The opencode readiness and marker measurements were made on Linux, not
on a Mac, and the docs now say so. A worker whose pane ends after it
wrote its answer file but before the marker matched answers 3 with no
answer: the rc 3 row now says the file may still be in its folder. The
example's input folder is named input, so the prompt reads cleanly.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Measured on opencode 1.3.0 in a private tmux socket, with a fake
OpenAI-compatible endpoint streaming the reply a character or two at a
time: the marker was on the screen, but the stripped client stream read
D, spinner, O, spinner, N, ... because opencode redraws its spinner
between the streamed pieces, so wait-output never matched it. sendmark
then waited its whole timeout and answered 2 for a reply that had
finished, with the answer file already written (opencode's write tool
wrote it without asking).
The marker wait now runs in rounds of at most 10 s, and between rounds
the answer file is a way out too: a non-empty regular file whose
checksum held still for one round is read, with matched false. The
marker stays the fast path. The answer-file wait after a marker no
longer spins when the exit wait gets no answer, and treats an ended
wait as the worker gone.
The same run measured the readiness mark: with a fresh home and a
custom provider, the first composer bar came with the composer and a
prompt pasted with its Enter at that moment was submitted, so the docs
say so instead of "not measured". The example keeps its input in a
subfolder, apart from the case's CLAUDE.md.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
sendmark's comment and verbs.md 5.5 listed six external modes by name,
and test/agent-skill-mode-lists.test.ts refuses any partial list of them
(the one a ninth CLI would silently miss). Both now say what the class
is: a hook-less claude, a worker on the local model, and every external
agent mode but deepseek.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
SKILL.md gets a subsection after the DeepSeek Harness workers: why to hand
work to the model on this Mac (bulk work with no per-token bill, files
that stay on the machine, a second opinion, a worker that needs no
network), the copy-paste block (local_model, spawn_worker local, sendmark,
delete_session), and the limits as the code has them: a person installs
the model, one request at a time, slower than the cloud, markers not
hooks, a spawn can start a runtime the person stopped, admin only and
experimental.
The description now names the local model, so "use the local model"
reaches the skill. Section 2 gains a row, the hook-less row points at
sendmark, and reference/verbs.md gets 5.16 with every local_model reason,
the spawn steps and the sendmark exit codes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The codeman skill's preamble learns the model Codeman installs on this Mac:
- local_model asks GET /api/v1/local-model and prints one JSON line: the
installed model, the coding agent that runs it and its endpoint, or the
reason there is none (not a Mac, nothing installed, an unfinished
install, a blocked install, admin only, a server without the routes).
Exit 0 only when a worker can start now or after a runtime start.
- spawn_worker <name> local (and name:local in spawn_workers) starts a
stopped runtime the way the window's Start button does, quick-starts the
installed agent with customModel, and waits for its composer (OpenCode's
bar, the claude path for a claude agent, LOCAL_READY_MARK otherwise). A
confirmation question from quick-start fails the spawn with empty stdout;
nothing is ever confirmed on the person's behalf.
- sendmark <sid> <prompt> drives any agent worker without an end-of-turn
signal: the exactly-once input body, a split marker through wait-output,
then the answer read back from a file the worker wrote in its folder
(regular files only, 256 KB at most), with one exit code per outcome.
The preamble stamp moves to 1.50.0 so every cached copy is rewritten.
The tests run the real preamble against a stubbed server.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every place that called the Codeman Agent Skill setting off by default now
says it is on by default since 1.50.0, where to turn it off, and that turning
it off still removes no copy already written (`codeman skill uninstall --case
<name>` does). The README, the wiki's Codeman Skill page and the FAQ say an
agent inside Codeman usually has the skill without an install step, and that
the copy ignores itself in git.
Also written down: an install whose App Settings were saved on an earlier
version stored the old default and stays off until switched on; with the
Claude Code plugin installed, Claude Code lists the skill twice (both work);
and, in the invariants, the self-ignoring `.gitignore` rules and the
measurement that Claude Code 2.1.319 never runs `git check-ignore` on a skill
folder. The agent control plan keeps its original default-off decision and
gains a dated note for the flip.
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>
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>
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>
The self-gate now says the skill reads saved Codex conversations offline outside a session; the staging
reference says only tagged input gets 409 during a guarded submit (the rest is held), and the API
reference notes a managed write past a full hold queue falls back to a direct write. Also: missing
reference rows, agent --help naming inspect/stage/submit, the tunnel opt-in in Remote Access, MCP wording.
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>
Cursors shared one global FIFO of 1,024 and were never retired on use, so one
agent polling every second evicted every other caller's cursors after about
17 minutes. Each owner and session now keeps its newest 8 cursors, older ones
retired first, under the same global backstop; the cursor just used stays
among the newest, so a retry of the last call still works.
`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.
