The root CLAUDE.md had grown to 202 KB, all of it loaded into every
session. This lands the split drafted on 2026-10-10 (it sat uncommitted
in the shared checkout through two releases), redone on top of today's
master so nothing that landed since is lost:
- src/web/CLAUDE.md: the frontend invariants (every src/web/public/ UI
subsystem, the module notes, the XLSX preview limits, the z-index
stack). Claude Code loads it when a file under src/web/ is read; the
root file tells sessions to Read it before editing src/web/public/.
Its link targets are relative to the file so they resolve on GitHub.
- docs/releasing.md: the COM procedure (now nine steps, with the MCP
registry publish), behind a pointer in the root COM section. The
Version line stays in the root file.
- Root CLAUDE.md (130 KB): everything else, plus the split's trims: the
Core Files table, the reference-only rows of the Additional Commands
table, Data Flow and the respawn presets, whose rules already live in
the root's other paragraphs (the "Read before touching a subsystem"
line keeps the table's doc pointers).
Every other paragraph of master's CLAUDE.md lands in exactly one of the
three files, checked line by line; the paragraphs master changed since
the draft (tile grid, OSC 52, prompt uploads, file-path links and the
HTML view, markdown preview, z-index, MCP server, agent CLI and others)
are in their current form. Both new files join CLAUDE.md in
.prettierignore. Four code comments and docs/architecture-invariants.md
now point at src/web/CLAUDE.md for the moved sections.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The row said the path is "on the machine hosting Codeman" for every session.
A remote SSH session's workingDir is the path on the remote host, and a
Docker session's CLI runs inside the container the host folder is mounted
into. openSessionOptions now sets the description from session.remote /
session.docker (the id it targets was added with the layout fix).
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Conflict resolved in docs/api-reference.md: #607's prompt cache section and
#528's tabGroupId section are both kept.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude Code's tracker nulls recache_tokens_if_cold at a compaction or a tool-result clearing and only counts the expected rebuild at the next request, which also closes the window, so no report carried both and the old rule never fired. Stamp on the first warm null report after one that carried a value, carry it through idle re-reports and drop it at the next request; the readout now says "Context compacted at HH:MM" since a clearing opens the same window.
Also persist a changed report so a crash restores the latest one, rename the session field to statusLineExporter (statusLineTelemetry is the registry capability) and document its values, word the stake as re-cached, move the readout block above the SSE staleness heading, and drop keep-warm mentions until it lands.
Claude Code's statusline has carried a prompt_cache object since v2.1.251, and Codeman's statusline exporter already received it, but StatusTelemetrySchema stripped the whole object, so Codeman never knew whether a session's conversation was still cached. Keep it and show it.
StatusTelemetrySchema now lists every documented scalar field null-tolerant (several are documented as possibly null, and the object gains fields across CLI versions, so a strict shape would 400 the post and blank the footer), while parsePromptCache normalizes only the subset Codeman stores, so a hostile localhost payload cannot bloat state. Session.promptCache rides toState with a change-only session:promptCache event, and the route broadcasts the stored object.
The Session Options (Respawn tab) readout shows warm-until or cold with the re-read stake, the cache hit rate, the last miss's causes, and, for Claude Code's own idle compaction (recache_tokens_if_cold null while expected_rebuilds rose), a "compacted at HH:MM" note that is never raised as an alert. setPromptCache stamps that on a new object rather than mutating the parsed report, so the stamp reaches the broadcast. Sessions without a statusline of their own also get a cache:until HH:MM / cache:cold group in the terminal footer. The last report is restored on a Codeman restart (like displayModel) so the readout is not blank until the pane's next render; the readout is time-aware, so a value whose expiry has passed reads as cold, not stale-warm. A launch without the exporter records why (collection off, workspace statusline, remote) so the row says the cause instead of "not reported yet" forever.
This is the sensor a later opt-in keep-warm would read, and the TTL it reports is the source of truth rather than the plan tier.
New sessions, spawned child sessions and saved web tabs now land in tab
groups instead of always starting in Ungrouped.
New session in a group:
- The group menu gains "New session" (first item). It expands a collapsed
group and runs ONE launch with the current case and run mode; a launch
already in flight is reported, not queued.
- run({ count, tabGroupId }) threads the group through every launch path
(local POST /api/sessions, remote/docker and external-CLI
/api/quick-start). The count overrides the steppers for that launch only.
- Server: POST /api/sessions and /api/quick-start accept an optional
tabGroupId (Zod, 1-100 chars; null/empty is a 400). The routes pass it to
addSession(), and TabLayoutService.sessionCreated() places the session at
the end of that group in the SAME versioned write that first records it.
The session is added to the live map inside the owner lock (with a
rollback when the write fails), so no queued layout edit can commit it
first. The group is looked up in the creating owner's own layout, so an
unknown, deleted or foreign id is ignored instead of failing the spawn. An
explicit group is a hand placement: a child placed this way is manual.
- The create response carries the committed tabLayout (only when tabGroupId
was sent), adopted before the new tab is drawn. Responses without the
field are unchanged.
Child sessions (parentSessionId / X-Codeman-Parent-Session):
- A child nobody placed follows its parent: the server's existing
normalization already puts it after the parent's rows; the browser now
draws a not-yet-stored child there too (project({ parents })) and, while
groups exist, adopts the server's order instead of echoing its own append
back through PUT /api/session-order (which pinned every child manual).
- The row menu says where a child sits (follows, placed by hand, parent
closed, parent loop) and offers "Follow parent again" only to a hand-placed
child. A child whose parent is gone stands on its own and is never
re-adopted.
Saved web tabs:
- Web tabs are layout refs like sessions; openness stays per device. A
grouped web tab shows (and takes an Alt+N slot) only while open here and
reopens where the layout keeps it. Pinned by tests; no behaviour change.
Unchanged: the flat rail and header strip (markup, HTML5 drag, append and
save on create), the tree semantics and single tab stop, sessionOrder and
Alt+N, and every request that does not send tabGroupId.
The owner asked to drop the "+" (Add Case) and gear (case settings) buttons
beside the toolbar case picker. Their two actions now close the picker's own
list instead, as "New or link a case…" and "Case settings…" rows in a sticky
footer, so nothing becomes unreachable: on desktop the "+" was the only door to
Add Case (create, link, clone, manage), and the gear the only one to the
per-case Agent Teams / 1M Opus overrides.
The rows are part of the arrow-key walk (after the last case) and Enter runs
them, they also show when nothing matches the filter, and the case settings
popover still opens anchored to the case group. The picker input gets its
right-hand corners back, and the dead .btn-case-add / .btn-case-settings rules
(desktop, phone and two skin selector lists) are gone. Phones keep their own
case sheet and gear.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Only the stepper half of #428 lands here. Its other half, the phone case
picker search, shipped separately in #488 (1.33.1) and is kept as it is on
master, so every file of this merge starts from ours and only the stepper
changes are ported onto it:
- index.html: the second `− 1 +` group (#shellCount) after Run Shell is gone.
