Commit Graph
558 Commits
Author SHA1 Message Date
Codeman maintainer 2cd3cbd6a0 fix(local-model): count what llama-server keeps beside the K/V cache, and bound its checkpoints
The llama.cpp memory rule of the catalogue left out two allocations that the llama.cpp the
runtime bundles (b12111, the runtime's LLAMA_CPP_VERSION) makes for every GGUF row:

- Context checkpoints. For a model whose state cannot be rolled back (the recurrent state of
  the Qwen-family rows, the sliding window of North Mini Code), llama-server keeps host copies
  of that state, two or three per request, up to 32 per slot by default
  (tools/server/server-context.cpp create_checkpoint). For the 27B that is 32 x 157 MB = 5 GB,
  none of which was counted. The runtime now sets LLAMA_ARG_CTX_CHECKPOINTS=8 (read by
  llama-server from its environment like LLAMA_ARG_CACHE_RAM; 8 was llama.cpp's own default
  before it went to 32), and every llamacpp row counts 8 copies of its state.
- Multi-token prediction. The two -mtp tags and qwen3.8:27b-q8_0 carry a prediction layer
  (nextn_predict_layers 1, read from the first bytes of each GGUF; the 9B tags and North Mini
  Code have none). The runtime then always passes --spec-type draft-mtp --spec-draft-n-max 4,
  so llama.cpp keeps 4 rollback copies of the recurrent state (need_n_rs_seq(),
  llama-memory-recurrent.cpp) and the prediction layer's cache in the draft context's cache
  type, f16 by default. The rows counted one state and that layer at q8_0.

What moves (test/local-model-recommend.test.ts, "every memory size", re-pinned):

- 16 GB: limited -> none. MiMo 9B at 65,536 tokens needs 10.2 GB, 0.987 of the 10.4 GB
  estimate. With the budget the Mac mini measured (10.7 GB after the reserve) it is offered,
  0.954, tight; that test is kept. With 4 checkpoints instead of 8 it would be 0.966 on the
  estimate: this size sits on the edge, and only a run on such a Mac settles it.
- 18 GB: the same pick, 0.964 instead of 0.928.
- 36 GB: the same picks, 0.966 (27B on M4/M5 Max) and 0.976 (35B-A3B GGUF on M3).
- 48 GB on a Max chip: the 27B at 262,144 tokens is tight (0.853) instead of good.
- 32 GB with a measured budget of 0.74: North Mini Code at 131,072 tokens (was 262,144), the
  27B at 65,536 on a Max chip (was 131,072).
- Every MLX row, and everything from 64 GB up, is unchanged.

test/local-model-catalog.test.ts recomputes the new rule from the architecture table and holds
the catalogue to LLAMA_ARG_CTX_CHECKPOINTS. The catalogue header, runtime.ts, the types,
docs/local-models.md, CLAUDE.md and architecture-invariants say the same. Read in the source,
not measured.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 10:26:57 +01:00
Codeman maintainer f60b63c005 feat(local-model): q8_0 K/V cache, flash attention and a bounded prompt cache for llama.cpp
runtimeEnv() now also sets OLLAMA_KV_CACHE_TYPE=q8_0, OLLAMA_FLASH_ATTENTION=1
and LLAMA_ARG_CACHE_RAM=1024. Read in the v0.40.15 source of the pinned
runtime: the first becomes --cache-type-k/-v of llama-server (17/32 of the
f16 cache), the second --flash-attn on (a quantized V cache needs it, and
"auto" or "off" would fail such a load), and llama-server inherits the third
from ollama serve's environment, which bounds its host prompt cache to
1 GiB instead of letting it grow by gigabytes in a session. The MLX runner
reads none of them.

