Kiro and Kimi share Hermes' ACP architecture and already accept
SystemPrompt prepended in front of the user prompt (kiro.go:244-247,
kimi.go:256-257). Without daemon-side opt-in, ExecOptions.SystemPrompt
is never set, so per-task agent identity instructions are lost in
deployments that rely on inline injection (e.g. K3 Lens-style
daemon → wrapper → docker compose exec acp).
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): mark provider 429 / out-of-credit runs as failed, not completed
Two bugs combined to silently report failed agent runs as
"Completed" in the UI when the upstream LLM returned a 4xx (e.g.
HTTP 429 rate-limit / no credit on the account).
1. ACP backends (hermes, kimi, kiro) only promoted the run status to
"failed" when their stderr sniffer fired AND the agent output
buffer was empty. But hermes injects a synthetic agent text turn
("API call failed after 3 retries: HTTP 429...") on retry
exhaustion, so the buffer was never empty in the rate-limit
case and the promotion never ran. Drop the empty-output
precondition: the sniffer's regex (HTTP-status markers, named
error types) is specific enough to trust on its own.
2. The daemon's task-result switch only routed "blocked" through
FailTask; every other status — including "cancelled", and any
future status we forget to enumerate — fell through to
CompleteTask. Invert it so only an explicit "completed" status
reports success, and extract the switch into reportTaskResult
for direct testing. Cancelled now defaults to failure_reason
"cancelled" instead of being silently completed.
Closes GitHub multica#1952.
Co-authored-by: multica-agent <github@multica.ai>
* fix(agent): only promote ACP run to failed on terminal provider error
Address GPT-Boy's review on the multica#1952 fix. The previous
promotion rule ("any sniffer line → fail") was too broad: the
existing sniffer also captures transient per-attempt warnings
("API call failed (attempt 1/3): RateLimitError [HTTP 429]"), and
those lines stay in the buffer for the rest of the run. A retry
sequence whose first attempt blipped but whose third attempt
succeeded would have been wrongly reported as failed.
Tighten the criteria with two additional signals, both defined on
the existing acpProviderErrorSniffer / output buffer:
- acpTerminalErrorRe — sticky `terminal` flag set when stderr shows
an exhausted/non-retryable marker (❌, [ERROR], "after N retries",
Non-retryable, BadRequestError, AuthenticationError). Per-attempt
warnings deliberately don't match.
- acpAgentOutputTerminalRe — matches the synthetic "API call failed
after N retries..." turn that hermes-style adapters inject into
the agent text stream when they give up; this catches multica#1952
even if hermes' stderr only logged transient attempts.
Promotion logic becomes a shared helper, promoteACPResultOnProviderError,
called from hermes / kimi / kiro. Promotes when (a) terminalMessage
is non-empty, (b) output contains the synthetic give-up turn, or
(c) output is empty and the sniffer captured anything at all
(preserves the original empty-output safety net for transient-only
sequences with no real result to fall back on).
Tests:
- TestHermesProviderErrorSnifferTerminalVsTransient — transient
attempt 1/3 alone returns terminalMessage="" but message!="";
a follow-on terminal marker flips terminal on.
- TestHermesProviderErrorSnifferTerminalNonRetryable — confirms
BadRequest / Authentication / Non-retryable / ❌ / [ERROR] are
classified terminal even on the very first attempt.
- TestHermesBackendDoesNotPromoteOnTransientRetry — fake hermes
emits attempt 1/3 to stderr then a normal agent text turn and
end_turn; resulting Status must stay "completed".
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(quick-create): add project picker that remembers last pick
Quick-create users targeting one project repeatedly had to restate "in
project X" in every prompt. The modal now exposes a project picker beside
the agent picker, persists the selection per-workspace, and pins the
agent's `multica issue create` invocation to that project so the prompt
text doesn't have to.
The picked project also flows to the daemon as ProjectID/ProjectTitle and
its github_repo resources override the workspace repo fallback — same
treatment issue-bound tasks already get.
Co-authored-by: multica-agent <github@multica.ai>
* fix(quick-create): move project picker into property pill row
Reviewer feedback: the picker felt out of place wedged next to the agent
header. Move it into a property toolbar row above the footer, reusing the
shared `ProjectPicker` + `PillButton` so its placement and styling line up
exactly with the manual create panel.
This also drops the bespoke dropdown / aria / label strings that were only
needed while the picker rendered inline beside "Created by".
Co-authored-by: multica-agent <github@multica.ai>
* fix(quick-create): clear stale persisted project + carry across mode switch
Two review-blocking bugs in PR #2321:
1. The stale-id sweep in AgentCreatePanel only fired when projects.length > 0
and only cleared local state, leaving lastProjectId pointing at a deleted
project. The next open re-seeded the dead UUID and submit hit the server's
`project not found` rejection. Gate on the query's `isSuccess` so we can
tell "loading" apart from "loaded as empty", and clear both local state
and the persisted preference when the selection isn't in the resolved list.
2. ManualCreatePanel's switchToAgent dropped the picked project from the carry
payload, so flipping manual → agent silently fell back to the agent panel's
own lastProjectId — potentially routing the issue to a different project
than the one shown in manual mode. Forward project_id alongside prompt /
agent_id, and add a regression test.
Co-authored-by: multica-agent <github@multica.ai>
* test(quick-create): pass new isExpanded props in stale-project tests
Main got an expand button on AgentCreatePanel via #2320 while this branch
was open, adding `isExpanded` / `setIsExpanded` to the panel's required
props. The two new stale-project tests still passed `{ onClose }` only,
which CI's typecheck (run on the main+branch merge) caught while my
local run did not.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* refactor(timeline): drop server-side comment + timeline pagination (MUL-1929)
The cursor-paginated /timeline and /comments endpoints were sized for a
problem the data shape doesn't have: prod p99 is ~30 comments per issue
and the all-time max is ~1.1k. Time-based pagination also splits reply
threads across page boundaries (orphan replies), which the frontend was
papering over with an "orphan rescue" that promoted disconnected replies
to top-level — confusing UX with no real benefit.
Replace both endpoints with a single full-issue fetch, capped server-side
at 2000 rows as a defensive safety net (never hit in practice).
Server
- /api/issues/:id/timeline now returns a flat ASC TimelineEntry[]
(matches the legacy desktop contract — older Multica.app builds keep
working because the wrapped TimelineResponse + cursors are gone, and
the raw array shape was always what they consumed).
- /api/issues/:id/comments drops limit/offset; only ?since is honoured
for the CLI agent-polling flow.
- Drop ListCommentsBefore/After/Latest, ListActivitiesBefore/After/Latest
and the timelineCursor encoding.
- Replace with ListCommentsForIssue / ListCommentsSinceForIssue /
ListActivitiesForIssue (capped by argument).
CLI
- multica issue comment list drops --limit / --offset and the X-Total-Count
reporting; --since is preserved for incremental polling.
Frontend
- Replace useInfiniteQuery with useQuery in useIssueTimeline; drop
fetchOlder/Newer, jumpToLatest, isAtLatest, newEntriesBelowCount.
- Remove timeline-cache helpers (mapAllEntries / filterAllEntries /
prependToLatestPage) and the TimelinePage / TimelinePageParam types.
- WS event handlers update the single flat-array cache directly.
- Drop the orphan-reply rescue in issue-detail — every reply's parent
is now guaranteed to be in the same array.
- Strip the "show older / show newer / jump to latest" buttons and their
i18n strings.
Co-authored-by: multica-agent <github@multica.ai>
* fix(timeline): address review feedback on pagination removal
Three issues caught in PR #2322 review:
1. /timeline broke for stale clients between #2128 and this PR. They send
?limit/?before/?after/?around and parse with the wrapped TimelinePageSchema;
the new flat-array response was failing schema validation and falling back
to an empty timeline. Restore the wrapped shape on those query params
(DESC entries, null cursors, has_more_*=false), keeping the flat ASC array
for bare requests. Around-mode now also fills target_index from the merged
slice so legacy clients can still scroll-to-anchor without a follow-up.
2. The agent prompts in runtime_config.go and prompt.go still told agents
that `multica issue comment list` accepts --limit/--offset and to use
`--limit 30` on truncated output. With those flags removed in this PR,
new agent runs would hit "unknown flag" or skip context. Update the
prompt copy to "returns all comments, capped at 2000; --since for
incremental polling".
3. useCreateComment's onSuccess was a bare append to the timeline cache
with no id-dedupe, so a fast comment:created WS event firing before
onSuccess produced a transient duplicate. Restore the id guard the old
prependToLatestPage helper used to provide.
