Every App Settings Save up to 1.49.0 wrote `agentSkillEnabled: false`, chosen
or not (the switch loaded an absent key as off and Save sends the whole form),
so the new default never reached an install that had ever saved. On its first
start the server now replaces a stored false with true, once per data dir, and
logs one line when it does. It cannot tell a deliberate off from the old
default; that is accepted and stated in the release notes. An off set after it
ran stays off.
It stores true rather than deleting the key: the page's merge overwrites only
the synced keys the server has, so every device that saved on 1.49 kept its own
false, showed the switch off and wrote false back on its next Save (measured in
the JSDOM harness). True wins on every device, including a browser still on a
cached settings-ui.js. For a server with no key the page now drops the device's
copy as well, so the switch shows the default.
The "done" marker is its own file, `agent-skill-default-migrated.json` in the
data dir: it is not a setting, so GET /api/settings never returns it, no Save
can send it back (the strict schema would refuse it) or drop it (which would
re-arm the migration), and a config-backup restore leaves it alone. It is
checked before anything is read and written only after the settings write
landed. The migration runs in WebServer.start() before the first settings read
and before listen (skipped in test mode, like the other boot-time writes),
writes only through mutateSettingsFile(), drops the 2 s settings cache, and
leaves a settings.json that does not parse alone with no marker, so the next
start after the fix runs it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An absent `agentSkillEnabled` now means on, on the server
(`getAgentSkillEnabled()` reads `!== false`, like `workspaceHooksEnabled`)
and on the page (the App Settings switch loads `!== false`, so a Save of any
other setting no longer writes the old default back). Only an explicit false
turns it off. A partial settings PUT that omits the key leaves it as stored,
since the route merges the request into the file.
The switch's help text says it is on by default, that the copy stays out of
git, and that turning it off removes no copy already written. The shared
route-test mock now defaults to on too, so route tests see what a user sees.
Tests: quick-start against a real server (absent key injects, a partial PUT
keeps it on, an explicit false stays off through a later partial PUT), the
real openAppSettings/saveAppSettings in JSDOM (absent shows on, explicit false
shows off, a Save on a never-touched install sends true and passes the
schema), and the plain create route at the mock's default.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The read-only card is gone. The welcome screen has one button, "Run a local
model" ("Local model" once one is installed), and App Settings > Models has
one row; both open the same window.
The window follows `install.state`: choose a model (a radio group, with a
memory bar filled to what the selected model needs), confirm the sizes and
the folder, watch the download and the steps, and end on "Start a session".
Paused, failed, installed (running or stopped), Remove and "no model fits"
are screens of the same window. It polls the GET once a second while open.
Every dynamic string goes in through textContent, labels and sentences come
from the payload, no CLI id is compared, and every new string has a zh-CN
entry.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The read-only face of GET /api/local-model: what the Mac the server runs on
can run as a local coding model.
- local-model-ui.js: one builder paints both containers from the same
payload: the hardware line, the server's headline, the pick with its numbers
(context, download, memory need against the budget, speed), the server's
notes, the other models that fit with their Good, Tight, Slow or Speed
unknown labels, and one line saying that setting it up from Codeman is the
next step and is not built yet.
- The welcome card ships hidden and shows only once the server answered for a
Mac. It stays hidden for not-macos, for a refused request (a non-admin in
multi-user mode) and after "Hide", a per-device localStorage key. The App
Settings group "Model on this Mac" (Models) carries the loading and failure
sentences and is the way back after a Hide.
- Every dynamic string goes in through textContent, both containers are
data-i18n-skip and the module translates its own sentences, repainting on a
language change. Sizes are printed as sent. Labels and harness names come
from the payload: the module names no CLI and the word "Recommended" is not
in it.
- One request a minute at most, shared while in flight; a failed refresh keeps
the last answer on screen.
- i18n.js: zh-CN entries for the module's strings and for every server label.
