The dedicated route got this order at merge and quick-start kept the old one, so
a user could agree to a swap only to get the 400. It also runs on the pure build
now, so a refused id writes no config dir to clean up.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Say that settings.yaml is shared only until the session's first settings write
(dsh saves by rename, which replaces the link), warn when a session's own DSH_HOME
does not answer and the server's home is linked instead, test
guardSessionConfigDirHome, and document the linkFromRealHome exception and what a
custom-model dsh session does not carry over.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The launch-id check is pure, so it now runs before the context warning and the
swap confirmation: nobody agrees to evict a model only to get the 400. Also the
search-box and in-use comments, the model-plain-colon wording, and the wiki's
order of the picker's marks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Round-four review item 3: the swap route wrote the new config.toml into the very dir a live codex session uses as CODEX_HOME before checking the pattern, and its refusal then deleted that dir. buildCustomModelInjection is pure, so the check runs on its result and a refused id never touches the filesystem. Pinned by a two-apply codex route test.
Second review round on PR #755: skip non-absolute DSH_HOME candidates so a relative home can never mkdir under the server cwd; probe a session-supplied home with probePathKind in both async routes before the synchronous apply; test the session env-override lookup (seventh arg) incl. the self-link fall-through and the relative-home skip; reject '.' and '..' as realHomeFallback and enforce linkFromRealHomeDirs subset in the schema; fix the stale apply JSDoc and the two doc lines lagging the verified dsh run; state the shared/isolated split plainly.
- linkFromRealHome/realHomeFallback on the configDir recipe; the apply consumer is generic and names no CLI
- lstat guard so boot-recovery re-applies survive a dangling link; symlink is best-effort
- resolve the real home from the session's own dirEnvVar override before the server's, threaded through both routes and boot recovery (Session.envOverrideValue)
- deepseek links profiles/sessions/settings.yaml; boot-recovery test covers the session lookup
- share one context-length resolution (discovered figure, endpoint default fallback) across the routes and boot recovery, with a recovery test
- record listed per-slot context figures with a slot count of 1 and force the slot-count fallback once per rediscovery
- open up the codex model launch token for qwen3-style ids (model-plain-colon), pinned by a spawn-golden case
- pass the full discovered window to opencode as limit.context
- translate the picker search strings and document the discovery precedence
A remote-SSH session's workingDir is a path on the remote host, and the
image watcher watched it on the local disk: a folder that is not there,
or a same-named local folder whose images then popped up as the remote
session's. Same root cause as the Ralph @fix_plan.md watcher fix.
Three places start a watch, and all three now skip a remote session:
setupSessionListeners(), the app-wide toggle in PUT /api/settings (which
re-watches every enabled session), and POST /api/sessions/:id/image-watcher,
which refuses to turn it on (INVALID_INPUT, like the Git fetch settings
route) and still lets it be turned off. The Session Options row is hidden
for a remote session, the way the Git tab is, since the client's
_apiPost() does not throw on a refused request.
The merged PRs (mostly #714's git fetch) added about 120 em-dashes in
comments, docs, test names and three settings strings. Each one is now a
comma, colon, semicolon or parentheses. The English settings strings in
index.html and their i18n.js keys change together, and the zh-CN value
for the fetch interval uses full-width parentheses instead of a double
dash. The one left is the regex in constants.js that matches a dash
typed as a word, which is behaviour, not punctuation.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Conflicts resolved by keeping both sides:
- CLAUDE.md (Agent CLI): #694's opening (an HTTP client, the experimental
agent-session-routes behind agentCoordinationEnabled) with #708's clause
on the directory spawn and its two refusals.
- docs/api-reference.md (codeman agent): #708's spawn paragraph and --json
shape, with #694's inspect/stage/submit in the verb list and the guarded
endpoints named before "adds no route for the other verbs".
- src/cli-agent.ts (@fileoverview): #708's quick-start / directory spawn
routes and #694's experimental routes in one endpoint list; the two
node:fs/promises imports (#708's realpath+stat, #694's open+stat) merged
into one.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Conflict in CLAUDE.md (Adding Features, App setting) resolved by keeping
both sides: #714's sentence that a setting the server acts on must be
synced, after the `.strict()` clause, and #719's mutateSettingsFile() rule
at the end of the bullet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- src/web/routes/session-routes.ts:2102: the guarded-submit 409 now applies to tagged input (clientId + seq) only; untagged input is held like a WebSocket frame. The raw write (:2228) goes through holdForGuardedLease and answers 200 once held (a send-and-wait reads `delivered` from the held write; a full queue releases the waiter and answers 409); a mux write takes its own turn in writeViaMux.
