mirror of
https://github.com/Ark0N/Codeman.git
synced 2026-10-05 23:19:43 +02:00
ffaa5ee80c583b8e2983e773c0f1e0924bebaf34
26
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Codeman maintainer
|
b451b3851e |
fix(mcp): no file text in sync errors, follow relocated config dirs, docs and Settings polish (#521 review)
Maintainer merge-time fixes for the MCP server sync (opt-in mcpSyncEnabled, synced, default OFF).
M1, parse errors echoed config text (secrets included) into the HTTP response and Settings:
smol-toml's TomlError carries a code frame of the offending lines and V8's JSON "Unexpected
token" errors quote source. Both catch sites now go through describeMcpSyncError(): a parse
failure is reported by line/column only ("not valid TOML (line 3, column 21)", "not valid
JSON"), an errno failure by Node's own message (code, syscall, path), the module's own
messages via a McpConfigError class, anything else as "unexpected error". Tests put a secret
on the broken line (TOML, both JSON message shapes, and a write refused at the re-parse that
would have quoted a copied server's env) and assert it is absent from the result and from the
route's response body; they fail against the old code.
M2, CODEX_HOME / CLAUDE_CONFIG_DIR / XDG_CONFIG_HOME were ignored, so a sync could create a
file the CLI never reads and report success: new optional registry field
capabilities.mcpConfig.relocation { envVar, path } (registry data, no id branch; schema
reuses the env-name and no-traversal path rules). Declared for claude (CLAUDE_CONFIG_DIR,
checked in the 2.1.289 binary), codex (CODEX_HOME), opencode (XDG_CONFIG_HOME) and gemini
(GEMINI_CLI_HOME, gemini-cli paths.ts); antigravity follows $HOME only (agy 1.1.12 has no
relocation var). Resolved from the server process env at call time: absolute moves the file,
empty means unset, anything else reports the target with the new status "skipped" plus the
reason and writes nothing. Dedupe is now by resolved file. When a caller overrides `home`
without passing `env`, process.env is not consulted, and the route tests clear those vars so
a CI runner's XDG_CONFIG_HOME can never aim a write outside the temp HOME.
M3, feature undocumented: CLAUDE.md Key Patterns paragraph (opt-in, admin-only, additive
only, backups, re-parse validation, 0600 for copied secrets, names-only responses with
position-only parse errors, capabilities.mcpConfig and relocation), a Settings-Reference row
in the wiki, and docs/cli-registry.md + docs/api-reference.md updated for relocation, the
"skipped" status and the error policy.
Nits:
- N1 Preview/Sync before Save: the UI remembers the saved value on open and says "Save
settings to turn MCP sync on first" instead of calling the routes; the 403 message also
says to turn it on and save.
- N2 non-admins in multi-user mode: _applyMcpSyncAdminGate() hides the whole MCP group, called
from applyMcpSyncVisibility() and the codeman:me event like the CLI-management gate.
- N3 scope chip says "synced".
- N4 "(1 servers)" pluralised; the unsupported list only names installed CLIs (route test
pins it with a per-test installed set).
- N5 McpSyncResult / McpSyncTargetResult moved to src/types/mcp-sync.ts (barrel export); only
the route imported them, so no churn.
Verified with an isolated instance (throwaway HOME, own instance and tmux socket) and
Playwright: chip, save-first message, preview rendering and the admin gate.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
|
||
|
Codeman maintainer
|
9649b5019b |
Merge pull request #521 from opticon454/feat/mcp-sync
feat(mcp): sync MCP servers across enabled CLIs # Conflicts: # src/config/cli-registry/schema.ts # src/config/cli-registry/types.ts # src/web/public/settings-ui.js |
||
|
DevvynandClaude Sonnet 5.5
|
f39c66e4e8 |
feat(terminal): newline chord as registry data, plus a Key tester in Settings
capabilities.newline replaces choosing the Shift+Enter bytes in the send-key route. Key tester shows the keydown/keypress/keyup a browser reports. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> |
||
|
DevvynandClaude Sonnet 5.5
|
4398dbfad0 |
feat(mcp): make sync opt-in and address review
Opt-in (mcpSyncEnabled, default OFF; routes 403 until on). Review fixes: - codex TOML read/validated with smol-toml: CRLF, inline tables and command-less tables no longer yield a duplicate [mcp_servers.x]; the new text is re-parsed before writing - null-prototype tables and own-key checks; unsafe names ignored at every level - servers switched off in their own CLI (codex/opencode/antigravity) are not copied - only CLIs that are installed or already have a config file take part - files receiving env/headers are left 0600; symlinked configs are written through - one apply at a time (409), unique tmp files cleaned on failure, failed status - routes set real HTTP status codes; api-reference section; format type single-sourced Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> |
||
|
DevvynandClaude Sonnet 5.5
|
41a10b159e |
feat(mcp): add Antigravity, fix Gemini http/sse shape, report unsupported CLIs
Formats verified against real agy/gemini/codex mcp add output. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> |
||
|
DevvynandClaude Sonnet 5.5
|
e6b258fc44 |
feat(mcp): sync MCP servers across enabled CLIs
Adds capabilities.mcpConfig to the CLI registry (Claude, Gemini, Codex, OpenCode), an additive src/mcp-sync.ts, GET/POST /api/mcp-sync and a Settings > Agents & CLIs control. Never edits or removes an existing server; backs up each file it changes; reports conflicts. Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com> |
||
|
Codeman maintainer
|
7659ca8b44 |
fix(session): keep a tab working while Claude waits for its own workers