The catalogue's llama.cpp rows are computed for these values, so the two
change together. Not yet measured on a Mac.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 09:18:51 +01:00
Codeman maintainer 54c02990ba Revert the skill default flip on this branch: it ships in its own pull request
This reverts commit 0aa34da8, which made the codeman agent skill default on here as well. That change lives in feat/agent-skill-default-on, together with the self-ignoring copy and the reference-folder symlink check it needs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 09:00:59 +01:00
Codeman maintainer 0aa34da80f feat(settings): the codeman agent skill is on by default
agentSkillEnabled now reads an absent key as ON, the way
workspaceHooksEnabled does: only an explicit false turns it off. A new
session therefore finds the codeman skill in its folder without a
setting first, and with it the verbs that hand work to other CLIs and to
the local model on this Mac. Settings shows the switch on for the same
absent key.

The injection itself is unchanged: add-only, marker-owned, never through
a symlink, never for remote sessions or a plain shell. Turning the
setting off still removes nothing already written.

The quick-start test now pins the new default (injected on an absent
key, nothing after an explicit false), and the docs that said "default
off" say when that changed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 08:13:51 +01:00
Codeman maintainer 7238ced571 docs(local-model): the install guide, the API and the rules
docs/local-models.md is the guide: the steps, the layout on disk, what is
written outside the folder, the failures and their next steps. The API
reference documents the install object and the five verbs, and how the list
is ordered. The rules for the server side are in CLAUDE.md and
architecture-invariants.md, the user-facing pages in the wiki.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-11-06 22:16:38 +01:00
Codeman maintainer a651616907 fix(custom-model): keep the launch model out of the stored config
Quick-start wrote a selection's launchModel into the session's stored
<Mode>Config, which is what a clear falls back to, so a clear relaunched
the CLI with the endpoint's model id on its native backend. Only API
callers can reach that, since no page sends a clear.

The first launch now takes the forced model from the session's selection,
through the same _withCustomModelLaunchModel() the respawn path uses, so
the stored config keeps the model chosen at create. That also carries the
model onto a new tmux session for a selection applied to a running
session, which the create path used to lose.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 12:41:32 +01:00
Codeman maintainer e9ab694a55 docs: record the file surfaces as the adopted session exception
Owner decision for 1.49.0: a container or ssh tab keeps using this
host's /tmp and paths, with gating planned as a follow-up.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 10:43:46 +01:00
Codeman maintainer 37dfb73b1e fix: flag a Files panel folder that did not answer the probe (release review)
A subfolder whose bounded probe answered `unknown` came back as `children: []`
with no `incomplete` and `truncated` false, so a dead mount, or a healthy one
slower than the 1.5 s probe on first touch, read as an empty folder and a
search missed it in silence. `unknown` is never `absent` (#516).

Such a folder now goes on the walk's `unread` list, which flags the node and
sets `truncated` in both walks. A folder the filesystem says is gone drops out
quietly as before. The row said "file limit reached", which would be false
here, so it now reads "Not fully scanned" for either reason.

Reproduced on a real disk with a parent at mode 0444, where the child's stat
answers EACCES: the API, the search and the panel all report it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 08:41:15 +01:00
Codeman maintainer 3e5211e18b fix: note the silent skip of codeman-named tmux sessions and two adopted details (release review)
A session named codeman-* or claudeman-* on any socket is dropped with no
note, which contradicted the docs. paneCwd is absent for an adopted session,
and only a claude wrapper reports statusLineExporter.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 08:23:43 +01:00
Codeman maintainer 1c4cef1ccc fix: say how the git and Edit history routes answer an adopted session (release review)
The adoption section said every git route answers unsupported, but git-diff
and git-fetch-settings answer 400, and the Git status section listed only
remote and docker. Edit history's `adopted` reason was documented nowhere.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 08:23:43 +01:00
Codeman maintainer 436037e0e3 fix: offer New folder in Clone Repo's parent folder picker (release review)
Clone Repo's custom folder became a parent that must already exist (#774),
while its picker still had no New folder button (#761 turned it on for
Create New only). A parent that does not exist yet was refused with no way
to make it from the form, so the same job worked on one tab and dead-ended
on the other.