Adds two new boundary tests:
- TestListTimeline_LegacyWrappedShape_OnPaginationParams
- TestListTimeline_LegacyWrappedShape_AroundFillsTargetIndex
Co-authored-by: multica-agent <github@multica.ai>
* test(handler): fix timeline test assertions for handler-package isolation
The TestListTimeline_* assertions assumed CreateIssue would seed an
"issue_created" activity_log row, but the activity listener that publishes
those rows is registered in cmd/server/main.go — handler-package tests
don't wire it up. CI saw 5 entries (3 comments + 2 activities) where the
test expected ≥6.
Drop the auto-activity assumption: assert exactly 5 entries in
TestListTimeline_MergesCommentsAndActivities, and tighten
TestListTimeline_EmptyIssue to assert a fully-empty timeline.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): treat upstream API 400 invalid_request_error as poisoned session
A markdown-linked image in an issue description that the agent downloads as
a tiny CDN auth-error file and Read's as a PNG poisons the conversation:
the LLM API rejects the bad image with 400 invalid_request_error, the
session_id is pinned mid-flight, and every follow-up task on the issue
(comment-trigger, auto-retry) resumes the same poisoned conversation and
hits the same 400 — the issue can no longer be executed even after the
description is cleaned up.
Mirror the existing fallback-output classifier on the error side: detect
"API Error: ... 400 ... invalid_request_error" in the agent error string,
persist failure_reason='api_invalid_request', and add it to the
GetLastTaskSession exclusion list so the next task starts a fresh
session that re-reads the (now-clean) description.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): unblock issues already poisoned by API 400 invalid_request_error
The forward-only classifier from the previous commit only tags new failures.
Issues like MUL-1918 already have multiple failed-task rows whose
failure_reason is the pre-fix default 'agent_error', and GetLastTaskSession
falls back to those legacy rows on the next claim — so deploying the
classifier alone leaves existing poisoned issues stuck (GPT-Boy review
on PR #2314).
Two complementary changes:
- Migration 079 backfills failure_reason='api_invalid_request' on every
pre-existing 'agent_error' row whose error text matches the canonical
Anthropic 400 invalid_request_error shape. Keeps observability
consistent (multica issue runs / UI now report the right reason).
- GetLastTaskSession adds a defensive ILIKE clause on error text. Closes
the deploy-window gap where the old binary could write a new
'agent_error' row between the migration running and the new code
taking over, and protects against future error-format variants the
daemon classifier might miss.
Plus regression tests covering the legacy + new coexistence case GPT-Boy
flagged, and a guard rail asserting benign 'agent_error' failures
(timeouts, tool errors) still resume their session.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
Two follow-up nits from PR #2211 review:
- Rename the package-local `repoCache` interface to `repoCacheBackend`
so the field declaration `repoCache repoCacheBackend` no longer shadows
its own type name.
- Bump the `/health`-must-respond timeout in
`TestHealthHandlerRespondsWhileTaskRepoLookupWaits` from 200ms to 1s.
The regression case blocks indefinitely on the old code, so a 1s
upper bound still fail-fast detects it while leaving headroom for
loaded CI runners.
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): add disk-usage CLI to surface per-task / per-workspace footprint
Adds `multica daemon disk-usage [--by-workspace] [--by-task] [--top N]
[--output json]`, walking the workspaces root to report task and workspace
disk consumption without requiring a running daemon. Sizing reuses the GC
artifact patternSet (basename-only) so the reported "artifact" footprint
matches what `cleanTaskArtifacts` would actually reclaim, and the walk
honors the same safety contract: never enters .git, never follows symlinks,
counts only regular files.
Refactors WorkspacesRoot resolution into an exported `ResolveWorkspacesRoot`
so the read-only CLI picks the same root the running daemon would have.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): distinguish displayed totals from scan totals; add workspace artifact ratio
- Track scan-wide TotalTaskCount / TotalWorkspaceCount on the report so
`--top N` no longer leaves the table footer claiming the truncated row
count is the full count. The CLI now prints a "Showing top N of M …
Displayed: X. Scan total: Y" line whenever truncation happens, and keeps
the bare "Total: …" footer for the un-truncated case.
- Add ArtifactRatio (0..1) on WorkspaceDiskUsage and TotalArtifactRatio on
the report. The workspace table renders an `ARTIFACT %` column. ratio()
guards size=0 so empty workspaces report 0% instead of NaN%.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): extend GC to chat / autopilot / quick-create tasks
Before this change the daemon's GC was strictly issue-centric: only tasks
with a non-empty issue_id ever wrote .gc_meta.json, and shouldCleanTaskDir
called only the issue gc-check endpoint. Chat / autopilot run / quick-create
tasks fell through to the GCOrphanTTL mtime path, which mis-killed active
chat sessions while leaving deleted ones around far longer than necessary.
Schema:
- GCMeta gains a Kind discriminator and per-kind ID fields
(ChatSessionID / AutopilotRunID / TaskID). WriteGCMeta now takes a
GCMeta struct so the call site classifies the task explicitly.
- ReadGCMeta defaults empty Kind to GCKindIssue, so legacy on-disk meta
files keep flowing through the issue path with no migration required.
Server endpoints (siblings of /api/daemon/issues/{id}/gc-check, all behind
requireDaemonWorkspaceAccess for the same anti-enumeration shape):
- GET /api/daemon/chat-sessions/{id}/gc-check -> {status, updated_at}
- GET /api/daemon/autopilot-runs/{id}/gc-check -> {status, completed_at}
- GET /api/daemon/tasks/{id}/gc-check -> {status, completed_at}
shouldCleanTaskDir dispatches on Kind:
- chat: active is hard-skipped (no mtime fallback) so idle sessions are
never reclaimed; archived + GCTTL cleans; 404 falls back to mtime to
stay safe for cross-workspace tokens.
- autopilot_run: terminal (completed/failed/skipped/issue_created) +
GCTTL cleans; running/pending skips. Uses run.completed_at as the TTL
anchor since autopilot_run has no updated_at column.
- quick_create: terminal task status cleans immediately (workdir is not
reused by the linked issue task, which has its own envRoot); running
skips.
Also drops the "skipping .gc_meta.json: issue_id is empty" warn — with
the new kind dispatch, chat/autopilot/quick-create tasks now write a
proper meta file instead of triggering this log.
Refs: GC follow-up to PR #2077 (symptom fix) and #2115 (chat hard delete).
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): chat gc-check 404 cleans immediately, no mtime gate
PR review caught that the chat 404 path was routing through
orphanByMTime, which deferred reclamation to GCOrphanTTL (72h) when
acceptance #3 calls for cleanup within one GC cycle (≤ 1h) after the
user hard-deletes a session.
Every chat_session_id we ever ask about was written by this same daemon
under its current token, so the cross-workspace probe defense the issue
path needs doesn't apply here. Drop the gate and clean on 404 directly.
Test updates:
- TestShouldCleanTaskDir_KindDispatch/chat_404 flips the locked
expectation from gcActionSkip to gcActionClean.
- Adds TestShouldCleanTaskDir_ChatHardDeletedFreshMtime: GCOrphanTTL
set to a year so any mtime-based path is unmistakably out, and the
fresh-mtime workdir still cleans on the chat-404 fast path.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): use brew prefix symlink for self-restart so Linux Cellar deletion does not orphan runtimes
After brew upgrade on Linux, os.Executable() resolves /proc/self/exe to
the Cellar path (e.g. .../Cellar/multica/0.2.9/bin/multica), which
brew cleanup deletes. The previous IsBrewInstall() short-circuit skipped
EvalSymlinks to 'preserve' the symlink, but on Linux there was nothing
to preserve - the path was already resolved.
Use cli.GetBrewPrefix() to resolve the stable symlink path
<brewPrefix>/bin/multica for brew installs. Fall back to
EvalSymlinks(os.Executable()) with a warning log when GetBrewPrefix()
returns empty (brew binary missing from PATH).
Introduce package-level function vars (isBrewInstall, getBrewPrefix) so
the daemon test can override them without modifying the cli package.
Closes#1624
* fix(daemon): harden brew-prefix fallback and document the WHY
When `brew --prefix` is unavailable but the binary is under a known Cellar
root, recover the prefix from cli.MatchKnownBrewPrefix and target
<prefix>/bin/multica instead of falling back to the resolved Cellar path
(which brew cleanup just deleted).
- Extract knownBrewPrefixes + MatchKnownBrewPrefix in cli/update.go and
reuse from IsBrewInstall to keep one source of truth for the install-root
list.
