Commit Graph
1332 Commits
Author SHA1 Message Date
Codeman maintainer 5548c17c4a chore: version packages
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-20 04:46:20 +01:00
Codeman maintainer a9ed3f55c3 Merge #832: a replayed Discord reply is typed once, and a store failure never costs a reply
Each allowed Discord reply is claimed by its message id in a small private store (discord-reply-dedupe.json, 0600) before the rate-limit and exited-agent checks; when the store fails the bridge falls back to memory and still types the reply.
2026-11-20 04:05:22 +01:00
Codeman maintainer acd90efe73 fix(webview): the review items of #825
The owner of a managed dsh tab is compared with the server's starter only in
multi-user mode: a record created there keeps its owner, while a single-user
start records none, so that tab would never get its cookie again (new route
test). CLAUDE.md and the invariants doc name the cookie rules. The third item,
Codeman's session cookie filtered on the WebSocket leg whether or not the dsh
cookie is injected, came in with the merge itself, where it met #827.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-20 04:04:58 +01:00
Codeman maintainer 1207c316c0 Merge #834: codeman tui attaches by session name
codeman tui <name> attaches by an exact session name as well as by list number.
2026-11-20 04:00:05 +01:00
Codeman maintainer 923db64a10 Merge #831: the wheel is forwarded for any CLI whose registry entry asks for it
The wheel gate reads each CLI's wheelForward rule from the registry (window.__codemanWheelForward) instead of a list of ids, so a custom full-screen CLI in clis.json can opt in.
2026-11-20 04:00:05 +01:00
JD c7b6e1cb4e fix(watchers): re-arm a stopped TeamWatcher watcher from the poll
chokidar 3 reports a one-off ENOENT race (a new file gone between its
stat and its watch) through the same TypeError as a lasting EMFILE, so a
watcher that stayed closed ended live team and task updates until a
restart. Each poll tick now re-creates a stopped watcher, as
WorkflowRunWatcher already does, and an outage warns once rather than
once per attempt. Also imports getErrorMessage from the types barrel.
2026-11-19 02:52:40 -05:00
Saqeb Akhter ce899f59cc docs(discord): document reply replay guard in agent guide (#218) 2026-11-18 11:07:32 +04:00
Kamil KaliszandClaude Opus 5.5 a36b875363 feat(tui): attach by session name, codeman tui <name>
codeman tui <session> takes a list number or a session name. Digits only
stay a number; anything else matches the session name exactly
(case-sensitive, never a prefix, folder or prompt). Names are not unique,
so two live matches refuse and print their numbers; a name only a RECENT
row carries says the session has finished. The target is resolved before
the TTY check, so scripts get these answers without a terminal.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 23:23:56 +01:00
JD 3ef4900e60 fix(web): forward the wheel for any CLI whose registry entry asks for it
The browser's wheel gate named copilot, pi, claude and codex by id, so a custom clis.json entry that launches pi could not get the forwarding #771 gave stock pi: after every tab switch or reload its wheel scrolled an empty local buffer. Copying pi's altScreen value into such an entry made it worse, since the mouse DECSETs were then stripped while nothing forwarded the wheel.

The server now publishes every CLI's wheelForward rule as window.__codemanWheelForward, disabled entries included because disabling a CLI leaves its sessions running, and _shouldForwardWheelToApp reads that map instead of an id list. Stock CLIs keep their behaviour, and a minVersion that is not MAJOR.MINOR.PATCH refuses forwarding instead of comparing as passing.
2026-11-17 00:43:09 -05:00
JD 10e443a309 fix(watchers): stop a chokidar watcher whose fs.watch fails instead of retrying forever
chokidar 3 with `persistent: false` has no guard for an `fs.watch` that throws (EMFILE once the inotify instance limit is used up, ENOSPC once the watch limit is). It emits the error, then a TypeError, then retries on the parent directory, and ends up re-adding `/` forever. TeamWatcher only logged its `'error'` events, so one failed watch became an endless stream of stack traces. WorkflowRunWatcher already closed its watcher on error, but `close()` removes every listener, so the TypeError from the same pass became an unhandled rejection, one per 10 s poll, and the server exits after five of those in a minute.