The test pin that kept Clone off dated from when the field was the exact
target, which could be a folder not yet created. Clone moves to the on side
of that pin, so every picker in the file stays covered.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 08:01:39 +01:00
Codeman maintainer e7c68f1340 fix: let go of an adopted tab whose tmux session ended (release review)
When a foreign session ended, remain-on-exit kept Codeman's own tmux client
on the wrapper's dead pane, so the tab kept its pid and busy, input went
nowhere, both attach routes refused it, and a new session of that name only
led back to the dead tab. paneExit stays out of it by design.

The reconnect watcher's tick now detaches a client from a dead wrapper. That
is an ordinary PTY exit with status 0, so the pid goes null and selecting the
tab runs the attach again: it joins the target if it is back and otherwise
prints the existing guard text. Checked on an isolated instance and in a
headless browser: boot recovery, target gone, target back, view detached, tab
closed, and no restart loop while the tab sits unselected.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 07:44:22 +01:00
Codeman maintainer 800b3f4658 fix: keep foreign probe parsing linear in what it reads (release review)
The parser and classifier run synchronously on the event loop over text a
pane, a container or an ssh host wrote, and one process could stall the
server for every session: 4 s for a 128 KiB argv of `/pi/` tokens, about a
minute for 2 MiB of socket rows.

The `cli.js` launcher rule leaves the signature regex for a per-word scan,
socket rows dedupe through a Set, the process row regex takes the `s` flag
(a bare CR made `$` fail and `\s+` give its spaces back, quadratic in a row),
argv and pane command are cut at FOREIGN_MAX_ARGV_CHARS, and one matcher per
scan answers each distinct argv once, since every pane of a hostile host can
claim the same process tree.

Measured on a private tmux server with the same 131 KiB argv: the largest
event-loop gap went from 3991 ms to 45 ms. The worst scan the caps allow
takes about 80 ms. Socket rows stay uncapped on purpose (see the docs).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 07:10:49 +01:00
Codeman maintainer 2c084966f1 fix: refuse one-shot prompts on an adopted session (release review)
`POST /api/sessions/:id/run` had no adopted gate, so while the wrapper had no
attached PTY it spawned `claude -p --dangerously-skip-permissions <prompt>`
in /tmp, a launch every other adopted route refuses.

The route answers INVALID_INPUT, and `runPrompt()` refuses too, which also
covers the legacy `sendInput()` path and leaves no direct spawn in Session
that an adopted session can reach.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 07:10:49 +01:00
Codeman maintainer 7e70f6f0c3 fix: keep an adopted session off the direct-PTY fallback (release review)
A wrapper that could not start fell back to a direct PTY: `claude
--dangerously-skip-permissions` or a server-account shell in /tmp on this
host, under a tab still carrying the foreign session's name, so someone who
opened an ssh or container session ended up typing into this machine.

startInteractive and startShell now fail the start for an adopted session
and leave `_useMux` on, so selecting the tab tries the wrapper again. The
`error` event carries the reason, since the browser's re-attach does not
read the route's answer. A session with no mux at all is refused the same
way.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 07:10:49 +01:00
Codeman maintainer 9b8f853c94 fix(custom-model): keep a session's own config dir conversation across an endpoint
A claude session on its own CLAUDE_CONFIG_DIR launched on an endpoint with
<isolated>/projects linked to the server's tree. The resume pin looks there, so
apply found no transcript and started a new conversation, and on clear the
endpoint's transcript stayed behind in the server's tree.

The link now goes to <own dir>/projects when the session set one, so the
conversation and what the endpoint run adds stay on the session's own account
across an apply, a clear and a restart. It goes through linkRealHomeEntry(),
which also creates a missing projects folder instead of leaving a dangling
link, in the own dir and in ~/.claude/projects on the default path. A relative
CLAUDE_CONFIG_DIR of the server gets no link, since joining it would create
projects under the server's working directory.

Rule #516: guardSessionConfigDirHome() now covers configDirVar, so all three
apply sites (route, quick-start, boot recovery) probe the own dir bounded before
the apply touches it, and a dir that does not answer falls back to the server's
tree. Under test, HOME is a temp dir and CLAUDE_CONFIG_DIR is stripped by
test/setup.ts, which a new test pins.