When Claude hands work to an ultracode workflow or background agents, it ends its own turn and closes it with `✻ Waiting for 1 dynamic workflow to finish` instead of `✻ Brewed for 1m 18s`, then resumes by itself when the workers report back. The pane sits quiet with the composer up, so the idle probe called the session idle for the whole wait. At phone width the workflow's progress row also drops its ticking timer, so nothing on screen changes for minutes. A new optional registry field, `capabilities.workDetect.awaitingLine`, names that closing row, and `_probePaneWorking()` counts it as work. Claude renders the row once from a snapshot and never redraws it, so the same words stay on screen after the workers finish. `isAwaitingWorkers()` therefore tests only the newest column-0 row directly above the composer, never the whole pane and never the PTY stream; a follow-up turn always puts rows of its own there. The column-0 anchor also keeps an agent from holding its own tab busy by printing the sentence. Verified against the live Mac mini pane that reported the bug (2.1.283), and end to end on an isolated instance: an ultracode session running a 90 s workflow at 46 columns stayed busy through the wait and the follow-up turn, then went idle 6 s after that turn closed. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com> |
||
|
Codeman maintainer
|
8536aaef7b |
Merge pull request #473 from irisitymichaelgrundberg/feat/session-watching-badge
feat(approvals): let a session watching its own background work keep quiet (#468) # Conflicts: # src/config/cli-registry/stock.ts |
||
|
Michael GrundbergandClaude Opus 5
|
05c788ce9d |
fix(watching): close the review findings on the label and its window
A dual review (Codex CLI and Claude's code-reviewer, same diff, same brief) found the trust boundary weaker than the comments around it claimed. Eleven findings, all applied. The two blockers were both about who can write the row the label is read from. Claude's window covered two rows, and the second one is the status line, whose command a session running with permissions bypassed can write into its own `.claude/settings.json` — so an agent could print `· 1 monitor ·` onto a row of its own and silence its own idle alert. The default window is one row now, which is the footer and nothing else, and the constant says why. Separately, the label reached `data-tab-meta-sig` unescaped while the row is installed with innerHTML, which is an injection sink for any config-supplied pattern whose capture group is permissive; it goes through escapeHtml() like every other untrusted string in that file. The Codex entry could not be fixed the same way, and now says so. Its row is third from the bottom only while a terminal runs; with none running that slot holds the last row of the transcript, so matching the complete row (with the `/stop to close` tail, window narrowed to three) raises the bar without closing it. What contains it is `hooks: 'none'`: no hook event from a codex session reaches notePrompt(), so a forged label costs a wrong badge and cannot quiet an alert. The registry comment, `docs/cli-registry.md` and the test all state that rather than claiming a guarantee the code does not have. Also from the review: the TUI header badge no longer counts an acknowledged item, which was the same gate the classifier fix already went through and was wrong for human acknowledgement too; the TUI approval card reads the quiet reason and drops to a new `info` tone instead of asking for a reply; the badge carries an aria-label, because the phone it was built for has no hover target; the schema refuses `watchingLines` without a `watchingLine`; and the pattern and its window are resolved together rather than one memoized and one not. Documentation moved with it. The mechanism now lives in `docs/architecture-invariants.md` with CLAUDE.md keeping the rule and a pointer, `docs/wiki/Notifications-And-Approvals.md` tells users why a session stopped buzzing, and both that page and the changeset name the limitation neither did before: a question asked in plain prose is not a dialog, so it is silenced along with the false alarms while background work runs. Verified live again after the narrowing, on an isolated beta: a Claude session reported `1 monitor` and took its idle prompt acknowledged, and a Codex session reported `1 background terminal` against the full-row anchor. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Michael GrundbergandClaude Opus 5
|
ce80b7a212 |
feat(terminal): take the transcript gutter off a copy, at the width the CLI declares
Copying a paragraph out of a Claude Code or Codex pane puts that pane's own two-column transcript gutter on the clipboard, so every pasted line arrives indented. #451 shipped the trailing half of the copy clean and left the leading half out, because deriving the width from the selection fires on 73% of ordinary indented text and cannot tell a margin from content. The width is DECLARED rather than derived. `capabilities.transcriptGutter` on the CLI registry is a bounded integer; claude and codex each declare 2, measured on live panes, and no other stock entry declares any, so a CLI whose transcript layout nobody has measured is never touched. The server publishes the map as `window.__codemanTranscriptGutter`, built by filtering `enabledClis()` on the capability rather than by listing ids, and `_activeCliGutterColumns()` looks the active session's mode up in it. The copy path reads no terminal buffer at all. The declared width is a CEILING, not the answer: `clean()` strips the lesser of it and the run every selected line shares. A block can therefore only shift as a unit, the structure inside a selection survives by construction, and a selection reaching column 0 loses nothing. That is what keeps a `git log` body at its own four-space indent inside an agent's two-column gutter. Codex was measured separately, because it renders nothing like Claude: it draws boxes narrower than the pane and pushes its transcript into ordinary scrollback. On a live 0.154.0 answer its `•`/`›`/`⚠` markers sit in the gutter, prose continuations sit at 2, and a nested YAML block the model wrote rendered at 2/4/6/8 for its own 0/2/4/6. Replayed at 100, 120, 160, 198, 235 and 282 columns its indents were 0, 2, 4, 6 and 8 at every one, never 1. Copying that YAML out of a live Codex pane now yields 0/2/4/6: gutter gone, nesting intact. Two derived versions were built and measured first, and both are recorded in the code because both looked correct: - Painted trailing padding — a full-screen TUI writes real spaces across the unused part of a row, a shell leaves them never-written for xterm to trim — has no false positives and never over-stripped. It is also a function of pane WIDTH: the padding exists only while a rendered line stops short of the CLI's own layout width, and Claude's