`closeWatcherOnError()` closes the watcher on its first error, keeps a no-op listener on it, and turns its `add()` into a no-op, since a callback chokidar still has in flight can otherwise re-add a path and reopen it. TeamWatcher logs one line per watcher and relies on its 30 s poll; WorkflowRunWatcher still drops the watcher and re-arms it on the next poll.
2026-11-14 15:14:35 -05:00
Codeman maintainer 574eae72f3 chore: add a dead-code check for the frontend scripts
src/web/public is plain <script> files with no imports, so knip cannot
follow it and ESLint does not cover it; leftovers there went unnoticed
until this cleanup. `npm run check:frontend-dead` is the counterpart of
`npm run knip` for that tree:

- JavaScript: every function, method and top-level binding, counted
  against the identifiers and string literals of the frontend files,
  index.html (inline handlers), the gesture overlay's source and the
  tests. A name with no reference but its own definition fails the check.
- CSS: every class and id of styles.css and mobile.css against the same
  text. A class built at runtime is recognised by its prefix or suffix.
- `--production` also lists what only tests reference.

It parses with the TypeScript compiler and PostCSS, both already dev
dependencies. Clean on this tree; run against the tree before the
cleanup it reports the 28 functions and 43 selectors that were removed.
On demand for now, not a CI step.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 20:39:05 +01:00
Codeman maintainer 03cb6a68b4 chore: drop obsolete scripts and a stale dev dependency, make knip report clean
- Nine one-off scripts from January and February that nothing references:
  three Ralph wizard drivers that click the start-screen button removed in
  1.50 (against the production port, with a personal case name), a respawn
  monitor with a hardcoded session id, link-detection experiments for
  patterns that no longer exist, and two screenshot and data helpers.
- @types/uuid: uuid 14 ships its own types and TypeScript already
  resolves them from the package.
- config/knip.json now describes the workspace layout it runs in (its
  top-level entry and project keys were being ignored), names the manual
  scripts as entries, lists the system binaries tests shell out to, and
  honours @knipignore. `npm run knip` reports nothing; CLAUDE.md says so.
- Two more unused tap helpers in the mobile test toolkit.
- Docs that pointed at files which no longer exist: the browser testing
  guide (four deleted test files), the orchestrator panel's file name, two
  spawn modules in the Ralph guide, the respawn mock utilities.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-13 14:25:41 +01:00
Codeman maintainer fa4815b465 fix(response-viewer): a session on a relocated Claude config folder gets its answers back (#701)
The viewer looked for a Claude transcript under ~/.claude/projects only, and
for the conversation after a /clear in ~/.claude/history.jsonl only. A session
started with its own CLAUDE_CONFIG_DIR (a second account, #255), or any session
on a server that exports one, writes both elsewhere, so the eye button showed
"No response yet" or a terminal dump, and codeman agent read and the Discord
bridge's last message came back empty. This is the third part of the report
in issue 701; the other two are a design choice and a feature request.

lastResponseFor() now asks claudeConversationDirs() for the folder the
session's claude writes to: its own override, then the server's, then
~/.claude, through claudeProjectsDir(), which the relaunch pin and the Edit
history panel already use. The rename's /resume title takes the same lookup
when no hook has named the transcript yet.

- Local sessions only. In a Docker case or on a remote host the override
  names a folder over there, and the same path on this host is someone else's.
- A relocated folder is a path somebody chose, so it is probed bounded first
  (the rule from issue 516). Anything but a directory reads as no transcript,
  never as a reason to look under ~/.claude, where a file of the same name is
  another account's conversation.
- The default folder is not probed, so that path is as before.

Not changed: the resume pre-validation at session create and the host-wide
history scans still read the default folder.

Tests: five route cases for the viewer (own folder, the server's, no fallback,
/clear through the relocated history, Docker left alone) and one for the
rename. Each part of the change fails one of them when reverted.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 14:39:13 +01:00
Ark0N a26be7c98f Merge #803: Muse Glimmer 30B as its MLX build, with figures measured on a Mac
The two commits of #803 that came after 1.51.0 was cut. The earlier commits (every model that fits, Muse Glimmer 30B and Ornith 1.0 9B) shipped in 1.51.0. No changeset: the next release names it.
2026-11-12 14:08:41 +01:00
Codeman maintainer 88ed3eef37 chore: version packages
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 03:02:57 +01:00
Codeman maintainer 5396e33b48 feat(local-model): Muse Glimmer 30B as its MLX build, with figures measured on a Mac
Run on a MacBook Pro (M5 Pro, 48 GB, runtime 0.40.15) on 2026-11-12, after the GGUF build
this branch lists turned out to be unusable in agent use there: an OpenCode turn of one
line showed no answer after 7 minutes, twice, although the runtime alone wrote 15 tokens
per second.