- session-ui.js: incrementShellCount/decrementShellCount are removed and
runShell() reads the toolbar's one stepper through _readTabCount(), the
helper master grew since #428 was opened (same clamp and absent-element
fallback as #428's _toolbarInstanceCount()).
- run-mode-ui tests stub #tabCount instead of #shellCount, plus #428's
"toolbar instance count" block adapted to _readTabCount() and a markup check.
- wiki: "the instance counter", singular.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Since the CLI registry gave claude kind 'agent' (#476), isExternalCliRunMode() reads claude as an external CLI, so Session Options opened every Claude session on Summary and hid the Respawn and Ralph tabs and every Claude-only control (auto-resume, the respawn loop). The browser catalog now carries the registry's capabilities.external, the flag the server's isExternalCliMode() already reads, and Session Options asks that instead. run() keeps isExternalCliRunMode(): choosing a launch path is a different question, and custom agents rely on it.
Every Run path makes each session it created visible through
_ensureCreatedSessionVisible and then selects the first one, a human
selection that used to leave the grid for the single view. That helper now
hands the new session to _joinTileGridFromRun: with the grid open it joins the
next free slot, so Run's selection focuses its tile. No Attach overlay flashes
on it while Run starts its pane. Sessions created elsewhere (agents, other
devices, cron) arrive only by session:created and never join; a grid already
holding what the window fits does not take it, and a hint says the new
session opens on its own.
A tile's + adds "New session in this case": the normal Run (current run mode)
for the case the tile's session belongs to, with the toolbar's case put back
afterwards; the session it creates joins the grid like any Run from this tab.
Disabled for a session outside every case.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
- Route test hygiene: each test works in its own mkdtemp folder, every
deletion goes through safeRmHomeTree, and the suite refuses to start
outside test/setup.ts's temp HOME, so a raw `npx vitest` can no longer
delete a real ~/projects or the live linked-cases registry.
- Path policy: the symlink-resolved target is also judged against the
resolved home, data dir and system roots (home reached through a link,
macOS /etc -> /private/etc); test expectations are realpath-safe.
- Refuse a target equal to or inside the caller's or the shared cases
directory, pointing at plain Create New (it would list twice, and
deleting the local copy removes files).
- The registry re-read comment no longer claims to prevent the
lost-update race; documented as narrowing it, like /api/cases/link.
- UI: the success toast names the folder the server created, the
"under ~/codeman-cases" blurb and name hint change while a custom
folder is ticked, a "/" parent previews and sends /<name> instead of
an empty path, and the new labels have zh-CN entries.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
fix(cases): bound path probes for linked workspaces and session creation, so an unreachable mount cannot freeze the server
# Conflicts:
# src/web/routes/case-routes.ts
Reopening the editor over a rename still in flight filled it from the name
the server had not replaced yet, so dismissing it (blur commits) queued the
old name behind the new one and undid the rename. The queue now records the
newest queued name per session (_inlineRenamePending, cleared with the queue
entry), and a reopened editor takes its prefix, input and "unchanged"
comparison from it. An untouched confirm sends nothing more.
A failed write only toasted while its editor was still current. The queue
reports the failure itself now, and the editor only puts its label back.
One rejected task blocked every later rename of that session until reload.
Each task now chains from a settled predecessor, the local apply after a
successful PUT is guarded, and the queue entry is cleaned up on either
outcome.
The rail and sidebar editor's 4rem floor moves from a stylesheet
`!important` into the inline min-width startInlineRename already writes per
layout (0 in the header strip, 4rem in the rail and sidebar).
Tests: the reopened-editor case now expects only "First" to be sent; new
cases cover a 500 answered after the editor is gone and a throw in
updateSubagentParentNames; the long-prefix check runs in the sidebar and
detailed sidebar too and asserts the inline floor; the header strip editor
keeps min-width 0.
Two problems with renaming a tab in the vertical rail, both easier to hit now
that the grouped rail has its own inline editor beside the session one.
Writes. A committed rename PUT its name and only applied the answer if the
same editor was still open when it came back. Reopening the editor before the
PUT answered (F2 or right-click again, or starting a group rename, which
cancels the session editor) threw the confirmed name away, so the tab kept
showing the old name until an SSE frame happened to repaint it. Two quick
renames also raced as two concurrent PUTs. Inline renames now go through a
per-session queue: one PUT at a time in the order they were made, the
confirmed name applied to app.sessions whatever happened to the editor, and
the "already that name" check made when the write runs rather than when Enter
is pressed, so confirming the name still on screen over a write in flight is
a real write.
Layout. The editor (a flex row) could not shrink below the input's intrinsic
width, so a long w<n>-<case> prefix pushed the label past its row: the prefix
slid out of view in the detailed rows and the input was clipped mid-word in
the compact rail. The label now has min-width 0, the prefix gives way first
(down to 2rem, with an ellipsis), the input keeps 4rem, and in the compact
rail the row's adornments step aside while the name is edited. The detailed
rows' three-line clamp also outranked the shared unclamp rule, which is what
the existing "unclamped editor" browser test caught; it is restated there.
Header strip, sidebar and flat-rail markup are unchanged.
Tests (test/inline-rename.test.ts, browser suite): the unclamp check runs for
simple and detailed rows; a write-ordering describe covers ordering, a
reopened editor cancelled over a confirmed write, a re-sent unchanged name and
a group rename taking over; a long-prefix describe drives real rows from a
live session in simple, detailed and compact rails.
The bounded path probe answered "absent" both when a path did not exist and
when it simply did not answer, so a stalled linked case 404'd and the Run
button scaffolded a stray local case over it, and two stalled paths anywhere
made every unrelated path read as absent (hooks skipped, statusLine
overridden, the clone warning lost).
- probePath()/probePathKind() are tri-state: present (or directory/file),
absent (ENOENT/ENOTDIR only) and unknown (timeout, other errors, refusal).
boundedPathExists() stays as the display-only boolean.
- A stalled path takes only its own mount out of probing (deepest mount
point from /proc/self/mounts, never /; just the path itself when there is
no mount table). Unrelated paths keep probing. The process-wide cap is a
backstop that answers unknown, and a single-path user request can probe
past it ({ pastCap: true }), still bounded and still recorded as stalled.
One console.warn when a path first stalls and one when the cap engages.
- GET /api/cases/:name keeps NOT_FOUND for definite absence only. An
unreachable linked case answers with its registered path and
unreachable: true; a local one answers OPERATION_FAILED. runClaude and
runShell create a case only on errorCode NOT_FOUND. The case list keeps an
unreachable linked case, marked unreachable, instead of dropping it, and
fix-plan reports an unreadable plan as an error, not "no plan".
- applyWorkspaceHooks and the statusLine helpers skip only a workspace that
is absent or on the stalled mount; a capacity refusal no longer stops
hooks being installed elsewhere, and an unreadable settings file never
lets the exporter override a user's own statusLine.
- The clone flow's repo-settings warning is back on its synchronous check,
and stripCaseEnvKeys uses pathExistsForWrite.
- POST /api/sessions (workingDir) and POST /api/quick-start (case folder)
probe with the bounded probe instead of statSync/existsSync. Missing and
non-directory keep INVALID_INPUT; unknown is OPERATION_FAILED, and
quick-start never scaffolds over a folder that did not answer.