- test/guarded-lease-held-input.test.ts: real-Session route tests for an untagged raw POST during the lease (written after the Enter) and a held send-and-wait (delivered: true); both fail without the fix.
- test/routes/session-routes.test.ts + test/mocks/mock-session.ts: the 409 test now covers tagged input only; new tests for untagged raw (held), untagged mux (own turn) and a full hold queue (409); MockSession gains holdForGuardedLease/releaseGuardedLease and a lease-aware writeViaMux.
- src/session.ts:4787 (guardedInputHeld JSDoc) + write() + docs/architecture-invariants.md: write() refuses during the lease only, so cron's paste mode can land ahead of input still draining.
- docs/api-reference.md: the input route's 409 is for tagged input; untagged input is held.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The input lease is held across the awaited tmux Enter, so WebSocket frames
keep arriving while it is held. A tagged frame (seq N) was refused and its
seq rolled back, but the browser's WebSocket path does not wait for ACKs:
seq N+1 landed after the lease and moved the watermark past N, and the
redelivered N was then dropped as a duplicate. The keystroke was lost.
Input that arrives during the lease is now held and written in arrival order
when the lease is released, whatever the submit's outcome. A WebSocket frame
is applied and ACKed only once written; managed writes (writeViaMux) and
named keys (send-key) wait for their turn the same way, and a held write that
is still being sent holds everything behind it. A keystroke held before the
guard runs still moves the input revision, so it still invalidates the Enter.
The hold is capped per lease (256 inputs, 1 MiB): past it the WebSocket is
closed with 1013 and nothing later from it is applied, so the browser resends
every unACKed frame in order, and send-key answers 409 CONFLICT instead of
logging a tmux failure as INTERNAL_ERROR. POST .../input keeps its 409 for the
lease plus the held input's drain; its browser drainer is serialized.
Docs: correct the api-reference paragraph that said these keystrokes are
redelivered, and describe the capture fallback and the per-scope cursor cap
from the previous two commits in api-reference, architecture-invariants and
the changeset.
Quick-start saved lastUsedCase with an un-awaited, non-atomic read-modify-write, and the settings PUT, model config, case order, case rename, Ralph start and the boot tunnel reset each ran their own. Two overlapping truncate-then-write calls left one write's bytes over the tail of the other (the CI flake in test/quick-start.test.ts), and most writers then read the torn file as {} and wrote back only its own keys, erasing the rest of the user's settings.
All of them now go through one writer that runs one change at a time, replaces the file atomically, and refuses (409 CONFLICT) to overwrite a file that does not parse.
Stage now re-reads the pane after typing (every 50 ms, up to 1 s) and
issues a receipt only for a frame with the same generation, the input
revision its own write moved, and a composer hash equal to the
message's. Codex repaints 30 to 60 ms after the keys, so the first
capture was often stale and stage refused with the text already typed.
Every refusal after typing now says the message may be in the composer
and points at the Ctrl+U recovery. A visible-frame capture reads the
screen and the caret in one tmux invocation, with the old two calls as
the fallback.
Codex draws its suggestion popups above the composer and keeps the
footer, so a staged /stat verified and submit ran /status. Stage now
refuses a leading / or ! and a last word starting with @ or $ before
typing, and stage and submit refuse a frame with popup rows just above
the composer. The pattern and characters are registry data
(composerPopupLine, composerCommandPrefixes, composerCompletionSigils),
read from the codex 0.162.0 bottom_pane sources.
Submit waits until 250 ms after the staged keys: codex turns an Enter
within 120 ms of a typed burst into a newline. POST .../input answers
409 with its seq returned while a guarded submit holds the input lease,
instead of 200 for bytes it never wrote.
Also align the attribution memo comment with the code (a verified file
whose incremental scan fails is not re-walked, since the full walk
reads a superset), and list stage as a fromUser source in CLAUDE.md.
The scheduler is the part that runs with nobody watching, so it is decided per folder
rather than per session: sessions sharing a folder are the same clone and share one run
that both see, `inFlight`/`lastRunAt` are keyed by the resolved folder, the schedule is
stamped when a folder is picked instead of when its run starts, and a tick is skipped
while the previous one is still going. The click route joins a run already going for the
same folder rather than starting a second fetch in one clone.