prose wraps to fill it. Dragging the same two prose rows of one live transcript at five window sizes, the share of padded rows ran 44%, 6%, 6%, 7% and 87% at 123, 160, 198, 235 and 298 columns, so the strip silently did nothing at every ordinary size while a corpus captured entirely at 282 columns said it worked. - Taking the narrowest indent on the rows around the selection fires at every width and over-strips about 1% of selections, because a file listing inside the transcript can be the narrowest thing on screen. Measured over 1,392,281 selections — every 1, 2, 3, 5, 10 and 20-row window of real Claude screens replayed from live PTY streams at 100, 120, 160, 198, 235 and 282 columns — the declared width over-strips none, breaks no relative indent and alters no text, and serves 100% of the selections whose own indent covers the gutter. Verified end to end in a browser with a real mouse drag and a real Ctrl+C: Claude and Codex panes paste flush at 123, 198 and 298 columns, a shell pane is untouched at every one. The strip sits behind `copyStripMargin` (App Settings, Selection & clipboard), per-device and default ON: a display key, absent from the .strict() SettingsUpdateSchema, read as `!== false` because the desktop branch of getDefaultSettings() returns {}. The toggle is checked before the map. Two review findings from #451, handled: - The mid-row flag governs ONE line now. `range.start.x > 0` excludes only the first selected line, the one whose margin the mousedown genuinely cut off, so the same three rows no longer produce three different clipboard results. - The reversed-drag finding does not reproduce on the pinned xterm. `getSelectionPosition()` reads `_selectionService.selectionStart`, whose getter returns `SelectionModel.finalSelectionStart`, and that swaps the pair when `areSelectionValuesReversed()` says so. A real upward mouse drag through chromium against xterm 6.0 reports the same range as the downward drag. `_normalisedSelectionRange()` keeps the ordering as a guard, because the model one layer down exposes the unnormalised fields under the same two names. Tests: test/terminal-copy-clean.test.ts (64, up from 31), plus the injected script stripped in test/server-index-title.test.ts. Every guard is pinned: removing any one of seven reds at least one test, including declaring the wrong gutter width. Full suite green, 7,861 passed, 0 failed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Michael GrundbergandClaude Opus 5
|
64c288a683 |
feat(codex): read Codex's own background-terminal row
Codex states background work too, and it says so in a different place. Claude writes `· 1 monitor ·` on the last row of the screen; Codex pins `1 background terminal running · /ps to view · /stop to close` ABOVE its composer, which puts that row third from the bottom once the status line and the composer are counted. So how far up the screen to look is now per-CLI data as well: `capabilities.workDetect.watchingLines`, bounded to 1..8 by the schema, and defaulting to Claude's two. That bound is the point. The window is half the injection guard, since every row it adds is another row the agent itself may be able to write, and the label is what silences an idle alert. The other half is the anchor, and Codex's is ` · /ps to view`: chrome naming a slash command only the CLI can offer, so a session that writes "I left 1 background terminal running for you" into its own output matches nothing. Measured against a live codex-cli 0.154.0 pane rather than read out of a binary. The row appears when the terminal starts, follows the composer down as the conversation grows, and is gone after `/stop`. Verified end to end on an isolated beta: the session payload carried `watching: "1 background terminal"` and the badge rendered with it, and both cleared when the terminal stopped. The fixtures in the tests are that capture verbatim. Codex has no hook signals, so no idle prompt and no false NEEDS YOU row: for a Codex session this is the badge alone, which is the case the maintainer said a registry field could cover and a hook never could. Cross-CLI tests pin that neither pattern fires on the other's screen, and that a CLI declaring nothing still reports nothing. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Michael GrundbergandClaude Opus 5
|
3f2cde2db7 |
feat(session): say when a session is watching its own background work
An agent that arms a monitor, backgrounds a shell or hands a task to a cloud session is told to end its turn. The pane then falls quiet, Claude Code's idle_prompt notification arrives a minute later, and every surface files the session under NEEDS YOU with nothing for a human to answer. Claude states what it is still running on the last row of its screen (`⏵⏵ bypass permissions on · 1 monitor · ← for agents`). That row is now `capabilities.workDetect.watchingLine` in the CLI registry, guarded by compileVersionRegex() like every other config regex, and the idle probe reads it off the capture it already takes: `watchingLabel()` in session-activity.ts searches the last five lines only, so a session that PRINTS "1 monitor" is not mistaken for one running it. The label lands on Session.watching and rides toLightDetailedState() out to every surface. The phone overview, the desktop home rail and the rich sidebar rows wear it as a `watching` badge in the accent colour, beside the state pill and never in place of it: an agent can arm a monitor and ask a question in the same breath, and only the pill says which. Verified end to end against a throwaway session on an isolated beta instance: the payload carried `watching: "1 monitor"` once the turn ended, the badge rendered next to a yellow `waiting` pill, and both cleared when the monitor died. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
DevvynandClaude Sonnet 5
|
e2034177c5 |
fix(custom-model): root-cause and fix DeepSeek's HTTP_404 (missing /v1)
DeepSeek Harness's own bundled provider module
(@deepseek-ai/dsh-llm-deepseek) builds its request URL as
`${DEEPSEEK_BASE_URL}/chat/completions` with no `/v1` insertion of its
own (its real public API, https://api.deepseek.com, expects the
caller's base URL to already carry any needed prefix), while
llama-swap/llama.cpp only ever serves the OpenAI-conventional
`/v1/chat/completions`.
Confirmed two ways:
- Installed the real @deepseek-ai/dsh package (all its actual
published dependencies) into a scratch dir purely to read
dsh-llm-deepseek's source: `fetch(`${connection.baseURL}/chat/
completions`, ...)`, baseURL read straight from DEEPSEEK_BASE_URL —
the same grep-the-real-source bar pi/grok's fixes were held to.
- Live against the test-picker's llama-swap: `POST <baseUrl>/chat/
completions` -> 404, `POST <baseUrl>/v1/chat/completions` -> 200,
same endpoint. dsh's own error template ("DeepSeek API error (HTTP
${status})") reproduces the originally-reported
"dsh: HTTP_404: DeepSeek API error (HTTP 404)" exactly.
- New registry field `appendV1Suffix` (env kind only, deepseek's entry
alone — claude/gemini must NOT get it, since claude was already
confirmed working against the unmodified baseUrl). When set,
buildCustomModelInjection runs endpoint.baseUrl through the same
withV1Suffix() helper configDir-kind CLIs (pi/grok/codex) already
use, instead of writing it verbatim.
Not yet re-run end-to-end through a real dsh binary — no install
available in this environment (not in PATH, and the test-picker
container doesn't bundle it) — so this is source-confirmed and
live-verified at the HTTP level, not yet promoted to "verified"
alongside claude/opencode/pi/grok/omp. Docs (custom-model-endpoints.md,
the plan doc's confidence table, the wiki page, CLAUDE.md) all updated
to reflect this precisely rather than leaving the old "root cause not
identified" claim in place.
2 new/updated tests for the /v1 suffix (including idempotency against
a baseUrl that already ends in /v1) plus a corrected mock-server
contract test. Typecheck/lint clean; full suite shows no new
regressions.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
|
||
|
DevvynandClaude Sonnet 5
|
211b872335 |
feat(custom-model): skip Claude Code's first-run wizard on custom-model launches
A fresh, isolated CLAUDE_CONFIG_DIR (used to keep an injected API key away from a stored claude.ai OAuth login) looks like a brand-new Claude Code profile to the CLI, so it replays its ENTIRE first-run sequence on every single launch: the theme picker, the security-notes screen, the per-project "trust this folder?" dialog, and (running with --dangerously-skip-permissions) a one-time bypass-permissions warning — confirmed live, none of which a real, already-onboarded profile shows again. - New registry-declared env-kind field `skipFirstRunPrompts` (alongside apiKeyTrustFile, which it reuses) — claude's entry only, carried through buildCustomModelInjection (pure) into applyCustomModelInjection (IO). - seedFirstRunOnboardingState(): merges hasCompletedOnboarding: true and this session's own projects[workingDir].hasTrustDialogAccepted: true into the same <configDir>/.claude.json the API-key trust file already writes to — other projects and other fields on this session's own entry are left untouched. - seedSkipBypassPermissionsPrompt(): merges skipDangerousModePermissionPrompt: true into <configDir>/settings.json, a separate file, same corrupt-tolerant merge behavior. - applyCustomModelInjection() gains an optional workingDir parameter, threaded from session.workingDir (dedicated apply route) / resolvedCasePath (quick-start route) — boot recovery omits it (a dialog already answered once needs no re-seed on the same, persisted isolated directory). Tests added at the pure-builder, IO-wrapper (including merge-preserves- other-fields and corrupt-file-tolerance cases), and existing directory- listing assertions updated for the new settings.json file. Typecheck/ lint/format clean; full suite shows no new regressions (baseline pre-existing Windows-environment failures unchanged, 8 more passing tests than before — the ones added here). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG |
||
|
DevvynandClaude Sonnet 5
|
97464bfa27 |
fix(custom-model): pre-approve the injected API key in the isolated Claude config dir
The CLAUDE_CONFIG_DIR isolation from the previous commit fixed the cosmetic
auth warning but introduced a real regression: an otherwise-empty config
directory has none of a real profile's prior custom-API-key approvals, so
Claude Code stops at an interactive 'Detected a custom API key - use it?'
prompt on every single launch. Confirmed live. With nobody at a TTY to
answer, the prompt's own default ('No') silently refuses the very key this
feature just injected, which looks like the endpoint being ignored.
Adds apiKeyTrustFile to the env-kind customModelInjection capability shape
({relPath, shape: 'claude-api-key-responses'}), set on claude's entry to
{relPath: '.claude.json', shape: 'claude-api-key-responses'}. The apply step
merges customApiKeyResponses.approved: [apiKey] into
<isolatedConfigDir>/.claude.json - the exact field a real answered prompt
itself writes to (confirmed against a real ~/.claude.json after answering by
hand once), so this answers the prompt in advance rather than bypassing it.
Merges onto whatever the CLI already wrote into that file on an earlier
launch in the same isolated directory rather than overwriting it; a missing
or corrupt file is treated as empty rather than failing the apply.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
|
||
|
DevvynandClaude Sonnet 5
|
0e8b1981af |
fix(custom-model): isolate Claude config dir and inject real context length
Addresses two live-validation findings on the Run-menu custom-model picker: 1. Both claude.ai and ANTHROPIC_API_KEY set warning. Claude Code still coexists an OAuth login with an injected ANTHROPIC_API_KEY in the same config directory and warns about it (confirmed cosmetic - the API key wins for actual requests, verified via a real session's own API Usage Billing line). A custom-model claude session now gets an isolated CLAUDE_CONFIG_DIR (registry-declared via a new configDirVar field, empty, no files written into it) so there is nothing to conflict with. projects is symlinked (junction on Windows) back into the real config dir so the response viewer, subagent windows and Read My Mind keep working for that session, best-effort. 2. Context-window overflow. Claude Code assumes a large default context window for a model id it doesn't recognise and never compacts, so a custom endpoint's real, much smaller context (verified live: a 400 exceeding a 16384-token llama-swap model with a stock ~33.7K-token system prompt) silently overflows. Discovery now also learns each model's real context length from llama.cpp/llama-swap's GET /props?model=<id> (n_ctx), but ONLY for a model llama-swap's own /v1/models response already marks status.value === 'loaded' - never an unloaded one, since llama-swap treats ?model= as a routing hint and probing an unloaded model risks triggering an actual, slow, GPU-swapping load as a side effect of read-only discovery. A server with no status field at all gets no enrichment rather than a guess; a model not probed this round keeps its previously-learned value until it disappears from the list entirely. Stored per model (CustomModelHost.modelContextLengths) and applied via a new contextLengthVar registry field, set to CLAUDE_CODE_MAX_CONTEXT_TOKENS for claude. Both new fields live on the existing env-kind customModelInjection capability shape, declared only on claude's registry entry - every other CLI's injection is unaffected (pinned by test). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG |
||
|
Codeman maintainer
|
942bf37e48 |
fix(custom-model): unset injected env on clear, resume on restart, select the model for pi/omp/grok
Custom Model Endpoint Profiles (#393) let a session point its CLI at a custom OpenAI-compatible endpoint by injecting env vars or a config file and restarting the CLI in place. Review of the apply path found four things, two of them destructive. This lands all four plus the smaller items from the same review. 1. Clearing a selection did not clear it. The injected vars reach the CLI via `tmux setenv`, which persists at the tmux-session level and is inherited by `respawn-pane` (measured: `setenv FOO bar` survived two successive `respawn-pane -k`), so deleting the keys from the session's envOverrides relaunched the CLI still pointed at the old endpoint, and for the configDir kinds at a HOME/CODEX_HOME/GROK_HOME that had just been deleted. `Session.setCustomModel()` now reports the removed keys, queues them (`_pendingEnvUnsets`), and `RespawnPaneOptions.unsetEnvKeys` carries them into `applyEnvOverrides()`, which `setenv -u`s them before re-applying the live overrides, on the same path that already unsets the legacy CLAUDE_CODE_EFFORT_LEVEL. Verified on a private tmux socket that `setenv -u HOME` hands the next respawn the global HOME back. 2. Applying a model to a local claude session killed the pane. The relaunch was `claude --session-id <id>` and Claude refuses an id that already has a transcript, and unlike the dead-pane respawn this one kills a working pane first. `restartCli()` now pins the live conversation id as the resume id for that respawn when the CLI's launch declares a `fallback` chain, which renders the same `--resume <id> || --session-id <id>` shape the docker and remote pane commands use. Gated on the registry shape, not the CLI id: an entry whose resume id is minted by the CLI itself never declares that chain. 3. pi, omp and grok wrote their config file and then launched without the `--model` that selects it, so the file was ignored. The registry entry now declares `customModelInjection.launchModel` (`custom/{modelId}` for pi and omp, grok's `[model.codeman-custom]` block name), the builder renders it, and `_withCustomModelLaunchModel()` applies it onto the respawn options through `legacyConfigField`, leaving the stored <Mode>Config untouched so a clear falls back to the user's own model. A model id the CLI's `model` token pattern cannot carry is refused with a 400 rather than silently dropped by the argv engine. 4. Remote (SSH) and Docker sessions reported `restarted: true` and changed nothing: their `restartCli()` reattaches the durable tmux rather than relaunching the agent, and the env lands on the local pane. Both are refused with a 400 until those paths are plumbed. Smaller items from the same review: - The selection survives a Codeman restart as the disk-only `__customModel` bookkeeping (endpoint, model, injected key NAMES, config dir, launch model; never the values, which carry the API key). Recovery re-derives the values from the endpoint store through the same apply path the route uses and keeps the bookkeeping even when the endpoint is gone, so a later clear still has keys to unset. - Discovery goes through `webviewFetch()`, so the RESOLVED address is judged by the same egress guard the web-tab proxy uses, and `baseUrl` reuses `webviewUrlSchema` (http(s) only, no embedded credentials, link-local and cloud-metadata addresses refused). undici's `fetch failed` wrapper is unwrapped so the user sees the ECONNREFUSED underneath. - `custom-model-hosts.json` is written 0600 via tmp+rename, the per-session config dir 0700/0600 (pi and omp embed the key literally), and that dir is removed with the session. - `PR.md` is gone from the repo root and the design doc moved to `docs/custom-model-endpoints-plan.md` with the LAN address and the personal name scrubbed; every reference follows. The guide's `authStyle` text matches the shipped schema (`bearer | api-key`, default `bearer`) and says that `customModelEndpointsEnabled` is read by nothing until the picker lands. - `config/tsconfig.scripts.json` typechecks `scripts/test-local-llm-harnesses.ts` (four real type errors fixed). It is not yet wired into `npm run typecheck` because that line differs on master; adding `&& tsc -p config/tsconfig.scripts.json` there is the one-line follow-up. Tests: `test/session-custom-model-restart.test.ts` drives a real Session and fails on the unfixed code for items 1 to 3; the route suite covers item 4 and the pattern refusal; `test/tmux-manager.test.ts` pins that the unsets run before the overrides and that a shell-metachar key never reaches tmux. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> |
||
|
Codeman maintainer
|
1e42cb4e2d |
Merge pull request #393 from opticon454/feature-custom-llm-server-support
feat: Custom Model Endpoint Profiles (local or cloud, all harnesses) |
||
|
DevvynandClaude Sonnet 5
|
a0628a40e8 |
fix(cli-registry): address maintainer review on #380
Rebased onto current master (the one real conflict was the import line
in docker-hosts.ts Ark0N flagged; kept both), then addressed every
point from the review:
**1. Rebase.** Done — this branch now sits on current upstream/master.
**2. Agent-image special cases are data now, not an id-keyed table
outside stock.ts.** `AGENT_IMAGE_SPECIAL_CASE_IDS`/`AGENT_IMAGE_SPECIAL_CASES`
are gone. `CliDiscovery.install.agentImageLayer?: { kind: 'dedicated';
reason: string }` is a field on the registry entry itself (pi,
deepseek), `reason` is required by schema.ts, both producers
(docker-hosts.ts and cli-catalog.mjs) filter on its presence instead
of an id, and the coverage test reads it from the generated catalogue.