Measured on a real Codeman server with a fake claude: apply and re-apply resume
under the isolated dir with the transcript landing in the own dir, a clear
resumes on the own dir, the isolated dir goes while the transcript stays, and the
same holds across a server restart. The documented limits come out.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 06:10:41 +01:00
Codeman maintainer cd0bbc3e3a Merge #774 fix(clone): treat Clone Repo's custom folder as a parent, like Create New
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:37:14 +01:00
Codeman maintainer c65706a3e4 Merge #510 feat(adopt): adopt tmux sessions a human started, in all three locations
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>
2026-11-06 05:36:20 +01:00
Codeman maintainer 7594c7fc0b fix(clone): keep the preview and the wording on the parent folder
The "Will clone into" line named a folder the request would not use: the
preflight replaces the page's guessed case name with the server's (for a
URL such as .../repo?tab=readme the guess is repo-tab-readme and the server
says repo) and nothing refreshed the preview, so it stayed on the old name
while the field and the request moved on. It is now refreshed there too.

The Browse picker's title and the empty-field toast still said "Choose the
folder to clone into", the old exact-target meaning. Both now ask for the
parent folder, matching the field's label.

CLAUDE.md and the invariants paragraph split the two meanings: path on the
API is the exact folder, the Clone Repo tab's field is a parent and the page
sends <folder>/<case name>.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:20:37 +01:00
Codeman maintainer aacf105cea Merge #614 fix(files): prevent large folders starving File Viewer results
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:04:44 +01:00
Codeman maintainer 76e40668fc Merge #766 feat: edit history panel for remote (SSH) claude sessions
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:04:19 +01:00
Codeman maintainer 44349395d0 Merge #753 feat(codex): let Codex sessions drive other sessions through the codeman skill
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:03:54 +01:00
Codeman maintainer 11208a153c Merge #768 feat(install): install without administrator rights (--no-admin)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:03:29 +01:00
Codeman maintainer a2c530b93c Merge #573 feat(docker): guided first run for the Compose deployment
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:03:04 +01:00
Codeman maintainer cddfc07550 Merge relprep/rtl fix(response-viewer): lay out Persian, Arabic and Hebrew right to left (#715)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:02:36 +01:00
Codeman maintainer 9ba5a89123 Merge #761 feat(picker): New folder button for Create New's custom folder picker
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:02:08 +01:00
Codeman maintainer f8832ec78f Merge #772 fix(files): list the git worktree an agent moved into
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:01:41 +01:00
Codeman maintainer 9751f51bdc Merge #767 fix(custom-model): give a session its own env values back when the selection goes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:01:14 +01:00
Codeman maintainer 4d20b9c898 Merge #771 fix(pi): keep the mouse wheel working after a tab switch or reload
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:00:46 +01:00
Codeman maintainer 9e9031214e Merge #770 fix(remote): stop the local shell expanding the remote launch (exit 127 since 1.47.0)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 05:00:18 +01:00
Codeman maintainer 39d0e6c5ab docs: describe right-to-left rendering in the manual and the invariants (release review)
The wiki gains right-to-left notes for Last Response, the phone's Compose
editor and the rendered Markdown view, plus a Troubleshooting entry for the
#715 report: the terminal is xterm.js, which has no right-to-left support
(xtermjs/xterm.js#701). src/web/CLAUDE.md and the invariants now state the dir
pins, the logical-property rule and that the direction pass runs last.

The changeset claimed every file path stays left to right. It now says only
what holds: the paths the viewer links on its own.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:49:02 +01:00
Codeman maintainer 2d7cd49449 fix: keep foreign discovery from throwing, and correct the adoption docs (release review)
candidatesFrom had moved outside the try when the transports moved to
runForeignProbe, so a classifier failure would have reached the route as a 500.
The module promises it never throws, so the guard is back for local and docker.