The MLX build of the same model (`muse-glimmer:30b-mlx`, 19.1 GB) on that Mac:
- 32.6 tokens per second for a 1,500-token answer. The tag carries a draft model, and the
  runtime logs speculative decoding with 0.34 to 0.62 of the drafts accepted.
- A correct tool call in under 3 seconds, and the same OpenCode turn finished in 45 seconds.
- Memory, read from the runner's own log line after every request: 37,900 to 45,100 bytes
  held per token (the GGUF build computes to 7,072), prefix snapshots that filled their
  8 GiB during twelve separate prompts, and a process peak 3.0 to 3.3 GB above what stayed
  held.

So it gets a row of its own, the second with measured figures. They put it at 34.6 GB for
65,536 tokens: offered from 48 GB up, never on the 32 and 36 GB Macs, which keep the GGUF
row untouched (it is still the pick of a 32 GB Mac with a Max chip: whether it should be
is the maintainer's decision). It is never the pick of a Mac whose disk has room for
Qwen3.6 35B-A3B, and it has no `tested` entry: one turn is not a test.

Also written down from the same session: the session of many prompts the Qwen3.6 35B-A3B
row owed (5.6 GiB of prefix snapshots after twelve prompts, still growing; its figures are
unchanged), and what the two open runtime issues on the MLX tag say against what ran.

Not done: the row was not installed through the window, and the measurement used a second
instance of the pinned runtime, not Codeman's.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-12 02:52:59 +01:00
Codeman maintainer c2d31b11f4 docs: CLAUDE.md names the auto-compact rules that prevent a wrong /clear (#777)
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:57:17 +01:00
Codeman maintainer d45b1ff248 Merge #650: jcode as a run mode
Conflict in skills/codeman/SKILL.md (and its plugin mirror): the list of
modes with neither stop nor blocked gained jcode here and the omp
exception from #798 on the release branch; both are kept.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:27:26 +01:00
Codeman maintainer 18b309fc02 Merge #797: the File Viewer edits workspace dotenv files
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:23:25 +01:00
Codeman maintainer f7fccc5dfc Merge #806: pick the coding agent per session, with Pi and DeepSeek Harness, and install a missing one
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:15:38 +01:00
Codeman maintainer f07cbccb0b Merge #804: a library of models on this Mac, with sizes, delete, add and switch
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:15:34 +01:00
Codeman maintainer c9f84c443d Merge #803: list every model that fits, and add Muse Glimmer 30B and Ornith 1.0 9B
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 20:15:30 +01:00
Codeman maintainer 3eb0689f6d fix(omp): an omp alert stays up until omp says the dialog closed (#798)
The four edits promised in the review of #798:

- An omp alert could clear while omp's dialog was still up. omp items got
  the same pane `capture` as Claude's, which the inbox re-reads with
  Claude's numbered-dialog parser. omp's dialog has no numbered rows, but an
  agent's plan above it does, so the list was parsed as the item's options,
  and once it scrolled out of the frame the item was resolved as answered in
  the terminal. An approval-only item now takes the frame once as `context`
  and gets no `capture`, like a screen-read item (web/screen-blocked.ts), so
  the module's `elicitation_complete` is the only thing that clears it. A
  route test puts a numbered list above an omp-shaped dialog and fails on
  the old code at both steps (options parsed, alert cleared).
- The reboot-restore install is dropped: the restore plan skips every CLI
  whose transcript is not `claude-jsonl` (omp's is `omp-jsonl`), so it never
  ran, and it sat after the start, when omp has already scanned its hooks.
- The docs that say which CLIs raise `blocked` and open alert-only items now
  name omp: api-reference, CLAUDE.md, architecture-invariants, an entry for
  `approvalHookFile` in cli-registry, and the skill with its plugin mirror
  (verbs.md listed omp among the modes where `blocked` is a 400, one line
  above the paragraph that says it works).
- Two comments: the schema's file-name rule is a pattern, not a closed list,
  and the marker check takes the marker anywhere in the file.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 10:27:38 +01:00
Codeman maintainer 9a34797cd5 docs(local-model): the coding agents of a model, what each was measured with, and the agent install
- docs/local-models.md: the four agents with their first request, whether
  the window installs them and what was seen where (a real model, a
  scripted endpoint, Linux, not the pinned runtime); what differs for Pi
  and for DeepSeek Harness; installing one more agent beside a model.
- docs/api-reference.md: `POST /api/local-model/agent`, `install.harnesses`,
  the `install-agent` action, and `install.cli` as the default agent.
- docs/architecture-invariants.md, CLAUDE.md, src/web/CLAUDE.md: the
  rules: the agent is chosen per session, the agent install is not a
  job, a launcher is never installable, a readiness mark is a measured
  one, and the window's one builder for the agent chips.
- docs/custom-model-endpoints.md: Pi's context window.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 10:04:47 +01:00
Codeman maintainer 8bedbbe793 chore: version packages 2026-11-10 23:59:42 +01:00
Codeman maintainer 2f17b8067a docs(local-model): the models on this Mac, add, switch and delete
The guide, the API reference, the invariants and the two CLAUDE files
describe the library with one model in use: the state file's list, the
three verbs and their refusals, the two cached listings of the view, and
the window's list with its row actions.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 23:52:14 +01:00
Codeman maintainer 9608a17d99 feat(local-model): list every model that fits, and add Muse Glimmer 30B
The "Run a local model" chooser showed the pick and four more models. It now
lists every catalogue model that fits the Mac, and the install accepts every
listed row.

- MAX_ALTERNATIVES goes from 4 to 11, above what the catalogue holds. It stays
  a bound: test/local-model-catalog.test.ts fails for a catalogue that outgrows
  it, so nothing drops off the list unseen.
- New row `muse-glimmer:30b-q4_k_m` (Meta, Apache-2.0): SWE-bench Verified 76.0,
  SWE-bench Pro 51.2, Terminal-Bench 2.1 51.7 on Meta's card. Its K/V cache is
  the smallest of the 27B class, so it is the first model of that class a 32 GB
  Mac holds: 21.2 GB at 65,536 tokens, 0.970 of the estimated budget. Figures
  computed from its config.json and its GGUF header by the llamacpp rule (13
  full-attention layers, 39 sliding-window layers of 2,048 tokens, no
  prediction layer); the sliding-window cache rule was read again in llama.cpp
  b12111 (src/llama-kv-cache-iswa.cpp). Never run on a Mac: `estimated`.
- What changes for a Mac: 32 GB is no longer `limited`. On an M1 Max or M2 Max
  the pick is Muse Glimmer; on a base or Pro chip the dense model is slow and
  the pick stays MiMo V2.6 9B, now with the small-pick note. Every other pick
  is unchanged.
- The "set aside" list was read again at its sources on 2026-11-10 and gained
  ripple-preview:65b (every build requires runtime 0.40.16, one above the pin),
  Ornith 1.0 (runtime issue 16992), nemotron-3.5-super:120b, qwen3.5:4b,
  qwen3-coder-next and the MLX and DFlash tags of Muse Glimmer.
- The header and the guide now say that runtime issue 16992 has one diagnosed
  cause in the tool parser every Qwen-family row shares (a tool argument that
  quotes a whole tool call is cut off; the fix is runtime PR 17021, open).