- Add a WHY comment above the brew branch in triggerRestart explaining the
/proc/self/exe -> Cellar -> deleted-by-brew-cleanup chain.
- Cover both fallback paths (matched / unmatched) in daemon_test.go.
---------
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
* fix(cli): add --content-file / --description-file for non-ASCII on Windows
Windows PowerShell 5.1 (the Win11 default) and cmd.exe re-encode HEREDOC
content through the active console codepage before piping it to a child
process. Characters the codepage cannot represent are silently replaced
with `?`, so agents on Chinese Win11 hosts emitting `--content-stdin` /
`--description-stdin` HEREDOCs land all of their Chinese as `?` in the
issue body and comments. The daemon log shows the original Chinese
correctly because slog writes to a file directly, so the regression
hides until the user opens the issue page.
Add a `--content-file <path>` / `--description-file <path>` source to
`resolveTextFlag`: the CLI reads the file straight off disk, preserves
UTF-8 bytes verbatim, and skips the shell entirely. The runtime config
injected into AGENTS.md / CLAUDE.md now surfaces this as the canonical
Windows fallback when the daemon host runs on Windows; non-Windows hosts
keep the existing stdin/HEREDOC guidance untouched.
Closes#2198, #2236.
Co-authored-by: multica-agent <github@multica.ai>
* fix(execenv): route every Windows-host stdin directive at --content-file
GPT-Boy on PR #2247 caught that the previous patch only inserted a Windows
fallback into the Available Commands section. Two later prompt surfaces
still hard-coded `--content-stdin` and overrode it for the agent:
- The Codex-specific paragraph in `buildMetaSkillContent`, which always
said "always use `--content-stdin` with a HEREDOC".
- `BuildCommentReplyInstructions`, which is re-emitted on every turn for
comment-triggered tasks (both via the AGENTS.md/CLAUDE.md workflow and
the daemon's per-turn prompt) and mandated the same HEREDOC pipe.
On Windows hosts we now branch both surfaces to a file-based template:
the agent writes the body to a UTF-8 file with its file-write tool and
posts via `--content-file <path>`. Non-Windows hosts keep the existing
stdin/HEREDOC guidance untouched.
Tests:
- `TestBuildCommentReplyInstructionsWindowsUsesContentFile` pins the
Windows / non-Windows reply-instruction text directly.
- `TestInjectRuntimeConfigWindowsCommentTriggerHasNoStdin` asserts that
the end-to-end CLAUDE.md / AGENTS.md surface for a comment-triggered
Windows task has no remaining `--content-stdin` directive that could
override the Windows fallback (covers Claude + Codex providers).
Co-authored-by: multica-agent <github@multica.ai>
* fix(execenv): make Windows comment block file-first, pin tests by GOOS
GPT-Boy's second review on PR #2247 flagged two follow-up blockers:
1. The Windows comment/description block in `buildMetaSkillContent` was
"stdin first, file caveat appended" — agents on Windows still saw
"Agent-authored comments should always pipe content via stdin" /
"MUST pipe via stdin" / `--description-stdin` directives before
reaching the Windows fallback, so the contradicting instruction was
live in the same prompt. Rewrite the entire Available Commands
bullet for Windows hosts as file-first: the headline line names
`--content-file`, the bulleted rules name `--content-file` /
`--description-file`, and stdin only appears in anti-prescriptive
"do NOT pipe via …" prose.
2. The existing non-Windows tests (TestBuildCommentReplyInstructions
IncludesTriggerID, TestInjectRuntimeConfigDirectsMultiLineWritesToStdin,
TestInjectRuntimeConfigCodexEmphasizesStdinForFormattedComments,
TestInjectRuntimeConfigCommentTriggerUsesHelper) all depended on
`runtimeGOOS` defaulting to non-Windows; they would silently fail on
a Windows test runner. Pin them to `runtimeGOOS = "linux"` via
save+restore and drop t.Parallel so they don't race with the
GOOS-mutating Windows tests.
Test additions:
- TestInjectRuntimeConfigWindowsRecommendsContentFile now asserts the
Windows AGENTS.md does NOT contain prescriptive stdin phrasings
(`MUST pipe via stdin`, `use --description-stdin and pipe a HEREDOC`,
`<<'COMMENT'`, `Agent-authored comments should always pipe content via
stdin`, `always use --content-stdin`) on top of the file-first
positive assertions. The ban list pins prescriptive substrings, not
bare flag names, so anti-prescriptive prose like "do NOT pipe via
--content-stdin" doesn't trip the ban.
- TestInjectRuntimeConfigWindowsCommentTriggerHasNoStdin gets the same
expanded ban list across the Available Commands, Codex paragraph,
and per-turn reply template surfaces.
- The non-Windows side of TestInjectRuntimeConfigWindowsRecommendsContentFile
pins that the Linux stdin/HEREDOC contract is still in place, so a
future refactor can't accidentally move every host to file-first.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): tighten quick-create prompt to drop meta-instructions and apologetic Context
The quick-create prompt was producing descriptions that:
1. Echoed routing meta-instructions ("create an issue for me", "cc @X") into
the User request body, even though those phrases are handled by separate
CLI flags and are not spec content.
2. Emitted a Context section to apologize for resources it could not fetch
(e.g. an image attachment not piped through to the run), instead of
staying silent and letting the executing agent ask the user.
3. Preserved pure conversational fillers ("对吧?", "嗯", "那个…") because the
model treated removing them as forbidden paraphrasing.
Updates the prompt to call out each of these as explicit non-spec material
to strip before writing the description, while keeping the "high fidelity /
no paraphrasing of substantive content" invariant. Adds a regression test
that locks in the new rules at the substring level.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): preserve cc mention links in quick-create description
Stripping "cc @Y" wholesale would have lost the mentioned member's only
routing channel: `multica issue create` has no --subscriber/--cc flag, and
the platform auto-subscribes members by parsing `[@Name](mention://member/<uuid>)`
links from the description body. Without the mention link in the body, a
cc'd member would never get subscribed or notified.
Updates the prompt to:
- Strip only the verbal "cc" wrapper from the User request body.
- Append a trailing `CC: <mention links>` line to the description so the
platform's auto-subscribe logic still picks the mentions up.
- Spell out the contrast for assignee mentions, where --assignee-id is
the routing channel and the body should not double-encode the mention.
Also adds a substring assertion for the "Pure conversational fillers" rule
that was missing from the original regression test.
Co-authored-by: multica-agent <github@multica.ai>
* refactor(daemon): trim quick-create prompt rules to general principles
Reviewers pointed out the previous rewrite traded one prompt smell (over-
permissive verbatim quoting) for another (too many specific rules and
exhaustive bilingual example tables). Rewrites the description block as
general principles with a single representative example each, trusting the
model to generalize:
- "Strip non-spec material before writing" replaces the multi-bullet list
of routing-meta-instruction and conversational-filler enumerations.
- "Include Context only when references were fetched and produced facts;
never use it as an apology log" replaces the three "Do NOT emit a
Context section to" sub-bullets.
- The CC exception (the only operationally non-obvious rule, since
`multica issue create` has no --subscriber flag) is kept inline as a
single sentence and is still locked in by the regression test.
Net: ~16 fewer lines of prompt text without losing any of the rules the
test asserts.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(timeline): cursor-paginated timeline to stop long-issue freeze (#1968)
Opening an issue from Inbox with thousands of timeline entries used to
hard-freeze the browser tab on a synchronous render of every comment +
activity. The whole pipeline was unbounded: the API returned every row,
TanStack Query cached the full array, and IssueDetail mounted N
CommentCards (each running a full react-markdown + lowlight pipeline)
in one frame.
This swaps the timeline endpoint to keyset cursor pagination and rewires
the frontend to useInfiniteQuery so a long issue costs the same as a
short one on first paint.
API:
- GET /issues/:id/timeline now accepts ?before / ?after / ?around (mutex)
+ ?limit (default 50, max 100); response wraps entries with next/prev
cursors and has_more flags. Cursors are opaque base64 (created_at, id).
- ?around=<entry_id> anchors a window on the target so Inbox notifications
pointing at an old comment never trigger the freeze.
- New composite indexes on (issue_id, created_at DESC, id DESC) replace
the redundant single-column ones so keyset queries are index-only scans.
- /issues/:id/comments default branch now caps at 50 instead of returning
every row unbounded; the unbounded ListComments / ListActivities sqlc
queries are deleted.