Docs:
- The api reference said `blocked` waits are always refused, and listed Ralph as
  refused while two of its file routes were not (they are now).
- The invariants doc and CLAUDE.md gain the rules this review turned up: target
  syntax in names, the ping before list-panes, nothing typed into an adopted pane,
  quoteAdoptLaunch.
- CLAUDE.md no longer says every claude session gets hooks or a stop wait.
- ForeignTmuxSession's mode and workingDir describe the first listed pane, not
  the active one.
- The wiki had no page on adoption: The Dashboard gains an Opened outside Codeman
  section, and the remote and docker pages point at it. docs/docker-cases.md now
  separates an adopted container from an adopted tmux session.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:45:29 +01:00
Codeman maintainer c97b592ee2 fix: bring the docs in line with the no-admin route (release review)
Name the real trigger and CODEMAN_NO_ADMIN=0 in the READMEs and the
Installation page, add the install without git to the update tables and the
updater notes, record the installer's downloads in the supply chain section,
and say that the data directory question also removes a kept runtime.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:34:18 +01:00
Codeman maintainer ba2475c84f fix: updating a Compose install takes a git pull, and the docs say what the script does (release review)
The summary and README said rerunning the script updates Codeman. It never
fetches, so that was a successful no-op. The summary, README, its zh-CN mirror
and the wiki now say git pull, then rerun, with the in-app route first.

Also corrects "printed once" (twice at a terminal, never off one), says a typed
answer beats a preset, adds the first-run setup, the 180 s wait, --no-wait and
the changeme refusal to Running-As-A-Service and Troubleshooting, and records in
architecture-invariants why docker/.env is generated FROM .env.example.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:31:26 +01:00
Devvyn d2c75784d3 fix(clone): treat Clone Repo's custom folder as a parent, like Create New 2026-11-06 11:22:34 +08:00
Codeman maintainer aae0951d4e fix: name which picker rules skip the container picker (release review)
The New folder rule in the same paragraph does cover that picker, so "none of
the host rules" said too much.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:06:52 +01:00
Codeman maintainer 19a2197f84 docs: say which picker each statement covers (release review)
The picker is now reached from every Add Case Browse button, so three lines
in the manual and the opening of the CLAUDE.md and architecture-invariants
paragraphs read wrong. A Browse fills its form field, only the Path key types
into a prompt, and Docker's Container Workdir picker lists the inside of the
container through POST /api/docker-cases/browse: it always shows dot entries
and the host allowlist does not apply to it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 04:03:32 +01:00
Codeman maintainer fafec35344 fix: bound what the Files panel walk reads and keep its subfolders in it (release review)
The round-robin walk capped what it listed, not what it read: every queued
folder was read whole, sorted and held until drained, so one GET could pull
millions of entries (100 folders of 50,000 files killed a 400 MB heap). A read
now keeps only the entries the listing can use, and MAX_WALK_ENTRIES_READ stops
opening folders at 250,000 entries, leaving the rest queued and flagged.

A folder also spent its whole share on its own files, leaving nothing for the
subfolders it had just found, alone in its round or beside a sibling, so search
hits inside them were lost. Its files now count as one more share beside those
subfolders. Math.max(directoriesInRound, 2) would have fixed only the sole-folder
case and cut a wide root's folder list short.

Folders below the walk root are probed before their readdir (#516), since the
walk reaches folders the depth-first one never did.

Filtering at the read also clears the false flag on a folder whose only unread
entries were hidden or excluded, and an exactly-full workspace now finishes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:53:08 +01:00
Codeman maintainer dbb3202161 fix(picker): word the cases-folder refusal for both pickers, and finish the review items
With the folder field empty, Create New's Browse opens in the cases folder, and New
folder there answered "Use Add Case > New Case". There is no tab of that name (the
label is Create New), and a Create New user is already on it. The refusal now reads
right from Link Existing and from Create New's custom folder. Its test pin, the code
comment, the manual, api-reference, CLAUDE.md and architecture-invariants move with it.

The block() helper in the New folder picker test returned an empty string for a name
that is not in session-ui.js, so .not.toContain passed and a renamed picker dropped out
of the check. It now asserts the name was found.