- frontend-cli-no-id-branching.test.ts scans the new module.
Tests: test/local-model-ui.test.ts (JSDOM over the real markup),
test/local-model-i18n.test.ts.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Conflict in src/session-cli-registry-bridge.ts: kept the PR's gateVersion() (gates measured against the gated CLI's own version) and added master's Discord startup hint engine value.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Codeman itself always lived under $HOME; administrator rights were only
spent on what it needs first (system packages for Node.js, tmux and git,
Homebrew on a Mac). An account without those rights could not install it:
the installer died in ensure_sudo, or in Homebrew's own installer.
install.sh now has a no-admin route, taken by itself when the account has
no administrator rights (no sudo binary; outside sudo/wheel/admin and
`sudo -n true` fails; a refused sudo password; a Mac account outside the
admin group with no writable Homebrew) and forced with --no-admin or
CODEMAN_NO_ADMIN=1:
- Node.js: the official tarball from nodejs.org, checked against the
SHASUMS256.txt published beside it, into ~/.codeman/runtime/node.
- tmux: the tmux project's own build (tmux/tmux-builds 3.7c), checked
against a SHA-256 pinned in the installer, into ~/.codeman/runtime/bin.
- Both are linked from ~/.local/bin (never over a file that is not ours),
and the runtime is on PATH and on the LaunchAgent's PATH.
- git is never installed. Without a working git the source comes as an
archive, the install is marked with .install-source, and it updates by
re-running the installer: the new tree is built beside the old one and
swapped in only after the build succeeded. A later re-run on a machine
that has gained git turns it back into a clone.
- Nothing on this route runs sudo, Homebrew or `xcode-select --install`,
and the route is never decided by `sudo -v`.
What it cannot supply is checked before the first download: a C/C++
toolchain on Linux (node-pty 1.1.0 compiles there), musl, and macOS below
15 (the tmux build's deployment target).
Along the way:
- check_git no longer trusts `command -v git`. On a Mac without the Xcode
Command Line Tools /usr/bin/git is a stub that opens Apple's install
dialog; it is judged by `xcode-select -p` and never executed. Any other
git is asked for its version.
- scripts/git-hooks.mjs answers "not a checkout" without running git, for
the same reason: postinstall calls it on every npm install.
- The in-app updater knows the install kind `archive` and points such an
install at the installer instead of `npm i -g aicodeman@latest`.
- download() and download_to_stdout() resolve DOWNLOADER themselves. Only
main() used to set it, so `install.sh cloudflared` died on `set -u` with
the message swallowed by the step log.
- The AI CLI menu leaves out a Homebrew-only install command where there
is no Homebrew.
Verified with the real installer: a bare Ubuntu 24.04 container as an
unprivileged user (install, a PTY round trip through the API, update by
re-run, cloudflared, uninstall), the same without a compiler (stops before
any download), with a broken then working git, with sudo present but not
usable, and on macOS 26 (arm64) in an isolated HOME with sudo, brew, git,
the compilers, launchctl and tailscale replaced by tripwires. Not verified
on a real standard macOS account: that account was an administrator.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Owner decision. Typing the note into a brand-new non-Claude tab spent a model
turn per tab and, for a spawned worker or a scheduled run, landed with the first
real prompt. Claude keeps its hint through the system prompt, and every other CLI
is told nothing. The setting goes with the path it gated: sessionIdle, the fresh
set, isHintableSession and the session:idle wiring. sendInput loses `fromUser`,
which was only ever false for the hint, and the deps test pins that a reply is a
person's own input.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Both _abandonTunnelEnable() returns come after saveAppSettingsToStorage() wrote
the new values to this device but before _unsavedSettingsBaseline was set, so
after cancelling the no-password prompt the next Save sent no
showPlanUsageLimits flip and did not reload for a gesture-control change.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Measured on 1.47.0 with the same "spawn a shell worker, echo, read, delete"
task: DeepSeek Harness and OpenCode already pass end to end; Codex 0.162
failed three ways, fixed here.
