Copilot's registry entry takes no agent skill, like Pi and a plain shell, but
the changeset, the App Settings help text, the Settings Reference and
CLAUDE.md named only Pi (and the shell). The Agent CLIs wiki page still said
no CLI but Claude gets the bundled skill; every CLI except Pi and Copilot
gets it, in `.agents/skills/`.
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>
Conflicts resolved as on test/desktop-macbook: config/test-suites.ts keeps both browser tests (desktop-connect-page and local-model-ui), and the CLAUDE.md state-files line keeps #778's cli-installed entry with the local model's local-model.json and local-model/ entries.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The owner's verdict on the chooser: nice, but not nice enough, too much just
blue. He also wants "Run a local model" on top of the start screen, above
Run Claude Code.
The memory bar is now a map: the model, its context and the brief peaks side
by side on the track of what this Mac can give a model, each with its size in
a legend, and the verdict on the fit beside the figure. recommend() sends what
the need is made of as `Candidate.memory`.
Colour now carries meaning: green for good and tested, amber for tight, orange
for slow, teal for the context. Violet is the feature's own colour, on its
start screen button and its main action. Every row has a size tile and a speed
gauge scaled to the fastest row in the list. The light skins get deeper values
of the same colours, and the window is 40 px taller to hold it without
scrolling.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The window is one frame for the whole flow: a fixed height on desktop, App
Settings' boxed close button, the buttons in a foot of their own outside
the part that scrolls, so a click never moves the next button away and
nothing is cut off; the short screens are centred in it on desktop and sit
above the buttons on a phone.
The chooser lists the pick first and then the other models by download
size, largest first, a column the reader can see. A pick that only just
fits says "Best fit, tight". The memory figure is an estimate and says so
once, in whole GB; its legend names the peak, and the installed line uses
the same words beside what the model takes now, so the two figures are not
read as a contradiction. The legend, the column headers and the foot's
promise are set in --text-dim, the bar's track in --text-muted so its free
part can be seen, and only the download figure keeps tabular figures.
The consent screen is the download as a table: the chosen row, the runtime,
the coding agent with its installer's command as the row's second line, the
total in the strong weight, then where it goes in one line. The download bar
means the model download alone and is gone once the model is in; the screen
that ends an install shows "Start a session" alone; an error on an installed
model is the headline with a grey dot; an error's first sentence is the
headline; Remove is quiet everywhere but red in its own question. The
no-recommendation reasons are one sentence each, and the untested note is
in Codeman's voice. A refusal the server names is printed from its sentence.
Co-Authored-By: Claude Fable 5.1 <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 owner asked for it to go for the next release. The button, its two
style rules and its translation entry are removed; nothing else changes.
The Ralph wizard itself stays in the code, but this button was its only
entry point, so the wizard can no longer be opened from the interface.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Review fixes for the read-only recommendation and its card.
Recommendation (pure):
- `limited` is now a statement about the Mac: no model with 12 billion
parameters or more fits. It is judged on everything that fits, before
the disk filter and whatever the pick is. A 32 or 36 GB Mac whose pick
is a 9B model no longer reads "This Mac can run a small model" above a
list of 20B, 27B and 35B models, and knowing the chip no longer lowers
the verdict. A small pick under `ok` carries a note that says so.
- A model that fits the memory but has no room on the disk is no longer
dropped in silence: the best-ranked one is named in a note with the GB
that are missing. A full disk cannot turn a 48 GB Mac into a
small-model Mac.
- "Models fit, but not at a context a harness needs" has its own
sentence with the budget and the need, worded as an estimate. The
16 GB Mac mini misses by 1.3 points (10.3 of 10.4 GB) and was told
flatly that its memory is too little, the sentence of an 8 GB Mac.
- The installed memory is named by the size the Mac is sold as (48, not
51.5): the hardware line and the memory sentence. Every computed size
stays decimal GB from the one formatter. An unknown memory size is no
longer reported as "0.0 GB".
- Slow is graded on the unrounded speed: 9.95 to 9.9996 tokens per
second printed as 10 and read ok.
- The disk sentence names the 10 GiB that must stay free, so its
numbers add up for the reader.
Card and Settings group:
- The Settings group "Model on this Mac" is hidden on a server that is
not a Mac, and until the first answer says it is one.
- Only `403 FORBIDDEN` is a refusal. `403 PASSWORD_CHANGE_REQUIRED`
(an admin who must change the password) is a failed request and is
asked again, so that admin no longer loses the card until a reload.
- Each fit and speed label carries what it measures as its tooltip and
accessible name, an alternative with a speed estimate prints it, and
the count beside "Other models that fit" is gone (it was the number
of rows, capped at four, not the number of models that fit).