- PATH_PROBE_TIMEOUT_MS and MAX_STALLED_PATH_PROBES move to
src/config/path-probe.ts, overridable via CODEMAN_PATH_PROBE_TIMEOUT_MS
(default 1500) and CODEMAN_PATH_PROBE_MAX_STALLED (default 3), and are
documented in the Settings Reference.
- The probe is exported from the utils barrel and imported from there.
POST /api/cases takes an optional path; Add Case > Create New gets a 'Create in a
custom folder' option with Browse. The folder is created (or an empty one filled),
scaffolded like a normal case and registered as a linked case. System, home,
credential and Codeman folders are refused; a folder with files is Link Existing's
job; a failure after the first write undoes what this call created. Admin only in
multi-user mode, like Link Existing.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude Code's advisor tool (code.claude.com/docs/en/advisor) lets the session's
main model consult a second, stronger model at decision points: before
committing to an approach, on a recurring error, and before declaring a task
done. Codeman can now start claude sessions with one.
- `advisorModel` field on POST /api/sessions, /api/quick-start and
/api/ralph-loop/start (fable, opus, sonnet or a full model id in those
families; haiku cannot advise and is refused). Stored on the session and
persisted, so respawn, boot restore and reboot restore keep it. Remote and
docker quick-starts refuse it, as they refuse effort.
- App Settings, Models, "Advisor" segment (Default / Sonnet / Opus / Fable),
synced as `claudeAdvisorModel`. Run, resume and the Ralph wizard send it.
Default sends nothing, leaving the CLI's own /advisor choice in charge.
- Carried as the `advisorModel` key in the launch's single --settings JSON,
merged with ultracode and the statusLine exporter, never the --advisor
flag: `claude --advisor haiku` exits 1 at launch, which would leave a dead
pane on every respawn, while the settings key degrades to no advisor. A
launch without an advisor is byte-identical to before.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
The phone case picker had no way to narrow a long case list, so finding
one meant scrolling a sheet that showed about six rows at a time.
- A search field filters rows by name (every typed word must match, any
order, case-insensitive), with a "No matching cases" state. Enter picks
the case when exactly one row is left; Escape clears, then closes.
- The field is not auto-focused, so opening the picker does not raise the
keyboard. The list holds its unfiltered height while searching so the
sheet does not jump, and the input is 16px so iOS Safari does not zoom.
- Layout: the sheet padded the home-indicator inset on top of the footer
already doing so, leaving a dead band under Create New Case; the sheet
now grows to 80dvh and the list fills it instead of a separate 50vh cap.
- Opening scrolls the list (its own box, not scrollIntoView) to the
currently selected case.
Co-authored-by: Codeman maintainer <noreply@anthropic.com>
The Run bar's case picker only loaded /api/cases at page load, so folders
deleted or created on disk stayed listed until a reload. It now refetches
on open and every 5 seconds while open, repainting only when the list
changed and falling back to another case if the selected one was removed.
The Manage tab of Add Case gains a search box filtering by name or path.
Reorder arrows are disabled while a filter is active so a swap cannot
involve a hidden case.
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
* feat(cli-registry): add cliManagementEnabled flag and GET /api/clis
Phases 1-2 of docs/cli-enable-disable-plan.md ("PR C" from the #343
review): a synced, default-OFF master flag gating the upcoming CLI
management surface, plus a read-only GET /api/clis endpoint listing
every registry entry (stock + custom, enabled or not) for the
Settings UI. Non-admins in multi-user mode see an empty list rather
than a 403. Write endpoints, auto-install, custom entry CRUD and the
Settings UI list itself land in later phases.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* feat(cli-registry): Phases 3-6 - write API + custom entries + Settings UI
Completes docs/cli-enable-disable-plan.md ("PR C" from the #343 review).
Phase 3: PUT /api/clis/:id toggles enabled for any EXISTING entry (stock or
custom) via a shallow merge onto its clis.json override; shell/claude are
structurally un-disableable (Decision 4), an unknown id 404s rather than
becoming a creation backdoor.
Phase 4: POST /api/clis/:id/install runs a STOCK entry's already-vetted
install command (shell:true, bounded by timeout, process-group killed on
expiry, output captured, audit-logged). A custom entry's id is refused
outright, independent of anything Phase 5 does (Decision 3: a custom
entry's install text is display-only, never executed).
Phase 5: POST /api/clis (create) / PUT /api/clis/custom/:id (update) /
DELETE /api/clis/:id (custom only) — a deliberately minimal request shape
(id/label/shortBadge/binaries/a simple launch variant), assembled into a
full CliEntry with conservative capability defaults and re-validated
through CliEntrySchema before writing, never a relaxed path for
UI-originated entries. Stock-id collisions, duplicate custom ids, and
edits/deletes against a stock id are all rejected explicitly.
Phase 6: the Settings UI section (App Settings -> Agents & CLIs), gated
independently on cliManagementEnabled AND admin-in-multi-user-mode
(Decision 5), fetching/rendering GET /api/clis and wiring every write
endpoint above.
Every write endpoint answers the same way when the feature is off: 403
FORBIDDEN via one shared requireCliManagementGate() (Phase 1's own
checklist item). registry-writer.ts is a new, deliberately separate write
module so registry.ts itself stays import-side-effect-free, same tmp+
rename+0600 shape as custom-model-hosts.ts.
27 new/updated route tests covering every gate, collision, and cleanup
path; full CI gate green (415/416 files, 7854 tests).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* fix(cli-registry): toggling a CLI off in Settings never hid it anywhere else
window.__codemanCliAvailable — the flag isCliAvailable() reads client-side
to gate the welcome-screen buttons, the Run-menu dropdown and the mobile
overview — was built purely from each CLI's own installed-on-PATH resolver
(isClaudeAvailable() etc.), with no reference to the registry's `enabled`
flag at all. So disabling a CLI via the new Settings UI (or a hand-edited
clis.json) updated the settings row and nothing else: every launch surface
kept offering it, both live and after a full page reload, since even a
fresh render never consulted the registry.
Fixed in two places:
- server.ts: after building `available`, intersect the nine real
SessionMode ids against `enabledClis()`. git/cloudflared (utility
binaries, not CLI registry entries) and deepseekBinary (a secondary
installed-only flag for the "add a profile" affordance) are deliberately
left alone.
- settings-ui.js: `toggleCliEnabled()` now patches
`window.__codemanCliAvailable` in place and refreshes the welcome screen,
the mobile overview and an already-open Run menu, mirroring the existing
`installDeepSeekProfile()` pattern for the same "injected once, needs an
explicit patch" reason — without this half, the server-side fix alone
still left every surface stale until the next reload.
New test in test/render-index-html.test.ts: an installed-but-disabled CLI
(codex, forced via clis.json + reloadCliRegistry()) reads as unavailable,
while an installed-and-enabled one (claude) is unaffected by the override.