Frontend:
- useIssueTimeline switches to useInfiniteQuery, exposes
fetchOlder/fetchNewer/jumpToLatest + isAtLatest + newEntriesBelowCount.
- WS handlers respect the at-latest invariant: comment/activity:created
prepends to pages[0] only when the user is reading the live tail;
otherwise it just bumps a counter so the UI offers a "Jump to latest"
affordance without yanking scroll.
- Optimistic mutations adapted to the InfiniteData shape via shared
helpers (mapAllEntries / filterAllEntries / prependToLatestPage in
core/issues/timeline-cache.ts) and use setQueriesData so all open
windows of the same issue stay in sync.
- IssueDetail Activity section gets a TimelineSkeleton placeholder
during the brief load window plus subtle text-link load-more buttons
matching the existing Subscribe affordance (no Button chrome). Top
uses a divider for boundary clarity; bottom shows
"Jump to latest · N new" weighted slightly heavier when there's
unread state.
- highlightCommentId now flows into the hook's around parameter so
Inbox jumps fetch the surrounding 50 entries directly.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* chore(agent): default comment list to 50 + prompt hint about long issues
The CLI's "multica issue comment list" used to default to --limit 0
(meaning "fetch every comment"), which lets an agent on a long issue
fill its context window with thousands of rows. The default is now 50;
agents that need older history can pass --limit or --since explicitly.
The local-coding-agent prompt also gains a single-line note about this
in both the comment-triggered and on-assign flows so the agent knows to
scope its fetches when issue size is unknown. Autopilot run-only mode
is intentionally unchanged — it has no issue context to query.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
* fix(server): return 500 for transient DB errors in daemon task lookup
requireDaemonTaskAccess used to turn any GetAgentTask error into
404 "task not found", including transient DB connection / pool errors.
Combined with PR #2107 — which added 404+"task not found" as a daemon
cancellation trigger — that means a single DB hiccup could kill an
in-flight agent run.
Distinguish pgx.ErrNoRows (real "task gone", 404) from other errors
(transient, 500 + warn log) using the existing isNotFound helper.
Tests cover both paths via the mockDB pattern already used by
TestFindOrCreateUserGating.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): honor task-deleted signal in post-runTask completion guard
The final pre-completion check in handleTask only looked for
status == "cancelled" and ignored errors. After PR #2107 added a 404
task-deleted cancellation path to the in-flight watcher, this trailing
guard fell out of sync — if the task was deleted between the watcher's
last poll and runTask returning, handleTask would still try to call
CompleteTask and only learn about the deletion via the 404 from that
callback.
Reuse shouldInterruptAgent so the same truth table (cancelled OR
404 task-not-found, but NOT transient errors) drives both polling and
the final guard.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
When the server deletes a task while the daemon's agent is still running
(issue removed, agent reassigned, workspace cleanup), GetTaskStatus
starts returning 404 "task not found". The previous polling loop only
checked for status == "cancelled" and silently swallowed the error, so
the local agent kept emitting tool calls against a dead task until its
own timeout fired — minutes of wasted model spend and patch_apply
operations against a workdir nobody would consume.
Changes:
- Add isTaskNotFoundError next to isWorkspaceNotFoundError so the daemon
can distinguish "task gone" 404 from "workspace gone" 404 (already
handled separately) and from generic network errors.
- Extract the cancellation polling goroutine in handleTask into
watchTaskCancellation, plus a pure shouldInterruptAgent decision
helper. The pure helper makes both signals (cancelled status and 404
task) easy to unit-test without spinning up a real backend.
- Trigger interruption on the new 404 path. Transient errors (5xx,
network) intentionally still don't cancel — the next poll will retry
and a flaky link should not kill an in-flight agent.
Tests cover the helper truth table, the existing "status cancelled"
path, the new "task deleted (404)" path, and a negative case ensuring a
running task is not interrupted.
Co-authored-by: “646826” <“646826@gmail.com”>
`ensureSymlink` previously short-circuited whenever `dst` already existed
as a regular file ("Regular file exists — don't overwrite"). On Windows
that branch is reachable via the createFileLink copy fallback that fires
when `os.Symlink` is unavailable, so once a per-task `codex-home/auth.json`
was written as a copy it would never be refreshed by subsequent
Prepare/Reuse calls. If the shared `~/.codex/auth.json` rotated (e.g.
Codex Desktop refreshed the token in the background), the daemon kept
handing Codex a now-revoked refresh_token, which the OAuth server
rejected with `refresh_token_reused` / `token_expired`. Renaming the
workspace directory was the only recovery path.
Treat any non-matching dst — wrong-target symlink, broken symlink, or
stale regular file — as something to delete and re-create via
createFileLink, so each Prepare/Reuse mirrors the current shared source.
Add a `logCodexAuthState` info log (file kind, link target, size, mtime —
never contents) so operators chasing the same symptom can see at a glance
whether the per-task home is tracking the shared auth or has drifted.
Tests cover: stale regular-file dst is replaced, copy-fallback dst is
refreshed when the shared source rotates, and a high-level
prepareCodexHome regression simulating the Windows + token-rotation
scenario from issue #2081.
Co-authored-by: multica-agent <github@multica.ai>
A non-trivial fraction of completed task workdirs (~28% in field reports)
end up with .gc_meta.json files containing issue_id: "". Empty issue_id
defeats the daemon's own GC loop (gc.go:139 calls
GetIssueGCCheck(meta.IssueID)) and external retention scripts that
cross-reference issue status before deleting orphaned workdirs.
Refuse to write the file when issueID is empty, logging a Warn so
operators have a starting point for debugging the upstream race
condition. Skip is preferred over a sentinel-marker file: it keeps the
data invariant clean (a .gc_meta.json file always carries a valid
issue_id) and matches the repo CLAUDE.md preference for not preserving
dual-state behavior.
WriteGCMeta now takes a *slog.Logger so it can emit the warning. The
package already uses log/slog (Prepare/reuseEnv), and daemon.go:884 has
taskLog in scope at the only call site.
Closes#1913
Co-authored-by: Matt Van Horn <455140+mvanhorn@users.noreply.github.com>
* fix(daemon): isolate runtime poll & heartbeat schedules per runtime
A daemon serving multiple workspaces ran a single round-robin poll loop
and a single HTTP heartbeat loop across every registered runtime. A 30s
HTTP timeout for any one runtime serialized that delay across all the
others — observed in production as one workspace's runtimes wedging
every other workspace's runtimes on the same daemon.
This change:
- Replaces the shared runtime-set channel with a multi-subscriber
watcher so taskWakeupLoop, heartbeatLoop, and pollLoop can each
react to runtime-set changes independently.
- Splits heartbeatLoop and pollLoop into supervisor + per-runtime
worker goroutines. Each runtime owns its claim cadence and its
heartbeat ticker, so a slow request on one runtime no longer blocks
any other.
- Stagers the per-runtime heartbeat first tick by a jittered delay up
to one full interval to avoid a thundering herd at startup.
- Sizes the WS writer channel to scale with the runtime count
(max(16, 2*N)) so a full per-runtime heartbeat batch always fits;
the previous fixed 8-slot buffer dropped heartbeats whenever a
daemon watched more than ~8 runtimes.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): acquire execution slot only after ClaimTask, drain pollers before taskWG
Two issues from review on the previous commit:
1. Acquiring the shared task slot before ClaimTask reintroduced the very
head-of-line blocking the refactor was meant to remove. With
MaxConcurrentTasks=1, a slow claim on one runtime parked the only slot
for the duration of the HTTP timeout (up to 30s), starving every other
runtime's claim attempts. Slots are now acquired after the claim
returns a task; other runtimes' pollers stay free to claim. The
already-dispatched task waits for a slot under MaxConcurrentTasks
bounds, which is the same backpressure shape we had before.
2. pollLoop's shutdown path called taskWG.Wait immediately after
cancelling pollers, but a poller could still be between ClaimTask
returning a task and taskWG.Add(1). When taskWG's counter is zero
that races with Wait — undefined sync.WaitGroup misuse, sometimes
panic. Added a pollerWG so the supervisor blocks until every poller
goroutine has actually returned before reaching taskWG.Wait.
Tests:
- TestRunRuntimePollerIsolatesSlowRuntime now uses MaxConcurrentTasks=1
(was 4) so it would have failed under the old slot-before-claim path.
- New TestPollLoopShutdownWaitsForPollersBeforeTaskWG drives the exact
race window — claim returns a task at the same moment shutdown fires —
under -race.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): acquire slot before ClaimTask so capacity-waiters never enter dispatched
The previous commit moved slot acquisition AFTER ClaimTask to address a
review concern about head-of-line blocking with MaxConcurrentTasks=1.