The manual's path picker list said two places and left out Create New, which the New
folder paragraph names. It now lists every Browse that opens the picker, and that
paragraph is rewrapped to the page's width.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:40:58 +01:00
Codeman maintainer 36d8942744 docs(adopt): add the frontend note and scan the module for CLI ids
foreign-sessions.js joins the files the no-id test scans, so the catalog lookup
stays one. The block's rules go where a frontend reader looks, in
src/web/CLAUDE.md, and the architecture note no longer calls the file surfaces
read-only, since File Viewer edit mode writes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:38:38 +01:00
Codeman maintainer 1f6f21fd24 docs(adopt): document the routes and the overlay, correct stale comments
The two routes are public under /api/v1, so they get an API reference section.
The overlay gets an architecture note and a CLAUDE.md rule: an adopted session
has session.remote and session.docker undefined and a neutral workingDir, so any
new code that reads workingDir as a workspace must also test isAdopted. That is
the class of bug this round fixed a dozen times.

Records a measured limit: while the view exists an owner's kill-session leaves
the window alive under it until the tab closes.

Comments that still called workingDir the foreign pane's cwd now say what is
true since the wrapper got its neutral folder. Also drops a zh-CN key that
duplicated an existing one, and updates the two structure tests pinned on the
lines this round changed.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:29:35 +01:00
Codeman maintainer e10b84dcdd fix: refresh comments that still say claude is the only gated CLI (release review)
Codex now declares a version gate too, so the notes in session.ts and
docker-hosts.ts were wrong, the hooks-config caveat described every local codex
when --no-daemon now covers 0.162 and later, and session-routes left network
access out of the launch defaults. architecture-invariants gains --no-daemon and
the network config in its list of Codex flags. Comments and docs only.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:25:00 +01:00
Codeman maintainer 08d99da5ae test(edit-history): the ssh kill test no longer races the fake's pid file
The test waited for a real 1000 ms timeout and read the pid file afterwards.
On a loaded machine the kill could land before the fake ssh wrote it. It now
waits for the pid and sends the timeout's SIGTERM itself, which is all Node's
timeout does. Without exec the fake still survives and the test goes red.

The invariants said "the reads" go through buildRemoteEditHistoryCommand; the
image probes go through remoteProbePaths, on the same limiter.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:17:14 +01:00
Codeman maintainer b5066744be fix(edit-history): a remote read with many subagents spans several round trips
The read script carries one case line per subagent cursor, and the whole
script is one argument of the ssh line, which Linux caps at 128 KiB. From
about 1000 subagents the command failed with E2BIG. The cursors have no cap
and the stored conversation is read first, so the session stayed unavailable
and not even a /clear got past it.

A read with more than 300 subagent requests now takes several round trips.
The cut is by name range, not only by count: the script takes a file no case
line names for a new one, so plain groups would read each other's files as
new. Each round trip walks only the names between its cuts, through one awk,
so a new file lands in exactly one range. Budget and meta budget carry over,
and a later round trip still lists its files, because a requested file missing
from the result loses its cursor. A failed round trip fails the whole read and
nothing of it reaches the store. A read of up to 300 runs no awk at all.

Each round of the 60-seed fuzz is also cut at a random size and compared with
the local reader. Run outside the suite too: bash --posix, BusyBox and mawk,
and bash 3.2 in a container, which is macOS sh. That shell cannot parse a case
inside $(...), so the names come from a shell function.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 03:13:03 +01:00
Codeman maintainer 26b63aea2d fix(edit-history): remote lookup finds tmux, a timeout reaches ssh, docs follow
Applies the review of #766.

The live lookup ran tmux on the bare PATH of the ssh command. On a host
where tmux sits in ~/.local/bin or /opt/homebrew/bin it found no pane, the
2>/dev/null hid that, and the panel stayed on the launch conversation after
a /clear. It now goes through withRemoteTmuxPath(), inside the sh script and
scoped to the $(...), so the other tools keep the PATH they had. The fake
tmux of the test block moved to $HOME/.local/bin for the same reason: that
directory is first on the new PATH, so a real tmux is never asked.