Verified on the Debian devbox (codeman-devbox, real tmux — this sandbox has
none and WebServer's constructor hard-requires it): typecheck clean, the
new test passes (17/17 in render-index-html.test.ts), the CLI-registry
suites pass (86/86), and the full CI gate is green (415 test files, 7855
tests, 0 failures).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
* docs(cli-registry): update the CLI-management plan with status, gotchas, and the Run-menu gap
Phases 1-6 were implemented across two commits (da07b38c, db4557d9) with no
corresponding update to the plan doc itself — every checklist still read
Status: TODO and every box unchecked. Brings the doc in line with the tree:
- A new "Status as of 2026-09-22" section up top: what's actually
implemented (verified by grepping the routes/schema/UI, not just trusting
the commit messages), the availability-flag staleness bug found and fixed
in this session (commit 0c77dd0a) with its devbox verification record, and
one real outstanding gap.
- The outstanding gap: a custom CLI created via Phase 5's write API has no
way to actually be launched. The Run menu is static per-mode markup with
no consumer of window.__codemanCliCatalog, so Phase 6's own "create a
custom entry, confirm it can be launched" verify step was never actually
exercised against this. Documented with two candidate fixes, neither
started.
- Each phase's checklist flipped to [x] where confirmed present in the tree,
Status lines updated from TODO to DONE, and the two originally-open
questions (Phase 2's installed source, Phase 5's PUT endpoint shape)
marked resolved against what actually shipped.
No code changes in this commit — documentation only, so a future session
(or the one already mid-flight on a separate checkout of this same branch)
picks up accurate status instead of a stale plan.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
* docs: add the CLI-registry deployment plan and the parked Copilot plan
Both were sitting as untracked scratch files in the master checkout,
never committed to any branch. Moving them here rather than leaving them
loose:
- DEPLOYMENT_PLAN.md is the live tracker for the CLI-registry follow-up
series (PR A #347 merged, PR B #380 merged, PR B2 merged as #458) and
is where PR C (this branch's own CLI-management work) belongs.
- docs/copilot-integration-plan.md is explicitly PARKED, referenced by
name in docs/cli-enable-disable-plan.md's own header as a sibling plan
tracked separately — kept for continuity, not active on this branch.
The other scratch files found alongside these (PRA.md, PRB.md, PR-B2.md
and their review-response counterparts) described PR A/B/B2, all now
merged — deleted from the master checkout as stale rather than committed
anywhere, since their content is superseded by the real merged PRs.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
* fix(cli-registry): render enabled CLIs in launch surfaces
* test(cli-registry): update frontend branch guard
* fix(test): isolate suite from deployment environment
* fix(cli-registry): revise Decision 4 - claude is toggleable, shell stays permanent
shell/claude were both structurally un-disableable in the original plan
(Decision 4). Revised: shell keeps the hard backend guarantee (it is the
one non-agent mode several code paths assume always exists as a raw-
terminal fallback), but claude is now a normal toggleable entry like any
other CLI.
Safe to do because internal session creation (tmux-manager.ts, session.ts,
Ralph, plan-orchestrator) resolves a CLI via getCli(), which does not
check `enabled` at all - only the Run menu and the HTTP-facing
sessionModeSchema() (new session requests through the normal API) key off
it. Disabling claude therefore behaves identically in kind to disabling
any other CLI: no internal fallback path breaks, it just stops being
offered for new sessions until re-enabled.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* fix(cli-registry): hide shell's toggle entirely instead of greying it out
A permanently-disabled switch next to every other row's working toggle
read as broken rather than intentional. shell now renders no switch at
all - a plain "Always available" label - so there is nothing to click
that could look like it should work but doesn't. Backend guard is
unchanged (UNDISABLEABLE_IDS still refuses shell unconditionally); this
is UI-only.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* fix(cli-registry): sort the Installed CLIs list, installed-first then alphabetical
renderCliList() previously rendered in registry order (each entry's fixed
order field). Now sorts installed CLIs first, then not-installed, each
group alphabetical by label - matches how a user actually scans the list
(what's ready to use, then what needs installing).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* style: prettier fixes from the master merge
* fix(cli-registry): install/edit take effect immediately, confirm before install, phone labels
Four gaps found verifying #476 against the #343 review trail:
- Installed or edited CLIs kept reading as missing/stale. Every binary lookup
(the nine per-CLI resolvers and the generic registry one) caches in its own
closure, with a negative-cache backoff of up to 5 minutes, and nothing
cleared them. invalidateCliExecutableResolvers(binaries) now drops those
caches per binary; install (success or failure), create, edit and delete
call it plus invalidateCliResolverCache(id). Before this, a CLI installed
from Settings could fail to launch for minutes, and an edited custom entry
kept launching its old binary until a restart.
- The Settings "installed" badge for a custom entry used a private `which`,
ignoring the entry's searchDirs and the login-shell lookup that spawn and
the Run menu use; it now asks the same generic resolver they do.
- Install ran on a single click. The #343 review asked for auto-install to
sit behind an explicit confirm; the confirm now names the exact command,
which GET /api/clis returns for stock entries only (installCommand).
- The phone Run button showed the two-letter tab badge ("CC", "CX") instead
of the word ("Claude", "Codex"). It uses the registry label again, which is
identical to the old static table for every stock CLI (now pinned).
14 new tests; 9 of them fail against the previous head and pass here.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* fix(cli-registry): address #476 review — safe serialized writes, no id branches, docs
Must-fix:
- registry-writer: start fresh only on ENOENT; refuse (409) a clis.json that
does not parse or has group/world permission bits instead of overwriting it
(isUnsafePermissions now exported from registry.ts)
- mutateRegistryFile(): one promise chain for every mutation, with the
existence/duplicate checks inside the serialized step, plus a unique tmp
name per write
- docs: CLAUDE.md, architecture-invariants, cli-registry (new Settings
section) and api-reference (the six /api/clis routes)
- drop DEPLOYMENT_PLAN.md and docs/copilot-integration-plan.md
Smaller:
- PUT /api/clis/custom/:id keeps the entry's current enabled state when the
body omits it
- runMode setter falls back to the first enabled catalogue entry, not 'claude'
- shell guard keyed on kind === 'shell' (routes + Settings list); stock probe
map shared with server.ts via utils/cli-installed-probes.ts
- stock claude label is now 'Claude Code', so the Run menu / phone overview
label rewrites are gone (doctor row keeps "Claude CLI" via its override)
- welcome buttons are translatable again and read "Run Claude Code" /
"Run Shell"; zh-CN gains "Run Codex" / "Run OMP"
- install: per-id in-flight guard (409) and CODEMAN_* stripped from its env
- fileoverview / CliEnableSchema comments no longer say stock-only
- test-env isolation changes moved to their own PR
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
* test(cli-registry): pin the #343/#347 findings #476 makes reachable
A CLI toggled or created through the routes is accepted or rejected by
CreateSessionSchema with no restart (#343 finding 2), and a custom CLI created
through the API renders a real local, remote and docker launch command
(#347 finding 5: no more `cd <path> && undefined`).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
- test/opencode-resize.test.ts: retarget the launcher guard at the real code (this.selectSession(firstSessionId), any this.activeSessionId assignment) with an anti-vacuity check; the old strings existed nowhere, so it could never fail
- session-ui.js: restore as comments the two invariants the merged bodies lost (deepseek leaves statusReporting unset, i.e. ON; no effort field for external CLIs, it is Claude-specific)
- docs/cli-registry.md: move the frontend-guard paragraph below the two backend-guard paragraphs so they keep their antecedent, and note the widened comparison shape
- test/frontend-cli-no-id-branching.test.ts: the comparison shape accepts any left-hand identifier (const m = this._runMode; m === 'codex' was invisible), normalized to `mode`; the two `m !== 'shell'` display filters are allowlisted and the remaining blind spots documented
- test/run-mode-dispatch.test.ts: table-driven pin of run() dispatch (claude to runClaude, each RUN_MODE_LAUNCH id to _runCliMode(id), shell to runShell, unknown to runClaude, lock held and released)
- CLAUDE.md: name the second CI-gated guard next to the backend one
- server.ts: every </head> injection passes a replacer function; a clis.json label containing $' re-injected the rest of the document past escapeScriptJson (two render tests pin it, proven failing on the string form)
- _isAltCliMode(): no reference anywhere in the tree, nothing to fix
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
(cherry picked from commit 1ea363ff808a62861559bc141e724b163cc1c56e)
The maintainer's promised follow-ups to opticon454's picker promotion,
applied on the landing branch after the merge (ecb95b5d):
- session-ui.js: the promotion tag ("Currently loaded" / "Last used") and
the "Default" pill are two separate spans, so a promoted row that is
also the endpoint's defaultModelId shows both instead of silently
losing its Default marking; two tests pin it (both fail on the old
exclusive-slot rendering).
