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>
- test/cli-agent-project-spawn.test.ts:345: the doc-sync test no longer reads .changeset/project-worker-directories.md (changeset version deletes it at release); README, API reference and wiki stay.
- CLAUDE.md:132 + src/cli-agent.ts @fileoverview (invariant 5): the directory spawn (POST /api/v1/sessions plus /interactive or /shell, no Agent-Origin header, so no marker) and its refusals (empty --working-dir, bare spawn from a HOME cwd); the invariants now name test/cli-agent-project-spawn.test.ts too.
- test/cli-agent-project-spawn.test.ts:322: "allows a cwd below HOME" mocks the cwd to <temp HOME>/src/app, so it covers the case the guard must leave alone.
- docs/wiki/Driving-Codeman-From-An-Agent.md:59: split the sentence so exit 4 covers only the empty --working-dir; spawn "" reaches quick-start and exits 1.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
`codeman agent spawn` always sends its directory as an explicit
workingDir, so the server cannot apply its no-workingDir rule and
installs workspace hooks (and an injected skill) into ~/.claude when the
caller's cwd is HOME. A bare spawn whose cwd resolves to the home
directory now refuses with exit 4 before any request and names
`--working-dir ~`; an explicit `--working-dir ~` is still sent. Paths
are compared by realpath, so a symlinked HOME matches, and an
unresolvable HOME or cwd falls back to the resolved path without
throwing.
The directory-spawn --json shape now reads the same in the README, the
API reference, the wiki page and the changeset: `ready` when a
readiness wait ran, `readinessError` when that call failed, and
`startupError` when the start failed. A test pins all four.
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.
Codex's local_thread_store_compression rewrites cold rollouts to
*.jsonl.zst, which the store scan skipped without a trace. Each one is now
counted in compressedFiles (complete: false), skipped only when its plain
.jsonl sibling exists, as Codex's own discovery does, and a lookup that
misses names the compressed file whose name carries the wanted id. A
Zstandard file given to --file, or sitting in the store under a .jsonl
name, is recognised by its magic number.
Each selected rollout is parsed once into every view later needed of it,
so a legacy copy's boundary proof reuses the parent's own read instead of
charging it to --scan-bytes a second time (and counting its malformed or
inherited records twice).
A parent read that fails for any reason other than a budget now leaves
the boundary unproven (cut at the last candidate, unverifiedPrefixes,
complete: false) instead of failing a child whose own file is intact. A
budget error still fails the read.
--max-bytes is validated before the first file is read, next to the
other budgets, and every budget flag accepts plain decimal integers only.
`codeman agent spawn --working-dir "$WT"` with WT empty (a failed
`git worktree add`, say) resolved '' to the caller's cwd and started an
editing worker in the caller's own checkout. An empty or
whitespace-only --working-dir now refuses with exit 4 before any
request.
The emitJson comment names the directory-spawn exception to "the
envelope's data": `{ sessionId, workingDir, created: true, ready }`.
Tests: unit (`''`, spaces, tab: exit 4, no calls) and through the real
argument parser and HTTP transport (nothing sent, exit 4).
Docs: README, api-reference, wiki, SKILL.md (plugin mirror synced) and
the changeset note the refusal.
Replace docs/offline-history.md, which repeated the skill reference and was
linked from nowhere, with a README section and a wiki section beside the
codeman agent commands. Bring the skill reference, its plugin mirror, the
Codeman Skill wiki page and the changeset in line with the reader: forks,
the separate budgets and their flags, UTC dates, phases and complete:false.
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.
`codeman agent spawn ""` (for example `spawn "$CASE"` with CASE unset)
used to launch a worker in the caller's cwd. Both case checks now test
`caseName !== undefined`, so an empty name reaches quick-start and is
refused by its schema as before.
Drop the `{ id }` fallback on the create answer: `POST /api/sessions`
answers `{ session: { id } }`, and the test fakes now use that shape.
Tests: an empty case name (unit and through the real argument parser
and HTTP transport), the claude `--ready` order create, /interactive,
wait-output on the created id, and a non-JSON failed start (id alone on
stdout, reason on stderr, exit 1).
Docs: the spawn mapping and directory-launch JSON shape in
docs/api-reference.md, the README and wiki `codeman agent` sections, the
cli-agent @fileoverview and the skill reference tables; reflow the new
SKILL.md paragraph (plugin mirror synced); the changeset notes the
local exit-4 refusal of an unknown mode for named cases.