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>
Multi-user: add a (username, IP) failure bucket checked before verifyPassword, capped at AUTH_FAILURE_MAX, with the same decay as the other buckets; the per-IP pre-gate stays at AUTH_IP_FAILURE_MAX and the per-username bucket stays after the verify
A correct password now also clears that account's (username, IP) bucket, beside the IP and per-username buckets
The new bucket is disposed on server stop like the others; the comments above the gate and the constants' JSDoc describe the three buckets
Tests: 10 wrong then the correct password from one IP is a 429, the same account logs in from another IP, another account behind that IP is unaffected, and a correct password clears the pair bucket
test/multiuser-auth.test.ts: the spray test loops to AUTH_IP_FAILURE_MAX instead of a literal 50
Reworded the rate-limit lines in auth-config.ts, security-architecture.md, README.md, README.zh-CN.md, wiki/Security.md, endpoints.md (plus the plugin mirror), CLAUDE.md and architecture-invariants.md
docs/wiki/Remote-Access.md: add the multi-user note to the tunnel page
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>
Single-user mode has no per-username bucket, so its per-IP bucket is the
only limit on guesses against the one password, and behind a tunnel every
client shares 127.0.0.1. Put it back on AUTH_FAILURE_MAX (10).
AUTH_IP_FAILURE_MAX (50) now gates only the multi-user per-IP pre-gate,
which runs before the scrypt verify and so refuses even a correct password;
the per-username bucket still caps each account at 10.
Move the headroom test out of the single-user suite and add a multi-user
test that sprays wrong passwords across usernames (9 each) and expects 401
for the first 50, then 429 for the 51st and for a correct password.
Update the docs that still described 10 per IP for every mode, and resync
the plugin mirror of the codeman skill.
#670 stamped the preamble with the version it expected to ship in, 1.43.1.
The release is 1.44.0, so the stamp would name a version that never
existed. Any new value makes cached preambles from before #670's sendwait
change stale, which is what the stamp is for.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
A prompt made only of blank lines joined to nothing, and sendwait then sent
a bare Enter onto whatever sat on the worker's composer. It now refuses
with "sendwait: empty prompt" (the test fails without the check).
reference/verbs.md still said sendwait takes one line and a multi-line
prompt can sit unsent; it now says sendwait joins the lines with a space,
which loses their layout, so long multi-line content belongs in a file.
Plugin mirror regenerated.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
sendwait posted its prompt as is. With the mux now keeping line breaks, a
multi-line prompt goes in as a paste, and right after spawn_worker returns it
can land inside Claude Code's Enter-ignore window. Neither the Enter loop
here nor the server's submit check recognises a pasted block that is still on
the composer, so `Review this:\n- item 1` sat unsent while the re-wait ran
out. sendwait now trims each line, drops blank ones and joins the rest with a
space before building the body, the same result as toSingleLine, like every
other waiting sender.
The preamble stamp moves to 1.43.1 so cached preambles pick the change up;
the plugin mirror is regenerated with scripts/sync-plugin.mjs. The new test
runs the real preamble.sh with CURL stubbed and fails without the join.
docs/api-reference.md gets the submit-check sentence the README and wiki
already carry.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
verbs.md section 5.3 (both copies): sendwait's Enter loop and the server's submit
check cannot reliably recognise a multi-line paste, so join the lines or use a file
(section 5.9). docs/tui.md gives the same reason instead of the composer one.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
The tab layout's 512 refs also count pinned sessions kept as stopped records, so
the ceiling holds at the default MAX_WEBVIEWS and with no pinned closed sessions.
SKILL.md, verbs.md (both copies) and the cron guide no longer give a fixed 50/25.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
An owner's tab layout holds at most MAX_TAB_REFS (512) refs, counting saved web
tabs (up to MAX_WEBVIEWS, 50 by default) as well as sessions. With a ceiling of
500, session creation could still fail with HTTP 500 on the layout limit before
the capacity message. 512 - 50 = 462; a test pins the ceiling plus MAX_WEBVIEWS
inside MAX_TAB_REFS so the two limits cannot drift apart again.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
Review follow-up. Other bounds assume a small session count: an owner's
tab layout holds at most MAX_TAB_REFS (512) refs and PUT
/api/session-order accepts at most 500 ids, so with
CODEMAN_MAX_SESSIONS=600 the 513th session creation answered HTTP 500
instead of the capacity message. The value is now clamped to a named
MAX_CONCURRENT_SESSIONS_CEILING of 500; any digit string above it
(including one past the safe-integer range) resolves to 500 instead of
falling back to 50. The resolver reads process.env directly, the unused
env parameter is gone.
Docs: a CODEMAN_MAX_SESSIONS row in the Settings Reference environment
table, the env name next to the cap in the cron guide and the
architecture invariants, and both copies of the skill's endpoints
reference now give the per-user cap as half the global cap (25 by
default). The changeset says "1 to 500". The test drops the
`as unknown as string` casts and adds '1000', '501' and an
out-of-range value, each refusing at 500.
Co-Authored-By: Christian Haberl <116439789+christianhaberl@users.noreply.github.com>
Co-Authored-By: Claude <noreply@anthropic.com>
- sendInput's docstring said all text without `\r` is typed; that now holds
for single-line text only.
- The skill's big-input section still listed "the newline stripping" among
the hazards a workspace file avoids; it is the unconfirmed multi-line
paste now. Rewrapped, mirrored in plugins/codeman.
- The mobile composer's hand-back comment said the prompt transport strips
newlines. The hand-back writes to the terminal prompt, whose text reaches
the PTY as typed input, where a newline is a key; the behaviour (a
multi-line draft stays parked) is unchanged.
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>
Codeman maintainer