- styles.css: a dedicated #customModelPickModal .set-scope rule, since
the pill was only styled inside the three settings modals and rendered
as plain body text here; same skin tokens, modal layout untouched.
- docs/wiki/Custom-Model-Endpoints.md: describe the promotion (currently
loaded, else last used per device), the separate Default pill, and
that nothing is ever auto-chosen.
- CLAUDE.md + docs/custom-model-endpoints.md: credit the real "Last used"
writers (_runCustomModelEntryViaRestart and
_quickStartWithCustomModelConfirm; runCustomModelEntry only dispatches
since 88e5b7b2) and drop the now-wrong "both defer to Default" sentence.
- Not done: moving the one-shot "last used" write into
_runCustomModelEntryOneShot, because the existing one-shot tests assert
that _quickStartWithCustomModelConfirm writes the key itself.
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
(cherry picked from commit 0cb0f911adc14a852ba5c2951768a4aa87c25657)
Four things from the maintainer's review on PR #459, all fixed:
1. Bound _getCustomModelCurrentlyLoaded's probe client-side (~800ms via
Promise.race, on top of — never instead of — the route's own 5s
server-side timeout). Without it, an asleep/firewalled endpoint behind
a saved model list left the picker completely invisible for up to 5s
after the Run menu had already closed, with no spinner or toast.
`timeoutMs` is an optional param (default 800, real callers never pass
it) so a test can drive it in milliseconds, same pattern as
`_watchLlamaSwapLoading`'s own `pollIntervalMs` — this code runs in a
JSDOM window's own realm, whose setTimeout vi.useFakeTimers() cannot
patch.
2. "Last used" is now written only once a launch actually applies, never
on the mere click. It moved out of runCustomModelEntry (unconditional)
and into each path's own success point: _quickStartWithCustomModelConfirm
after the final post succeeds, and _runCustomModelEntryViaRestart right
after the apply's success check. A context-window-warning decline means
this exact model cannot work with this CLI at all, so the old
unconditional write would promote, next time the picker opened, the one
model guaranteed to fail again.
3. Documented the promotion/tag precedence and the new
codeman:customModelLastUsed:<mode>:<endpointId> localStorage key in both
CLAUDE.md's Custom Model Endpoint Profiles section and
docs/custom-model-endpoints.md's Run-menu picker section.
4. Added zh-CN entries for "Currently loaded" and "Last used" in i18n.js,
next to this modal's existing "Choose a model"/"Custom Endpoints" pair.
New tests: the client-side timeout (endpoint that never answers, one that
answers within the bound, and a rejected-after-timeout probe settling
quietly), and "last used" recording on success vs. NOT recording on either
confirmation's decline, for both the restart and one-shot paths.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
Code review (high effort) on the previous commit found a real race: making
_openCustomModelPickModal async (it now awaits the currently-loaded-model
probe before rendering) meant a second, faster call for a different
endpoint could render first, only for the first call's slower probe to
resolve afterwards and overwrite the modal with the wrong endpoint's model
list — while _pendingCustomModelPick (set synchronously, before either
await) still named the second, correct endpoint. Picking a model in that
state would launch/apply the wrong model on the wrong endpoint.
Fixed with the same mutable-generation-counter guard
_watchLlamaSwapLoading already uses for an identical async-superseded-by-
newer-call shape: every DOM write, including _pendingCustomModelPick
itself, is deferred until after the awaited probe, and a call that finds
its generation already superseded bails out untouched instead of clobbering
whatever a newer call already rendered.
Added a regression test driving two overlapping opens with a controlled
promise so the earlier, slower probe resolves after the later, faster one
renders, asserting the late response is a no-op.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
Custom Model Endpoint Profiles' "which model" picker (session-ui.js's
_openCustomModelPickModal) always listed models in their raw discovery
order, so on a host with several downloaded GGUFs the user had to
remember (or eyeball the "Default" tag) which one llama-swap actually
had hot before picking — the whole point of the picker being fast is
undone if it makes you think first.
The picker now promotes exactly one model to the top of the list:
- If llama-swap reports a model from this host's own list `ready`
right now (via the existing GET /api/model-endpoints/:id/running-status
route), that model is promoted and tagged "Currently loaded" — it's
what a launch attaches to with zero wait.
- Otherwise, the last model actually launched on this exact
(harness, endpoint) pair is promoted and tagged "Last used", read
from a new per-device localStorage key
(codeman:customModelLastUsed:<mode>:<endpointId>), written by
runCustomModelEntry on every launch attempt regardless of outcome.
- A plain (non-llama-swap) OpenAI-compatible server, an unreachable
endpoint, or a loaded-but-not-yet-ready model never promotes
anything — the rest of the list keeps its discovery order.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01N6eadpRyqpA9PD3i139cSD
Two required fixes from Ark0N's review of #458:
1. test/frontend-cli-no-id-branching.test.ts's ALLOWED_BRANCHES keyed on
<file>::<line>::<expression>. A single inserted line anywhere above an
entry shifted every subsequent line number, so all 21 entries went stale
simultaneously and the same 21 branches were reported as "new" — on a
file six other open PRs also touch. Dropped the line number from the key
(<file>::<expression>, matching the backend guard's own design), which
collapses 21 line-keyed entries to 11 or-collapse where the same
expression recurs at multiple call sites in the same file.