The tick keeps ONE bound for the git processes of the whole run and hands it to every
folder, and bounds its folders with a bound of its own: the same semaphore cannot serve
both levels, because a folder holding a slot would then wait for a slot its own fetch
needs. Both bounds are `FETCH_CONCURRENCY`, so the ceiling is unchanged. The bound claim
in CLAUDE.md, the `Limiter` jsdoc and docs/api-reference.md now describes it as it is.
Before anything is fetched the folder is probed with the bounded path probe, so a case on
a mount that stopped answering is skipped and never touched.
The rest of the review: the hooks are named as they really are (`reference-transaction`,
`pre-auto-gc` through the maintenance a fetch triggers, config commands such as
`credential.helper`) and `FETCH_CONFIG_ARGS` turns maintenance and gc off for an
unattended run; the claim that an agent in the same repository is not disturbed is
replaced by the ref-lock collision it actually is; the click route publishes its own run
as `trigger: 'click'`; `autoSaveGitFetch` uses `_apiJson` so a 400 shows the error toast
and applies the returned settings; and the two wording fixes.
Tests: the scheduler pins one run per folder, the two bounds, the probe before anything
runs, and that closing the session holding the override keeps the folder while another
session is still open on it; the route test pins the click publish and the join, asserting
the join before the held run is released — releasing first lets the run finish and clears
the lane, so the joiner would be entitled to its own fetch and the test would pass for the
wrong reason.
Fetch is the only git command Codeman runs that writes, and the only one that runs a
repository's own fetch-post hook, so it stays behind a click and off by default. The Git
status window's header row gains Fetch; App Settings -> Bottom bar gains the switch and
the interval, synced because the scheduler acts on them, and Session Options -> Git
overrides both per case. The scheduler reads settings fresh each tick, times the interval
from the start of a run, never overlaps runs, and re-checks the Docker and remote rules
every tick before any git runs. Nothing but remote-tracking refs moves: HEAD, the index
and the working tree are proven unchanged against real git while origin/main advances.
Tests: src/git-fetch.ts and the scheduler, the per-case settings route, the synced/display
setting split, the two new i18n rows, and the Fetch block of the Git status browser suite.
Conflict in src/web/routes/session-routes.ts (the import block) resolved
by keeping both sides: #680's claudeProjectDirName import stays, and the
fastify import takes #690's form without FastifyReply, since #690 moved
abortOnClientHangUp (its only user here) into route-helpers.ts.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- The history is deleted when the session's persisted record goes (forgetEditHistory):
kill via cleanupSession (a pinned record is only demoted and keeps it), the
persisted-only DELETE, and stale cleanup at startup. After remove() neither a sync in
flight nor a later request writes the file again; writes are serialized.
- load() re-bounds a damaged file: cursors, pending Bash calls (MAX_PENDING_BASH) and
subagent labels (MAX_AGENTS, oldest unused dropped first).
- Load older reads one block of every transcript, budget split between them, and only
the files it asked for; a block short of budget reads its end. A line longer than the
budget is skipped going back as well (floorMidLine).
- Concurrent first callers share one store; a forward request folded with an older one
still reads forward.
- Images outside the workspace get no thumbnail (one attachment id per render); a click
opens the shared preview, which registers once with notify: false.
- Docs: per-edit diff cap, deletion rule, load-time bounds, thumbnails, follow triggers.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- codeman agent post: accept text that starts with "-" (markdown from a
file), --json and -h stay options.
- DELETE /api/sessions/:id on a persisted-only row drops the inbox a detach
kept.
- inbox --wait: wait.ended is exit 3 only when the session list no longer has
the session; a restart or detach ending the wait is exit 2 (wait again).
- A read whose client hung up during ?wait= marks nothing seen.
- InboxPostSchema bound is 4x the byte cap, so every oversize message gets
the store's "post a file path" answer.
- Store: restore sorts oldest first; the TTL sweep checks every message,
not only the first.
- Docs: admins can act as any session of the receiver's owner (now tested
for admin and non-admin); a peek with ?wait= does not block; exit codes.
- Tests: partial PUT /api/settings keeps persistence on.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A coordinator can leave text for a worker without typing into its pane.