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-10 23:33:59 +01:00
JD 8b15c96c0f feat(files): let the File Viewer edit workspace dotenv files
The plain preview already serves a workspace dotenv file in full to the same user, so refusing the edit protected nothing. The edit gate now passes allowDotenv to the sensitive-path check, which skips only the two dotenv patterns; every other credential pattern, a dotenv file inside a blocked tree and Codeman's own data-dir login file stay blocked. Downloads and attachments are unchanged.
2026-11-09 16:44:27 -05:00
Codeman maintainer 7f35f798ee Merge #705: fix(voice): preserve thinking pauses and Android dictation 2026-11-09 18:16:12 +01:00
Ludo Fourrage 2d7cd46565 fix(voice): preserve Android transcripts and Claude utterances 2026-11-09 07:27:02 -08:00
Codeman maintainer 4f29b0187a Merge #732: feat(settings): sync case options and selection across devices 2026-11-09 08:01:43 +01:00
Devvyn ea27adf104 fix(settings): case sync follows only a picked case and keeps its popover and undo honest
- follow lastPickedCase (written by saveLastUsedCase while sync is on), not lastUsedCase, so a quick-start or an agent's spawned worker no longer moves other devices
- close the open case-options popover when the follow or an import changes what it shows; follow through selectQuickStartCase(save:false)
- failed save reuses _noteSettingsWriteResult and says the choice lasts until the next sync
- rename undo renames the shared entry back instead of restoring the whole map; lastPickedCase follows a rename
- caseSettings and lastPickedCase added to the redaction, rename and backup-volatile lists and the docs
2026-11-09 11:17:16 +08:00
Codeman maintainer 078bd74bd1 fix(files): the review's fixes for the Files panel delete
The fixes #529's review asked for, each with a test.

- No inline handler. The button quoted the path inside
  onclick="...decodeURIComponent('<path>')", and encodeURIComponent leaves
  ' alone, so a file named x'-alert(1)-'.txt ran script in Codeman's
  origin and it's.txt was a syntax error. It is now bound in the existing
  .file-tree-item loops from the row's escaped data-path.
- Symbolic links are refused, never followed. validateSessionFilePath()
  returns the realpath, so deleting AGENTS.md -> CLAUDE.md deleted
  CLAUDE.md and left the link dangling. The path as named is lstat'ed,
  a link answers 400, and the inode is compared again before the unlink.
- The edit route's confinement whole: validateLocalSessionFilePath()
  behind withGuardedOutsideWorktree(), so an absolute path in a followed
  outside worktree obeys the same rules, and the sensitive, blocked and
  .git checks run on both the realpath and the path as named.
- Adopted sessions are refused like remote ones (the /tmp exception of
  the older file surfaces is not copied to a new one); Docker workspaces
  are allowed, as on the edit route. The workspace is probed bounded
  first (#516). Errors are thrown with their status.
- Deleting from search results re-runs the search, the row buttons stay
  visible on touch screens, the confirm and toasts have zh-CN text, and
  no button is drawn for remote or adopted sessions.
- Docs: CLAUDE.md, architecture-invariants, api-reference and the
  Working With Files wiki page.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-09 03:09:46 +01:00
Codeman maintainer 2a876731f6 feat(jcode): add jcode as a run mode
jcode (1jehuang/jcode) joins the CLI registry as the `jcode` run mode:
Run menu, phone overview, TUI, quick-start and POST /api/sessions
(`jcodeConfig: { model?, resumeSessionId? }`), local, SSH and Docker
(dedicated agent-image layer), plus codeman doctor and install.sh
through the generated catalogue. Measured on a live jcode 0.98.1 pane.

- Work detection reads jcode's braille status row and `<n>>` composer;
  alt screen with mouse strip and PageUp/PageDown paging like opencode.
- Every jcode TUI is a client of one shared per-user daemon whose tools
  run with the daemon's env, so no agent skill injection and no JCODE_*
  envOverrides prefix.
- New `capabilities.sharedDaemon`: a session kill spares descendants
  outside the pane's process group, so closing the tab that started the
  daemon no longer cuts every other jcode session off (measured).
- last-response answers an honest empty for an external CLI with no
  transcript reader that the pane segmenter cannot read (jcode alone).
- GET /api/jcode/status via the generic registry resolver.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
2026-11-09 02:52:13 +01:00
Codeman maintainer 236fecf6b9 chore: version packages
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 11:11:06 +01:00
Codeman maintainer 8a54ded78b Merge #784: a local model catalogue for every Mac memory size, and its weekly check 2026-11-08 11:10:13 +01:00
Codeman maintainer 8fa2884f48 Merge #787: turn the Codeman agent skill on by default 2026-11-08 10:41:11 +01:00
Codeman maintainer 83fb523979 fix(local-model): rollback copies follow each tag's own draft length
The previous commit counted 4 rollback copies of the recurrent state for every GGUF with a
prediction layer, the runtime's default `draft_num_predict`. A tag can set its own in its
params layer, and the runtime then passes that as `--spec-draft-n-max`, which is what
`need_n_rs_seq()` turns into rollback copies. Read on 2026-11-08:

- qwen3.6:35b-a3b-mtp-q4_k_m: draft_num_predict 2, so 2 copies (was counted as 4).
- qwen3.8:27b-mtp-q4_k_m: draft_num_predict 4.
- qwen3.8:27b-q8_0: none in its params, so the runtime's 4.