- Start Codex 0.162+ with --no-daemon (new noDaemonFlag gate, fail-closed).
The shared app-server daemon stopped every launch on an "incompatible
feature settings" dialog when another version's daemon was running, and
ran commands with another session's CODEMAN_* environment.
- Evaluate registry version gates against the gated CLI's own version
(resolveSessionCliVersion) instead of claude's for every entry.
- Add the opt-in synced setting App Settings > Codex > Allow network access
(codexNetworkAccess, default off): --config
sandbox_workspace_write.network_access=true, filled as a launch default
and clamped off for non-granted owners like the bypass switch.
- Skill: carry on with the curl path when `codeman` is not on PATH, re-run a
sandbox-blocked call once through the CLI's approval path, name the new
setting. Wiki and registry docs updated.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude keeps the silent system-prompt hint (startupHint, on). Other CLIs are sent the typed message only with typedHint, which costs a model turn per tab.
Adds the codeman notify command, a startup hint (Claude via --append-system-prompt, other CLIs once on first idle), files saved from thread attachments into the tab folder, and --file uploads limited to the session folder.
Alerts for permission prompts, questions, idle and errors post into a per-tab thread; a reply from an allowlisted user is typed into that tab. Thread creation, thread cleanup on tab delete and pinging are configurable. POST /api/sessions/:id/discord-notify lets a CLI ask for the user. Setup is in docs/discord-bridge.md.
App Settings' save handled only the multi-user admin-only 403 and the tunnel's no-password 403, so a 409 for a settings.json that does not parse, a 400, a 500 or a dropped connection (`_apiPut` answers null) still toasted "Settings saved" and closed the modal, and the run mode and respawn preset writes failed with no word at all. Those failures now warn with the server's reason (else the HTTP status, else that the server could not be reached), the modal stays open, and nothing that assumes the server stored the save runs: Apply's refresh, the tunnel-starting toast and the gesture-control reload. Since the modal now invites a second Save, the plan-usage collection flip and the gesture reload are judged against the settings the failed save started from until a save lands, so the retry still sends the flip and still reloads.
A save with the tunnel switch on is read as a tunnel refusal only on a 403, so another failure no longer turns the switch off or shows the no-password message, and an accepted no-password retry now resends the whole save instead of the tunnel keys alone, which had left every other setting unsaved behind "Settings saved". Run mode and respawn presets stay saved on this device as before and now say they were not saved on the server. Stopping the tunnel from the welcome screen or the tunnel panel no longer says "Tunnel stopped" when the server refused the write, since the tunnel is then still running.
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>
The network acknowledgement that install.sh writes for every passwordless LAN install also satisfied the tunnel guard, so one click on the welcome screen's tunnel link published full terminal control to a public URL with no login and no confirm. The tunnel now needs CODEMAN_ALLOW_UNAUTHENTICATED_TUNNEL or --allow-unauthenticated-tunnel (carried by web -d and service install), and with no login the browser asks before every enable, reading a new loginConfigured field from GET /api/tunnel/status.
The guard is now decided once per request and required again where the tunnel starts, so a save that found the tunnel running can no longer restart it unguarded after a concurrent stop.
Closes#706
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.
Gate inspect, stage and submit behind the synced agentCoordinationEnabled
setting (default OFF, App Settings > Cross-session features, zh-CN
strings). While off, all three routes answer 403 FORBIDDEN naming the
setting, checked before session lookup; the CLI verbs print it verbatim.
Remember the attributed Codex rollout per session and re-verify only its
head on later calls, rescanning only date directories not older than it
for a /new conflict. The first walk reads 1 KiB prefixes first, so a
store of 2,100+ unrelated rollouts still attributes.
Answer unexpected inspection errors with 422 OPERATION_FAILED and log
the session id and error code only.