The two ssh commands get exec. Node signals the local sh -c, and dash stays
the parent of a plain command, so ssh survived the timeout. A test with a
fake ssh shows the process dies now and survives without exec.

The comment at the meta budget claimed a meta past it comes with a later
read. A meta comes only with a subagent's first read, so it is never sent.

Docs: the store is named as the exception to "never copied to local disk",
remoteProbePaths and the remote transcript lookup are described, and the
line saying a remote session loads no store is gone.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:57:58 +01:00
Codeman maintainer a908be05ac fix(files): mark folders the scan limit stopped short of
The fair rounds give a directory its node before reading it, so every folder
still queued when the 5,000-node budget ends sat in the tree with empty or
partial children and read as an empty folder. Keep the node on the tree cursor
and set an additive incomplete: true on every cursor left in the queue, then
draw one dim, inert row under such a folder while it is expanded. The envelope
check ignores keys it does not know, so old and new clients stay compatible.

Stop each round at the top once the budget is spent, before the shift: the
rest stay queued unread, and flagged, rather than read and sorted for nothing.

Say what the walk is: a per-directory round-robin (breadth-first), fair per
directory and not per subtree, with search results now shallow-first.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:57:28 +01:00
Codeman maintainer a8688f14a0 fix: disclose the tcsh regression and bring the launch docs in line (release review)
A tcsh login shell worked on 1.48.0 only because the local sh rewrote
${SHELL:-/bin/sh} to this host's shell. With the launch verbatim, tcsh gets -i -l,
refuses it and every stock launch leaves a dead pane. The changeset and
docs/remote-sessions.md described that as a standing limitation; they now name it
as a change in this release, with what the override workaround costs.

Also: extraSshOptions joins the list of values now literal at launch, the stock pane
command is shown as /bin/sh -c in the docs and the builder's JSDoc, the invariants
state how the launch must reach the far end, the manual pages cover $ in an override,
and the invariants no longer say extraSshOptions refuses a bare $ (it never did).

Reworded the em-dashes on the invariants line this rewrites.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:39:42 +01:00
Codeman maintainer 9b73ab3dbe fix: state what a clear and a restart keep in the custom-model docs (release review)
Records the limit on a session with its own CLAUDE_CONFIG_DIR, which does not
carry its conversation across an endpoint because the isolated projects link
goes to the server's tree. Also records that an own home set before a restart
with no selection is lost on clear, that only an absolute path is persisted,
and tells the user manual what a clear gives back.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:39:11 +01:00
Codeman maintainer b6eea702a8 fix: correct the pi wheel docs and comments (release review)
The gate comment in terminal-ui.js said a stale-false flag falls through
to the PageUp/PageDown fallback, which is false for pi since the second
commit of this PR removed that fallback. The FOOTGUN comment above it made
the same claim. Say what happens instead.

"Every pi below 1.0.0 emits no mouse enables" was too absolute: regular
was the default there, but fullscreen exists from 0.84.0. Measured with
--tui-mode fullscreen under tmux on 0.84.1, 0.85.0, 0.86.0 and 0.99.2:
alternate_on=1, mouse_any_flag=1, mouse_sgr_flag=1. Default settings on
0.99.2 report all 0.

Document that Wheel Scrolls Local History leaves the wheel dead in
fullscreen pi (wiki, integration guide, changeset), add a pi block to
Troubleshooting, cross-reference the accepted exception from the dead
gesture rule in architecture-invariants, and mark the pi-integration-plan
passages this PR reversed as superseded.

Comments and docs only, no runtime change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:35:41 +01:00
Codeman maintainer 4f7ed129a9 docs: describe the live worktree listing as it now works (release review)
The security wording claimed a folder strictly below workingDir was the whole
argument, which the symlink fix showed was only the lookup's half. The rest is
docs that were missing: liveWorktree, root=live and worktree in the API
reference, the mechanism section the CLAUDE.md paragraph had no pointer to, what
a root=live query matches against, and the limits a reader meets in the wiki
(the Git panel stays on the session's folder, a session started below the
repository's top is not followed, a page under .claude/worktrees opens as
source).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 02:26:36 +01:00