Boot prune keeps the inboxes of sessions on the reboot-restore offer (their records are already pruned and a rebuild reuses the id), with a case in test/agent-inbox-server-wiring.test.ts.
docs/wiki: post, inbox and ack in the codeman agent command block of Driving-Codeman-From-An-Agent, and "Keep agent inbox across restarts" in Settings-Reference.
codeman agent inbox prints message text through terminalSafeText (ANSI stripped, other C0, DEL and C1 controls shown as \xHH); --json stays as stored.
Shutdown flushes the inbox snapshot again after app.close(), for a post that lands after the first flush.
POST /api/cleanup-state drops the inboxes of the records it removes.
InboxPostSchema derives its fence from MAX_MESSAGE_BYTES instead of the literal.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The first commit left the old rule standing in places: the gotchas list in
extending-codeman.md still said newlines were stripped and that
"echo A\necho B\r" ran `echo Aecho B`, and so did both READMEs and the
skill's big-input section. Those now describe the paste.
Newlines are only kept on the mux path, so the docs that describe the paste
say "with useMux": without it a multi-line body is not a plain prompt and is
written straight into the pane.
Cron keeps rejecting multi-line prompts, but its docs and the code comments
in cron-service.ts, schemas.ts and respawn-controller.ts gave a reason this
change removes (writeViaMux joining lines, a newline submitting in Ink). The
reason that remains is the submit check, which cannot recognise a
multi-line paste in the composer, and for cron's paste mode the newlines
reaching the CLI as keys.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
TmuxManager.sendInput() removed every `\n` before the text reached tmux, so a
multi-line prompt sent with `useMux` (or a multi-line respawn prompt) arrived as
one line with its lines run together: `"echo A\necho B\r"` ran `echo Aecho B`.
The text half of a submit has gone in as one bracketed paste
(buildPasteTextCommands) since the Codex paste-burst fix, and inside the paste
markers Claude Code and Codex insert a pasted line break into the composer
instead of submitting. So the `\n` is now kept (`\r\n` loses only its `\r`) and
the existing paste carries the lines; the Enter stays a separate tmux call.
Multi-line text without an Enter is pasted too rather than typed with
`send-keys -l`, where every line break would reach the pane as a key.
Single-line input is unchanged.
The test-mode gate moves from the top of sendInput() into inputRunner(), as
readPaneRows() does, so a test subclass can record the commands sendInput()
would run instead of pinning the branch shapes on the source.
SubmitVerifier still compares the composer's last glyph line with the prompt
minus its newlines, so it does not reliably recognise a multi-line paste and
may not re-press an Enter that Claude Code ignored. `agent send` and the TUI
therefore keep refusing or joining multi-line input; the docs that described
the stripping now describe the paste and that limit.
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>
The skill only had a section inside "Driving Codeman From An Agent". It now
has its own page, docs/wiki/Codeman-Skill.md, built around three real runs:
- five Claude Code workers powering on in the tile grid (2026-10-15)
- eight worker tabs with lineage lines back to the lead (2026-10-15)
- a DeepSeek Harness worker and a Claude Code worker from one prompt
(2026-10-10)
plus every install route, prompts that work as written, a run start to
finish, which workers it can drive, what it will and will not do on its
own, the Codex notes and what is in the skill. The page says that the grid
recording put each worker on the grid as it started, since sessions an
agent starts do not join the grid by themselves.
The agent page keeps a short skill section (the heading anchor stays) and
links to the new page; the sidebar, Home, FAQ and Settings Reference link
to it too. The FAQ answer no longer says the skill is enabled per case only.
docs/media-assets.md records the new embeds.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The dialog's own prompt glyph armed idle confirmation and the quiet dialog passed it, so a fresh case reported idle about 4 s in. An agent that waited for idle and then prompted typed into the dialog, and its Enter confirmed No, exit and killed the pane.
Document what the two previous commits changed for users and for whoever
adds the field to another CLI:
- docs/cli-registry.md: the `blockedLine`/`blockedLines` fields, how codex's
pattern was measured, and the three rules any declaring CLI keeps (end on
chrome only the CLI draws, alert only; raise on one reading, clear on two;
hooks win).
- docs/architecture-invariants.md: a "Screen-read blocked dialogs (codex)"
entry, plus the wait-signal, idle-detection, watching and Approvals Inbox
entries it changes.
- docs/api-reference.md, docs/extending-codeman.md and the wiki (Agent CLIs,
Notifications and Approvals, Hooks, HTTP API, Driving Codeman From An
Agent): `blocked` now fires for codex, `stop` still does not, codex
approvals are alert-only cards answered in the terminal.