Also added the npm-package-name validation to the TS producer, which
only the .mjs one had — same SAFE_PACKAGE regex, duplicated
(necessarily, one side can't import the other) and now pinned
byte-identical by a new parity test.
**3. Changeset said five, it's eight.** (Not nine — see the DeepSeek
point below, which changes the true count.) Reworded to state it
structurally rather than pin a number that will go stale again.
Then the four behavior-changing findings:
- **DeepSeek was offered as a normal install option but can't actually
drive a pane.** `npm install -g @deepseek-ai/dsh` installs the
launcher only; DeepSeek ships no profile that can run standalone.
The generator now emits an empty install command for any
`launcherProfile` entry, so install.sh's menu (which requires a
non-empty command) skips it and falls through to its docs URL hint
instead — matching what the old hand-written code did before this
PR replaced it.
- **wget-only hosts lost every automatic install, including the npm
ones that never needed curl.** The menu-building loop now filters
PER ENTRY (only a command starting with `curl ` is held back) rather
than wiping the whole menu when DOWNLOADER != curl.
- **The DISPLAY/TRUSTED split and the catalogue refresh didn't hold up
under review** (refresh's only real write was the label; it ran
before the Node existence check; its own eval-detection test was
tripped by the word "eval'd" in a comment). Dropped entirely per
your own recommendation — embedded catalogue only, no network
fetch, no second array. install-sh-invariants.test.ts now asserts
the refresh/DISPLAY machinery does not exist rather than testing its
internals.
The three take-or-leave items, applied:
- `dsh_banner_probe`'s bash 3.2 empty-array bug: `${runner[@]}` →
`${runner[@]+"${runner[@]}"}`. Verified live in a real `bash:3.2.57`
container with `timeout` removed from PATH — crashed before, clean
now, full `detect_all_clis` path exercised end to end.
- `docker-agent-image-coverage.test.ts` now anchors on each layer's
`<binary> --version` proof line instead of `Dockerfile.includes(binary)`,
which stayed true if a layer were deleted but its comment survived.
- Doc drift: docs/docker-cases.md (four → five, and now describes the
data field), docker/agent.Dockerfile's "other four CLIs" comment (no
longer a magic number — CLI_NPM_PACKAGES is generated and can grow),
CLAUDE.md's install.sh size (104KB → ~112KB) and its stale mention of
the now-dropped refresh.
Verified: tsc clean, prettier clean, the full targeted suite (142
tests across the 8 affected files) green, and the full `npm test` gate
diffed BY TEST NAME against a clean upstream/master baseline run on
this same machine — identical 201-name failure set both sides (168
tests / 67 files, all pre-existing Windows-environment noise: symlinks,
PTY spawning, POSIX permission bits — none of it touching anything
this PR changes), zero new failures either side of the diff.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R9ZSTEenc8soSu9bTi8Xru
|
||
|
DevvynandClaude Sonnet 5
|
61779745aa |
test(custom-model): make the harness smoke test dynamic, verify all 9 CLIs end-to-end
Rewrites scripts/test-local-llm-harnesses.mjs -> .ts to read the live CLI
registry (enabledClis()) and call the real production
buildCustomModelInjection()/applyConfigDirInjection() instead of keeping a
second hand-maintained copy of every CLI's env/config shape. A future
registry change (new CLI, edited env var, fixed config template) is now
picked up automatically with zero edits to this script; only the one-shot
invocation flags (info the registry genuinely doesn't model) stay in a
small hand-maintained ONE_SHOT table, and a registry CLI with no entry
there reports UNKNOWN rather than being silently skipped.
Extracted src/custom-model-injection-apply.ts (applyConfigDirInjection/
removeConfigDir) so the production route and this script share one
implementation instead of two.
Full end-to-end run against a real llama-swap server, inside a
codeman/agent:llm-test Docker image with all 9 CLI binaries:
- claude, opencode, pi, grok, omp: PASS, real "hello world" replies
- codex: confirmed FAIL for a real protocol reason, not a bug — it only
speaks the Responses API since Feb 2026, which llama.cpp/llama-swap
don't implement
- gemini: confirmed FAIL, unresolved after real investigation — an
undocumented GATEWAY AuthType gemini-cli selects once
GOOGLE_GEMINI_BASE_URL is set rejects every auth-key format/override
tried
- deepseek: reaches the server (env vars are read) but gets a consistent
HTTP_404; root cause not identified, documented as best-effort/unknown
- antigravity: SKIP, no known mechanism (unchanged)
Two real bugs found and fixed along the way (grok, pi/omp registry
entries in stock.ts): grok's original recipe (env vars) was flat-out
wrong, not just unverified — the real mechanism is a config.toml
[model.<name>] block redirected via GROK_HOME. pi/omp's PI_CONFIG_DIR
does nothing for either (grepped pi's entire bundled source — the string
appears nowhere); the real redirect is the child process's own HOME, and
both need `models` as an array of {id} objects, not an object keyed by
id (silently loaded zero models otherwise).
deployment_plan.md, PR.md, docs/custom-model-endpoints.md, and CLAUDE.md
updated with the final confidence table reflecting all of the above.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017HqNWfmtBU2KN29SvSVWB3
|
||
|
DevvynandClaude Sonnet 5
|
41416566aa |
feat(custom-model): Custom Model Endpoint Profiles (local or cloud, all harnesses)
Point any Codeman-supported harness (Claude, opencode, Codex, Gemini, Pi, Grok, DeepSeek, OMP) at a custom OpenAI-compatible endpoint instead of its native cloud backend, for a given session. Covers local hardware (llama.cpp, Ollama, vLLM, DGX Spark, Strix Halo) and cloud (Azure AI Foundry, OpenRouter). Off by default (customModelEndpointsEnabled, synced, default OFF). - Registry: capabilities.customModelInjection per CLI entry (env / configContentEnv / configDir / unsupported kinds) - Pure injection builder (custom-model-injection.ts) turning an endpoint + model id into the real env vars / config content per CLI - Endpoint store + CRUD routes (custom-model-hosts.ts, custom-model-routes.ts), discovery via GET /v1/models, SSRF-guarded - Session integration: Session.setCustomModel()/restartCli() (POST /api/sessions/:id/custom-model), reusing the existing respawn-pane -k primitive to restart the CLI process with new env - Multi-user hardening: every new redirect-capable env var added to its CLI's privilegedEnvKeys, closing a pre-existing gap where several were already reachable via the generic envOverrides field's prefix allowlist - Standalone scripts/test-local-llm-harnesses.mjs: spawns real CLI binaries against a real endpoint outside the web UI, independent of tmux/sessions - Mock-server contract tests (test/fixtures/mock-openai-server.ts) replaying every CLI's injected values through a real HTTP shape Real end-to-end validation against a live llama-swap server (inside a codeman/agent:llm-test Docker image with all 9 CLI binaries) found and fixed three real bugs before they shipped: - Codex's config.toml schema was wrong ([model].default table instead of a top-level model string + [model_providers.custom]); fixing it then surfaced a genuine, documented protocol incompatibility (Codex only speaks the Responses API since Feb 2026, which llama.cpp/llama-swap don't implement) - Claude Code's async session-title-generation call validates ANTHROPIC_DEFAULT_HAIKU_MODEL against its own internal model list and hangs the whole -p invocation on an unrecognized name; documented for chunk 6, worked around in the standalone script only (--bare is NOT safe for a real interactive session, which needs hooks) - The discovery route's authStyle: 'both' option (send both Authorization and api-key headers) reliably hung a real server; removed the option entirely rather than just changing the default Status: draft. Chunk 6 (frontend toolbar/settings UI) not yet built — see PR.md and deployment_plan.md for the full chunk breakdown and confidence table. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017HqNWfmtBU2KN29SvSVWB3 |
||
|
Codeman maintainer
|
f1b7283393 |
fix(cli-registry): guard workDetect.workingLine like every other config regex
#385 made the composer glyph and the working status line per-CLI registry data, which is right, but `workingLine` arrived as a config-supplied regex validated with a bare `new RegExp()`. That skips `compileVersionRegex()`, the helper the registry uses for exactly this: a `~/.codeman/clis.json` override can set the field, the compiled pattern is run against every accumulated PTY chunk and every pane capture, and a nested quantifier there backtracks on the event loop for the whole server rather than one session. Route it through the helper in both places, which are not redundant: the schema refine rejects the entry at LOAD time so a bad pattern never reaches a session, and `_workingLinePattern()` compiles through the same helper so the runtime cannot hold a pattern the schema would have refused. The helper returns null instead of throwing, so the Claude-pattern fallback stops being a try/catch and becomes structural. Both shipped patterns compile unchanged, and Claude's is behaviourally identical to CLAUDE_WORKING_LINE_PATTERN. Also match the Codex footer case-insensitively on the E. It was characterised against codex-cli 0.152.1, which prints a lowercase `esc`; a version capitalising it would make the whole fix silently inert, since the pane would simply never look like it was working. Docs: CLAUDE.md, architecture-invariants and cli-registry.md all still stated the Claude-mode-only rule this PR retires, and none of them named the new capability or the regex guard. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|
Ark0N
|
a49be03f96 |
Merge pull request #385 from irisitymichaelgrundberg/fix/work-detection-external-clis
Merging with follow-up fixes applied on master: workingLine routed through compileVersionRegex() in both the schema refine and _workingLinePattern(), the Codex footer matched case-insensitively on the E, plus the doc passages that stated the retired Claude-mode-only rule. |
||
|
Michael Grundberg
|
51957e2ed4 |
fix(session): let each CLI declare how its own pane shows work
A Codex session reported `isWorking: false` for its entire life, including
mid-turn. Codeman has four paths that mark a session working, and all four were
inert for Codex:
- The spinner fast path tests eight braille frames, and Codex animates none.
- The activity-streak fallback was wrapped in `!isExternalCliMode(mode)`.
- The pane probe inside `_confirmIdle` would have matched, since Codex prints
`esc to interrupt`, but arming it required the literal glyph `❯` and Codex
draws `›` on its composer row.
- The text detector sat inside `_processExpensiveParsers`, whose first statement
returns early for an external CLI.
Add an optional `workDetect: { promptGlyph, workingLine }` to CliCapabilities,
so the two strings that differ per CLI are registry data rather than constants
in the detector. Claude declares its existing pair and behaves as before. Codex
declares `›` and `esc to interrupt`. The text detector moves above the
external-CLI early return, guarded on the descriptor so a CLI without one still
skips the ANSI strip that the early return used to save it.
A CLI that declares no descriptor falls back to Claude's pair, and the
activity-streak gate now reads "has a descriptor, or is not external", so the
plain shell mode keeps the behaviour it had.
Rewrite the test that asserted the old premise in its own comment, so it makes
the same guarantee for a genuinely uncharacterised CLI, and add Codex coverage
built from verbatim pane captures on Codex CLI 0.152.1.
|
||
|
Codeman maintainer
|
3d8ffcb9a2 |
Merge pull request #357 from dignfei/feat/docker-adopt-existing-container
feat(docker): attach a case to an already-running container Conflicts came from work that landed after the PR was opened, and each is resolved onto the newer abstraction rather than by keeping the older code: - `defaultDockerCommandForMode` is registry-driven since #347, so the PR's `runsAsRoot` arm became `overlays.docker.rootCommand` (claude only). Claude Code still refuses `--dangerously-skip-permissions` as root in 2.1.261 and the refusal is visible only inside the container, so an adopted root container otherwise just shows a dead pane. Which flag to drop is a per-CLI fact, and `test/cli-registry-no-id-branching.test.ts` forbids expressing it as a branch. - The probe's mode list and its mode -> binary table both duplicated the registry. They now read `enabledCliIds()` / `discovery.binaries[0]`, which is also what fixes the merge's silent regression: the hand-written list predates `omp`, and the run menu gates every docker case on this probe, so owned containers would have lost that mode. `shell` needs no arm — it declares no binary, so it is dropped from the lookup and reported available regardless. - The per-mode `mode === 'claude' && !cliDir` chain in `tmux-manager.ts` is one `missingCliMessage(mode)` gate since #347; the PR's docker exemption moved onto it. Its test now pins the single gate instead of counting seven arms. - The create arm keeps #349's swap-limit warning filter, which the adopted arm never reaches; the run-mode list gains `omp` from #353. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TecFD9hvPYJ1mkkMtBQbT1 |
||
|
DevvynandClaude Opus 5
|
4830e662f9 |
refactor(cli-registry): make CLI backends data instead of per-mode branching
Every run mode is now a `CliEntry` in `src/config/cli-registry/` — discovery (search dirs, version + identity probes), the launch argv template, env handling, the `capabilities` flags that replace per-CLI branching, and the `overlays` that back the remote/docker pane commands. Code that used to ask "which CLI is this?" reads the entry instead. Behaviour is unchanged. `test/cli-registry-spawn-golden.test.ts` pins every spawn command as a literal string, captured from the hand-written builders before they were deleted, and `test/location-overlay-commands.test.ts` does the same for all 20 remote and in-container pane commands. Config can never contain shell text: an entry declares typed argv tokens, literals are validated against a safe-word pattern at LOAD time (a bad literal rejects the whole entry — a silently dropped `--no-approve` is not cosmetic), and values resolve through patterns NAMED in code, so a user `clis.json` cannot widen its own validation. `~/.codeman/clis.json` overrides any entry, read-only in this release. OMP is included as a registry entry rather than a tenth hand-written builder, so `buildOmpCommand()`, the omp availability pre-flight, the omp arm of `buildPathExport()` and the omp entries in the truecolor/NO_COLOR, alt-screen and doctor ladders all drop out. Guard rails: - `test/cli-registry-no-id-branching.test.ts` fails the build if per-CLI-id branching reappears outside `stock.ts`, in any of its four shapes (`===`, `!==`, `switch`/`case`, `includes`) — an `===`-only version would miss the negated forms, which is how 36 of them survived an earlier pass. Every allowlisted branch carries its reason. - `external`, `hooks` and `altScreen` stay three INDEPENDENT capabilities; deriving one from another shipped the `until=stop`-hangs-on-shell bug. - `param` is two namespaces. `launch.params` keys, `configSetenv.fromParam` and `privilegedParams[].param` all name a LAUNCH param; the legacy `<Mode>Config` wire field is separate, bridged only by `legacyConfigAliases`. Getting `privilegedParams[].param` wrong is SILENT — it is the multi-user bypass clamp's only handle on a CLI's privilege switch, and a wrong name clamps nothing with no error and no failing test — so `schema.ts` rejects an entry naming a param it never declared. - Registry data resolves AT CALL TIME (`sessionModeSchema()`, `allowedEnvPrefixes()`, `dependencyRegistry()`, the resolvers' `searchDirs` thunks). A module-level const freezes at first import, so a CLI enabled while the server ran moved the run menu but not that surface. - Six fields are annotated DECLARED-FOR-LATER and read by nothing (`shortBadge`, `accent`, `capabilities.echo`/`wheelForward`/ `keyboardAccessory`/`maxFrameBytes`): all frontend behaviour, transcribed rather than measured. A test pins the list so it cannot quietly grow. Three user-visible changes, all deliberate and named: - `probeDockerCliVersion()` derives the in-container binary from the registry rather than assuming it equals the mode name (`antigravity` runs `agy`). - The remote CLI version probe now covers grok and deepseek, which the hardcoded map it replaces omitted while its own comment said the rule was "every mode except shell". - `codeman doctor`'s CLI rows are generated from the entries, so Claude's install hint is the install command rather than a docs URL, five CLIs gain hints they never had, and the row order follows the catalog. Also hardened along the way: `sessionModeSchema()` is bounded at 24 chars (matching the `cliId` pattern) before its failure message quotes the value back, and `deepMerge` skips `__proto__`/`constructor`/`prototype` when reading the hand-editable `clis.json`. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WQkoi1cNegqVwZHgzx5SbJ |