The 35B-A3B GGUF row's overhead drops by 132 MB: 0.971 instead of 0.976 on a 36 GB M3 Pro or
M3 Max, the same pick. test/local-model-catalog.test.ts now carries the drafted tokens per row
instead of a yes/no prediction layer.

Also states what was verified about llama.cpp's checkpoint default: 8 from b6800 to b8200,
32 from b8250 together with a checkpoint every 8,192 prompt tokens (common/common.h at those
tags), in place of an inferred reason. Checked in the b12111 source as well: the draft context
of a Qwen-family MTP model caches the prediction block alone (`mtp_on_hybrid_qwen`, layers at
or above n_layer()), and the main context leaves it out, so the row counts that layer once.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 10:38:12 +01:00
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 46fa954b2e docs(local-model): what each Mac gets, and where every memory figure comes from
docs/local-models.md gains "Which model fits which Mac": the answer of the
stock catalogue for every memory size from 8 to 512 GB, why the chip
changes it at 36 to 96 GB, and why nothing is offered below 65,536 tokens.
"How much memory a model needs" explains the two runners (llama.cpp
allocates its K/V cache at load, MLX grows it and keeps up to 8 GiB of
prefix snapshots), the three runtime settings the llama.cpp rows assume,
and per row where its memory and speed figures come from. The check after
the download now says that for an MLX build it proves only the weights,
and "What to know" says most figures are calculated, not measured.

CLAUDE.md: every row names its runner and carries its own figures, and
the llama.cpp rows and runtimeEnv() change together.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 09:35:28 +01:00
Codeman maintainer 0c0ada7cdb docs(agent-skill): existing installs that stored off are switched on once
The changeset, CLAUDE.md, the invariants, the agent control plan, both READMEs
and the wiki's Codeman Skill and Settings Reference pages said an install whose
App Settings were saved on an earlier version stays off until switched on. They
now say the first 1.50.0 start switches a stored off on once, and that turning
it off afterwards sticks. The changeset marks it "Behaviour change:", says the
migration cannot tell a chosen off from the old default, and tells users to
reload a tab left open from before the upgrade before saving App Settings in
it. CLAUDE.md lists the marker file among the data dir's state files, and the
invariants record why it stores true, why the marker is its own file, and
where it runs.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 09:15:58 +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 cd2265f8d0 docs(agent-skill): name GitHub Copilot among the CLIs that get no skill copy
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>
2026-11-08 08:35:38 +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 9c64fc128d docs(agent-skill): say the skill is on by default and stays out of git
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>
2026-11-08 07:45:20 +01:00
Codeman maintainer e8a63ede00 Merge feat/local-model-recommendation: recommend and install a local coding model on this Mac (experimental)
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>
2026-11-08 04:06:46 +01:00
Codeman maintainer 2f9cc7aabc Merge #780 feat(files): follow the agent into a worktree outside the session folder
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 04:05:56 +01:00
Codeman maintainer e6c79c8e8c Merge #779 fix(macos): never run Apple's placeholder git, which opens the developer tools window
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 04:05:49 +01:00
Codeman maintainer 98c4a3d386 Merge #778 fix(cli): a running server notices a CLI the installer just added
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 04:05:41 +01:00
Codeman maintainer 4b349b57f6 Merge #773 feat(desktop): install Codeman from the app, with no Terminal and no password
Conflicts resolved as on test/desktop-macbook: install.sh usage() lists CODEMAN_NO_ADMIN=1 or 0 and #773's CODEMAN_AI_CLI and CODEMAN_PROGRESS=1; probe.rs keeps #781's agent() with TIMEOUT, MAX_BODY and probe_within all pub; the desktop README keeps both known-limits entries.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-08 04:05:38 +01:00