setCustomModel() needs to undo a
@@ -710,6 +780,8 @@ export class Session extends EventEmitter {
       envOverrides?: Record<string, string>;
       /** Claude CLI effort level (soft default via --settings, switchable in-session via /effort) */
       effort?: EffortLevel;
+      /** Claude advisor model (soft default via --settings, switchable in-session via /advisor) */
+      advisorModel?: string;
       /** tmux history-limit (scrollback lines) allocated when this session's pane is created. */
       tmuxHistoryLimit?: number;
       /** Restored per-session attachment history. May include server-private external paths. */
@@ -718,6 +790,10 @@ export class Session extends EventEmitter {
       lastSubmitAt?: number;
       /** Restored conversation chain, oldest first (see `claudeSessionChain`). */
       claudeSessionChain?: string[];
+      /** Restored agent-exit observation for this session's pane (see `paneExit`). */
+      paneExit?: PaneExit;
+      /** This session was rebuilt from the tmux socket, so its metadata is a guess. */
+      discoveredMuxSession?: boolean;
       /** Restored wall-clock ms of the pane's last output (recovery only; see `_wireActivityAt`). */
       lastActivityAt?: number;
       /** Remote execution metadata for sessions launched through SSH inside local tmux. */
@@ -866,10 +942,23 @@ export class Session extends EventEmitter {
     if (config.effort && isEffortLevel(config.effort)) {
       this._effort = config.effort;
     }
+    if (isAdvisorModel(config.advisorModel)) {
+      this._advisorModel = config.advisorModel;
+    }
     this._tmuxHistoryLimit = config.tmuxHistoryLimit ?? DEFAULT_TMUX_HISTORY_LIMIT;
     this._remote = config.remote;
     this._docker = config.docker;
     this._owner = config.owner;
+    this._discoveredMuxSession = config.discoveredMuxSession === true;
+    // Restored so a record that says the agent exited survives a server restart
+    // rather than being blanked by the first persist after boot. It runs here
+    // because the scoping reads `_remote`, `_docker` and the mux fields, all of
+    // which are set by now. It is a claim about a pane this process has not
+    // looked at yet, so every path that starts or re-attaches a pane drops it
+    // (see `_setupOrAttachMuxSession`) and the pane-exit watcher's own tick
+    // replaces it with a first-hand reading. NOT the stats collector, which a
+    // browser panel arms and disarms — see `startPaneExitWatcher`.
+    this.setPaneExit(config.paneExit);
     // Never self-parent: a session pointing at itself would draw a zero-length
     // lineage arc under its own tab. Only reachable via the recovery path, where
     // both the id and the saved parent come from disk.
@@ -1097,6 +1186,118 @@ export class Session extends EventEmitter {
     return this._muxSession?.muxName ?? null;
   }
 
+  /**
+   * True when a tmux pane's death would mean THIS session's agent has exited.
+   *
+   * Four shapes fail the test, and each would otherwise publish a death that is
+   * not the agent's. A direct-PTY session owns no pane at all. A remote SSH
+   * session's local pane holds the ssh client, whose death means a transport
+   * drop OR an exit, which is the ambiguity PR #355 was about. A docker case's
+   * local pane holds a `docker exec` into the container's own tmux.
+   *
+   * The fourth is a session rebuilt from the socket. Absent `remote`/`docker`
+   * normally means "this is local", but on a discovered record it only means
+   * "Codeman never found the metadata": the synthetic `restored-<fragment>` id
+   * matches no `state.json` entry, so a remote session rediscovered after
+   * `mux-sessions.json` was lost arrives looking local, and its next transport
+   * drop would be published as an agent exit. Unproven locality fails closed.
+   */
+  private get paneExitApplies(): boolean {
+    if (this._discoveredMuxSession) return false;
+    return this._useMux && this._muxSession !== null && !this._remote && !this._docker;
+  }
+
+  /** What Codeman last observed of this pane's agent, or undefined for UNKNOWN. */
+  get paneExit(): PaneExit | undefined {
+    return this._paneExit ?? undefined;
+  }
+
+  /**
+   * True while a start, attach or relaunch is running for this session's pane.
+   * The exited-agent sweep reads it (see `pane-exit-sweep.ts`): the dead-pane
+   * branch of {@link _setupOrAttachMuxSession} respawns an exited pane, and
+   * until it finishes and clears the exit, the pane still reads as dead.
+   */
+  get paneLifecycleInFlight(): boolean {
+    return this._paneLifecycleOps > 0;
+  }
+
+  /**
+   * When the last start, attach or relaunch of this pane finished, or 0 when
+   * none has run in this process. The exited-agent sweep keeps an exit that
+   * lands within `CLEAN_EXIT_MIN_PANE_LIFETIME_MS` of it, since that reads as a
+   * CLI failing at startup rather than a user ending it. An attach to a pane
+   * that was already running stamps it too, which only costs a user who
+   * `/exit`s within seconds of a server restart a row to close by hand.
+   */
+  get paneStartedAt(): number {
+    return this._paneStartedAt;
+  }
+
+  /**
+   * Mark this session as being closed, or clear the mark after a close that
+   * failed. While it is set, {@link startInteractive} and {@link startShell}
+   * refuse to run. A start that raced a close would otherwise launch a CLI in a
+   * tmux session whose record is about to be deleted (Ark0N/Codeman#446).
+   */
+  markClosing(closing: boolean): void {
+    this._closing = closing;
+  }
+
+  /** Run one pane start, attach or relaunch with {@link paneLifecycleInFlight} raised. */
+  private async _withPaneLifecycle<T>(op: () => Promise<T>): Promise<T> {
+    this._paneLifecycleOps++;
+    try {
+      return await op();
+    } finally {
+      this._paneLifecycleOps--;
+      this._paneStartedAt = Date.now();
+    }
+  }
+
+  /**
+   * Forget this pane's exit, on both this record and the mux layer's cache.
+   * Every path that starts or relaunches a command in the pane calls it, and
+   * the mux half also invalidates a pane read already in flight.
+   *
+   * It does not persist or broadcast by itself; the caller owns both. ⚠ That
+   * caller MUST persist, and the pane-exit watcher is not a fallback for it:
+   * the watcher's next tick reads UNKNOWN, finds this field already cleared,
+   * reports no change and therefore writes nothing, so a caller that only
+   * broadcasts leaves `state.json` saying the agent exited for as long as the
+   * session stays quiet. `/interactive` and `/shell` did exactly that until
+   * Ark0N/Codeman#446 review; both now persist on their success path.
+   */
+  private clearPaneExitForNewPane(): void {
+    this.setPaneExit(undefined);
+    if (this._muxSession) this._mux?.clearPaneExit?.(this._muxSession.muxName);
+  }
+
+  /**
+   * Record what the mux layer observed of this pane's agent, and say whether
+   * that changed the answer. The caller persists and broadcasts on a true.
+   *
+   * A session the field does not apply to is forced to UNKNOWN here rather than
+   * at the reporting end, so the rule lives in one place and the mux layer stays
+   * free to report the raw pane reading its own remote-reconnect watcher needs.
+   */
+  setPaneExit(next: PaneExit | undefined): boolean {
+    const resolved = this.paneExitApplies ? (next ?? null) : null;
+    const prev = this._paneExit;
+    if (prev === resolved) return false;
+    if (
+      prev !== null &&
+      resolved !== null &&
+      prev.status === resolved.status &&
+      prev.signal === resolved.signal &&
+      prev.at === resolved.at
+    ) {
+      return false;
+    }
+    this._paneExit = resolved;
+    return true;
+  }
+
   /**
    * True when this session's PTY is a tmux client rather than the program itself.
    * Read by the replay-side alt-screen strip, which must apply the same
@@ -1118,6 +1319,16 @@ export class Session extends EventEmitter {
     return this._isWorking;
   }
 
+  /**
+   * What the pane says is still running in the background, e.g. `1 monitor`, or null when
+   * nothing is. A session with a label here has ended its turn without wanting anything
+   * from the user, so a surface that would otherwise file it under "needs you" can say
+   * what it is waiting for instead.
+   */
+  get watching(): string | null {
+    return this._watching;
+  }
+
   /**
    * Check if the session's process tree has active child processes beyond Claude itself.
    * Detects running bash tools, test suites, builds, servers, etc. that Claude spawned.
@@ -1421,6 +1632,19 @@ export class Session extends EventEmitter {
     return this._nameSource;
   }
 
+  /**
+   * The name to pin on the Claude CLI as `--name`, or undefined to let Claude
+   * title the conversation itself. `--name` is the prompt-box label, the
+   * `/resume` picker entry and the terminal title all at once, and a pinned
+   * title stops Claude generating its own, so only a name the user chose is
+   * worth pinning. Pinning the `w1-myapp` placeholder gave every conversation
+   * in a case the same `/resume` entry; an auto name is a cut of the first
+   * prompt, which Claude's own generated title already beats.
+   */
+  get cliPinnedName(): string | undefined {
+    return this._nameSource === 'manual' ? this._name : undefined;
+  }
+
   setAutoClear(enabled: boolean, threshold?: number): void {
     this._autoOps.setAutoClear(enabled, threshold);
   }
@@ -1614,12 +1838,17 @@ export class Session extends EventEmitter {
       ompConfig: this._ompConfig,
       resumeSessionId: this._resumeSessionId,
       effort: this._effort,
+      advisorModel: this._advisorModel,
       customModel: this.customModel,
       // COD-118: runtime-only — surfaced so the frontend can require explicit user
       // intent before restarting a crash-looped session. Deliberately NOT restored
       // by the constructor: a Codeman restart starts with a fresh breaker so boot
       // recovery can re-attach.
       respawnBlocked: this._respawnBlocked || undefined,
+      // Ark0N/Codeman#446 — the agent in this pane has exited, published here so
+      // it rides the existing `session:updated` broadcast and lands in state.json
+      // through the same persist. `status` and `pid` above stay untouched by it.
+      paneExit: this._paneExit ?? undefined,
       attachmentHistory: this.attachmentHistory.length > 0 ? this.attachmentHistory : undefined,
       lastSubmitAt: this._lastSubmitAt || undefined,
       // Only a chain the CLI's own hooks vouched for is persisted, and only when
@@ -1675,6 +1904,7 @@ export class Session extends EventEmitter {
       totalCost: this._totalCost,
       messageCount: this._messages.length,
       isWorking: this._isWorking,
+      watching: this._watching,
       lastPromptTime: this._lastPromptTime,
       // Buffer statistics for monitoring long-running sessions
       bufferStats: {
@@ -1731,41 +1961,90 @@ export class Session extends EventEmitter {
     respawnPaneOptions: import('./mux-interface.js').RespawnPaneOptions;
     createSessionOptions: import('./mux-interface.js').CreateSessionOptions;
     spawnErrLabel: string;
-  }): Promise<{ isRestored: boolean }> {
+  }): Promise<{ isRestored: boolean; respawnedResumeId?: string; respawnedDeadPane: boolean }> {
+    return this._withPaneLifecycle(() => this._doSetupOrAttachMuxSession(options));
+  }
+
+  private async _doSetupOrAttachMuxSession(options: {
+    respawnPaneOptions: import('./mux-interface.js').RespawnPaneOptions;
+    createSessionOptions: import('./mux-interface.js').CreateSessionOptions;
+    spawnErrLabel: string;
+  }): Promise<{ isRestored: boolean; respawnedResumeId?: string; respawnedDeadPane: boolean }> {
     const mux = this._mux!;
 