- CLAUDE.md: `stop` and `blocked` are no longer one rule, the config-regex
list gains `blockedLine`, and a short pointer that a codex dialog match is
only ever an alert.
- The codeman skill's signal table and verbs note, mirrored into
plugins/codeman by scripts/sync-plugin.mjs.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Codex starts stdio MCP servers with a minimal environment, so `codeman mcp`
under the documented Codex config never learned the session it runs in: the
self-protection and the children rule did not apply. Both Codex TOML snippets
now forward the two variables with `env_vars`.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Agents pick tools from MCP clients and registries, and Codeman had no MCP
surface: an assistant in Claude Desktop, Cursor, Codex or Gemini CLI could
not start or drive Codeman sessions without hand-written HTTP calls.
`codeman mcp` is a stdio MCP server and a CLIENT of the existing HTTP API
(it reuses codeman agent's transport and guards; no new route). Seven
tools: list_sessions, start_session, send_prompt, wait_for_session,
read_output, interrupt_session, delete_session.
- Dual-era: answers the legacy initialize handshake (2024-11-05 to
2025-11-25) and the 2026-07-28 revision (per-request _meta,
server/discover, resultType, and the ttlMs/cacheScope hints a modern
tools/list must carry: Claude Code 2.1.296 drops every tool without
them).
- Never guesses a server: the URL comes from --url or CODEMAN_API_URL.
Unconfigured, it still lists its tools and every call says how to
configure it.
- Prompting, interrupting and deleting are limited to sessions the process
started (or, inside a Codeman pane, that session's own workers) unless
--allow-any-session; never its own session. Control bytes are refused
before any request.
- Waits default to 45 s (Codex's MCP tool timeout is 60 s), max 600 s.
- read_output returns text only: a client that prefers structuredContent
otherwise showed the model metadata instead of the output.
- config/mcp-registry/server.json and package.json mcpName prepare the
official MCP registry listing; sync-plugin.mjs keeps its version.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The agent skill only reached Claude Code: injection wrote
.claude/skills/codeman, which no other CLI reads, and the per-session
preamble was seeded for claude alone. A Codex, Gemini, OpenCode,
Antigravity, Grok, DeepSeek or OMP session inside Codeman never learned it
could start and drive workers.
- Registry field capabilities.agentSkillDir (a closed enum, since
clis.json can set it and it decides where the server writes) names the
skills directory each CLI scans. Claude keeps .claude/skills; those seven
CLIs get the same skill in <case>/.agents/skills/codeman (each measured to
scan it; Claude Code does not, so it never sees two copies). pi gets none:
a project skill makes pi ask "Trust project folder?" at startup.
- The preamble is seeded for every local session whose CLI takes the
skill; nothing in it is claude-specific.
- The skill text is CLI-neutral and names the two CLI-side failures to
report instead of retrying: a sandbox that blocks loopback (Codex's
default), and commands that do not carry this session's environment
(Codex 0.162 runs them in a shared app-server daemon).
- POST /api/sessions injects after the launch pre-flight, so a CLI that
cannot start leaves nothing in the workspace.
- codeman skill install gains --mode; uninstall --case removes the copy
from every directory the registry can write.
- The settings toggle moves to Agents & CLIs > All agent CLIs.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
From the review of #557:
- An id shorter than 8 characters refuses with exit 4 before any request,
on every verb. `rm 9` resolved to whichever session was alone with that
first character (the user's own tab included) and deleted it. Same floor
as the server's PARENT_SESSION_ID_MIN_PREFIX. `rm` no longer claims a
lineage check: "Delete any session except this one".
- `wait --match` help and the README example say the marker must not appear
verbatim in the prompt (its echo matches at once) and show the split form.
- `send` reads the route's wake-on-LAN answers: `buffered` gets its own
line (exit 0), `dropped` exits 1 instead of printing "accepted".
- `--` for a prompt that starts with "-", in the `send` description and in
the one-argument refusal.
- `stripAnsi` builds on the shared one (OSC sequences go too); the
inputRefusal JSDoc sits above inputRefusal again.
- docs/wiki/Driving-Codeman-From-An-Agent.md gets a `codeman agent` section.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Lineage lines used to draw one glowing dashed bezier per parent/child pair,
hanging below the tab strip, for every family at once. With a parent on row 3
of a wrapped strip and ten children below it, the curves crossed every lower
row's tab names and ran through the terminal text.
- One rounded orthogonal tree per spawning tab: every route starts at the
parent, so siblings share a trunk. 1.5px, solid, 1px dark outline; only a
working child's branch is dashed.
- Routes run only through the gaps between tab rows, joined by a spine left of
every row (computeLineageTree/computeLineageRows in constants.js), so they
never cross a tab or reach the terminal. The vertical rail gets the same tree
on its existing left track.
- Only the selected tab's family is drawn (what it spawned, plus its parent and
siblings). Selection redraws, and the strip's size transitionend redraws once
more, since the active tab widens for ~150ms after the selection redraw.
- The routing room is reserved by .session-tabs.lineage-tree, keyed on whether
any lineage exists, never on the selection, so a tab switch never resizes the
header or the PTY.
- Colours stay per spawning tab, now claimed in strip order for every family so
selection order never decides who gets the skin blue.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The wiki was written for seven run modes and never received Grok Build, DeepSeek
Harness or OMP. They now appear everywhere the others do: the modes table and
per-CLI notes, install commands, environment prefixes, the Quick Start table, the
requirements rows, the vocabulary, and every "seven modes" count.
The 1.27 to 1.29.0 changes land on the pages that own them: attaching a case to an
existing container, multi-case adoption and the copy-a-case picker (Docker Cases);
file reads over ssh in remote cases and what stays unavailable (Remote SSH Sessions,
Working With Files, Security); single-page app routing, frame recovery, localhost
links as tabs and the egress guard (Web Tabs); DeepSeek as the one non-Claude mode
with real stop/blocked signals and Approvals items, Codex's own work detection,
last-response, the model-endpoint routes and refreshed counts (HTTP API, Driving
From An Agent, Hooks, Notifications, Keeping Agents Running, Core Concepts);
Shift+drag, right-click copy, Auto Copy, the Ctrl+Z guard, font weight, the vertical
rail and its activity sort (Keyboard Shortcuts, Input And Voice, The Dashboard,
Settings Reference); the 600px phone cutoff, Codex shift arrows and iPhone Duo
(Mobile Guide); the Docker Compose route and its update rule (Installation, Running
As A Service); four new symptom entries and a "which CLIs" question (Troubleshooting,
FAQ).
Custom model endpoints are deliberately left to #430, which adds that page and edits
Agent CLIs, Settings Reference and the sidebar; these edits stay out of the regions
#430, #428 and #376 touch, and all three still merge cleanly on top.
Both READMEs: the web-tab menu entry is labelled "Add URL" in the UI, not
"Add dashboard".
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Measured with both installed: a fresh Claude Code lists `codeman` (the
user-level or per-case copy) and `codeman:codeman` (the plugin). Neither
shadows the other and both work, so this is noise rather than breakage, but
the README, the wiki and the plugin README now say to choose one.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
`.claude-plugin/marketplace.json` at the repo root makes
`/plugin marketplace add Ark0N/Codeman` work, and the one plugin it lists is
the repo itself (`source: "./"`), whose one component is `skills/codeman/`.
So `/plugin install codeman@codeman` is a third install route next to
`npx skills add` and `codeman skill install`, and the skill shows up in the
plugin directories that index Claude Code marketplaces.
Both manifests carry package.json's version: `scripts/sync-plugin-version.mjs`
rewrites them inside `version-packages`, right after `changeset version`, and
`test/plugin-manifest.test.ts` pins the equality, the skill's frontmatter name
(without it the installed skill would be named after a versioned cache dir),
and that no other plugin component (`commands/`, `agents/`, `hooks/`,
`.mcp.json`, `settings.json`) appears at the repo root, since an install would
silently ship it.
Verified with `claude plugin validate` (one expected warning: CLAUDE.md at a
plugin root is not plugin context) and a local marketplace add, install,
details, uninstall cycle against a clean checkout of this commit.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
30 pages covering install, concepts, the dashboard, the agent CLIs, unattended
runs, remote and Docker cases, security and the HTTP API, plus a sidebar and a
footer. The wiki repo has no CI and no review, so docs/wiki is the source of
truth and .github/workflows/wiki-sync.yml mirrors it on every push to master.
The workflow refuses to mirror when docs/wiki is missing or holds no pages,
because it deletes before it copies and would otherwise publish the deletion of
every page. The footer carries a {{VERSION}} placeholder stamped at publish
time rather than a hand-written version, which went stale on every release.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Codeman maintainer