That introduced a strictly worse failure mode: server-side ClaimTask
flips the task to `dispatched` immediately (agent.sql:174-176), and the
runtime sweeper fails any task in `dispatched` for >300s with
`failed/timeout` (runtime_sweeper.go:25-28). When local execution
capacity is full and the next claimed task can't acquire a slot within
5 minutes, the user sees the exact failure this issue is fixing —
`dispatched_at` set, `started_at` NULL, `failure_reason=timeout`.
Reverted to slot-before-claim. The trade-off is the original review
concern: with MaxConcurrentTasks=1 and a slow ClaimTask, other
runtimes' claims are delayed by up to client.Timeout=30s. That's a
30s polling delay, not a failure — server-side those tasks remain
`queued` (no timeout in that state) until a slot frees. 30s ≪ 300s,
so other runtimes' tasks cannot get sweeper-failed because of this.
The pollerWG fix from the previous commit (avoiding sync.WaitGroup
misuse on shutdown) is preserved.
Tests:
- TestRunRuntimePollerIsolatesSlowRuntime: MaxConcurrentTasks back to
4 (the pre-issue baseline) — the headroom case where slot-before-
claim still gives full per-runtime isolation.
- New TestRunRuntimePollerSkipsClaimWhenAtCapacity: holds the only
slot and verifies the poller never calls ClaimTask while sem is
empty. The previous "claim first" path would have failed this.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(projects): add resource_count breadcrumb to project responses
Closes#2087
`multica project get` previously returned project metadata with no signal
that resources existed. Agents that fetched a project this way had no way
to discover its attached resources without already knowing about
`/api/projects/{id}/resources` or the on-disk `.multica/project/resources.json`.
Rather than inline the full resource list into the parent payload (which
conflates parent metadata with a child sub-collection and locks the
resource_ref shape into the project endpoint's contract), this adds a
scalar `resource_count` breadcrumb to ProjectResponse. The actual list
stays at the dedicated sub-collection endpoint.
Changes:
- GetProjectResourceCounts :many — new batched sqlc query
- ProjectResponse.ResourceCount populated in GetProject, ListProjects,
SearchProjects, and the with-resources CreateProject echo
- multica project get prints a stderr hint pointing at
multica project resource list <id> when count > 0; the JSON on stdout
stays parseable
- Meta-skill (runtime_config.go) lists multica project get and
multica project resource list in Available Commands so agents that
read CLAUDE.md / AGENTS.md know about both paths
Co-authored-by: multica-agent <github@multica.ai>
* fix(projects): wire ResourceCount through Update + Create event payload
Review feedback on #2118.
- UpdateProject now reloads ResourceCount before responding/publishing.
Previously a title- or status-only PUT served (and broadcast over WS)
resource_count: 0 even when resources existed.
- The with-resources CreateProject path sets resp.ResourceCount before
the project:created publish, so the WS event payload matches the HTTP
echo. The hand-rolled response map collapses to an embedded
ProjectResponse + resources array — one source of truth for the
serialized shape.
- packages/core/types/project.ts: Project gains resource_count: number
to keep the TS contract aligned with the server response.
Tests:
- TestProjectResourceCountBreadcrumb extends to assert UpdateProject
preserves the breadcrumb.
- TestCreateProjectWithResourcesEchoesCount asserts the create echo
carries resource_count matching the attached resources.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(cli): add --assignee-id / --to-id / --user-id for unambiguous targeting
`multica issue {create,update,list}`, `issue assign`, and `issue subscriber
{add,remove}` accepted only fuzzy name matching, which fails in workspaces
where one user's name is a substring of another (e.g. agent "J" vs
"Cursor - J" / member "Jiayuan"). #1642 added UUID acceptance through the
existing flags, but there was still no explicit path that signals "this is a
UUID, not a name" — important for scripts that read IDs from
`multica workspace members --output json`.
Adds an `-id`-suffixed counterpart for every assignee-taking flag:
- `issue list` : --assignee-id
- `issue create` : --assignee-id
- `issue update` : --assignee-id
- `issue assign` : --to-id
- `issue subscriber {add,remove}` : --user-id
The new flags route through `resolveAssigneeByID`, a strict resolver that
requires a canonical UUID and fails with a clear error when the entity is
not in the workspace (no name fallback). A shared `pickAssigneeFromFlags`
helper enforces mutual exclusion between the name and id flags so a script
that accidentally sets both never silently applies one over the other.
Refs MUL-1254.
Co-authored-by: multica-agent <github@multica.ai>
* fix(cli): detect assignee flag presence via Changed, not value-emptiness
`pickAssigneeFromFlags` previously branched on `flag value != ""`, so
explicitly passing an empty UUID silently routed through the "no flag set"
path:
multica issue list --assignee-id "" # listed every issue
multica issue create --assignee-id "" # created an unassigned issue
multica issue subscriber add --user-id "" # subscribed the caller
This is exactly the failure mode the strict-UUID flag was added to prevent —
a script interpolating `--assignee-id "$MAYBE_UUID"` against a missing env
var should fail loudly, not silently degrade to a different operation.
Switch the picker (and the assign-command top-level guard) to use
`Flags().Changed`, so an explicit empty value reaches `resolveAssigneeByID`
/ `resolveAssignee` and surfaces a clear "expected a canonical UUID" /
"no member or agent found matching" error.
Co-authored-by: multica-agent <github@multica.ai>
* docs(cli): cover --assignee-id / --to-id in user docs and quick-create prompt
Follow-up to the --*-id flag rollout: surface the new flags everywhere the
old ones are documented so users (and agents) can discover them.
- assigning-issues.{mdx,zh.mdx}: the page explicitly calls out the
duplicate-name footgun ("first one listed wins, so rename before
assigning") — replace that workaround with a --to-id <uuid> example
- cloud-quickstart.{mdx,zh.mdx}: add a --to-id hint after the substring-
match callout so first-time users learn about the strict path
- internal/daemon/prompt.go (quick-create injected prompt):
- default-to-self: pass --assignee-id <task.Agent.ID> instead of
--assignee <name>; the picker agent's UUID is already in scope and
UUID matching is unambiguous in workspaces with overlapping agent
names (J / Cursor - J / Pi - J etc.)
- user-named: tell the agent to prefer --assignee-id <uuid> using the
user_id/id from the JSON it already fetched; --assignee <name> stays
a fallback for unambiguous workspaces
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): remove Co-authored-by hook when workspace setting is off
The prepare-commit-msg hook is installed in the bare repo's shared
hooks dir, so once installed it persists across worktrees. CreateWorktree
only installed the hook when the setting was enabled, but never removed
it — so disabling the workspace toggle had no effect on subsequent
commits.
Add removeCoAuthoredByHook and call it in both CreateWorktree branches
when the setting is disabled. Use a marker comment in the hook script so
removal only deletes hooks the daemon owns; user-installed hooks at the
same path are left alone.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): recognize legacy Multica prepare-commit-msg hook on removal
The first cut of removeCoAuthoredByHook only recognized hooks installed
by the new code (containing the multicaHookMarker sentinel). Bare clones
already on disk from previous daemon releases carry the older script
without that line, so toggling the workspace setting off would have
treated them as user hooks and left the trailer in place — exactly the
state reported in MUL-1704.
Match against a list of known daemon signatures (current marker + the
legacy "Installed by the Multica daemon." comment), and add a test that
seeds the verbatim legacy hook before CreateWorktree(... disabled) to
keep recognition aligned with what production hosts actually have on
disk.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
TestRegisterTaskReposSurvivesWorkspaceRefresh started flaking on CI
after #1988 (`feat: support repo checkout ref selection`) extended the
bare-clone path to run an extra `git fetch` to backfill
refs/remotes/origin/* under the new refspec layout. The race was
already latent: registerTaskRepos kicks off `go syncWorkspaceRepos(...)`
to clone a repo into the cache root, which in tests is `t.TempDir()`.
Once the test waited on `repoCache.Lookup` to return a path it would
proceed and return — but the bg goroutine was still inside
`ensureRemoteTrackingLayout` running git operations on the clone dir.
`t.TempDir`'s cleanup then races with those git commands and surfaces
either as "directory not empty" or "fatal: cannot change to ... No such
file or directory", with no hint that the failure is unrelated to the
test's actual assertion.
Track the background goroutine on the Daemon via a sync.WaitGroup and
expose `waitBackgroundSyncs()` for tests. `newRepoReadyTestDaemon`
registers a t.Cleanup that calls it, so every test that uses the
helper now drains in-flight syncs before t.TempDir cleanup runs. No
production-behavior change — registerTaskRepos still fires-and-forgets
from the caller's perspective.
Verified with `go test ./internal/daemon -run
TestRegisterTaskReposSurvivesWorkspaceRefresh -count=30` (was failing
within ~10 iterations before, 30 green after) and the full
`go test ./internal/daemon/...` suite.
Co-authored-by: multica-agent <github@multica.ai>
Follow-up nits from PR #1988 review:
- Move the comment that documents getRemoteDefaultBranch's resolution
walk into the resolveBaseRef call site description, and rephrase the
"" branch so it's clear that path only fires for the default-branch
case (the requested-ref path returns an explicit error before
reaching it).
- Add TestCreateWorktreeWithRequestedTagRef to lock in the
refs/tags/<ref> candidate. The test tags the initial commit, advances
the default branch past it, then asserts the worktree HEAD matches
the tagged commit (so the tag must have been resolved, not the
default branch).
Co-authored-by: multica-agent <github@multica.ai>
* fix(server): persist ModelListStore across replicas via Redis
The model picker uses a pending-request pattern: the frontend POSTs to
create a request, the daemon pops it on its next heartbeat, runs
agent.ListModels locally, and reports back. Until now the store was a
plain in-memory map per Handler instance.
That works for self-hosted single-instance deploys but fails in any
multi-replica environment (Multica Cloud). Each replica has its own
map, so:
POST /runtimes/:id/models → request stored in replica A
GET /runtimes/:id/models/<requestId> → polls land on B/C → 404
daemon heartbeat → only A sees PendingModelList
POST .../<requestId>/result → daemon's report has to land on A
Success probability ~1/N². The visible symptom is "No models available"
in the picker for every provider, even those (Claude/Codex) whose
catalog is statically populated end-to-end.
Same shape of bug, same Redis-backed fix as multica-ai/multica#1557 did
for LocalSkillListStore / LocalSkillImportStore. Reuse the operational
playbook (namespaced keys, ZSET-backed pending queue, atomic
ZREM+SET-running via the shared Lua script) so we don't introduce a
second concurrency model for the same primitive.
Changes:
- Convert ModelListStore from struct to interface with context-aware
methods. Add HasPending for cheap heartbeat-side probing.
- InMemoryModelListStore — single-node fallback, used when REDIS_URL
is unset (self-hosted dev / tests).
- RedisModelListStore — multi-node implementation using the same key
layout and Lua atomic claim as RedisLocalSkillListStore.
- Use RunStartedAt (not UpdatedAt) as the running-timeout reference
point, matching the local-skill stores so subsequent UpdatedAt
bumps don't reset the running clock.
- Heartbeat now uses the probe-then-pop pattern for the model queue
(matching local-skills) so a slow Redis can't stall every connected
daemon. Extends heartbeatMetrics + slow-log with probe_model_ms /
pop_model_ms / probe_model_timed_out for parity.
- Wire the Redis backend in NewRouterWithOptions when rdb != nil.
- Tests for both backends. Redis tests gate on REDIS_TEST_URL so
laptop runs without Redis still pass; CI provides it.
Co-authored-by: multica-agent <github@multica.ai>
* fix(server): persist RunStartedAt + retry model report on transient failures
Two follow-ups from PR #2022 review:
1. RedisModelListStore was dropping ModelListRequest.RunStartedAt on
persistence — the field is tagged json:"-" so it doesn't leak into
the HTTP response, which made plain json.Marshal(req) silently
discard it. Across-node readers saw RunStartedAt=nil and
applyModelListTimeout's running branch became a no-op, so the 60s
running-timeout escape hatch never fired. CI's
TestRedisModelListStore_RunningTimeout was failing on this exact
case. Fix mirrors RedisLocalSkillImportStore's envelope pattern —
wrap in an internal struct that re-promotes the field. HTTP shape
stays clean. Adds a no-Redis unit test that pins the round trip.
2. Daemon's handleModelList called d.client.ReportModelListResult
directly and swallowed any 5xx, leaving the pending request
stranded in "running" until its 60s server-side timeout — exactly
the failure mode the multi-node store fix was meant to eliminate.
Generalize the existing local-skill retry helper into
reportRuntimeResultWithRetry (kind: model_list / local_skill_list /
local_skill_import) and wire handleModelList through a new
reportModelListResult helper. Renames the test-overridable
var localSkillReportBackoffs → runtimeReportBackoffs to match.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): add safe.directory=* to gitEnv to fix CI dubious ownership errors
TestRegisterTaskReposAllowsProjectOnlyURL and
TestRegisterTaskReposSurvivesWorkspaceRefresh fail on GitHub Actions CI
because git clone --bare from local temp directories triggers git's
safe.directory ownership check when the runner UID differs from the
directory owner.
Set safe.directory=* via GIT_CONFIG env vars in gitEnv() so all daemon
git subprocesses trust any directory. The daemon manages its own bare
caches and worktrees, so the ownership check provides no security value.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): preserve existing GIT_CONFIG_* entries in gitEnv
Instead of resetting GIT_CONFIG_COUNT to 1, read the existing count
from the environment and append safe.directory at the next available
index. This preserves any env-scoped git config (auth, URL rewrites,
extra headers) injected into the daemon process.
Adds TestGitEnvPreservesExistingConfig to verify the append behavior.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
The previous description rule ("stay faithful + keep it concise") caused
agents to over-compress user input into vague single-sentence summaries,
losing context that the executing agent needs.
Key changes:
- Replace "keep it concise" with structured two-section format:
User request (faithful restate) + Context (verifiable external facts)
- Add hard rules against information compression and semantic downgrading
- Remove "one-line description" phrasing (UI supports richer input)
- Strip redundant behavioral rules from issue_context.md (already
covered by AGENTS.md guardrails and per-turn prompt)
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): reclaim disk on long-open issues + correct cancelled-status check
Two related fixes for GitHub #1890 (self-hosted disk space growth):
- The GC's done/cancelled branch compared `status.Status` against `"canceled"`
(single l), but the issue schema and the rest of the daemon use `"cancelled"`
(double l). Cancelled issues therefore never matched and only fell out via the
72h orphan TTL, which itself doesn't fire because cancelled issues are still
reachable. Aligning the spelling lets cancelled-issue task dirs be reclaimed
on the normal TTL path.
- Add a third GC mode, artifact-only cleanup, for the common case the report
flagged: an issue stays open for days while many tasks complete on it, so
per-task `node_modules`, `.next` and `.turbo` directories accumulate without
ever becoming GC-eligible. The new branch fires when `.gc_meta.completed_at`
is older than `MULTICA_GC_ARTIFACT_TTL` (default 12h), the env root is not
currently in use by an active task, and the issue is still alive. It removes
only directories whose basename matches `MULTICA_GC_ARTIFACT_PATTERNS`
(default narrow: `node_modules,.next,.turbo`); source, `.git`, `output/`,
`logs/` and the meta file are preserved so subsequent tasks can still resume
the workdir. Patterns containing path separators are dropped, `.git` subtrees
are never descended into, symlinked matches are not followed, and every
removal target is verified to live inside the task dir.
Bookkeeping: `Daemon` now tracks active env roots with a refcounted set so the
GC loop never reclaims a directory that is mid-execution; `runTask` claims the
predicted root early plus the prior workdir on reuse paths. The cycle log is
extended with bytes reclaimed and per-pattern counts so self-hosted operators
can see what was freed.
Docs: extend the daemon configuration table in CLI_AND_DAEMON.md with the new
GC env vars and add a Workspace garbage collection section explaining the
three modes and the artifact-pattern contract.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): protect active env root from full GC removal too
Address GPT-Boy's PR #1931 review: the active-root guard only fired in the
artifact-cleanup branch, leaving a real race on the full-removal paths. A
follow-up comment on a long-done issue dispatches a task that reuses the prior
workdir, but `CreateComment` does not bump issue.updated_at — so the issue
still satisfies the done+stale GCTTL window and `gcActionClean` would
`RemoveAll` the directory mid-execution. The orphan-404 path is similarly
exposed when a token's workspace access is in flux.
Move the `isActiveEnvRoot` check to the top of `shouldCleanTaskDir` so all
three delete actions (clean, orphan, artifact) skip an in-use env root in one
place, and drop the now-redundant guard from the artifact branch.
Add tests covering the three at-risk paths: active root + done/stale issue,
active root + 404 issue past orphan TTL, active root + no-meta orphan past
TTL.
Also align two stale comments noted in the same review: cleanTaskArtifacts now
documents that symlinks are skipped entirely (the previous note implied the
link itself was removed), and GCOrphanTTL no longer claims that 404s are
cleaned immediately — the implementation gates them on the same TTL.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* refactor(repos): drop unused description + tighten create-project layout
Two related changes that touch the workspace-repos surface together.
1. Remove the per-repo `description` field everywhere it was threaded.
The only place it ever surfaced was a markdown table column the daemon
wrote into the agent runtime config, where most rows just read "—"
anyway. Agents already discover project structure by running
`multica project` / `multica issue` against the CLI, so the human-
readable description string carried no real value while taking up an
extra Settings input row and propagating through six layers (settings
UI → workspace.repos jsonb → handler RepoData → daemon RepoData →
repocache.RepoInfo → execenv.RepoContextForEnv).
- Settings → Repositories drops the description input; the URL field
now spans the whole row.
- WorkspaceRepo TS type loses `description`; backend RepoData /
RepoInfo / RepoContextForEnv all collapse to URL only.
- Daemon's runtime_config Repositories block changes from a
`| URL | Description |` markdown table to a simple bullet list.
- Tests updated; jsonb residue in existing workspaces is dropped at
normalize time, so no migration needed.
2. Tighten the Create Project modal footer: pull the Status / Priority /
Lead / Repos pills onto the same row as the Create Project button
(Linear-style single-row footer) instead of stacking them above it,
and swap the Repos pill icon from `FolderGit` to a real GitHub mark
(lucide-react v1 dropped brand icons, so the mark lives inline as a
small SVG component in this file).
I tried promoting Repos to its own "Resources" strip above the footer
to separate the resources abstraction from project metadata, but with
a single pill it looked too sparse — leaving a TODO comment in the
footer to revisit once we add Linear / Notion / Figma / Slack
resource types.
* fix(daemon test): drop residual Description field on RepoData literals
* fix(repos): drop Description residue surfaced after rebase on #1929
Project-resource github_repo lift path (#1929) and registerTaskRepos
both still constructed RepoData{...Description: ...} after the rebase.
Two test sites in daemon_test.go and execenv_test.go also reintroduced
the field. Strip them so the Description-removal change builds and
tests pass with the latest main.
* feat(projects): project github_repo resources override workspace repos
When an issue's project has at least one github_repo resource, the daemon
claim handler now sends only those as resp.Repos — workspace-level repos
are hidden to avoid mixing two repo lists in the agent prompt. With no
project github_repos (or no project), behavior is unchanged: workspace
repos are surfaced as before.
Lifts each project github_repo's url (and label, when present) into a
RepoData entry so `multica repo checkout` and the meta-skill render the
same URLs. The full structured list still ships at
.multica/project/resources.json for skills that want everything.
Adds TestProjectReposReplaceWorkspaceReposInMetaSkill covering the
rendering side. Docs updated to spell out the new precedence.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): allow project repo URLs through the checkout allowlist
When ClaimTaskByRuntime narrows resp.Repos to project github_repo URLs,
the daemon receives URLs that may not exist in the workspace's
GetWorkspaceRepos response. The existing checkout flow rejected those
with ErrRepoNotConfigured because the allowlist (and cache) was built
only from workspace-bound repos.
Adds registerTaskRepos in daemon.runTask: before agent spawn, merge
task.Repos into a new task-scoped allowlist (separate from the
workspace-scoped one so a workspace refresh doesn't wipe project URLs)
and kick off a background cache sync. ensureRepoReady now treats either
allowlist as valid.
Tests:
- TestRegisterTaskReposAllowsProjectOnlyURL — project-only URL is
checkout-able and does not trigger a workspace-repos refresh
- TestRegisterTaskReposSurvivesWorkspaceRefresh — task URLs persist
across refreshWorkspaceRepos
- TestClaimTask_ProjectGithubReposOverrideWorkspaceRepos — claim
handler returns only project repos when present, no workspace leakage
- TestClaimTask_ProjectWithoutRepos_FallsBackToWorkspaceRepos — fall
back to workspace repos when project has no github_repo resources
Docs updated to spell out the daemon-side allowlist behavior.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(task): rerun starts a fresh session, skip poisoned resume
When a task ended in a known agent fallback ("I reached the iteration
limit and couldn't generate a summary.", "Put your final update inside
the content string. Keep it concise.") the (agent_id, issue_id) resume
lookup would still pick that session, so a manual rerun inherited the
poisoned state and reproduced the same bad output.
Two complementary guards:
1. Daemon classifies poisoned terminal output and routes it through the
blocked path with failure_reason set ('iteration_limit' /
'agent_fallback_message'). GetLastTaskSession excludes failed tasks
with those reasons, so even comment-triggered tasks no longer resume
them. Tasks that failed mid-flight (timeout, runtime_recovery, etc.)
are still resumable, preserving MUL-1128's auto-retry contract.
2. Manual rerun marks the new task force_fresh_session=true. The daemon
claim handler skips the resume lookup entirely when the flag is set,
capturing the user-intent signal that "the prior output was bad" even
when poisoned classification misses a future fallback wording.
Auto-retry of orphaned mid-flight failures (MaybeRetryFailedTask →
CreateRetryTask) does not take this path, so it keeps resuming.
Tests: classifyPoisonedOutput unit test; integration tests assert the
SQL filter excludes poisoned classifiers, RerunIssue flips the flag,
and the normal enqueue path leaves it false.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): cap poisoned-output matcher to short trimmed text
GPT-Boy review on MUL-1630: the previous strings.Contains match would
classify any output that quoted the marker substring — including a
review/analysis that simply discussed the marker itself. Real fallback
messages are short single-sentence affairs, so cap the candidate at
~one paragraph and trim whitespace before matching. Adds regression
tests covering a long quoting review and a marker buried in a long
real conclusion; both must stay classified as completed.
Co-authored-by: multica-agent <github@multica.ai>
* fix(migrations): rename 065 force_fresh_session → 066 to clear collision
main introduced 065_project_resources after this branch was cut, so
both files shared the 065_ prefix. The readiness check
(server/cmd/server/health.go → migrations.LatestVersion) takes the
last entry by lexical order, which is 065_project_resources, leaving
this branch's 065_force_fresh_session unguarded — a deploy that
applied project_resources but not force_fresh_session would still
report ready, and the next enqueue / rerun / claim would crash on
"column force_fresh_session does not exist".
Renaming to 066_force_fresh_session puts it strictly after
project_resources so readiness blocks until it's applied.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(projects): typed project resources + agent runtime injection
Adds a `project_resource` table that lets a project carry typed pointers
(github_repo today, more later) and surfaces them at agent runtime.
Server
- migration 065: project_resource (resource_type TEXT + resource_ref JSONB)
- sqlc CRUD + handler at /api/projects/{id}/resources
- claim handler attaches project_id/title + resources to issue tasks
Daemon
- TaskContextForEnv carries project context
- writes .multica/project/resources.json into workdir
- adds "## Project Context" block to CLAUDE.md / AGENTS.md / GEMINI.md
via type-dispatched formatter so new resource types just add a case
CLI
- multica project create --repo <url> attaches repos in one step
- multica project resource add/list/remove
Frontend
- Project create modal: Repos pill (workspace repos + ad-hoc URL)
- Project detail sidebar: collapsible Resources section with attach/remove
Docs
- New "Project Resources" chapter explaining the abstraction and
exactly what code to touch when adding a new resource type
Co-authored-by: multica-agent <github@multica.ai>
* fix(projects): transactional resources[] on create + generic CLI ref + test fix
Addresses review feedback on PR #1926:
1. CI red: TestProjectResourceLifecycle delete step called withURLParam
twice, which replaced the chi route context and dropped the project id.
Switched to the existing withURLParams helper from daemon_test.go.
2. POST /api/projects now accepts resources[] and attaches them in the
same transaction as the project. Invalid refs roll back the whole
create — no more half-attached projects on failure. Web modal + CLI
`project create --repo` both use the new bundled payload.
3. CLI `project resource add` now accepts a generic --ref '<json>' flag
so a new resource_type works without a CLI change. Per-type
shortcuts (--url for github_repo) remain as a convenience but are no
longer the only way in. Docs updated to drop the CLI from the
"files you must touch" list.
Adds two new server handler tests:
- TestCreateProjectAttachesResources (resources[] happy path)
- TestCreateProjectRollsBackOnInvalidResource (transactional rollback)
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): add Co-authored-by trailer for Multica Agent to git commits
Install a prepare-commit-msg hook in worktree bare repos that appends
"Co-authored-by: multica-agent <github@multica.ai>" to every commit
made by agents. Uses git interpret-trailers for proper formatting and
skips duplicates.
* feat(settings): add Co-authored-by toggle in workspace Labs settings
Add a workspace-level toggle to enable/disable the Co-authored-by
trailer for agent commits. Default is enabled (on).
Backend:
- Include workspace settings in daemon register response
- Store settings in daemon workspaceState
- Thread CoAuthoredByEnabled through WorktreeParams to conditionally
install the prepare-commit-msg hook
- Parse co_authored_by_enabled from workspace settings JSONB
Frontend:
- Replace empty Labs tab placeholder with a Git section containing
a Switch toggle for the Co-authored-by trailer setting
- Optimistically update the workspace query cache on toggle
* chore(daemon): skip squash commits in Co-authored-by hook
Test commit to verify the prepare-commit-msg hook appends the
Co-authored-by trailer automatically.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
The description rule in buildQuickCreatePrompt() instructed the agent to
"always provide a rich, self-contained description" and "spell out what
needs to be done", which caused the agent to fabricate detailed product
specs, implementation phases, and design decisions from a one-line input.
Replace with a faithfulness-first rule: enrich with factual context
(fetched PR details, linked resources) but never invent requirements,
design decisions, or constraints the user did not express.
Fixes MUL-1605
* feat(quick-create): enrich issue title and description with URL context
Update the quick-create agent prompt to fetch context from URLs in user
input (GitHub PRs, issues, web pages) before creating the issue. The
agent now produces semantically rich titles (e.g. "Review PR #123:
Refactor auth to OAuth2" instead of "review PR #123") and includes
summarized link content in the description so issues are self-contained.
* refactor(quick-create): let agent decide when to fetch URL context
Replace prescriptive URL enrichment instructions (hardcoded gh/WebFetch
commands) with goal-oriented guidance. The agent now uses its own
judgment to decide whether fetching referenced URLs would produce a
meaningfully better title/description, rather than being told exactly
which tools to use.
* fix(quick-create): always generate rich description for agent execution
The description was previously optional ("omit if simple request"). Since
quick-create issues are executed by agents, richer context leads to
better execution — update the prompt to always produce a substantive
description with actionable context.
* fix(quick-create): remove Chinese text from prompt, use English only
Replace Chinese examples in priority mapping and assignee matching with
language-agnostic English equivalents, per project coding rules.
* fix(quick-create): remove language-related hints from prompt
Agent doesn't need to be told about language handling — remove
"(in any language)" and "or equivalent in any language" qualifiers.
Keep prompt purely in English with no language-related content.
* fix(execenv): default-disable Codex native multi-agent in per-task config
Recent Codex app-server releases enable features.multi_agent by default,
exposing spawn_agent / wait / close_agent tools that let a parent thread
spawn nested subagents. The daemon currently models only the parent thread,
so the parent's turn/completed is treated as task completion even when
spawned children are still running — leading to premature task completion
and dropped child output.
Disable features.multi_agent by default in the per-task CODEX_HOME/config.toml
so Multica's task lifecycle is the only orchestration layer in play. Strip
both the dotted-key form (features.multi_agent) at TOML root and the
multi_agent key inside a [features] table; siblings and unrelated tables
are preserved. Honor MULTICA_CODEX_MULTI_AGENT=1 as an opt-out for users
who explicitly want Codex native subagents inside a Multica task.
The user's global ~/.codex/config.toml is never modified — only the daemon's
isolated per-task copy.
Also widen managedBlockRe to consume `\n*` rather than `\n?` so reruns
don't accumulate blank lines when both the sandbox and multi-agent managed
blocks coexist.
* fix(execenv): inject managed multi_agent inside existing [features] table
Per PR review (codex_multi_agent.go:77-83 vs :112-115): when the user's
config.toml already has a top-level `[features]` table, writing
`features.multi_agent = false` at the TOML root implicitly redefines the
same `features` table. The strict TOML parser used by Codex (`toml-rs`)
rejects that with `table 'features' already exists`, so Codex would fail
to load the per-task config and refuse to start the thread. Verified the
strict-parser failure with pelletier/go-toml/v2; the previous
BurntSushi/toml-based regression test was permissive enough to miss it.
Detect a root-level `[features]` header and place the managed block
inside that table (`multi_agent = false` with marker comments). When no
such header exists, keep the existing root-level dotted-key form. The
managed-block regex matches both layouts so reruns and layout
transitions stay idempotent. A `[features.experimental]` sub-table
without a bare `[features]` header still uses the root dotted-key form,
which is spec-valid (no explicit redefinition).
Tests now use pelletier/go-toml/v2 to actually parse the output and
assert features.multi_agent decodes to false; the regression case from
the PR review is covered explicitly.
* fix(execenv): recognize feature table header variants
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Two coordinated fixes for a quick-create case where the agent ended up
creating duplicate issues. Repro: user pasted an image into the
quick-create prompt; the front-end uploaded it and embedded the URL as
markdown in the user input; the agent saw the URL, assumed it was an
attachment, and ran `multica issue create … --attachment "https://…"`.
The CLI POSTed the issue first, then failed to read the URL as a file
(`os.ReadFile("https://…")`) and exited 1. The agent treated exit 1 as
"create failed" and retried — but the first issue already existed, so
the workspace ended up with two of them.
CLI (`server/cmd/multica/cmd_issue.go`):
- `runIssueCreate` pre-validates `--attachment` BEFORE POSTing. URLs are
warned about and skipped (they are never local files); local-path
read errors fail before the issue is created so no half-baked issue
lands. Once the POST succeeds, post-create upload failures only
print a stderr warning and the issue metadata is still emitted —
never a non-zero exit, so callers cannot mistake "attachment upload
hiccup" for "create failed" and retry.
- `runIssueCommentAdd` already uploads attachments BEFORE the comment
is created, so its failure mode is fine; it just gets the same
URL-skip behaviour for consistency.
Quick-create prompt (`buildQuickCreatePrompt`):
- Tells the agent NOT to pass `--attachment` for prompt-embedded image
URLs (they are already part of the description as markdown).
- Hardens the "no retry" rule: even on a non-zero exit, do not retry
`issue create` — the issue may already exist.
GitHub #1839: when an issue is reassigned from agent A to agent B, B
often only reads the issue body and misses context A added in comments
(e.g. which repo to clone). The assignment-triggered workflow injected
into CLAUDE.md / AGENTS.md said "Read comments for additional context
or human instructions" — vague enough that agents routinely skipped
it. The comment-triggered branch already gives an explicit
`multica issue comment list` invocation, so behavior diverged.
Promote step 3 to a concrete CLI call, mark it mandatory, and surface
the most common failure mode (stale instructions on reassignment) so
the agent recognizes when it matters. Reorder so comments are read
*before* flipping status to `in_progress`, matching how a human would
catch up on a thread before claiming work.
* feat(quick-create): default assignee to picker agent when user didn't name one
The quick-create prompt previously told the agent to OMIT --assignee
when the user's input didn't name a person. That left almost every
quick-created issue unassigned, which doesn't match user intent — the
user opened quick-create with a specific agent picked, so that agent
is the obvious owner.
Both prompt surfaces (BuildPrompt for the dispatched message, plus
the workflow block in injected CLAUDE.md / AGENTS.md) now instruct
the agent: if the input doesn't name an assignee, pass
`--assignee "<your name>"`. The picker agent's name is interpolated
into the prompt at task-build time so the agent has a literal value
to use rather than guessing its own name. The "explicitly named
assignee → resolve via members" branch is unchanged.
* refactor(execenv): drop duplicated quick-create field rules from CLAUDE.md/AGENTS.md
The quick-create field rules (title / description / priority / assignee
fallback / project / status) lived in two places — the per-turn user
message built by BuildPrompt, and the workflow block injected into
CLAUDE.md / AGENTS.md by buildMetaSkillContent. Same content, two
sources, easy to update one and forget the other (the assignee-default
change in this PR had to touch both).
Quick-create is one-shot, so the per-turn user message is always
present and is the natural single source of truth. The injected
file's quick-create section now keeps only the hard guardrails:
"do exactly one issue create, no issue get / status / comment add,
exit on CLI error". Those guardrails stay in BOTH surfaces because
they're the safety net for providers that don't propagate the user
message into resumed-session context.
renderQuickCreateContext (issue_context.md) was already
guardrails-only — no change needed there.