2. test/run-mode-ui.test.ts's terminal-ownership guard scanned method
bodies via `^ {2}async (run[A-Za-z]*)\(\) \{$`, which matched the 8
one-line run<Mode>() wrappers PR B2 introduced but not _runCliMode(mode),
where the real logic (and the actual risk the guard exists to catch) now
lives. Fixed the regex to `^ {2}async (_?run[A-Za-z]*)\(\w*\) \{$` and
added _runCliMode to the sanity list. Same-class fix in
test/opencode-resize.test.ts, which had the identical blind spot via
runOpenCode.toString().
Both reproduced live before fixing (inserted the same comment line; added
this.terminal.clear() to _runCliMode) to confirm the bug, then confirmed
the fix catches it and the suite stays green otherwise.
Also resolves Open Question 2 by dropping window.__codemanCliCatalog
entirely: nothing consumed it, and a registry DECLARED_FOR_LATER field
costs nothing until read while an unconsumed script tag on every page
render is a different trade. Reverts Phase 1 cleanly — server.ts's
injection, shortBadge back in types.ts's DECLARED_FOR_LATER list and the
pinned guard test, and the three associated render-index-html.test.ts /
server-index-title.test.ts assertions.
Full gate: 405 files / 7717 tests / 0 failures (net unchanged), typecheck/
lint/format clean.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
PR #380 (PR B) held back the frontend half of the CLI registry refactor,
explicitly deferring window.__codemanCliCatalog and making session-ui.js /
mobile-overview.js catalogue-driven as "PR B2".
- Inject window.__codemanCliCatalog in renderIndexHtml(), following the
existing __codemanCustomModelClis pattern (escapeScriptJson-guarded,
resolved per-request). Reading CliEntry.shortBadge here is what makes it
genuinely read, so it drops out of types.ts's DECLARED_FOR_LATER list.
- Consolidate session-ui.js's 8 near-duplicate run<Mode>() launch functions
(opencode/codex/gemini/antigravity/pi/omp/grok/deepseek) into one shared
_runCliMode() plus a local RUN_MODE_LAUNCH config table. The 8 method
names stay as thin wrappers (index.html calls them by name; tests assert
on the name). Also collapses a duplicated 8-way isAltMode/isExternalCli
OR-chain (same expression, copy-pasted twice in openSessionOptions) into
one EXTERNAL_CLI_MODES check.
- Add test/frontend-cli-no-id-branching.test.ts, a guard scoped to
session-ui.js/mobile-overview.js only (not the rest of src/web/public/,
which stays explicitly out of scope per CLAUDE.md), mirroring the
backend's own no-id-branching guard.
mobile-overview.js and the wiring of accent/echo/wheelForward/
keyboardAccessory were investigated and deliberately left alone: the first
is already a single, tested, gated table (not duplicated logic); the second
set belongs to terminal-ui.js/keyboard-accessory.js/styles.css, files
outside this PR's mandate.
Verified on a tmux-capable devbox (this sandbox has no tmux): full CI gate
at 405 files / 7717 tests / 0 failures, typecheck clean, 94 targeted tests
covering exact per-CLI wire-body shapes unmodified and passing, and a live
anti-vacuity check on the new guard (injected a real branch, confirmed it
fails, reverted, confirmed green).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GuHtuPiHXdykq9T6rKQJ9n
More from the review of 5fc391a4, all documentation rather than behaviour.
The changeset was 1602 words of development log, written as the PR grew, with bullets
and loose paragraphs interleaved. That text becomes CHANGELOG.md and the GitHub release
body verbatim, so it is now one user-facing account of what the feature does and what
the real-server work bought, at roughly a fifth the length.
docs/api-reference.md promised a `cmd` field on running-status that the route
deliberately strips (it carries model paths and can carry --api-key).
Two places claimed the apply routes validate `modelId` against the endpoint's
discovered models. Neither does. Dropped the claim rather than adding the check:
discovery can be up to five minutes stale, so a 400 there would refuse a launch that
actually works, and a typo'd id already fails on the CLI's own first request. CLAUDE.md
now says so explicitly, since the absence is the surprising part.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Two findings from the review of 5fc391a4, both fixed here rather than sent back.
**The API-key trust seed never matched a real key.** `seedApiKeyTrustFile()` wrote the
key verbatim into `customApiKeyResponses.approved`, but Claude Code stores and compares
only the last 20 characters (`key.trim().slice(-20)`, applied on both the write and the
lookup). For any real key the seed missed, so claude stopped at the interactive
"Detected a custom API key in your environment" prompt, whose default is
"No (recommended)": the launch hangs, or silently refuses the key this feature just
injected and falls through to an OAuth login the isolated config dir does not have. It
survived review because a keyless llama.cpp/llama-swap endpoint uses DEFAULT_API_KEY
('local-dummy-key', 15 chars), where slice(-20) returns the whole string and the seed
matches by accident, and every test used a key shorter than that. Now truncated through
`truncateApiKeyForTrustFile()`, with a test using a 57-character key that also asserts
the full credential never reaches that second file.
**One `confirmed` flag answered two different questions.** The context-floor warning
("this model's window is below what this CLI needs") and the swap-conflict warning
("loading this unloads the model another session is using") shared it, and the context
check runs first, so a user clicking "launch anyway" past the context warning silently
consented to evicting someone else's model. They are about different people, so an
answer to one is not consent to the other. Both routes now read `confirmedContext` and
`confirmedSwap` independently; the legacy `confirmed` still means both, because it
shipped in this feature's HTTP-API-only cut and an existing caller must keep working.
The frontend answers each question with its own flag and accumulates them, on the
one-shot path, the restart path and the batch carry-forward alike.
Also from the same review: the swap-confirm dialog no longer renders " are currently
using ..." when multi-user scoping leaves the affected-session list empty (the swap is
blocked regardless of ownership; only the NAMES are scoped), and the per-endpoint
llama-swap log tails are closed in `WebServer.stop()` instead of only by the idle sweep
whose interval that same teardown disposes.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
#454: the behaviour the PR adds had no test, so a regression test drives
runGrok() at tabCount 3 and asserts three quick-start POSTs with sequential
w<n>-<case> names (verified to fail against master's session-ui.js). Each
caller now reads the count BEFORE its opening banner and announces it there,
the way runClaude() already did, so a launch no longer prints two headers and
a launch with another session already active still says how many are starting.
runClaude() calls the shared _readTabCount() instead of its own copy of the
1..20 clamp, and that helper optional-chains the element read, since hoisting
it above each caller's try block would otherwise let a missing #tabCount throw
where the launch-error path cannot report it.
#435: sizeMovedUnderLoad derived from data.source alone. `mux-visible` is not
sufficient: a failed display-message cursor query makes capturePaneBuffer skip
the snapshot repaint and return the raw capture, which the route still labels
mux-visible, so a size that moved during such a load bought a full forced
reload to repair a frame that was never positioned. It now tests
Number.isFinite(data.captureRows) like its two siblings.
Plus the invariants and CLAUDE.md lines promised on #435: a visible capture
reports its geometry and omits it when nothing was positioned, the comparison
runs on mux-visible only, and the replay is capped at one attempt and latches
per session when it cannot converge.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
runOpenCode(), runCodex(), runGemini(), runAntigravity(), runPi(), runOmp(),
runGrok(), and runDeepSeek() all ignored the "Instance count" stepper next
to the Run button and hardcoded a single quick-start call — bumping the
counter to 2 or 3 while on any of these modes silently launched exactly one
session, with no error. Only runClaude() ever read it.