- Store (src/web/agent-inbox.ts): read until ack by id, seen only for the
receiver, 16 KiB/message, 512 KiB + 200 messages per inbox, full = 409
CONFLICT (never drops the oldest), 12 h TTL from each message's createdAt.
- Routes (routes/inbox-routes.ts): POST/GET /api/sessions/:id/inbox
(?wait= parks while nothing is unseen), POST .../inbox/ack (receiver
only, 403 otherwise), GET /api/agent-inbox/summary (owner-scoped counts,
not in toState()). Caller = resolveParentSessionId().
- Inbox waiters are the wait registry's third kind: same caps, ended by
cancelAll/cancelEverything.
- Opt-in snapshot (agentInboxPersistEnabled, synced, default off):
agent-inbox.json via dataPath(), 0600 tmp+rename, off deletes it, boot
prune only after a successful restore. Dropped on delete, kept on detach.
- CLI: codeman agent post | inbox [--wait] | ack, INBOX column in ls.
- waitCapacityResponse/abortOnClientHangUp moved to route-helpers.ts
unchanged.
- Docs: api-reference, README, CLAUDE.md, architecture-invariants, skill +
plugin mirror.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Only an admin's rename touches the server-wide settings.json, which is now
written before linked-cases.json with the registry restored on failure. The
Resume list follows a renamed folder, the owner's default session group is
carried over, remote sessions are never listed or stopped, errorCode maps
EXISTS and BUSY, and the unmigrated items are documented.
Conflict in CLAUDE.md's State Files line resolved by keeping #661's new
config-backup entries and this PR's "case default groups" in state.json.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Squash of PR #658. Discovery records each llama.cpp model's parallel slot
count (from --parallel/-np, or /props total_slots when the launch command
states none), and a Claude launch warns when the context split across
those slots leaves less than 40K tokens per request. An explicit
--parallel beside a /props context records a slot count of 1, so a later
round overwrites an earlier count, and a non-2xx /props is remembered per
launch command while a network error is retried.
Merge-time fix by the maintainer: the architecture-invariants sentence on
the explicit --parallel case now says it records a slot count of 1.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Merge-time fix for #676 (review finding 1 and nit 7). The Git worktrees modal
launches Claude through POST /api/sessions with workingDir
<case>/.claude/worktrees/<name>, which inferLocalCaseName did not recognise,
so the session landed in Ungrouped while the same gesture for any other CLI
(quick-start with the case name) landed in the group. The inference now
strips a trailing .claude/worktrees/<name> lexically before its two checks,
reusing CLAUDE_WORKTREE_PATH (hoisted to module scope). It also runs only for
a named workingDir, never on the server's own cwd, as the hook and skill
injection above already do. Route tests for both, failing without the fix;
api-reference and architecture-invariants say so.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Case settings gains a "Default session group" selector (Ungrouped plus every
named tab group of the owner). A new session of the case lands in that group
in the same versioned layout write that registers it, so it is drawn in place
with no Ungrouped-to-group jump.
- Stored per owner and case in state.json (caseDefaultGroups), as the group's
stable id or null for Ungrouped; read and written only through
TabLayoutService under the owner lock.
- Precedence in sessionCreated: explicit tabGroupId, then the parent
placement, then the case default, else Ungrouped. A deleted or foreign id
never fails a spawn and is forgotten only after the creating write lands.
- POST /api/quick-start (local, linked, remote, Docker) and
/api/ralph-loop/start pass their case; POST /api/sessions infers it
lexically from workingDir. The create response carries tabLayout when a
case default placed the session.
- GET/PUT /api/cases/:name/default-group; deleting a case (or an admin
deleting a user's case folder) forgets the value.
- The selector mirrors desktop and phone, reverts on a refused save, and is
redrawn from every adopted tab layout; zh-CN strings added.
Claude Code lets a subscription's one-hour prompt cache expire after an hour idle, and the first turn back re-writes the whole conversation at the cache-write rate; nearly every gap over an hour goes cold, while the saving is concentrated in gaps of one to four hours. Codeman now sends one short keep-alive turn five minutes before the expiry Claude Code reports on its statusline, so the next real prompt still reads the conversation from cache, and stops two hours (configurable) after the last real prompt.
Codeman owns the idle policy for these sessions, as agreed in Discussion #554: a launch with keep-warm on also carries idleCompaction: false in its one --settings JSON, so Claude Code's own idle compaction cannot replace the conversation with a summary a minute before the nudge. It is decided once per launch (keep-warm on, the statusLine exporter injected, Claude Code 2.1.290 or newer, an unknown version fails closed like --name), recorded on the mux record, and picked up by any relaunch; a launch with keep-warm off is byte-identical. A session switched on after launch is kept warm best-effort and the readout says so.
Every guard lives in one pure rulebook: the opt-in (an agent-spawned session does not inherit the app default), a launch that reports cache state, a warm 1h cache with enough tokens at stake and no compaction this gap, a live pane, no usage-limit pause, no respawn, Ralph, task or waiting agent, idle, no open dialog, an empty composer and no recent keystroke. The nudge is a submit and moves lastSubmitAt, which the response viewer's conversation correlation needs; the cap counts from its own persisted lastRealPromptAt instead. Read My Mind drops the exact nudge text, and the turn's stop hook and idle prompt open pre-acknowledged so nothing alerts. The last cache report and the clock survive a restart, so the timer re-arms.
GitHub Copilot CLI (`copilot`) becomes a run mode: Run menu, welcome
screen, cron and CLI management once it is installed, tmux-backed like
the other agent CLIs, working/idle and the model read off its footer,
launch options through `copilotConfig` (model, resume, continue, the
multi-user-clamped allowAll), Custom Model Endpoints via Copilot's BYOK
variables, MCP sync of its mcp-config.json, a status probe, and the
`codeman agent` verbs (spawn waits for its composer, read returns its
last answer).
The plan-usage quota row that earlier rounds carried was split out on
review and is not part of this merge.
Merge-time commits on top: the wider COPILOT_* clamp and the zh-CN
README rows (maintainer), the Docker sign-in docs, divider rows inside
an answer kept by `agent read`, route tests for the screen-read
last-response branch, and doc drift (Past Sessions, wheelForward JSDoc,
COPILOT_/OMP_ in the env prefix lists).
Verified before merge on Copilot CLI 1.0.98: injected keystrokes,
bracketed paste and Enter reach the TUI in tmux (github/copilot-cli#4180
does not reproduce), a shell tool call completes inside tmux (#4223 does
not reproduce), and a session driven through this branch answered over
send-and-wait.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Now that the set is exported for the parity test, type it read-only like
VIDEO_ATTACHMENT_EXTENSIONS, so an importer cannot add to the live upload
allowlist.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
`/api/sessions/:id/last-response` fell through to the Claude transcript scan for copilot (not in the
external-CLI list), so `codeman agent read` answered empty even with an answer on screen. Copilot
is a repainting full-screen TUI whose stream is absolute cursor moves, so the buffer cannot be cut
into lines either; the route now reads the pane's visible screen (tmux capture-pane) for such
modes and falls back to the buffer where there is no pane.
The segmenter gets a small per-CLI "pane dialect" row instead of another branch in the
Codex-oriented loop: `❯ <prompt> HH:MM`, `● <answer>` with indented continuation, the cwd /
`Session: N AIC used` row, composer, footer and the `┃` scrollbar gutter are chrome, and
everything before the first prompt (banner, trust dialog) is dropped so a session that has not
been asked anything answers nothing rather than serving its logo.
Fixture is a real Copilot 1.0.95 pane. Tool-call rows are not modelled and read as answer text.
Copilot (`copilot`, npm @github/copilot) as a stock CLI entry with the same launch options as the other agent CLIs: model (--model), resume (--resume), continue (--continue) and allow-all (--yolo, clamped off for non-granted multi-user owners). Adds a resolver and GET /api/copilot/status probe, the agent-image package, Run-menu/mobile/logo entries, skill docs and tests.
An Excel or Notepad CSV/TXT export (UTF-16 with a BOM, or Windows-1252) was refused as "File bytes do not match declared type", which reads like a corrupt file. Name the encoding and tell the user to save it as UTF-8.
The browser cannot import the server's document allowlist, so the classifier, the three pickers' accept lists and the two file-path link patterns each carry a hand-kept copy. A missed copy fails silently: a file greyed out in the picker, an upload dropped client-side, or a pasted path that is no longer a link. Hoist the set to module scope so the test reads the shipped list.
In multi-user mode any signed-in non-admin could rewrite the server-wide
~/.codeman/settings.json through PUT /api/settings (feature switches, the
plan-usage collection switch, run mode, respawn presets, the tunnel), although
docs/multi-user-plan.md makes settings writes admin-only.
PUT /api/settings now answers 403 FORBIDDEN for a non-admin before anything is
parsed, written, toggled or started. The other request paths that write a
server-wide setting get the same gate: PUT /api/execution/model-config (the
modelConfig key), PUT /api/config (state.json app config) and
PUT /api/cases/order (the one global caseOrder list). Quick-start and
ralph-loop start no longer record a non-admin's lastUsedCase in settings.json,
where every user could read it. GET /api/settings stays readable by everyone;
single-user mode is unchanged (requireAdmin short-circuits there).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
feat(codex): raise codex approval, question and trust dialogs as BLOCKED
Conflict resolved against #634 in src/session.ts _probePaneWorking():
#624's assignment (a dialog on screen is never work) is kept, and #634's
trust-dialog verdict block (log the hold once, remember the reading)
follows it, before _readWatching().
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
sendInput() typed the text of a text+Enter pair with `send-keys -l` and
sent Enter 50 ms later. Codex detects an unmarked paste from a fast
character burst and folds an Enter inside that window into the paste as a
newline, so the prompt stays in the composer unsubmitted. Measured with
codex-cli 0.162.1 in a throwaway tmux pane: 1505 chars stuck 3/3 as
`[Pasted Content 1506 chars]`, a 98-char line stuck 1/4. SubmitVerifier
re-presses Enter for the short case, but it cannot match the long one: the
composer shows the placeholder instead of the prompt's head.
The text now goes in via set-buffer + `paste-buffer -p -d` (markers only
when the pane requested bracketed paste), followed by the separate Enter as
before. Same pane, same texts: 4/4 and 3/3 submitted. Each send gets its
own named buffer; a paste that fails (pane or server gone) deletes it,
since tmux never trims named buffers on its own.
Also escapes a trailing `;` in the text, which tmux treats as a command
separator (`send-keys -l 'x;'` typed `x`, a lone `;` typed nothing).
sendInputToPane() has no callers in src/ and is left as it was.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
`GET .../wait` answers `blocked` at once for a codex pane showing a dialog,
because a screen-read dialog is a level the server is still reading. The
duplicate branch of `POST .../input` (a tagged retry after a dropped
connection, answered from current state) still used the plain
`currentSignalFor()`, so a retry with `wait: "blocked"` on a pane the first
delivery had already blocked waited out its whole timeout for an edge that
had passed. It now uses `currentSignalForWait()` like the GET route; a
caller that asked only for `idle` still gets `idle`.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A codex dialog the session now reads off its screen gets exactly what a
Claude `permission_prompt` hook gets, so every surface that already handles
that event needs no second path: `web/screen-blocked.ts` turns the session's
`blockedChanged` edge into the `blocked` wait signal, an Approvals Inbox
item, the `hook:permission_prompt` broadcast (with `source: 'screen'`), web
push and webhooks, and a run-summary row. That lights the red "needs you"
tab alert and desktop notification, the phone overview's NEEDS YOU row and
the TUI. When the dialog leaves the screen the item it opened is resolved,
and `approval:resolved` clears every client.
It is an ALERT and never a keystroke, following #610's shape for DeepSeek:
the item is `answerInTerminal`, push carries no `approvalId` (so no
Approve/Deny), and the answer route refuses it. The dialog was read from a
screen the agent writes most of, so a forged match must cost a false alert
and nothing more. The message every surface shows is built from the CLI's
registry label, never from the dialog's text. The item gets no `capture`
callback, only its frame as context, because the inbox's option parser and
staleness sweep are shaped for Claude's dialogs and the session owns this
item's lifetime. A CLI whose hooks report blocked gets nothing from the
screen, so declaring both could never alert twice.
The answer route now checks `answerInTerminal` BEFORE its hooks gate and
names the CLI: a codex session has no hooks, and "Session mode cannot have
pending approvals" would be false about the item the caller holds.
Wait signals: `blocked` is available where hooks report it OR a CLI declares
`blockedLine` (`blockedSignalAvailable()`); `stop` stays hooks-only, since
nothing on a screen says a turn ended, so `until=stop` on codex is still a
400 (now suggesting `idle, blocked or exit`). A screen-read dialog is a
level the server keeps reading, so a `GET .../wait` that asks for `blocked`
while one is up answers at once; a caller that asked for `idle` alone keeps
getting `idle`. The MCP and `codeman agent` help text say so.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>