Read the guarded composer glyph and footer from the CLI registry: codex
workDetect.promptGlyph and a new workDetect.composerFooterLine
capability, compiled through compileVersionRegex. Codex footer effort
words are one shared list with modelDetect.screenLine.
Fix the wiki API reference link, frame the versioning policy entry as a
case of the experimental rule, join the CLAUDE.md Agent CLI paragraph,
and update the changeset, skill reference and architecture notes.
Opening another session in the case you are already working in meant re-picking the case and the mode in the toolbar. An opt-in + now sits with each tab's gear and close icons (App Settings, Tabs, New Session Button on Tabs: per device, off by default everywhere). It opens a menu of the CLIs that tab's case can start, each shown with its logo and name as in the Run menus, and a pick starts one session in that tab's case, or the managed worktree it runs in, and in its named group, without changing the Run button's mode or case.
The CLIs offered follow the Run menu's own rule for the case, so a Docker case lists what its container has rather than what the host has. A tab outside any named group sends no group, so the case's default session group places the new session the way it places a toolbar Run. Wherever a tab has a row menu (the vertical rail, the sidebar) that menu gains "New session here…", the keyboard route to the same picker, since Enter on the + itself does nothing. On a phone the + joins gear and close on the active tab only, and the label reserve grows to 68px while the setting is on, so the tab's centre stays off the icons.
The shared tab layout menu no longer closes when focus leaves an item for nowhere: Safari never focuses a clicked button, so pressing an item blurred the focused one with no related target and the click was lost. This is the tile count menu's rule, and it fixes the named-group menu as well.
Every keyboard open and close resized the PTY, and Claude Code's inline renderer answers each height change by clearing the screen and reprinting only the transcript tail that fits, so rows above that tail were lost from tmux for good. Measured on Claude Code 2.1.306 with tmux 3.2a: five keyboard cycles (62x38 to 62x15 and back) left 75 of 100 numbered lines in the pane's history; with the rows held the PTY stays 62x38, no SIGWINCH reaches the pane and all 100 remain (#672).
While the keyboard is up the rows captured at the show transition are held through getTerminalDimensions, columns still follow the box, and the screen, now taller than its box, is translated up by --kb-clip so the last content row sits at the bottom of the visible area. This is the one documented exception to the columns-only geometry rule: there the extra rows came from another device and nothing kept the composer in view, here they are this device's own rows held on purpose and the clip keeps the composer visible. The local-echo overlay's setRowLimit narrows the renderer's existing totalRows bound, so one place decides where a long draft stops growing downward.
Only inline renderers hold, through a new registry capability keyboardHold: 'inline' (Claude alone) published to the page as window.__codemanKeyboardHoldModes. Full-height layouts such as codex, Claude's fullscreen mode (mouse tracking on, unmeasured), and remote or docker panes resize as before. The hold is released on keyboard close, a shape change, a tab switch, a session update, a reconnect, or the setting turned off. Per-device setting Keep Size Under Keyboard, default on.
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>
Part 1 of #643 (local sessions only; remote follows as its own PR). An
opt-in, per-device header button opens a panel with the active session's
edits, newest first: every Edit/Write/MultiEdit/NotebookEdit of the main
agent and its subagents with its diff, plus images a Bash call rendered or
the agent sent. Remote, Docker and non-claude sessions answer `unsupported`.
- Reads only on request: `?sync=1` when the panel opens; while it is open on
that session it re-reads after an edit-capable `transcript:tool_end` or a
`transcript:complete` from the existing transcript watcher. No hook, timer,
second watcher or new SSE event; a wiring guard pins it.
- Main transcript: the path the transcript watcher follows (hook-reported),
else `<id>.jsonl` under the session's own CLAUDE_CONFIG_DIR override or
the server's config dir. A config dir set outside Codeman is found with
the next hook; until then the panel says so.
- Store: dataPath('edit-history')/<id>.json, 0600 via tmp+rename, capped at
500 entries and 4 MiB of diff text per session, deleted with the session,
blocked in isSensitivePath, never fed to /api/search. Every route goes
through findSessionOrFail with req.
- Images only through existing file surfaces: file-raw inside the
workspace, the attachment route with notify:false outside it.
- textContent rendering, bounded byte-offset reads, marker-class header
button, hidden on phones (locked in the mobile policy test).
Docs: Working-With-Files, Settings-Reference, architecture invariants, API
reference, CLAUDE.md key pattern.
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>
Conflicts in CLAUDE.md, README.md, docs/api-reference.md and
src/web/server.ts were additions beside #662's Copilot quota read and
#666's keep-warm sections; both sides kept.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Merge-time fix for #661. A restore that could not write one file (a full
disk, a directory where the file should be) used to stop there and answer a
bare 500, naming neither the files it had already put back nor the
pre-restore copy, and the Settings form was not re-read, so the next Save
wrote the old settings back over a restored settings.json.
restoreConfigBackup now writes every verified file it can, then throws
ConfigBackupPartialRestoreError with restored, failed (name and error),
untouched and safetySnapshot. The route runs the same reload hooks and audit
for the files written as a full restore does, and answers 500 with the error
envelope plus those fields (and restartRequired) in data, as the tab-layout
409 carries its layout. Settings refills the form when settings.json is among
the restored files, also on that path. Tests: a unit case where a later file
is still restored, the clis.json-as-a-directory route case, and two vm cases
for the Settings handler.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Review round 3 on #661: retention aged each snapshot by its own createdAt, so the first change after a quiet month deleted the last good copy; it now ages from when the next snapshot was made. users.json lastLoginAt, settings.json lastUsedCase and intents.json recentPrompts/updatedAt are volatile keys for the change check. The keep count has a minimum of 2. Wiki restore paragraph aligned with RESTART_REQUIRED.
Review round 2 on #661: the hostname in the origin orphaned every snapshot when a Docker container was recreated, so the origin is a random id kept in <data dir>/config-backup-id; after restoring settings.json the Settings form is re-read from /api/settings so Save cannot write the old values back; the restore confirm names the files and the credential ones; clis.json is reloaded (reloadCliRegistry) and users.json needs no restart; API reference and route docs corrected.
Review round on #661: webhook.json and intents.json are redacted in compare and URL values lose userinfo/query; a custom folder is probed (bounded, pastCap) before each pass and in each route and only created when its parent exists; manifests record an origin and change check, prune, list, restore and diff are scoped to it; a restore reloads IntentStore, lists untouched files and treats settings.json as restart-required; remote-cases.json is tracked; stale .tmp-cfg-* folders are swept and a failed restore unlinks its temp; the group is hidden from non-admins; an empty days field saves 30.
Settings -> System -> Config backups gains a Compare view: a backup against the
running config, a backup against the one before it, or any two backups. Each
differing file lists its changed keys as before/after, plus files that appeared
or vanished. GET /api/config-backups/diff?from=&to= serves it (`to` defaults to
`current`; admin only in multi-user mode).
Credential values are never returned: .env, users.json and push-keys.json report
names only, and any other key that looks like a token, secret, password,
credential or key is reported as changed without its value. A non-JSON file
reports only that it differs, a file is cut at 200 changes, and a self-refreshed
discovery timestamp does not count as a difference.
The files that hold a user's customization (settings.json, clis.json, custom-model-hosts.json,
webhook.json, intents.json, linked-cases.json, push-keys.json, users.json, .env) are plain JSON
in the data dir, rewritten by the server, the Settings UI and the CLI, with no copy to go back to.
A snapshot is taken at startup and whenever the tracked files' content changes (checked every
five minutes, and only written when a digest of the file set differs from the latest snapshot's),
into `<data dir>/backups/config` by default or any absolute folder. Retention keeps the newest
configBackupKeepCount (1-500) and, when configBackupKeepDays > 0, drops older ones; it only ever
deletes folders it made (name pattern and a parseable manifest) and never the newest.
GET/POST /api/config-backups list and back up now; POST .../:id/restore verifies every file against
the manifest's SHA-256, takes a pre-restore snapshot, then replaces files atomically with mode
0600, writing only allowlisted names. Snapshots are 0700 folders of 0600 files and all routes are
admin only in multi-user mode. Settings -> System gets the controls and a Restore list.
Only a human spends an idle alert, but the keep-alive turn resolved an unseen one three ways: its working transition, its stop hook, and its own idle prompt replacing the item with a pre-acknowledged one. While the turn runs, a pending idle item is now left exactly as found, the page's stop handler returns on the keep-alive reason before clearing hooks or raising Response Complete, and session:working/session:idle carry keepAlive so the stuck-detection timer neither restarts nor re-arms.
The window that marks the turn closes on its own idle prompt or any other submit instead of a fixed three minutes, which a slow turn's idle prompt (sent a minute after the turn ends) could outlast. The service keeps the default and cap in memory, read through a strict reader so a mid-write read is retried rather than kept, and the cap is clamped before the strict settings save.
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.
- A closing notice card stays in the DOM for its 200 ms fade, and its
link and "See what's new" buttons still worked there: a double click
opened the notice twice. close() now makes the card inert and every
button handler does nothing once it is closing.
- Notice links (and the combined card's "See what's new") open with
noopener,noreferrer. noopener alone still sent this instance's origin,
which can be a tailnet name or a tunnel URL, as the Referer. The plain
update toast is unchanged.
- The https rule is checked again at the button
(CodemanSecurityNotices.urlOk): a caller handing showSecurityNotice or
showUpdateNotice an unchecked URL gets no link button.
- A detached session window (/session/:id) is rendered without
__codemanCliAvailable, so it could never select the OpenCode notice,
yet it took the update toast and recorded the version, and the
dashboard then showed the notice as a separate card. While any notice
is pending, a solo window now shows and records nothing and leaves
both to the dashboard; with none pending it shows the plain toast as
before.
- The wiring tests pin the page's own clock (JSDOM gives the window its
own Date). On the real clock 18 of them would have failed on every push
from 2027-01-01, when the fixture notice expires. New tests pin the
once-only close directly (the old double-click comment claimed more
than it checked), the single open, the sink check, the solo windows,
the scroll cap and the light-skin ink.
- CLAUDE.md now says the public .json files are served no-cache, the
exception to the year-long immutable cache.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A hand-maintained src/web/public/security-notices.json carries warnings
about things outside Codeman that its users should act on. The first:
OpenCode's report of unauthorized access to its legacy Console, which
may have exposed provider API keys saved there.
- Pure core in constants.js (CodemanSecurityNotices): select() keeps the
notices that apply now (inclusive local-day dates, not yet seen, https
links, malformed entries skipped), and one naming a CLI only when
window.__codemanCliAvailable[cli] === true. Unknown means not
installed: a warning about software you do not have is noise. The CLI
id is data in the JSON; no code branches on it. plan() decides the
surface, so a load shows each notice once.
- An existing install on a new version gets the notice INSIDE the
release's update toast: the highlights as before, a warning section,
and the notice's link next to "See what's new". With no notice the
update toast is the plain one it always was.
- Everyone else (a fresh install, a same-version reload) gets its own
card in the toast stack: shield, "Security notice" eyebrow, title,
message, the link, Dismiss and the ×; amber-to-red accent bar, theme
tokens only (dark and light skins), full width on phones, an
opacity/transform entrance and none under prefers-reduced-motion,
role=alert.
- A notice is recorded as seen only when the user closes it, dismisses it
or follows its link, never when it appears. Storage blocked shows
nothing. The notice's own text is textContent and carries its own
zh-CN, so i18n.js leaves it alone; the card's own copy translates.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Codeman maintainer