Extract the shared launch-N-sessions-and-select-the-first loop into
_launchQuickStartInstances(), reused by all eight modes, and _readTabCount()
for the shared clamp-and-parse. Each mode still builds its own quick-start
body (config differs per CLI), just via a closure passed to the shared
loop instead of a single inline fetch.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Four blockers from the 2026-09-18 review:
- PUT /api/model-endpoints/:id now merges modelContextLengths/
modelSizesGB back in from the stored record instead of trusting the
editor's body, so renaming an endpoint or changing its default model
no longer silently drops the context-window floor check and
CLAUDE_CODE_MAX_CONTEXT_TOKENS injection.
- custom-model:swapped-out is now session-scoped (added to
SESSION_PREFIXES) instead of broadcasting to every connected client.
- The quick-start custom-model path now hands setCustomModel() only
the endpoint's own injected env vars, not the full merged set,
matching the restart-in-place path — the full set put
CLAUDE_CODE_EFFORT_LEVEL back after the Session constructor had
already stripped it.
- The quick-start launchModel override for pi/grok/omp is now applied
generically via the registry's legacyConfigField, mirroring
Session._withCustomModelLaunchModel, instead of three hardcoded
mode === '<id>' branches a future CLI's injection recipe would miss.
Also scopes the sticky-toast default (item 5): reverted the blanket
"all error toasts are sticky" default, which had no container cap or
eviction, back to a flat 3s; the one message that needs a moment to
read (a failed custom-model apply) now passes an explicit
duration: 0 at its own call site.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ea59JhUmHBm1gRCsiYF33R
Replaces the size-scaled expected-time estimate + matching auto-timeout
with a generic hardware/model-size disclaimer and a user-driven Cancel
button, per explicit request. Real load time depends on hardware this
feature has no way to know (VRAM, storage speed, GPU contention), so
the old estimate/timeout was a guess dressed up as a fact — worse, one
that could kill a genuinely slow load partway through on slower
hardware.
- _watchLlamaSwapLoading (session-ui.js): dropped maxWaitMs/deadline
entirely — polls indefinitely until ready or cancelled, no automatic
give-up. Message is now "Loading <model> (<size>) on <endpoint> —
this can take a while depending on your hardware and the model
size.", with the real llama.cpp log line still on its own second
line. Removed _MODEL_LOAD_TIME_MATRIX/_estimateModelLoad/
_formatRemaining (dead code once the countdown is gone) —
_lookupModelSizeGB is kept, the GB figure still shows.
- _showCenterStatus (panels-ui.js) gains opts.onCancel: renders a real
"Cancel" button (distinct from the error-type "×" close button,
since Cancel has a real consequence) that calls it on click. Caller
owns what cancelling actually means, same split as the swap-confirm
modal's promise-resolving buttons.
- Cancelling dismisses the banner, shows an info toast (not an error —
this was deliberate), and closes the session, mirroring what the old
timeout used to do automatically but now on the user's own call.
- New .center-status-cancel CSS (bordered pill button, distinct from
the plain "×" close glyph).
Test changes: removed the now-invalid timeout-auto-close/estimate
tests, added cancel-flow tests (dismiss/toast-type/session-close,
never-closes-with-no-sessionId, unbounded-polling), and real-DOM tests
for the new Cancel button (bootAppWithRealCenterStatus, evaluating
panels-ui.js instead of stubbing _showCenterStatus, since this button
is worth verifying for real rather than just through the stub every
other test in the file uses). Typecheck/lint/frontend-syntax clean;
full suite shows no new regressions.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Answers the underlying request behind investigating llama.cpp log
access: surface what the backend is actually doing, live, on top of
the existing countdown timer during a model load.
- getLatestLlamaSwapLogLine()/pruneIdleLlamaSwapLogTails()
(custom-model-routes.ts): one persistent GET /api/events (SSE)
connection held open per endpoint, parsing logData frames and
keeping the latest source:"upstream" (backend llama-server) line —
filtering out llama-swap's own source:"proxy" request-access lines.
Idle-closed after 30s of no polling, same 20s sweep as the existing
swap-displacement check.
- running-status route now returns logLine alongside the existing
isLlamaSwap/running fields.
- Frontend: _watchLlamaSwapLoading's banner gains a second line
("llama.cpp: <line>", bootlog timestamp/level/component prefix
stripped for display) that stays on the last real thing llama.cpp
said rather than clearing to blank between polls.
⚠️ Caught and fixed before merge, not after: the first cut targeted
GET /logs (the endpoint the name suggests), shipped a working-looking
implementation with passing tests, and only failed a live check against
the real Nemesis llama-swap deployment — /logs turns out to carry ONLY
llama-swap's own proxy request-access log and never once showed a
single backend line, even seconds after a real, confirmed model swap
triggered via a direct API call. GET /api/events's logData frames
(with an explicit source field distinguishing upstream from proxy) are
the only source that actually has backend output; corrected and
re-verified live end-to-end through an actual forced swap before
writing this commit, confirmed live to hold its connection open
indefinitely (unlike /logs, which closes after a fixed ~100KB).
12 tests for the corrected /api/events parsing (SSE frame buffering
across chunk boundaries, source filtering, malformed/wrong-type frames,
connection reuse, idle pruning) plus 2 for the frontend banner
rendering. Typecheck/lint/frontend-syntax clean; full suite shows no
new regressions (14 more passing than baseline, matching the new
tests; same pre-existing Windows-environment failures).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Claude Code's own fixed per-turn overhead (system prompt + tool schemas,
~36.4K tokens measured live) can exceed a small local model's entire real
context before any conversation history exists to compact — confirmed
live twice as an in:0 out:0 failure on the very first message sent.
CLAUDE_CODE_MAX_CONTEXT_TOKENS cannot fix this: it only governs when
history gets compacted, and there is none on message one.
- exceedsSafeContextFloor() (custom-model-routes.ts): true when a CLI's
registry entry declares contextLengthVar (currently only claude) and
the model's discovered context is below CLAUDE_MIN_SAFE_CONTEXT_TOKENS
(40000). A no-op for every other CLI by construction.
- Both apply routes (POST /api/sessions/:id/custom-model and the
quick-start customModel path) check this before the swap-conflict
check and before launching/restarting anything, returning
{requiresContextWarning, modelId, contextLength, minSafeContextTokens}
— skipped when confirmed:true.
- Frontend: #customModelContextWarningModal + _confirmContextWarning/
_resolveContextWarningConfirm (session-ui.js), wired into both
_quickStartWithCustomModelConfirm and _runCustomModelEntryViaRestart
(the path Claude actually uses) ahead of the swap-confirmation check.
Explains the fix in-modal: give the model an explicit larger -c/
--ctx-size in llama-swap instead of relying on --fit-ctx, which
optimizes for the biggest model that fits rather than the biggest
context.