-    // Verify stale mux session — tmux may have been destroyed (e.g., killed externally)
+    // Verify stale mux session — tmux may have been destroyed (e.g., killed externally).
+    // A session that HAD a mux session relaunches its CLI below just like a failed
+    // respawn does (tmux kill-server, a tmux crash, an external kill-session), so
+    // its transcript collides with the bare `--session-id` the same way. A
+    // genuinely new session starts with `_muxSession` null and never sets this.
+    let muxSessionVanished = false;
     if (this._muxSession && !mux.muxSessionExists(this._muxSession.muxName)) {
       console.log('[Session] Stale mux session detected (tmux gone):', this._muxSession.muxName);
       this._muxSession = null;
+      muxSessionVanished = true;
     }
 
     // Check if session exists but pane is dead (remain-on-exit keeps it alive)
     // Respawn the pane instead of creating a whole new session — preserves tmux scrollback
     let needsNewSession = false;
+    let respawnedDeadPane = false;
+    let respawnedResumeId: string | undefined;
     if (this._muxSession && mux.isPaneDead(this._muxSession.muxName)) {
       console.log('[Session] Dead pane detected, respawning:', this._muxSession.muxName);
       // Confirmed dead — safe to resolve/pin now (see `_pinOmpRespawnId()`).
       // `options.respawnPaneOptions` was built eagerly before this dead-pane
       // check ran, so it still carries the pre-pin ompConfig; rebuild it.
       this._pinOmpRespawnId();
-      const newPid = await mux.respawnPane(this._buildRespawnPaneOptions());
+      const respawnOptions = await this._buildRespawnPaneOptionsWithResumePin();
+      const newPid = await mux.respawnPane(respawnOptions);
       if (!newPid) {
         console.error('[Session] Failed to respawn pane, will create new session');
         needsNewSession = true;
       } else {
+        respawnedDeadPane = true;
+        respawnedResumeId = respawnOptions.resumeSessionId;
         this._pendingEnvUnsets.clear();
         // Wait a moment for the respawned process to fully start
         await new Promise((resolve) => setTimeout(resolve, MUX_STARTUP_DELAY_MS));
       }
     }
 
+    // Whatever the last reading said about the OLD command in this pane is now
+    // history: the branch above either respawned the pane or found it alive, and
+    // the branch below creates a new one. The paths that reach here are boot
+    // recovery and an explicit start, NOT a click on an exited tab — the browser
+    // re-attaches only on a null pid, and the premise of Ark0N/Codeman#446 is
+    // that an exited pane keeps its pid. `restartCli()` clears separately.
+    this.clearPaneExitForNewPane();
+
     // Check if we already have a mux session (restored session)
     const isRestored = this._muxSession !== null && !needsNewSession;
     if (isRestored) {
       console.log('[Session] Attaching to existing mux session:', this._muxSession!.muxName);
     } else {
-      // Create a new mux session
+      // Create a new mux session. When this is the FALLBACK after a failed
+      // respawn, the eagerly-built create options still carry the unpinned
+      // launch seed, so a session whose transcript exists would meet the same
+      // `--session-id ... already in use` refusal the respawn just lost to —
+      // the recovery of last resort failing for the very reason it was needed.
+      // A genuinely new session has no transcript under any of its candidate
+      // ids, so nothing is pinned and its command shape is unchanged.
+      //
+      // `_resumeSessionId` is written alongside, not just the create options:
+      // this branch leaves `isRestored` false, so the block that sets
+      // `_claudeSessionId` below reads that field and would otherwise settle on
+      // `this.id` while the CLI resumes the chain tail. The response viewer,
+      // Read My Mind and the unified-list alias map all read `_claudeSessionId`
+      // until the next first-hand hook, so the two have to name the same
+      // conversation. The vanished-tmux-session branch above relaunches for the
+      // same reason and takes the same pin.
+      if (needsNewSession || muxSessionVanished) {
+        const pinned = (await this._buildRespawnPaneOptionsWithResumePin()).resumeSessionId;
+        if (pinned) {
+          options.createSessionOptions.resumeSessionId = pinned;
+          this._resumeSessionId = pinned;
+        }
+      }
       this._muxSession = await mux.createSession(options.createSessionOptions);
       console.log('[Session] Created mux session:', this._muxSession.muxName);
       // No extra sleep — createSession() already waits for tmux readiness
@@ -1800,13 +2079,14 @@ export class Session extends EventEmitter {
           env: buildMuxAttachEnv(cliExportsTruecolor(this.mode)),
         })
       );
+      this._notePtySpawnGeometry(ptyCols, ptyRows);
     } catch (spawnErr) {
       console.error(`[Session] Failed to spawn PTY for ${options.spawnErrLabel}:`, spawnErr);
       this.emit('error', `Failed to attach to mux session: ${spawnErr}`);
       throw spawnErr;
     }
 
-    return { isRestored };
+    return { isRestored, respawnedResumeId, respawnedDeadPane };
   }
 
   /**
@@ -1844,6 +2124,9 @@ export class Session extends EventEmitter {
       console.error('[Session] reattachRemote: respawnPane failed for', this._muxSession.muxName);
       return false;
     }
+    // No-op for the record (a remote session's field is always UNKNOWN), but the
+    // mux layer's cache is keyed by muxName and this pane now runs a new client.
+    this.clearPaneExitForNewPane();
     console.log('[Session] reattachRemote: reattached remote session', this._muxSession.muxName, 'pid', newPid);
     return true;
   }
@@ -1869,6 +2152,10 @@ export class Session extends EventEmitter {
    *   the mux session is gone — see {@link reattachRemote} for that reasoning).
    */
   async restartCli(): Promise<boolean> {
+    return this._withPaneLifecycle(() => this._doRestartCli());
+  }
+
+  private async _doRestartCli(): Promise<boolean> {
     if (!this._useMux || !this._mux || !this._muxSession) return false;
     const mux = this._mux;
 
@@ -1878,26 +2165,16 @@ export class Session extends EventEmitter {
     }
 
     this._pinOmpRespawnId();
-    const options = this._buildRespawnPaneOptions();
-    // Unlike the dead-pane respawn, this one kills a WORKING pane whose conversation
-    // already has a transcript, and a CLI that launches with `--session-id <id>` refuses
-    // an id that is already in use (claude: `Error: Session ID ... is already in use.`),
-    // which turned an endpoint switch into a dead pane and a lost session. A launch that
-    // declares a `fallback` chain renders `resume || new` once a resume id is set, the
-    // same `--resume <id> || --session-id <id>` shape the docker and remote pane commands
-    // already use, so pin the live conversation id for THIS respawn only. The registry
-    // shape is the gate, not the CLI's name: an entry whose resume id is minted by the
-    // CLI itself (codex/pi/omp/grok) never declares that chain, and its resume field is
-    // read from its own `<Mode>Config` rather than this top-level one anyway.
-    if (!options.resumeSessionId && getCli(this.mode)?.launch.chain === 'fallback') {
-      options.resumeSessionId = this._claudeSessionId ?? this.id;
-    }
-    const newPid = await mux.respawnPane(options);
+    const newPid = await mux.respawnPane(await this._buildRespawnPaneOptionsWithResumePin());
     if (!newPid) {
       console.error('[Session] restartCli: respawnPane failed for', this._muxSession.muxName);
       return false;
     }
     this._pendingEnvUnsets.clear();
+    // A relaunch in the same pane, so any exit observed of the previous command
+    // is history. Without this the caller's persist-and-broadcast writes the old
+    // exit straight back onto a session that is running again.
+    this.clearPaneExitForNewPane();
     console.log('[Session] restartCli: restarted CLI for', this._muxSession.muxName, 'pid', newPid);
     return true;
   }
@@ -1914,6 +2191,7 @@ export class Session extends EventEmitter {
       workingDir: this.workingDir,
       mode: this.mode,
       name: this._name,
+      cliName: this.cliPinnedName,
       niceConfig: this._niceConfig,
       model: this._model,
       claudeMode: this._claudeMode,
@@ -1939,6 +2217,7 @@ export class Session extends EventEmitter {
       envOverrides: this._envOverrides,
       unsetEnvKeys: this._pendingEnvUnsets.size > 0 ? [...this._pendingEnvUnsets] : undefined,
       effort: this._effort,
+      advisorModel: this._advisorModel,
       historyLimit: this._tmuxHistoryLimit,
       remote: this._remote,
       docker: this._docker,
@@ -1947,6 +2226,112 @@ export class Session extends EventEmitter {
     return this._withCustomModelLaunchModel(options);
   }
 
+  /**
+   * Respawn options for a pane whose command is being REPLACED, with the
+   * conversation pinned so the relaunch resumes rather than collides.
+   *
+   * A CLI that launches with `--session-id <id>` refuses an id that is already
+   * in use (claude: `Error: Session ID ... is already in use.`), and every
+   * session whose agent has been prompted owns a transcript under that id. So
+   * relaunching such a pane with the bare launch line fails, the pane dies
+   * again immediately, and the user's conversation is stranded. A launch that
+   * declares a `fallback` chain renders `resume || new` once a resume id is
+   * set, which is the shape that survives both cases.
+   *
+   * Three candidates are tried in priority order — the conversation chain's
+   * tail, the launch seed, then the session's own id — and the first one a
+   * transcript backs is pinned. Four conditions gate that walk, each protecting
+   * against a way of resuming the WRONG conversation or of making a working
+   * relaunch fail.
+   *
+   * ⚠️ **A remote or docker session is never pinned.** Unlike `restartCli()`,
+   * whose route refuses both, the dead-pane respawn is reached by every session
+   * shape. Their pane commands (`buildRemoteLaunchCommand`,
+   * `claudeDockerPaneCommand`) already render a SELF-HEALING
+   * `--session-id <sid> || --resume <sid>`, and both flip to resume-first the
+   * moment the resume id differs from the session id. The conversation lives on
+   * the far side, so a local id pinned onto it resolves to nothing there, the
+   * resume fails, and the `--session-id` fallback then collides with the
+   * transcript the far side really does hold — both branches fail and the pane
+   * dies. `_pinOmpRespawnId()` refuses remote for the same reason.
+   *
+   * ⚠️ **The candidates come from the conversation CHAIN, never from
+   * `_claudeSessionId`.** That field holds either a first-hand id from the
+   * CLI's own hook payload or a history correlation, which is a guess keyed on
+   * the working directory. `_recordClaudeSessionInChain()` refuses a guess
+   * precisely so it cannot "write a foreign conversation into this pane's
+   * permanent record", and launching from one would do worse than the display
+   * bug that rule exists to prevent: the relaunched CLI would open and WRITE to
+   * a conversation that was never this pane's. The chain's tail is the live
+   * conversation and is hook-vouched, so it leads the walk, ahead of the launch
+   * seed, which is written once at construction and never moves off a `/clear`.
+   *
+   * ⚠️ **Every candidate must be backed by a transcript, the session's own id
+   * included, and a candidate that has none is passed over rather than ending
+   * the walk.** A pin that differs from the session id leaves
+   * `--session-id <this.id>` in the fallback branch, so a resume that finds
+   * nothing collides there and the pane dies exactly as it did before this
+   * pinning existed. Pinning `this.id` renders the self-healing
+   * `--resume <id> || --session-id <id>`, which is correct whether or not a
+   * transcript exists, but a pane that has none pays for the shape twice:
+   * claude prints "No conversation found" into the scrollback of a session that
+   * is brand new, and `wrapWithNice()` prefixes only the FIRST branch of the
+   * rendered `a || b`, so the branch that actually runs loses its priority for
+   * the life of the session. Falling off the end of the walk therefore adds
+   * no pin (the options keep any launch seed they already carried), which is
+   * the right answer: with no transcript anywhere there is nothing for the
+   * bare `--session-id <this.id>` to collide with.
+   *
+   * The create route pre-validates a resume id for the same reason, though it
+   * additionally requires the transcript be substantial — here mere existence
+   * is the question, because a one-line transcript still makes `--session-id`
+   * collide.
+   *
+   * The registry shape is the last gate, not the CLI's name: an entry whose
+   * resume id is minted by the CLI itself (codex/pi/omp/grok) declares no
+   * `fallback` chain and reads its resume field from its own `<Mode>Config`.
+   *
+   * `reattachRemote()` deliberately does NOT call this. It re-runs the remote
+   * session command, which attaches to the durable remote tmux with the agent
+   * still inside it and renders no local `--session-id` to collide.
+   */
+  private async _buildRespawnPaneOptionsWithResumePin(): Promise<import('./mux-interface.js').RespawnPaneOptions> {
+    const options = this._buildRespawnPaneOptions();
+    if (this._remote || this._docker) return options;
+    const entry = getCli(this.mode);
+    if (entry?.launch.chain !== 'fallback') return options;
+
+    const resumeIdPattern = entry.launch.params?.resumeId;
+    const configDir = this._claudeConfigDir();
+    const chainTail = this._claudeSessionChain[this._claudeSessionChain.length - 1];
+    const candidates = [chainTail, options.resumeSessionId, this.id].filter((v): v is string => !!v);
+    for (const candidate of candidates) {
+      // A session Codeman DISCOVERED on the socket rather than created carries a
+      // synthetic `restored-<fragment>` id, which fails claude's `uuid` token
+      // pattern. The renderer would silently drop the resume flag and emit the
+      // unpinned command, so say so here rather than letting the caller believe
+      // the pane was pinned.
+      if (resumeIdPattern?.type === 'token' && !matchesPattern(resumeIdPattern.pattern, candidate)) {
+        console.log(`[Session] Not pinning resume id ${candidate} for relaunch: the CLI cannot accept that id shape`);
+        continue;
+      }
+      if (!(await claudeTranscriptExists(candidate, configDir))) continue;
+      options.resumeSessionId = candidate;
+      return options;
+    }
+    // Nothing on disk to collide with, so the bare `--session-id <this.id>` the
+    // unpinned options already carry is the correct command.
+    return options;
+  }
+
+  /** The session's Claude config dir when it has been relocated (#255), else undefined. */
+  private _claudeConfigDir(): string | undefined {
+    // Trimmed like `claudeProjectsDir()` trims the process-wide override: the
+    // envOverrides schema validates keys only, and a whitespace-only value would
+    // otherwise resolve to a relative path and read "no transcript" for everything.
+    return this._envOverrides?.CLAUDE_CONFIG_DIR?.trim() || undefined;
+  }
+
   /**
    * Force the custom-model selection's `launchModel` (pi/omp `custom/<id>`, grok's
    * `[model.<name>]` block name) onto the CLI's `model` launch param. Where that param
@@ -2160,6 +2545,9 @@ export class Session extends EventEmitter {
     if (this.ptyProcess) {
       throw new Error('Session already has a running process');
     }
+    if (this._closing) {
+      throw new Error('Session is being closed');
+    }
 
     // Bounds the workspace-trust scan (see _maybeAcceptTrustDialog). Stamped here
     // rather than at PTY spawn so a slow mux attach still counts as startup.
@@ -2268,7 +2656,7 @@ export class Session extends EventEmitter {
     // If mux wrapping is enabled, create or attach to a mux session
     if (this._useMux && this._mux) {
       try {
-        const { isRestored } = await this._setupOrAttachMuxSession({
+        const { isRestored, respawnedResumeId, respawnedDeadPane } = await this._setupOrAttachMuxSession({
           // Single source of truth shared with reattachRemote() (COD-108).
           respawnPaneOptions: this._buildRespawnPaneOptions(),
           createSessionOptions: {
@@ -2276,6 +2664,7 @@ export class Session extends EventEmitter {
             workingDir: this.workingDir,
             mode: this.mode,
             name: this._name,
+            cliName: this.cliPinnedName,
             niceConfig: this._niceConfig,
             model: this._model,
             claudeMode: this._claudeMode,
@@ -2291,6 +2680,7 @@ export class Session extends EventEmitter {
             resumeSessionId: this._resumeSessionId,
             envOverrides: this._envOverrides,
             effort: this._effort,
+            advisorModel: this._advisorModel,
             historyLimit: this._tmuxHistoryLimit,
             remote: this._remote,
             docker: this._docker,
@@ -2315,7 +2705,18 @@ export class Session extends EventEmitter {
         // persisted chain's tail is that conversation, reported first-hand by
         // the CLI's own hook, so it outranks every fallback here. A NEW pane has
         // an empty chain and falls through to the resume/alias fallbacks.
-        restoredConversation = isRestored ? this._claudeSessionChain[this._claudeSessionChain.length - 1] : undefined;
+        //
+        // A dead-pane respawn is NOT that case for a CLI whose relaunch the resume
+        // pin walk governs (`launch.chain === 'fallback'`): the CLI did stop, and
+        // the walk may have passed over a chain tail with no transcript behind it,
+        // so the conversation is whatever the respawn actually resumed. Undefined
+        // there means the pane launched unpinned, which the fallbacks below name.
+        const pinGovernsRespawn = respawnedDeadPane && getCli(this.mode)?.launch.chain === 'fallback';
+        restoredConversation = pinGovernsRespawn
+          ? respawnedResumeId
+          : isRestored
+            ? this._claudeSessionChain[this._claudeSessionChain.length - 1]
+            : undefined;
         this._claudeSessionId =
           restoredConversation ||
           this._resumeSessionId ||
@@ -2403,8 +2804,9 @@ export class Session extends EventEmitter {
           this._model,
           this._allowedTools,
           this._effort,
-          this._name,
-          getClaudeCliVersion()
+          this.cliPinnedName,
+          getClaudeCliVersion(),
+          this._advisorModel
         );
         this.ptyProcess = spawnPtyWithHelperRepair(() =>
           pty.spawn(getClaudeBinaryPath(), args, {
@@ -2416,6 +2818,7 @@ export class Session extends EventEmitter {
             env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
           })
         );
+        this._notePtySpawnGeometry(120, 40);
       } catch (spawnErr) {
         console.error('[Session] Failed to spawn Claude PTY:', spawnErr);
         this._status = 'stopped';
@@ -2708,10 +3111,82 @@ export class Session extends EventEmitter {
     if (now - this._lastPaneProbeAt < PANE_PROBE_MIN_INTERVAL_MS) return this._lastPaneProbeWorking;
     this._lastPaneProbeAt = now;
     const text = this._mux.capturePaneText?.(this._muxSession.muxName) ?? null;
-    this._lastPaneProbeWorking = text === null ? null : this._workingLinePattern().test(text);
+    // A turn that ended by handing off to workers the CLI waits for is work too: the
+    // composer is up and the pane is quiet, but the next turn starts without the user.
+    this._lastPaneProbeWorking =
+      text === null ? null : this._workingLinePattern().test(text) || this._paneAwaitsWorkers(text);
+    this._readWatching(text);
     return this._lastPaneProbeWorking;
   }
 
+  /**
+   * Read the background-work chip off the same capture the working probe just took.
+   *
+   * The two questions are different. A turn that is running is work the user is waiting
+   * for; a monitor, a backgrounded shell or a cloud session the agent started is work
+   * the AGENT is waiting for, and it is the reason a pane can sit at its composer with
+   * nothing to say and still not want anything from the user. `_confirmIdle` takes this
+   * capture at exactly the moment the turn ends, which is the moment the answer starts
+   * mattering.
+   *
+   * A capture that could not be read CLEARS the label rather than keeping the last one.
+   * The two wrong answers are not symmetric: a stale label opens the next idle prompt
+   * already acknowledged, so a failed capture would silence a real alert, while a dropped
+   * label only costs a card and an alert that the next readable capture takes back.
+   * Degrading toward the alert is the rule the whole signal is built on.
+   */
+  private _readWatching(paneText: string | null): void {
+    const pattern = this._watchingLinePattern();
+    if (!pattern) return;
+    // `null` is "the screen could not be read". That is no evidence either way, so the
+    // label falls to null (and the change is announced below like any other).
+    const label = paneText === null ? null : watchingLabel(paneText, pattern, this._watchingWindow);
+    if (label === this._watching) return;
+    this._watching = label;
+    // ⚠️ This CHANGES while the session's status does not, so it needs an event of its
+    // own. The label is usually set on the idle transition, which broadcasts anyway, but
+    // it CLEARS when the work ends — and for a CLI whose background work ends without
+    // taking a turn (measured on codex: a background terminal finishing repaints the row
+    // away and nothing else happens) the session is idle before and after. Without this,
+    // the server knew the badge was gone and every open page went on drawing it until
+    // some unrelated event arrived.
+    this.emit('watchingChanged');
+  }
+
+  /**
+   * The regex matching this CLI's background-work chip, or null for a CLI whose registry
+   * entry declares none. Compiled once per session, like the working-line pattern, and
+   * null rather than a fallback: no other CLI has been measured drawing such a chip, and
+   * guessing one would badge sessions on the strength of an unread screen.
+   */
+  private _watchingLinePattern(): RegExp | null {
+    if (this._watchingLineRe === undefined) {
+      // The pattern and the window it runs over are one decision, so they are resolved
+      // together: how far up the screen a CLI's row can sit is as much a property of its
+      // layout as the row itself. Claude writes on the last row and keeps the default,
+      // Codex pins one above its composer and declares more.
+      const detect = getCli(this.mode)?.capabilities.workDetect;
+      this._watchingLineRe = detect?.watchingLine ? compileVersionRegex(detect.watchingLine) : null;
+      this._watchingWindow = detect?.watchingLines ?? WATCHING_TAIL_LINES;
+    }
+    return this._watchingLineRe;
+  }
+
+  /**
+   * Whether the newest turn on this screen ended waiting for workers the CLI started
+   * (Claude's `✻ Waiting for 1 dynamic workflow to finish`). False for a CLI whose
+   * registry entry declares no `awaitingLine`. See `isAwaitingWorkers()`.
+   */
+  private _paneAwaitsWorkers(paneText: string): boolean {
+    if (this._awaitingLineRe === undefined) {
+      const src = getCli(this.mode)?.capabilities.workDetect?.awaitingLine;
+      this._awaitingLineRe = src ? compileVersionRegex(src) : null;
+    }
+    if (!this._awaitingLineRe) return false;
+    const glyph = getCli(this.mode)?.capabilities.workDetect?.promptGlyph ?? '❯';
+    return isAwaitingWorkers(paneText, this._awaitingLineRe, glyph);
+  }
+
   /**
    * The regex matching this CLI's "a turn is running" status line.
    *
@@ -2914,6 +3389,9 @@ export class Session extends EventEmitter {
     if (this.ptyProcess) {
       throw new Error('Session already has a running process');
     }
+    if (this._closing) {
+      throw new Error('Session is being closed');
+    }
 
     this._resetBuffers();
 
@@ -2984,6 +3462,7 @@ export class Session extends EventEmitter {
             env: buildShellEnv(this.id),
           })
         );
+        this._notePtySpawnGeometry(120, 40);
       } catch (spawnErr) {
         console.error('[Session] Failed to spawn shell PTY:', spawnErr);
         this._status = 'stopped';
@@ -3093,6 +3572,7 @@ export class Session extends EventEmitter {
               env: { ...buildClaudeEnv(this.id), ...(this._envOverrides ?? {}) },
             })
           );
+          this._notePtySpawnGeometry(120, 40);
         } catch (spawnErr) {
           console.error('[Session] Failed to spawn Claude PTY for runPrompt:', spawnErr);
           this.emit(
@@ -3742,6 +4222,16 @@ export class Session extends EventEmitter {
     return false;
   }
 
+  /**
+   * Arm the composer check for a prompt that went out some other way than
+   * `writeViaMux`, e.g. cron's paste mode, which writes the body raw and its Enter
+   * separately. `text` is what the composer line starts with while the prompt is still
+   * unsent; the check re-presses Enter only while that holds.
+   */
+  verifySubmitted(text: string): void {
+    this._verifySubmitted(`${text}\r`);
+  }
+
   /**
    * Arm the composer check for a write that carried Enter (session-submit-verifier.ts):
    * Claude Code 2.1.277+ ignores Enter for the first 30-50 s after the composer paints,
@@ -3779,6 +4269,40 @@ export class Session extends EventEmitter {
   private _ptyCols = 120;
   private _ptyRows = 40;
 
+  /**
+   * Record the geometry a PTY was just spawned at. A reattached pane keeps the
+   * tmux window's size, not the constructor's 120x40, and without this
+   * `ptyGeometry` reported the old numbers for a live pane and the dedupe in
+   * `resize()` skipped a real resize that happened to match them.
+   */
+  private _notePtySpawnGeometry(cols: number, rows: number): void {
+    this._ptyCols = cols;
+    this._ptyRows = rows;
+  }
+
+  /**
+   * The geometry the CLI is actually drawing for, or null when nothing is
+   * drawing.
+   *
+   * Exposed because `resize()` can decline a request outright (arbitration
+   * below) and the asking client has no other way to find out: a browser
+   * terminal that keeps a shape the PTY refused renders garbled output rather
+   * than wrong-sized output, because Claude Code's repaints are computed from
+   * the width it was told (issue #464). Both transports report this back.
+   *
+   * ⚠️ NULL WITHOUT A PANE, never the field values. The fields are seeded at
+   * spawn (`_notePtySpawnGeometry`) and moved by `resize()`, but a session with
+   * a dead pane (or one created through the API and never started) still
+   * holds the constructor defaults of 120x40, or the size of a pane that is
+   * gone. Reporting those made a client adopt a size no process had ever
+   * been told, and on anything narrower than 120 columns it claimed another
+   * device owned the pane when none existed. `reconcilePtyGeometry` treats a
+   * report with no finite numbers as no evidence, which is the truth here.
+   */
+  get ptyGeometry(): { cols: number; rows: number } | null {
+    return this.ptyProcess ? { cols: this._ptyCols, rows: this._ptyRows } : null;
+  }
+
   /**
    * Live WebSocket connections that have announced a desktop viewport for this
    * session. While at least one is registered, small-viewport (mobile/tablet)
@@ -3864,6 +4388,10 @@ export class Session extends EventEmitter {
     }
     if (isSmallViewport && this._desktopSizeClaims.size > 0) {
       if (Date.now() - this._lastDesktopActivityAt < Session.DESKTOP_CLAIM_IDLE_MS) {
+        // Declined. The caller is told nothing here on purpose — the decision
+        // belongs to the session, not the socket — but the caller MUST report
+        // `ptyGeometry` back afterwards so the asking client can adopt
+        // the shape it did not get. Both transports do; see issue #464.
         return;
       }
       this._mobileSizeOverride = true;
@@ -3963,6 +4491,9 @@ export class Session extends EventEmitter {
   async stop(killMux: boolean = true): Promise<void> {
     // Set stopped flag first to prevent new timers from being created
     this._isStopped = true;
+    // A pane that is gone is watching nothing. Nothing probes a stopped session, so
+    // without this the last chip it drew would ride along on its row forever.
+    this._watching = null;
 
     this._clearAllTimers();
 

src/tmux-manager.ts

@@ -58,6 +58,7 @@ import {
   type SessionRemote,
   type SessionDocker,
   type DockerCommandMode,
+  type PaneExit,
 } from './types.js';
 import { getCli } from './config/cli-registry/registry.js';
 import { missingCliMessage, resolveCliBinDir } from './utils/cli-resolver.js';
@@ -152,6 +153,16 @@ const GRACEFUL_SHUTDOWN_WAIT_MS = 100;
 /** Default stats collection interval (2 seconds) */
 const DEFAULT_STATS_INTERVAL_MS = 2000;
 
+/**
+ * How often the pane-exit watcher re-reads every pane on the socket. The
+ * watcher owns this cadence: it does NOT ride `startStatsCollection()`, whose
+ * lifetime a browser panel controls (see {@link TmuxManager.startPaneExitWatcher}).
+ * Matched to the stats cadence above because both cost one batched tmux read.
+ * ⚠ It does NOT bound a read: EXEC_TIMEOUT_MS is 5000 ms, so a slow read can
+ * outlive two ticks, which is exactly why `paneExitReadInFlight` exists.
+ */
+const DEFAULT_PANE_EXIT_INTERVAL_MS = 2000;
+
 /** Default remote-reconnect watcher poll interval (5 seconds) — COD-108 */
 const DEFAULT_REMOTE_RECONNECT_INTERVAL_MS = 5000;
 
@@ -219,8 +230,18 @@ const DEFAULT_CODEMAN_TMUX_SOCKET = DEFAULT_TMUX_SOCKET;
  */
 const PANE_LIST_SEP = '|';
 
-/** Format string for `tmux list-panes -F`. Keep in sync with {@link parsePaneList}. */
-const PANE_LIST_FORMAT = `#{session_name}${PANE_LIST_SEP}#{pane_pid}`;
+/**
+ * Format string for `tmux list-panes -F`. Keep in sync with {@link parsePaneRows}.
+ *
+ * The three `pane_dead*` fields carry the agent-exit signal of Ark0N/Codeman#446.
+ * Appending them is backward compatible in both directions. A tmux that does not
+ * know a variable substitutes the empty string rather than failing, which is how
+ * tmux 3.2a answers `#{pane_dead_signal}` (added in 3.4), and the parser reads a
+ * short row as "pid known, deadness unknown" rather than discarding it.
+ */
+const PANE_LIST_FORMAT =
+  `#{session_name}${PANE_LIST_SEP}#{pane_pid}` +
+  `${PANE_LIST_SEP}#{pane_dead}${PANE_LIST_SEP}#{pane_dead_status}${PANE_LIST_SEP}#{pane_dead_signal}`;
 
 /**
  * 构建 pane 启动前的 nofile 修复命令。
@@ -235,26 +256,154 @@ export function buildNofileLimitCommand(targetLimit = CLAUDE_CODE_NOFILE_LIMIT):
   return `ulimit -Sn ${safeLimit} 2>/dev/null || ulimit -n ${safeLimit} 2>/dev/null || true`;
 }
 
+/** One pane of one tmux session, as {@link parsePaneRows} reads it off the wire. */
+export interface PaneRow {
+  /** tmux session this pane belongs to. Repeats once per pane of a split session. */
+  sessionName: string;
+  /** `#{pane_pid}` — the process tmux started in the pane. */
+  pid: number;
+  /** `#{pane_dead}` — true for 1, false for 0, undefined when tmux said nothing. */
+  dead?: boolean;
+  /** `#{pane_dead_status}` — the exit code, absent when tmux reported none. */
+  exitStatus?: number;
+  /** `#{pane_dead_signal}` — the killing signal, absent before tmux 3.4 and when unsignalled. */
+  exitSignal?: number;
+}
+
 /**
- * Parse the output of `tmux list-panes -a -F '#{session_name}|#{pane_pid}'`
- * into a Map of session-name → pane pid. Exported for unit testing.
+ * One pane-exit reading, with the pane pid that produced it.
+ *
+ * The pid never leaves this module. It is what distinguishes "the same dead
+ * pane, seen again" from "a second command in the same pane that also exited
+ * with the same status", so the `at` stamp can hold across the first and must
+ * not across the second. {@link PaneExit} itself stays free of it: the pid on
+ * the session record is the attach client's, and a second pid there would
+ * invite exactly the confusion Ark0N/Codeman#446 is about.
+ */
+export interface PaneExitObservation {
+  /** `#{pane_pid}` of the pane this reading came from. */
+  panePid: number;
+  /** What to publish on the session record. */
+  exit: PaneExit;
+}
+
+/**
+ * A {@link PaneExitObservation} as the manager stores it, with a count of the
+ * authoritative reads that have seen this same exit. The count is what lets
+ * the exited-agent sweep act only on a death that more than one read agreed on
+ * (`CLEAN_EXIT_CONFIRMING_READS` in `pane-exit-sweep.ts`). A failed or skipped
+ * read never reaches {@link TmuxManager.applyPaneExits}, so it neither raises
+ * the count nor resets it.
+ */
+interface TrackedPaneExit extends PaneExitObservation {
+  /** Authoritative reads that saw this exit, counting the first. */
+  reads: number;
+}
+
+/** Read one optional numeric field; a blank or non-numeric value is "not reported". */
+function paneField(fields: string[], index: number): number | undefined {
+  const raw = fields[index];
+  if (raw === undefined || raw === '') return undefined;
+  const value = parseInt(raw, 10);
+  return Number.isNaN(value) ? undefined : value;
+}
+
+/**
+ * Parse the output of `tmux list-panes -a -F` under {@link PANE_LIST_FORMAT}
+ * into one row per pane, in tmux's own order. Exported for unit testing.
  *
  * - Skips empty lines and lines without the separator.
  * - Skips entries with a non-numeric pid or empty name.
+ * - Leaves every field after the pid undefined when it is blank or absent, so a
+ *   row from an older tmux still yields its pid.
  */
-export function parsePaneList(output: string): Map<string, number> {
-  const result = new Map<string, number>();
+export function parsePaneRows(output: string): PaneRow[] {
+  const rows: PaneRow[] = [];
   for (const line of output.split('\n')) {
     if (!line) continue;
-    const sep = line.indexOf(PANE_LIST_SEP);
-    if (sep === -1) continue;
-    const name = line.slice(0, sep);
-    const pid = parseInt(line.slice(sep + 1), 10);
-    if (name && !Number.isNaN(pid)) {
-      result.set(name, pid);
-    }
+    if (!line.includes(PANE_LIST_SEP)) continue;
+    const fields = line.split(PANE_LIST_SEP);
+    const sessionName = fields[0];
+    const pid = parseInt(fields[1] ?? '', 10);
+    if (!sessionName || Number.isNaN(pid)) continue;
+    const deadFlag = fields[2];
+    rows.push({
+      sessionName,
+      pid,
+      dead: deadFlag === '1' ? true : deadFlag === '0' ? false : undefined,
+      exitStatus: paneField(fields, 3),
+      exitSignal: paneField(fields, 4),
+    });
   }
-  return result;
+  return rows;
+}
+
+/**
+ * Decide, from every pane tmux listed, which tmux sessions have an exited agent.
+ * Exported for unit testing. Returns one entry per session with a known answer;
+ * a session absent from the map is UNKNOWN, which must never render as alive.
+ *
+ * Two rules make a positive answer trustworthy:
+ *
+ * A session answers only when tmux listed EXACTLY ONE pane for it. Codeman
+ * creates one pane per session and `isPaneDead()` reads one pane, so a session
+ * the user has split by hand has no single "the agent" to report on, and
+ * guessing which of its panes speaks for the session could report a live
+ * session as exited.
+ *
+ * A pane answers only when `#{pane_dead}` said 1 or 0. An empty field is a tmux
+ * that did not answer, not a live pane.
+ *
+ * `status` and `signal` stay absent when tmux did not report them. Measured on
+ * tmux 3.2a, a SIGKILLed pane reports neither, so folding an absent status into
+ * 0 would turn an unexplained death into a clean exit.
+ */
+export function derivePaneExits(rows: PaneRow[], now: number): Map<string, PaneExitObservation> {
+  const panesPerSession = new Map<string, number>();
+  for (const row of rows) {
+    panesPerSession.set(row.sessionName, (panesPerSession.get(row.sessionName) ?? 0) + 1);
+  }
+  const exits = new Map<string, PaneExitObservation>();
+  for (const row of rows) {
+    if (panesPerSession.get(row.sessionName) !== 1) continue;
+    if (row.dead !== true) continue;
+    exits.set(row.sessionName, {
+      panePid: row.pid,
+      exit: {
+        ...(row.exitStatus !== undefined ? { status: row.exitStatus } : {}),
+        ...(row.exitSignal !== undefined ? { signal: row.exitSignal } : {}),
+        at: now,
+      },
+    });
+  }
+  return exits;
+}
+
+/**
+ * Could any of these tmux sessions ever produce a pane-exit answer? Exported
+ * for unit testing.
+ *
+ * Mirrors `Session.paneExitApplies`, which is where the rule is enforced. A
+ * remote session's local pane holds the ssh client, a docker case's holds a
+ * `docker exec` into the container's own tmux, and a record rebuilt from the
+ * socket carries no provenance at all, so the session end forces all three to
+ * UNKNOWN whatever tmux reports. A tick that sees only those has nothing to
+ * learn, and `refreshPaneExits()` skips its tmux read rather than paying for
+ * the answer.
+ *
+ * ⚠ This gates the READ, never the watcher. The watcher is always-on by
+ * design (see {@link TmuxManager.startPaneExitWatcher}), so it keeps ticking
+ * with nothing to observe and picks the read straight back up as soon as one
+ * local session exists.
+ */
+export function hasObservablePaneSession(sessions: Iterable<MuxSession>): boolean {
+  for (const session of sessions) {
+    if (session.remote) continue;
+    if (session.docker) continue;
+    if (session.discovered === true) continue;
+    return true;
+  }
+  return false;
 }
 
 /**
@@ -733,9 +882,11 @@ export function buildSpawnCommand(options: {
   ompConfig?: OmpConfig;
   resumeSessionId?: string;
   effort?: EffortLevel;
+  /** Claude advisor model, merged into the launch's one `--settings` JSON (see buildAdvisorSettings). */
+  advisorModel?: string;
   /** Resolved by resolveStatusLineCliCommand (hooks-config.ts) — undefined skips the exporter. Claude only. */
   statusLineCommand?: string;
-  /** Codeman session name, passed to claude as `--name` (version-gated, sanitized; local spawns only). */
+  /** Name pinned on claude as `--name` (version-gated, sanitized; local spawns only). Only a user-chosen name: see `Session.cliPinnedName`. */
   sessionName?: string;
   /**
    * Claude CLI version for the `--name` gate. Omitted = probe the local CLI
@@ -1527,6 +1678,30 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
   private mouseSyncInterval: NodeJS.Timeout | null = null;
   /** Track last-known pane count per session to avoid unnecessary tmux set-option calls */
   private lastPaneCount: Map<string, number> = new Map();
+  /**
+   * muxName → the exited agent the pane-exit watcher last observed
+   * (Ark0N/Codeman#446). Absence is the UNKNOWN arm of the tri-state, so an
+   * entry goes the moment tmux stops reporting the pane dead, and the map is
+   * empty until the first read runs. The manager reports what tmux says and
+   * nothing more: the scoping that hides this for remote and docker sessions
+   * lives on `Session`, because the remote-reconnect watcher above needs the
+   * raw pane reading.
+   */
+  private paneExits: Map<string, TrackedPaneExit> = new Map();
+  /** The pane-exit watcher's own interval. Runs whether or not stats are on. */
+  private paneExitInterval: NodeJS.Timeout | null = null;
+  /**
+   * True while a pane read is in flight. `EXEC_TIMEOUT_MS` is 5000 ms against a
+   * poll interval of 2000 ms, so without this a slow read overlaps the next two
+   * and the older one can resolve last and win.
+   */
+  private paneExitReadInFlight = false;
+  /**
+   * Bumped by every deliberate {@link clearPaneExit}. A read that started before
+   * a clear carries the older generation and is discarded rather than writing
+   * the death back over the pane that has just replaced it.
+   */
+  private paneExitGeneration = 0;
 
   // ── COD-108 remote-reconnect watcher state ────────────────────────────────
   /** Periodic watcher that re-establishes dropped remote sessions. */
@@ -1894,6 +2069,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       workingDir,
       mode,
       name,
+      cliName,
       niceConfig,
       model,
       claudeMode,
@@ -1909,6 +2085,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       resumeSessionId,
       envOverrides,
       effort,
+      advisorModel,
       historyLimit = DEFAULT_TMUX_HISTORY_LIMIT,
       remote,
       docker,
@@ -1996,8 +2173,9 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       ompConfig,
       resumeSessionId,
       effort,
+      advisorModel,
       statusLineCommand,
-      sessionName: name,
+      sessionName: cliName,
     });
 
     const config = niceConfig || DEFAULT_NICE_CONFIG;
@@ -2223,9 +2401,10 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       envOverrides,
       unsetEnvKeys,
       effort,
+      advisorModel,
       remote,
       docker,
-      name,
+      cliName,
     } = options;
     const session = this.sessions.get(sessionId);
     if (!session) return null;
@@ -2261,8 +2440,9 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       ompConfig,
       resumeSessionId,
       effort,
+      advisorModel,
       statusLineCommand,
-      sessionName: name,
+      sessionName: cliName,
     });
     const config = niceConfig || DEFAULT_NICE_CONFIG;
     const cmd = wrapWithNice(baseCmd, config);
@@ -2297,6 +2477,11 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       );
       // Wait for the respawned process to start
       await new Promise((resolve) => setTimeout(resolve, TMUX_CREATION_WAIT_MS));
+      // The pane now runs a fresh command, so whatever the last read observed of
+      // the old one is history. Clearing it here rather than waiting for the next
+      // poll also invalidates any read already in flight, which would otherwise
+      // write the old death back over the pane that just replaced it.
+      this.clearPaneExit(muxName);
       const pid = this.getPanePid(muxName);
       if (pid) session.pid = pid;
       return pid;
@@ -2508,6 +2693,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
         }
       }
       this.lastPaneCount.delete(session.muxName);
+      this.clearPaneExit(session.muxName);
       this.sessions.delete(sessionId);
       this.clearRemoteReconnectState(sessionId);
       this.saveSessions();
@@ -2618,6 +2804,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     }
 
     this.lastPaneCount.delete(session.muxName);
+    this.clearPaneExit(session.muxName);
     this.sessions.delete(sessionId);
     this.clearRemoteReconnectState(sessionId);
     this.saveSessions();
@@ -2671,7 +2858,14 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
         encoding: 'utf-8',
         timeout: EXEC_TIMEOUT_MS,
       }).trim();
-      active = parsePaneList(output);
+      const rows = parsePaneRows(output);
+      active = new Map(rows.map((row) => [row.sessionName, row.pid]));
+      // The same read answers both questions, so recovery starts with a pane-exit
+      // reading rather than waiting for the first stats tick — which may never
+      // come, since the collector only starts when boot found a live session.
+      if (rows.length > 0) {
+        this.applyPaneExits(derivePaneExits(rows, Date.now()));
+      }
     } catch (err) {
       console.error('[TmuxManager] Failed to list tmux panes:', err);
       active = new Map();
@@ -2686,6 +2880,7 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
       } else {
         dead.push(sessionId);
         this.sessions.delete(sessionId);
+        this.clearPaneExit(session.muxName);
         this.clearRemoteReconnectState(sessionId);
         this.emit('sessionDied', { sessionId });
       }
@@ -2722,6 +2917,13 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
         mode: 'claude',
         attached: false,
         name: `Restored: ${sessionName}`,
+        // Every field above except the name and the pid is a guess: this record
+        // was rebuilt from the socket because Codeman's own bookkeeping did not
+        // have it. The synthetic id also cannot find the session's state.json
+        // entry, so a remote or docker session rediscovered this way arrives
+        // looking local. Consumers that would be wrong about such a session
+        // read this flag and fail closed — see `Session.paneExitApplies`.
+        discovered: true,
       };
       this.sessions.set(sessionId, session);
       knownMuxNames.add(sessionName);
@@ -2882,6 +3084,185 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
     }));
   }
 
+  /**
+   * What the last pane read saw of this tmux session's agent. `undefined` is
+   * the UNKNOWN answer and must never be rendered as "alive": it covers a pane
+   * that is running, a tmux session that no longer exists, a probe that failed,
+   * and every poll that has not run yet. See {@link PaneExit}.
+   */
+  getPaneExit(muxName: string): PaneExit | undefined {
+    return this.paneExits.get(muxName)?.exit;
+  }
+
+  /**
+   * How many authoritative pane reads have agreed on the exit that
+   * {@link getPaneExit} reports, or 0 when it reports none. A new observation
+   * starts at 1, and every later read that sees the same pane with the same
+   * status and signal adds one.
+   */
+  getPaneExitReadCount(muxName: string): number {
+    return this.paneExits.get(muxName)?.reads ?? 0;
+  }
+
+  /**
+   * Re-read every pane on the socket and refresh {@link paneExits}. ONE batched
+   * `tmux list-panes -a` answers for every session at once, which is why this
+   * polls rather than probing per session.
+   *
+   * A failed or empty probe leaves the previous answers ALONE rather than
+   * clearing them, because the two cannot be told apart: the command ends in
+   * `|| true`, so a tmux that errored and a socket with genuinely no panes both
+   * arrive as empty output. Treating that as "tmux did not answer" is the
+   * conservative reading — clearing on it would turn a transient failure into a
+   * silent retraction of a death Codeman had already observed, and the cost of
+   * being wrong the other way is one stale entry for a socket that no longer
+   * has the pane. A NON-empty read is different: `list-panes -a` lists
+   * every pane on the socket, so it is authoritative and {@link applyPaneExits}
+   * prunes against it.
+   *
+   * Two guards keep a slow read from undoing a fast one. A read already in
+   * flight suppresses the next poll, and a read that started before a
+   * {@link clearPaneExit} is discarded when it lands.
+   *
+   * A third guard skips the read entirely while no session on this manager
+   * could produce an answer ({@link hasObservablePaneSession}). Skipping
+   * retracts nothing, for the same reason a failed read does not: the map
+   * still holds what the last real read saw, and every path that puts a new
+   * command in a pane calls {@link clearPaneExit} itself.
+   */
+  async refreshPaneExits(now: number = Date.now()): Promise<void> {
+    // Nothing on this socket could answer, so do not read tmux to find that
+    // out. See `hasObservablePaneSession`: the watcher above still ticks.
+    if (!hasObservablePaneSession(this.sessions.values())) return;
+    if (this.paneExitReadInFlight) return;
+
+    const generation = this.paneExitGeneration;
+    this.paneExitReadInFlight = true;
+    let rows: PaneRow[];
+    try {
+      rows = await this.readPaneRows();
+    } finally {
+      this.paneExitReadInFlight = false;
+    }
+    if (rows.length === 0) return;
+    // A pane was respawned or killed while this read was out, so what it saw is
+    // already history. Dropping it is what stops a freshly respawned pane from
+    // being republished as exited.
+    if (generation !== this.paneExitGeneration) return;
+
+    this.applyPaneExits(derivePaneExits(rows, now));
+  }
+
+  /**
+   * Read every pane on the socket. The ONLY part of the pane-exit watcher that
+   * touches tmux, which is what lets a test subclass drive the guards in
+   * {@link refreshPaneExits} — the in-flight suppression, the generation
+   * check, the empty-read retraction rule and the read gate — against rows it
+   * chooses. Split out for the reason `runRemoteReconnectTick` is: a guard no
+   * test can reach is a guard that can be deleted without anything failing.
+   *
+   * A failed read answers with NO rows, which the caller treats as "tmux did
+   * not answer" and which therefore retracts nothing.
+   */
+  protected async readPaneRows(): Promise<PaneRow[]> {
+    // The test-mode gate lives HERE rather than at the top of the tick, so that
+    // what tests cannot do is spawn a process, not exercise the bookkeeping.
+    if (IS_TEST_MODE) return [];
+    try {
+      // execAsync, not execSync: this runs on a 2000 ms timer, and a synchronous
+      // exec freezes the port while the process stays alive (see the
+      // event-loop-monitor note in CLAUDE.md). The three `isPaneDead()` callers
+      // stay synchronous because each is answering one request right then.
+      const { stdout } = await execAsync(`${this.tmux()} list-panes -a -F '${PANE_LIST_FORMAT}' 2>/dev/null || true`, {
+        encoding: 'utf-8',
+        timeout: EXEC_TIMEOUT_MS,
+      });
+      return parsePaneRows(stdout.trim());
+    } catch (err) {
+      console.error('[TmuxManager] Failed to read pane exit state:', err);
+      return [];
+    }
+  }
+
+  /**
+   * Fold one authoritative observation into {@link paneExits}. Split out from
+   * the tmux call so the merge rules are unit-testable.
+   *
+   * `observed` comes from a read of EVERY pane on the socket, so a session
+   * missing from it has no exit to report and its entry goes. That is what
+   * keeps the map from growing without bound as tmux sessions come and go
+   * outside `killSession()`. Only the caller may decide a read is authoritative:
+   * a failed or empty one never reaches here.
+   *
+   * An entry keeps the `at` of the FIRST read that saw that exit, so the stamp
+   * says when the agent was found gone rather than when the last poll ran. A
+   * changed status, a changed signal, or a different pane pid all start a new
+   * observation — the pid is what catches a second command in the same pane
+   * that happened to exit the same way.
+   *
+   * The same rule decides the read count: a repeat of the stored exit adds one,
+   * and anything that starts a new observation starts the count again at 1.
+   */
+  applyPaneExits(observed: Map<string, PaneExitObservation>): void {
+    for (const muxName of [...this.paneExits.keys()]) {
+      if (!observed.has(muxName)) this.paneExits.delete(muxName);
+    }
+    for (const [muxName, next] of observed) {
+      const prev = this.paneExits.get(muxName);
+      const sameExit =
+        prev !== undefined &&
+        prev.panePid === next.panePid &&
+        prev.exit.status === next.exit.status &&
+        prev.exit.signal === next.exit.signal;
+      this.paneExits.set(muxName, sameExit ? { ...prev, reads: prev.reads + 1 } : { ...next, reads: 1 });
+    }
+  }
+
+  /**
+   * Forget a session's exit observation, e.g. once its pane has been respawned.
+   * Also invalidates any read already in flight, so the answer this retracts
+   * cannot be written back a moment later.
+   */
+  clearPaneExit(muxName: string): void {
+    this.paneExits.delete(muxName);
+    this.paneExitGeneration++;
+  }
+
+  /**
+   * Poll for exited agents, on the manager's own interval.
+   *
+   * Deliberately NOT part of `startStatsCollection()`. That collector is armed
+   * when the browser opens the Monitor panel and DISARMED when it closes it
+   * (`panels-ui.js`), and it is skipped at boot entirely when no session was
+   * recovered — so riding it would leave a session created on a freshly booted
+   * server reporting nothing at all, and would let one browser turn exit
+   * detection off for every other. Started unconditionally, like the mouse-mode
+   * sync and the remote-reconnect watcher below.
+   *
+   * The `paneExitsUpdated` event is internal to the server; nothing here adds an
+   * SSE event, and the field reaches the browser on `session:updated`.
+   */
+  startPaneExitWatcher(intervalMs: number = DEFAULT_PANE_EXIT_INTERVAL_MS): void {
+    if (this.paneExitInterval) {
+      clearInterval(this.paneExitInterval);
+    }
+    this.paneExitInterval = setInterval(() => {
+      // No IS_TEST_MODE guard: `readPaneRows()` is the only thing that would
+      // spawn a process and it refuses under test, so a test can drive this
+      // whole loop with fake timers instead of being locked out of it.
+      void this.refreshPaneExits()
+        .then(() => this.emit('paneExitsUpdated'))
+        .catch((err) => console.error('[TmuxManager] Pane exit watcher error:', err));
+    }, intervalMs);
+  }
+
+  stopPaneExitWatcher(): void {
+    if (this.paneExitInterval) {
+      clearInterval(this.paneExitInterval);
+      this.paneExitInterval = null;
+    }
+  }
+
   startStatsCollection(intervalMs: number = DEFAULT_STATS_INTERVAL_MS): void {
     if (this.statsInterval) {
       clearInterval(this.statsInterval);
@@ -3101,6 +3482,8 @@ export class TmuxManager extends EventEmitter implements TerminalMultiplexer {
 
   destroy(): void {
     this.stopStatsCollection();
+    this.stopPaneExitWatcher();
+    this.paneExits.clear();
     this.stopMouseModeSync();
     this.stopRemoteReconnectWatcher();
     this.reconnectState.clear();

src/tui/tui-approvals.ts

@@ -28,8 +28,11 @@
 import type { ApprovalItem, ApprovalOption } from '../web/approval-inbox.js';
 import type { TuiApprovalAnswer } from './tui-client.js';
 
-/** Card severity, in the same red/yellow vocabulary the web inbox uses. */
-export type TuiApprovalTone = 'err' | 'warn';
+/**
+ * Card severity, in the same red/yellow vocabulary the web inbox uses, plus the quiet
+ * third case: an item that opened acknowledged asks for nothing and reads grey.
+ */
+export type TuiApprovalTone = 'err' | 'warn' | 'info';
 
 export interface TuiApprovalCard {
   tone: TuiApprovalTone;
@@ -50,8 +53,14 @@ function clean(text: string | undefined): string {
   return (text ?? '').replace(/\s+/g, ' ').trim().slice(0, MAX_CARD_TEXT);
 }
 
+/**
+ * How loud the card is. An idle prompt the inbox opened ALREADY acknowledged is not
+ * asking for anything — the session is watching work it started itself — so it drops to
+ * `info` and out of the warning vocabulary the other two share with the web inbox.
+ */
 export function approvalTone(item: ApprovalItem): TuiApprovalTone {
-  return item.kind === 'idle' ? 'warn' : 'err';
+  if (item.kind !== 'idle') return 'err';
+  return item.acknowledgedReason ? 'info' : 'warn';
 }
 
 /**
@@ -65,9 +74,13 @@ export function approvalCard(item: ApprovalItem): TuiApprovalCard {
   const summary = clean(item.toolSummary) || clean(item.toolName);
 
   if (item.kind === 'idle') {
+    // Say what it is waiting for rather than asking for a reply, in the same words the
+    // web drawer uses for the same item. The prompt is still answerable, so the hint
+    // stays either way.
+    const quiet = clean(item.acknowledgedReason);
     return {
-      tone: 'warn',
-      title: message || 'waiting for your reply',
+      tone: approvalTone(item),
+      title: quiet ? `quiet, ${quiet}` : message || 'waiting for your reply',
       detail: [],
       options: [],
       hint: 'p to reply',

src/tui/tui-model.ts

@@ -74,13 +74,25 @@ export function isLiveRow(session: TuiSessionRow): boolean {
  * outranks a stale `busy` status because the hook is the newer signal. An
  * errored session has no state of its own here and joins the waiting tier,
  * since it is equally something only a human can clear.
+ *
+ * ⚠️ An ACKNOWLEDGED item no longer decides the row. `acknowledgedAt` means the
+ * alert this prompt armed has been spent, either because somebody opened the
+ * session on another device or because the inbox opened the item that way for a
+ * session watching its own background work. The item itself stays pending and
+ * answerable, so the row keeps carrying it and the approval card still renders;
+ * it simply stops dragging the session into NEEDS YOU. The web has honoured
+ * that since acknowledgement existed (`approvals-ui.js` clears the pending hook
+ * that `_mobileOverviewState` reads), and this gate is where the TUI had been
+ * reading past it: acknowledging on a phone cleared the alert everywhere except
+ * here. Only `idle` can be acknowledged, so a permission or question dialog is
+ * unaffected by construction, and both are checked ahead of the flag anyway.
  */
 export function classifySession(session: TuiSessionRow, approval?: ApprovalItem): TuiSessionState {
   if (!isLiveRow(session)) return 'recent';
   if (approval) {
     if (approval.kind === 'permission') return 'blocked-permission';
     if (approval.kind === 'question') return 'blocked-question';
-    return 'waiting';
+    if (!approval.acknowledgedAt) return 'waiting';
   }
   if (session.status === 'error') return 'waiting';
   if (session.isWorking === true || session.status === 'busy') return 'working';
@@ -96,7 +108,11 @@ export function classifySession(session: TuiSessionRow, approval?: ApprovalItem)
  * turn's own start is the pane's last Enter.
  */
 export function stateSince(state: TuiSessionState, session: TuiSessionRow, approval?: ApprovalItem): number {
-  if (approval) return approval.createdAt;
+  // The prompt's own age measures the state only while the prompt is what put the
+  // row in that state. An acknowledged item still rides along on a row that is
+  // plainly idle or working, and dating such a row from it would report how long
+  // ago the prompt arrived as though it were how long the session has been quiet.
+  if (approval && STATE_GROUP[state] === 'needs-you') return approval.createdAt;
   if (state === 'working') return session.lastSubmitAt ?? session.createdAt ?? 0;
   return session.lastActivityAt ?? session.createdAt ?? 0;
 }

src/tui/tui-render.ts

@@ -462,7 +462,8 @@ export function computeListWindow(
  * The pending dialog, drawn above the tail: the question, the parsed options
  * with their digits, and the keys that answer them. Red for a permission or
  * question prompt, yellow for an idle one, the same severity vocabulary the web
- * inbox uses.
+ * inbox uses. An idle prompt that opened acknowledged carries neither: it reads
+ * grey with the idle glyph, because nothing about it wants the reader.
  */
 export function renderApprovalCard(
   item: ApprovalItem,
@@ -472,8 +473,8 @@ export function renderApprovalCard(
 ): string[] {
   const paint = painterFor(opts.color);
   const card = approvalCard(item);
-  const color = card.tone === 'err' ? SGR.red : SGR.yellow;
-  const glyph = card.tone === 'err' ? glyphs.blockedPermission : glyphs.waiting;
+  const color = card.tone === 'err' ? SGR.red : card.tone === 'warn' ? SGR.yellow : SGR.gray;
+  const glyph = card.tone === 'err' ? glyphs.blockedPermission : card.tone === 'warn' ? glyphs.waiting : glyphs.idle;
   const lines: string[] = [];
   const push = (text: string, style: string): void => {
     lines.push(padDisplay(paint(clipStyledLine(text, width), style), width));
@@ -571,10 +572,19 @@ function previewBody(
 // Chrome
 // ─────────────────────────────────────────────────────────────────────────────
 
-/** Sessions with a prompt waiting on a human, which is what the badge counts. */
+/**
+ * Sessions with a prompt waiting on a human, which is what the badge counts.
+ *
+ * An ACKNOWLEDGED item is not one of them. Its alert has been spent, either by somebody
+ * opening the session elsewhere or because the inbox opened it that way for a session
+ * watching its own background work, and the row has already left NEEDS YOU by the same
+ * flag (`classifySession`). Counting it here would put a number in the header for a
+ * group the reader can see is empty.
+ */
 export function pendingApprovalCount(model: TuiRenderModel): number {
   let count = 0;
-  for (const group of model.groups()) for (const row of group.rows) if (row.approval) count++;
+  for (const group of model.groups())
+    for (const row of group.rows) if (row.approval && !row.approval.acknowledgedAt) count++;
   return count;
 }
 

src/types/session.ts

@@ -377,6 +377,26 @@ export function isEffortLevel(value: string | undefined): value is EffortLevel {
   return value !== undefined && (EFFORT_LEVELS as readonly string[]).includes(value);
 }
 
+/**
+ * Model aliases Claude Code accepts for its advisor tool (a stronger model the session's
+ * main model consults at decision points; code.claude.com/docs/en/advisor). Haiku is left
+ * out on purpose: it can call an advisor but never act as one.
+ */
+export const ADVISOR_MODEL_ALIASES = ['fable', 'opus', 'sonnet'] as const;
+
+/** A full model id in one of the advisor-capable families, e.g. `claude-opus-5-5`. */
+const ADVISOR_MODEL_ID_PATTERN = /^claude-(?:fable|opus|sonnet)-[a-z0-9]+(?:-[a-z0-9]+)*$/;
+
+/**
+ * Type guard: is the value an advisor model Codeman will pass to claude? An alias from
+ * ADVISOR_MODEL_ALIASES or a full fable/opus/sonnet model id. ⚠️ This allowlist is also the
+ * injection guard: the value is rendered inside the single-quoted `--settings` JSON argument.
+ */
+export function isAdvisorModel(value: unknown): value is string {
+  if (typeof value !== 'string' || value.length > 64) return false;
+  return (ADVISOR_MODEL_ALIASES as readonly string[]).includes(value) || ADVISOR_MODEL_ID_PATTERN.test(value);
+}
+
 /** OpenCode session configuration */
 export interface OpenCodeConfig {
   /** Model identifier (e.g., "anthropic/claude-sonnet-4-5", "openai/gpt-5.2", "ollama/codellama") */
@@ -625,6 +645,55 @@ export interface CustomModelBookkeeping extends CustomModelSelection {
   launchModel?: string;
 }
 
+/**
+ * The agent inside a LOCAL tmux pane has exited, and the pane survived it.
+ *
+ * Codeman creates every pane with `remain-on-exit on`, so `/exit` ends the CLI
+ * while tmux keeps the pane, the tmux session and the `tmux attach-session`
+ * process Codeman records as the session's pid. No PTY exit handler runs, so
+ * without this record the session reads as a live idle one (Ark0N/Codeman#446).
+ *
+ * The field is TRI-STATE, and the third state is the absence of the field:
+ * `undefined` means Codeman does not know, and it must never be rendered as
+ * "alive". It is absent for a direct-PTY session (no pane exists), for a remote
+ * SSH session (the local pane holds the ssh client, whose death means transport
+ * drop OR exit) and for a docker case (the local pane holds a `docker exec`
+ * into the container's own tmux).
+ *
+ * `status` and `signal` are independently optional because tmux may know that
+ * the pane died without reporting how. Measured on tmux 3.2a: a SIGKILLed pane
+ * reports `pane_dead=1` with BOTH `#{pane_dead_status}` and `#{pane_dead_signal}`
+ * empty, and `#{pane_dead_signal}` does not exist at all before tmux 3.4. So an
+ * absent `status` means "the exit code is unknown", never "the exit code is 0".
+ *
+ * ⚠ AN ABSENT `status` STAYS ABSENT. Never write `status ?? 0`, and never read
+ * "no signal was reported" as "the exit must have been clean". On tmux 3.2a
+ * the absent status IS how a signal death presents, so absent-stays-absent is
+ * the only thing keeping the clean-exit sweep (`pane-exit-sweep.ts`) away
+ * from crashed agents: an agent SIGKILLed by the OOM killer would otherwise
+ * read as a user typing `/exit` and be closed. Nothing here fails when
+ * somebody adds that `??` — the types allow it and the label still renders.
+ * The rule is enforced in `derivePaneExits()` (`tmux-manager.ts`), which omits
+ * the key rather than defaulting it, and again in `isCleanPaneExit()`, which
+ * accepts only an explicit 0.
+ */
+export interface PaneExit {
+  /**
+   * tmux `#{pane_dead_status}` — the command's exit code. Absent when tmux
+   * reported none, which means UNKNOWN and never 0. See the ⚠ above before
+   * giving this a default anywhere.
+   */
+  status?: number;
+  /** tmux `#{pane_dead_signal}` — the signal that killed the command. Absent when unsignalled or unsupported. */
+  signal?: number;
+  /**
+   * Wall-clock ms when THIS server process first observed the pane dead. It is
+   * not when the agent exited, which nothing records, and a restart that finds
+   * the pane still dead respawns it rather than re-timing the old exit.
+   */
+  at: number;
+}
+
 export interface SessionState {
   /** Unique session identifier */
   id: string;
@@ -746,6 +815,8 @@ export interface SessionState {
   resumeSessionId?: string;
   /** Claude CLI effort level (soft default via --settings, switchable in-session via /effort) */
   effort?: EffortLevel;
+  /** Claude advisor model (`advisorModel` in the launch `--settings`, switchable in-session via /advisor) */
+  advisorModel?: string;
   /**
    * Custom Model Endpoint Profiles (docs/custom-model-endpoints-plan.md): the custom
    * OpenAI-compatible endpoint (local or cloud) this session's CLI is currently pointed
@@ -780,6 +851,21 @@ export interface SessionState {
    * (COD-118). Runtime-only: never restored on boot (fresh server = fresh breaker).
    */
   respawnBlocked?: boolean;
+  /**
+   * The agent in this session's LOCAL tmux pane has exited (Ark0N/Codeman#446).
+   * See {@link PaneExit} for the tri-state rule and for which session shapes
+   * leave it absent. `status` and `pid` are deliberately untouched by it: the
+   * PTY-exit breaker owns `status: 'error'`, and a null `pid` is what makes the
+   * browser re-attach and launch a fresh CLI.
+   *
+   * Persisted so a reboot restore can tell a session whose agent exited from one
+   * that was merely idle when the power went. `reboot-restore.ts` reads the
+   * persisted record and never builds a `Session`, so the record is the only
+   * place that survives the reboot to carry it. Nothing reads it there YET:
+   * making the restore refuse such a session is a behavior change, and it
+   * belongs with the part of Ark0N/Codeman#446 that closes exited sessions.
+   */
+  paneExit?: PaneExit;
 }
 
 /**

src/utils/claude-transcript.ts

@@ -0,0 +1,75 @@
+/**
+ * @fileoverview Does a Claude conversation transcript exist on this host?
+ *
+ * Claude writes one `<conversation-id>.jsonl` per conversation under
+ * `<config dir>/projects/<mangled cwd>/`. Two launch decisions turn on whether
+ * such a file exists: `--resume <id>` needs one, and `--session-id <id>` is
+ * REFUSED when one exists (`Error: Session ID ... is already in use.`).
+ *
+ * The project directory name is derived from the working directory, and a case
+ * that has been moved or renamed leaves its transcript under the OLD name, so
+ * the search is across every project directory rather than the one that matches
+ * the pane's cwd today.
+ *
+ * ⚠️ Existence is the whole question here, with no size floor. The create route
+ * additionally requires ~4 KB before it will resume, which is a "is this
+ * conversation worth resuming" judgement; for a relaunch the question is the
+ * opposite one — a one-line transcript still makes `--session-id` collide.
+ *
+ * ⚠️ A false answer is not the conservative one. Skipping a resume leaves the
+ * relaunch on `--session-id <id>`, which is safe only when no transcript backs
+ * that id either, so a lookup that misses the real config dir turns a
+ * recoverable pane into the collision this module exists to prevent.
+ *
+ * @dependencies none
+ * @consumedby session (relaunch resume pinning)
+ *
+ * @module utils/claude-transcript
+ */
+
+import { readdir, stat } from 'node:fs/promises';
+import { homedir } from 'node:os';
+import { join } from 'node:path';
+
+/**
+ * `<config dir>/projects`, honouring a session's relocated `CLAUDE_CONFIG_DIR`
+ * (#255) and, failing that, the server process's own.
+ *
+ * ⚠️ The process env is not optional here. A pane inherits the server's
+ * environment through tmux, so on an install that exports `CLAUDE_CONFIG_DIR`
+ * the CLI writes its transcripts there and a lookup under `~/.claude` answers
+ * "no transcript" for every conversation on the host. `claudeCredentialsPath()`
+ * (claude-credentials.ts) and `realClaudeConfigDir()`
+ * (custom-model-injection-apply.ts) resolve the same directory the same way.
+ */
+export function claudeProjectsDir(configDir?: string): string {
+  const fromEnv = typeof process.env.CLAUDE_CONFIG_DIR === 'string' && process.env.CLAUDE_CONFIG_DIR.trim();
+  return join(configDir || fromEnv || join(homedir(), '.claude'), 'projects');
+}
+
+/**
+ * True when a transcript for `conversationId` exists under any project
+ * directory. Returns false for a missing projects dir or an unreadable one,
+ * which leaves the caller unpinned: safe where nothing else can collide with
+ * the bare `--session-id`, and the reason the caller walks its candidates down
+ * to the session's own id rather than treating one false answer as final.
+ */
+export async function claudeTranscriptExists(conversationId: string, configDir?: string): Promise<boolean> {
+  if (!conversationId) return false;
+  const projectsDir = claudeProjectsDir(configDir);
+  let projectDirs: string[];
+  try {
+    projectDirs = await readdir(projectsDir);
+  } catch {
+    return false;
+  }
+  for (const projectDir of projectDirs) {
+    try {
+      await stat(join(projectsDir, projectDir, `${conversationId}.jsonl`));
+      return true;
+    } catch {
+      // Not in this project directory; keep looking.
+    }
+  }
+  return false;
+}

src/utils/cli-executable-resolver.ts

@@ -204,6 +204,28 @@ export function createProductionCliResolverHost(options: ProductionCliResolverHo
   };
 }
 
+/**
+ * Per-binary invalidation generation, bumped by `invalidateCliExecutableResolvers()`.
+ *
+ * Every resolver instance (each per-CLI module's private one AND the generic registry
+ * resolver in cli-resolver.ts) is built by the factory below and caches in its own
+ * closure, so there is no instance to reach from outside. Keying on the BINARY name is
+ * what lets one call reach all of them: the CLI-management install/update routes know
+ * which binaries just changed, and every resolver knows its own.
+ */
+const binaryGenerations = new Map<string, number>();
+
+/**
+ * Forget every cached result — success and negative-cache backoff alike — for these
+ * binaries, so the next `resolve()` re-runs the chain immediately. For an action that
+ * just changed what is on disk (an install) or what a CLI's binary IS (editing a custom
+ * entry): without it a CLI installed from Settings kept reading as missing for up to the
+ * 5-minute backoff, and an edited entry kept launching its old binary until a restart.
+ */
+export function invalidateCliExecutableResolvers(binaries: readonly string[]): void {
+  for (const binary of binaries) binaryGenerations.set(binary, (binaryGenerations.get(binary) ?? 0) + 1);
+}
+
 export function createCliExecutableResolver<T = undefined>(
   options: {
     binary: string;
@@ -235,6 +257,8 @@ export function createCliExecutableResolver<T = undefined>(
   let failures = 0;
   /** Timestamp of the most recent miss. */
   let lastFailureAt = 0;
+  /** The invalidation generation the cached state above belongs to. */
+  let generation = binaryGenerations.get(options.binary) ?? 0;
   const accept = (path: string | null, source: CliResolutionSource): CliResolution<T> | null => {
     if (!path || !isAbsolute(path) || !host.exists(path)) return null;
     const validation = options.validateCandidate?.(path) ?? ({ accepted: true } as CandidateValidation<T>);
@@ -249,6 +273,13 @@ export function createCliExecutableResolver<T = undefined>(
 
   return {
     resolve() {
+      const current = binaryGenerations.get(options.binary) ?? 0;
+      if (current !== generation) {
+        generation = current;
+        cached = null;
+        failures = 0;
+        lastFailureAt = 0;
+      }
       if (cached) return cached;
       // Negative cache: a miss is remembered and the chain — whose login-shell
       // tail is a synchronous 5s-bounded spawn — is not re-run until the

src/utils/cli-installed-probes.ts

@@ -0,0 +1,69 @@
+/**
+ * @fileoverview One answer to "is this CLI installed here?", shared by the page render
+ * (`renderIndexHtml` in server.ts, which injects `window.__codemanCliAvailable` and
+ * `window.__codemanCliCatalog`) and `GET /api/clis` (the Settings list's badge).
+ *
+ * The two used to keep their own copies of the per-CLI probe map, so they could drift apart
+ * and the badge could disagree with the Run menu.
+ *
+ * Every probe is a memoized resolver, so this is cheap to call per request. Dynamic imports
+ * keep the nine resolvers out of any module that never asks.
+ */
+
+import type { CliEntry } from '../config/cli-registry/types.js';
+import { isCliAvailable as isRegistryCliAvailable } from './cli-resolver.js';
+
+/**
+ * The stock CLIs whose own resolver answers availability. It keeps the resolver's specific
+ * semantics (pi/grok/deepseek identity probes). DeepSeek reports RUNNABLE here, not merely
+ * installed: `dsh` is a profile launcher, and a dsh with no pane-capable profile would
+ * offer a Run button that spawns a pane which dies on arrival.
+ */
+export async function probeStockCliAvailability(): Promise<Record<string, boolean>> {
+  const [
+    { isClaudeAvailable },
+    { isOpenCodeAvailable },
+    { isCodexAvailable },
+    { isGeminiAvailable },
+    { isAntigravityAvailable },
+    { isPiAvailable },
+    { isGrokAvailable },
+    { isDeepSeekRunnable },
+    { isOmpAvailable },
+  ] = await Promise.all([
+    import('./claude-cli-resolver.js'),
+    import('./opencode-cli-resolver.js'),
+    import('./codex-cli-resolver.js'),
+    import('./gemini-cli-resolver.js'),
+    import('./antigravity-cli-resolver.js'),
+    import('./pi-cli-resolver.js'),
+    import('./grok-cli-resolver.js'),
+    import('./deepseek-cli-resolver.js'),
+    import('./omp-cli-resolver.js'),
+  ]);
+  return {
+    claude: isClaudeAvailable(),
+    opencode: isOpenCodeAvailable(),
+    codex: isCodexAvailable(),
+    gemini: isGeminiAvailable(),
+    antigravity: isAntigravityAvailable(),
+    pi: isPiAvailable(),
+    grok: isGrokAvailable(),
+    deepseek: isDeepSeekRunnable(),
+    omp: isOmpAvailable(),
+  };
+}
+
+/**
+ * Is `entry` installed? A shell entry has no binary to probe, since it is the server's own
+ * login shell. A stock entry with a dedicated resolver uses `stockAvailability`. Anything
+ * else, custom entries included, uses the registry's GENERIC resolver. That is the one a
+ * session spawn uses, and it understands the entry's declared binaries and search dirs.
+ */
+export function isCliEntryInstalled(entry: CliEntry, stockAvailability: Record<string, boolean>): boolean {
+  if (entry.kind === 'shell') return true;
+  const id = entry.id as string;
+  return Object.prototype.hasOwnProperty.call(stockAvailability, id)
+    ? stockAvailability[id]
+    : isRegistryCliAvailable(id);
+}

src/web/approval-inbox.ts

@@ -71,6 +71,15 @@ export interface ApprovalItem {
    * and reach the user's other devices. See `acknowledge()`.
    */
   acknowledgedAt?: number;
+  /**
+   * Why the item arrived already acknowledged, for display only: the inbox
+   * writes `watching 1 monitor` for a session that went quiet because work it
+   * started itself is still running. A human acknowledgement leaves this unset,
+   * so a card can say "quiet, watching 1 monitor" rather than implying somebody
+   * looked. ⚠️ Pane-derived text, so it is bounded at the source and must not
+   * reach the DOM as markup — see `watchingLabel()` in `session-activity.ts`.
+   */
+  acknowledgedReason?: string;
   /**
    * Present only when the frame parsed confidently. Gates which digits the
    * answer endpoint accepts; absent → only approve('1')/deny(Esc) are allowed.
@@ -93,6 +102,12 @@ interface NotePromptArgs {
   toolSummary?: string;
   message?: string;
   cwd?: string;
+  /**
+   * What the session's pane says is still running in the background
+   * (`Session.watching`, e.g. `1 monitor`). An idle prompt from such a session
+   * opens ALREADY acknowledged: see `notePrompt()`.
+   */
+  watching?: string | null;
   /** Returns the raw (ANSI-bearing) pane frame, or null when unavailable. */
   capture?: () => string | null;
 }
@@ -217,6 +232,22 @@ export class ApprovalInbox {
    * Record a prompt for a session, superseding any previous item, and return
    * the new item. Captures context immediately and once more after a short
    * delay (see RECAPTURE_DELAY_MS).
+   *
+   * ⚠️ An idle prompt from a session that is WATCHING its own background work
+   * opens already acknowledged (`args.watching`). Claude Code ends the turn
+   * after arming a monitor or backgrounding a shell and then reports the pane
+   * idle a minute later, so the alert that follows asks a human to look at a
+   * session that wants nothing from them. Acknowledging is deliberately what
+   * happens here rather than skipping the item: the prompt is real and stays
+   * pending, answerable and available as Read My Mind context, and only the
+   * alert it would have armed is spent. A wrong label therefore costs a card
+   * that does not blink, never an alert that was never created.
+   *
+   * It re-arms by itself. The next idle prompt supersedes this item and builds
+   * a fresh one, so once the background work ends and the session goes quiet
+   * for an ordinary reason, that item carries no acknowledgement and alerts
+   * normally. Only `idle` is eligible: a permission or question dialog blocks
+   * the agent whatever else it started, so its alert must survive.
    */
   notePrompt(args: NotePromptArgs): ApprovalItem {
     this.resolveForSession(args.sessionId, 'superseded');
@@ -231,6 +262,10 @@ export class ApprovalInbox {
       message: args.message,
       cwd: args.cwd,
     };
+    if (args.kind === 'idle' && args.watching) {
+      item.acknowledgedAt = item.createdAt;
+      item.acknowledgedReason = `watching ${args.watching}`;
+    }
     this.applyCapture(item, args.capture);
     this.items.set(args.sessionId, item);
     if (args.capture) this.captures.set(args.sessionId, args.capture);

src/web/paste-image-gc.ts

@@ -12,7 +12,8 @@
  * image dir.
  */
 import fs from 'node:fs/promises';
-import { join } from 'node:path';
+import { realpathSync } from 'node:fs';
+import { join, resolve } from 'node:path';
 import type { SessionPort } from './ports/index.js';
 
 const MAX_AGE_MS = 7 * 24 * 60 * 60 * 1000; // 7 days
@@ -53,6 +54,73 @@ export async function sweepPasteImagesOnce(
   return { scanned, deleted };
 }
 
+/**
+ * The path two sessions must share to share a paste-image dir: the canonical
+ * path when it can be resolved, so a sibling that reaches the same directory
+ * through a symlink matches, and the normalised path otherwise (a directory
+ * that no longer exists has nothing left to protect).
+ */
+function canonicalDir(dir: string): string {
+  try {
+    return realpathSync(dir);
+  } catch {
+    return resolve(dir);
+  }
+}
+
+/** One session the paste-image guard weighs: its id, directory and, for a persisted record, its status. */
+export interface PasteImageDirUser {
+  id: string;
+  workingDir: string;
+  status?: string;
+}
+
+/**
+ * Does another live session still use this working directory's paste-image
+ * dir? Deleting a session removes `{workingDir}/.claude-images` recursively,
+ * and several sessions routinely share one case directory, so without this
+ * check closing one session deletes the pasted images a sibling in the same
+ * case still refers to.
+ *
+ * Two kinds of sibling count as live:
+ *
+ * - a session in the server's map, unless it is itself being killed;
+ * - a persisted record whose status is not `stopped`. That covers a session
+ *   detached with `killMux=false`, which leaves the server's map while its
+ *   tmux pane keeps running, and a session whose detach is still in progress.
+ *
+ * A session being KILLED does not count. Without that exemption, killing two
+ * sessions of one case concurrently (a bulk delete, or the exited-agent sweep
+ * closing two panes on one tick) would have each defer to the other, and
+ * neither would remove the dir.
+ *
+ * Erring toward "in use" only costs a missed deletion, which the periodic
+ * sweep above ages out. A pinned record whose tmux session is gone keeps its
+ * status through boot pruning, so it holds the dir this way until unpinned.
+ */
+export function pasteImageDirInUseByOtherSession(input: {
+  live: Iterable<PasteImageDirUser>;
+  persisted: Iterable<PasteImageDirUser>;
+  closingId: string;
+  workingDir: string;
+  killing: ReadonlySet<string>;
+}): boolean {
+  const target = canonicalDir(input.workingDir);
+  const matches = (user: PasteImageDirUser): boolean =>
+    user.id !== input.closingId &&
+    !input.killing.has(user.id) &&
+    !!user.workingDir &&
+    canonicalDir(user.workingDir) === target;
+  for (const user of input.live) {
+    if (matches(user)) return true;
+  }
+  for (const user of input.persisted) {
+    if (user.status === 'stopped') continue;
+    if (matches(user)) return true;
+  }
+  return false;
+}
+
 export function startPasteImageGc(ctx: Pick<SessionPort, 'sessions'>): () => void {
   const initial = setTimeout(() => {
     void sweepPasteImagesOnce(ctx);