- The line saying nothing can be set up yet sits right under the pick,
in the colour of every other line (it was 3.9:1), and says whose step
it is.
- The dismissal key is named for this stage, so hiding the read-only
card does not hide the install offer later.
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>
The contract three builders code against in parallel. Nothing is recommended
yet: the route answers 501 and the catalogue is empty.
- src/types/local-model.ts: HardwareFacts, the catalogue rows, HarnessFact,
Candidate, Recommendation, LocalModelStatus, and LOCAL_MODEL_LABELS, the one
list of sentences the server may put into the payload (the zh-CN dictionary
is keyed by them).
- src/local-model/format.ts: formatGb, the one place a byte count becomes a
size a person reads (decimal GB), and memClassGb.
- src/config/local-model-catalog.ts: the Zod schema (model ids are name:tag,
lowercase, no slash) and an empty stock catalogue. No override file.
- Skeletons with their final signatures: hardware.ts, recommend.ts,
harness-facts.ts, routes/local-model-routes.ts (injectable dependencies),
public/local-model-ui.js with its script tag.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
The button sat empty in the page while its strip was hidden, which the
mobile accessibility suite counts as a button with no name.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The attach line now takes the rule #770 gave remote and docker launches: bashCArg() single-quotes it at both respawn-pane sites, so it reaches bash verbatim. quoteAdoptLaunch is retired, since its double quotes kept the same $ and backtick safety but lost a real newline. #510's no-cd condition stays.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The setting told users the sandbox and approvals stay on. With it on, a
command in Codex's sandbox can call Codeman's API, which can start a session
outside the sandbox with no approval prompt. Measured on codex 0.162.0 with
`codex sandbox`: a touch the sandbox refused landed through POST /api/sessions,
and from inside a Codeman pane it landed with a password set too, because a
pane inherits CODEMAN_PASSWORD. Without that password the same call gets 401.
The settings row, the wiki, the skill and the changeset now say so, the wiki
Security page and security-architecture name it, and the docs scope the claims
to what the code does: app-wide, local launches only, not cron jobs, and
--no-daemon is a local launch's flag. Agent-CLIs gains the --no-daemon
trade-off. A test pins that no surface sells the sandbox as still in charge.
Text only: the switch, the clamp and the launch are unchanged.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The owner's answer to the PR's open question: the switch does not also pass
--sandbox workspace-write. Settings, wiki, skill and release note now state
the consequence: a folder Codex runs read-only keeps the network closed and
asks per command. A golden test pins the decision by name, and the stale
launch-defaults comments now name networkAccess.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Brings the 1.33.2 based adoption feature up to master. Conflicts were
resolved by keeping master's intent and re-applying the feature on top:
both sides kept for imports, the script tag and the stylesheet blocks; the
trust-dialog guard keeps master's stopped check plus the adopted refusal;
the Ralph and image watchers keep master's remote branch plus the adopted
skip; the close confirmation keeps master's worktree option plus the
adopted wording.
Co-Authored-By: Claude Opus 5.5 <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>
Claude Code's EnterWorktree moves the running process into
<repo>/.claude/worktrees/<name>, while Session.workingDir stays on the main
checkout. The Files panel kept walking workingDir, so it listed a tree the
agent had left.
paneCwd already follows the move, measured on Claude Code 2.1.318 in both
directions, so nothing new has to track the agent. It also follows every cd
in a shell, so a new SessionState.liveWorktree narrows it to a linked
worktree, read from the .git file without starting git.
Only a folder strictly below workingDir is ever an answer, and the listing
only starts there: returned paths stay relative to workingDir, so the
preview, raw and edit routes are unchanged and confinement does not widen.
A worktree outside the session folder stays unfollowed.
The panel asks with root=live, shows a strip naming the worktree with a
switch to the session folder, and follows the agent in and out while open.
Co-Authored-By: Claude Opus 5.5 <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>
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>
Review round on PR #757. The route turns EVERY upstream failure into
isLlamaSwap: false, so the old line silently promised an unreachable
endpoint was merely mute, and the live-session check missed a null pid
(the PTY exited, the same test keep-warm applies).
- Require pid !== null in _getCustomModelInUseBySession, pinned by a
'process exited' case in the marks-nothing table
- Reword #customModelPickUnknown to claim only that nothing was
reported, true for a down endpoint too; drop the 'stays quiet for a
failed probe' promise from changeset, docs and comments
- architecture-invariants: add the In-use tier, both pin fences
(customModel not displayModel; stopped/null-pid/paneExit never
count) and the unknown-line rule
- Mirror the wording through i18n (key + zh-CN), index.html fixture,
styles.css comment, and the run-menu tests
Only llama-swap answers what is loaded, so behind a gateway such as Bifrost
nothing was marked and the picker fell back to discovery order apart from the
one CLI that had launched there before. A live session whose own injected
endpoint is that host now promotes its model as "In use by a session", under
its own tag and below llama-swap's "Currently loaded" answer, reading only
what Codeman injected rather than terminal text, and never a stopped session.
When genuinely nothing is known the picker says so instead of leaving an
unmarked wall, and stays quiet for an endpoint that merely failed to answer.
- opencode: write limit.context/output from the discovered context length (#749)
- codex: override the native launch model when a custom endpoint is selected (#750), and set model_context_window
- model picker: add a search/filter box with a no-matches line
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>
git's refusal quotes the destination, so a folder named openssl or rustls
classified as HOST_UNREACHABLE and the cleanup emptied it. The cleanup now
tests git's own text, DESTINATION_EXISTS is matched first, and ssl/tls are
matched as words. Also: a test for the Docker refusal on the default branch,
the route JSDoc and constant comment, and the folder copy (empty, or new).
The custom folder was treated as a parent, so the repository landed in <folder>/<case name>. The chosen folder is now the clone destination: an empty existing folder is cloned into directly (CloneOptions.intoEmptyDir, no temporary sibling, never removed on failure), a new folder is created, and a folder with files is refused.
Clone Repo could only clone under ~/codeman-cases. POST /api/cases/clone now takes an optional path (parent folder plus case name) and the Clone tab gets a Clone into a custom folder option with a Browse button, mirroring Create in a custom folder. The path is judged by prepareNewCasePath, the clone is registered as a linked case, the option is admin-only in multi-user mode, and an existing target folder is refused.
- a lone digit reply is typed without Enter while the tab has a pending permission or question
- the gateway starts after restoreMuxSessions (hold and release), so a reply during restore is not told the tab is gone
- discord-notify resolves an id prefix only among sessions the caller may see
- restore docs/architecture-invariants.md from base and add only the Discord section
- docs: self-ignoring folder, no logging, Notifications group, Send test, local-tab-only Claude hint, typedHint wording
- discord-notify: per-session token bucket (6 a minute), 429 RATE_LIMITED, plain line from codeman notify
- fileProblem probes the working folder with the bounded probe before realpath
- sendTest uses its own DiscordApi and leaves this.cfg alone
- drop the resumed-tab check from the typed hint (only Claude's field was read)
- first sessionRenamed per session records the name without a PATCH
- boot goes through ensureLoaded, so one gateway starts
- a thread created without an id reports the failure
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.
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>
`execFile` signals the `git` parent only, so a fetch that times out can leave its http helper
still running, and on the interval that repeats every run with nobody watching. `runFetch` now
spawns `detached`, so the fetch and the helper it spawns share one process group, and the kill
is SIGTERM to the negative pid then SIGKILL `FETCH_KILL_ESCALATION_MS` later; the escalation is
not cancelled when the promise settles, because the caller is answered at the timeout while the
group is still dying. The output cap is kept, and the clone's slot queue is not needed here.
The tick is two passes: every enabled local session is collected by folder, a folder is due when
ANY session open on it is due, the folder is probed once for the group, and the run is published
to every session on it. A single pass decided by the order the sessions were read, so [long,
short] published only the short one and the 3600 s session's row never updated again while its
folder was fetched every 30 s.
`gitNonInteractiveEnv` writes BatchMode ssh as a default, not an override: `core.sshCommand` is
read inside the same slot and the same bound as the fetch it serves, and `fetchEnvFor` keeps the
repository's answer when it has one, because that is usually the setup that works on a machine
with several ssh setups. The `accept-new` host key it can write is stated next to the BatchMode
note: a prompt is stopped, a write is not.
The write claim is scoped to the Git panel and to the timer, with cloning and worktree management
named as the writes that happen when the user asked for them, and the zh keys sit with the group
of the UI surface their English string belongs to.
Tests: the process-group test proves the tree by group membership, because the helper is a
grandchild (`git fetch` runs `git remote-http`, which spawns `git-remote-http`) and because the
group is what the negative pid reaches, and it remembers each process once found instead of
re-scanning a group it had already emptied. The non-zero-exit test changed premises: `git fetch
--quiet` in a repository with no remote exits 0 on git 2.47.3, so resolving empty stdout there was
correct, and the case that has to reject is a remote pointing at a path that is not a repository.
The join test asserts after the run and does not await the request before the held run is
released, which would wait on the run the test is holding.
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.