Tests added for the route-level warning/confirm/skip cases and the
frontend modal + launch-flow wiring. Docs updated (custom-model-
endpoints.md, wiki/Custom-Model-Endpoints.md) and the PR's running
changeset extended.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Own review pass over the PR:
- `_flush` took the chunk out of the buffer only AFTER awaiting the write. Input
arriving during that await is enqueued (`waking` is still set, so it takes the
buffer path), and the 4 KB cap then drops the OLDEST chunk — which is the one
already on its way to the pane. The `shift()` that followed removed the NEXT
chunk instead, so the drop-oldest bookkeeping silently lost a chunk that was
never written, while the log line blamed the one that was. The chunk is now
removed before the await and re-inserted at the FRONT on a failed write, so the
order of the queue behind it is preserved. Regression test: a chunk enqueued
during the first write of a full buffer must still reach the pane (red against
the old order).
- `showCreateCaseModal()` reset the remote-host form fields but not the two new
wake inputs, so one host's MAC/command carried over into the next host that
form saved.
- The banner's pre-poll `wakeConfigured` labelled a command-only host as 'mac'.
Nothing reads the distinction, but the field is documented as which path is
configured, so it says the truth until the first poll corrects it.
- Stale `resolveRemote` comment ("only for sessions that have no usable target of
their own"): after the host config became authoritative in both directions it is
consulted on the TTL regardless.
The loading banner now shows a live countdown against its own timeout
(updated every poll, so every second by default) instead of a static
"this can take a while" — e.g. "Loading qwen3.8-27b (16.4 GB, typically
~1-3 min) on llama-swap - 47s remaining".
If the countdown reaches zero and the model still isn't ready, this is now
treated as a real failure rather than a "keep waiting" shrug:
- The banner turns into a sticky error (_showCenterStatus gains a `type`
option - 'error' drops the spinner and adds a close button, since nothing
is "in progress" anymore and a sticky message needs a way to dismiss it),
naming the llama-swap server's own logs as where to look for detail.
- The session that load was for is closed automatically (closeSession) -
requested explicitly: a console left open and pointed at a model that
never finished loading is worse than no console at all. Both apply paths
now thread the new session's id through to _watchLlamaSwapLoading for
this (new required 3rd parameter, after endpointId/modelId).
_watchLlamaSwapGeneration's existing stale-call guard extends naturally to
this: a superseded call's own eventual timeout recognises it no longer owns
the banner and neither shows the error nor closes a session that may by
then belong to a different, newer launch.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Discovery now also parses a GB figure out of an auto-discovered model's own
description (llama-swap writes "Auto-discovered 16.35 GB - parameters
auto-fitted by llama.cpp"), stored per model as modelSizesGB - unlike
context length this needs no /props probe (the figure is right there in
/v1/models) so it is populated for every model regardless of loaded state.
A hand-configured profile's own description has no such figure and
correctly gets no entry.
The loading banner (_watchLlamaSwapLoading) now looks this up and, when
known, shows it plus a rough estimate from a small size->time matrix
(_estimateModelLoad/_MODEL_LOAD_TIME_MATRIX, session-ui.js) -
"Loading qwen3.8-27b-ud-q4_k_xl (16.4 GB, typically ~1-3 min) on
llama-swap... this can take a while" - and uses that same estimate's own
bracket to scale the banner's default give-up timeout for a very large
model, instead of a flat 5 minutes for everything. Explicitly labelled as
an UNMEASURED, typical-hardware estimate in every relevant comment - this
is not benchmarked against any real endpoint's actual storage/GPU, just a
reasonable expectation-setter. A model with no discoverable size (a
hand-configured profile) gets no size/estimate shown at all, matching the
"never a guess" convention modelContextLengths already established.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Reported: the "Loading..." banner stayed up past 2 minutes even though
llama-swap itself had already finished loading the model. Three fixes:
1. pollIntervalMs default 3000ms -> 1000ms (as asked).
2. The loop now checks readiness IMMEDIATELY on entry rather than sleeping
a full interval first - a model that's already ready (a fast load, or a
re-apply onto one already loaded) shouldn't sit on "Loading..." at all.
3. maxWaitMs default 120000ms (2 min) -> 300000ms (5 min): a large (20GB+)
model reading from disk can genuinely take longer than 2 minutes, which
would have looked identical to the reported symptom - "still stuck past
the point it should have resolved" - except it would have actually
flipped to a "still waiting" warning toast at the 2-minute mark rather
than staying on "Loading" indefinitely, so this alone doesn't explain
what was reported, but is a real, separate improvement worth making.
Also fixes a real, separate bug this surfaced while reasoning through the
report: _showCenterStatus's banner is ONE shared, reused DOM node. A second
call to _watchLlamaSwapLoading (e.g. switching models again before the
first switch's loop had finished) would take over that shared banner, but
the FIRST loop was still running and would eventually dismiss or overwrite
it once ITS OWN deadline or readiness check resolved - clobbering whatever
the second, current loop had put there. A generation counter
(_watchLlamaSwapGeneration) now lets each call recognise when it no longer
owns the banner and stop touching it silently, rather than only the last
call to actually start ever safely reading or writing it.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
The "Claude started - switching to <endpoint>..." and "Loading <model> on
<endpoint>... this can take a while" messages lived in the top-right toast
corner along with everything else, easy to miss given they can each sit on
screen for well over a minute (a real llama-swap model load).
Adds _showCenterStatus() (panels-ui.js): a single, reused, screen-centred
banner with a spinner, non-blocking (no backdrop, pointer-events: none on
the wrapper) so it never gets in the way of using the app while it's up.
Both call sites (_runCustomModelEntryViaRestart's switching message,
_watchLlamaSwapLoading's loading message) now use it instead of showToast.
Every OTHER status in these two flows - the llama-swap conflict warning
already moved to its own modal, apply failures, cancellation, and
_watchLlamaSwapLoading's own final "ready"/"still waiting" outcome - stays
exactly where it was, in the corner.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
The llama-swap "this will unload it for session X" warning used a native
browser confirm() popup, which looks out of place next to the rest of the
app's own modals.
Adds #customModelSwapConfirmModal (index.html) with Cancel/Switch-anyway
buttons, styled to match the app. _confirmModelSwap(message) shows it and
returns a promise that resolves true/false the same way confirm() would;
_resolveModelSwapConfirm(proceed) (wired to both buttons and the backdrop
click) settles it. Both llama-swap conflict call sites
(_quickStartWithCustomModelConfirm for the one-shot launch path,
_runCustomModelEntryViaRestart for Claude's restart path) now await this
instead of calling confirm() directly.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG
Claude stays on the launch-then-restart path (see runCustomModelEntry's own
comment for why), but with nothing on screen during that window, a native
boot that briefly talks to the cloud model read as "the endpoint didn't
apply" rather than "the switch hasn't happened yet".
A sticky "Claude started - switching to <endpoint>..." toast now covers the
whole window from the native launch through the apply call, updated in
place (never stacked) as the outcome resolves: dismissed on cancel or
failure (replaced by the existing cancellation/error toast), handed off to
_watchLlamaSwapLoading's own sticky toast when a model swap is in progress,
or updated to the existing "Pointed at ... - restarting" message and
auto-dismissed after 3s on a plain success.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG