* fix(execenv): overlay per-task HERMES_HOME so Hermes discovers bound skills
Hermes has no workspace-relative skill discovery — it scans <HERMES_HOME>/skills
first, then skills.external_dirs from config.yaml (verified against the bundled
agent/skill_utils.py). The daemon wrote assigned skills to the generic
.agent_context/skills/ fallback, which Hermes never reads, so they silently never
took effect (#5242).
When (and only when) an agent has skills bound, redirect HERMES_HOME to a minimal
per-task compatibility overlay; a skill-less Hermes task keeps its real home and
original behavior:
- mirror every top-level entry of the shared home via symlink except the
overlay-owned ones (denylist), reconciling entries deleted from the shared home;
- derive a task-local config.yaml whose skills.external_dirs references the shared
skills dir plus the user's existing external_dirs, expanded against the
sanitized effective child env (unknown vars preserved, blocklisted keys resolved
to the process value) and normalized to absolute paths;
- write only the bound skills into the task-local skills/ dir (home skills scanned
first, so they win); global skills are referenced, not copied;
- keep memories/ overlay-owned (fresh per-task dir) AND disable the external
memory.provider, so neither on-disk memory nor a shared backend crosses tasks;
- keep active_profile/profiles out of the overlay so Hermes can't follow a sticky
profile and redirect past it at startup.
Profile handling mirrors hermes_cli.profiles: the daemon reads -p/--profile with
agent.HermesProfileFromArgs and seeds the overlay from that profile's home via
ResolveHermesSourceHome (default/invalid -> base, valid name -> <base>/profiles/
<name>, validated; a missing named profile fails closed). The profile flags are
stripped from the acp argv ONLY when the overlay is active (hermesLaunchArgs), so
a skill-less task's profile passes through unchanged. HERMES_HOME is no longer
custom_env-blocklisted: no skills -> user value passes through; skills -> overlay
overrides after layering. Fail closed — Prepare errors, Reuse returns nil.
Task home 0700, derived config 0600 via atomic replace. Platform-native default
home (%LOCALAPPDATA%\hermes, incl. the LOCALAPPDATA-missing fallback, on Windows).
Tests span execenv/daemon/agent: no-skill no-op, child-env layering + env
sanitization, profile parse/unquote + conditional strip + final args/env per
scenario, custom/profile/default/invalid/missing/Windows source home, sticky-
profile not mirrored, memory dir isolation + external provider disable, mirror
reconciliation, external_dirs rebasing + sanitized/unknown-var expansion,
local-precedence slug, perms, fail-closed, resume teardown. Docs (en + ja/ko/zh).
Fixes#5242
* fix(hermes): make profile selection one resolver contract matching Hermes
Round 5 review: the profile chain approximated Hermes' semantics in three
separate places (argv parsing, source-home selection, arg filtering), so it
diverged from native Hermes in several merge-blocking cases. Collapse it into
one authoritative resolution:
- agent.ParseHermesProfileArgs replaces HermesProfileFromArgs/
FilterHermesProfileArgs. It reproduces _apply_profile_override step 1/1b
(first occurrence, value-flag skipping, `--` and `mcp add --args` boundaries,
space-form profile-id guard) and returns the exact argv occurrence to consume;
StripHermesProfileArgs removes only that occurrence.
- execenv.ResolveHermesProfile replaces ResolveHermesSourceHome. It derives the
Hermes root exactly like get_default_hermes_root (an already-profile-scoped
HERMES_HOME roots at its grandparent), selects an explicit profile first,
otherwise trusts a profile-scoped home (step 1.5) and only then the sticky
<root>/active_profile (step 2), and validates via normalize/validate_profile_name
(reserved hermes/test/tmp/root/sudo and empty inline `--profile=` are hard
errors). Profiles always resolve under the root, so `-p default` re-roots and
`-p <sibling>` is a sibling, never nested.
- The daemon runs one parse + resolve, fails the task closed on a reserved/
invalid selection (matching Hermes' sys.exit(1)), and exports the selected
source home as the effective env's HERMES_HOME so ${HERMES_HOME} in a profile's
skills.external_dirs expands against the selected profile home (as native
Hermes does before loading config.yaml), not the root or the overlay.
Regressions added: root + sticky named profile selection; already-profile-scoped
home with no flag; that home with -p default and -p <sibling>; reserved and empty
inline profile values; and a selected profile whose external_dirs contains
${HERMES_HOME}.
* fix(hermes): overlay-owned derived .env + symlink-resolved root
Round 6 review, two remaining overlay-bypass paths:
1. A source `.env` could redirect HERMES_HOME after profile resolution. Hermes
runs `_apply_profile_override()` then `load_hermes_dotenv()`, which loads
`<HERMES_HOME>/.env` with override=True — so a mirrored source `.env` carrying
an out-of-band `HERMES_HOME=` overwrote the overlay's home, repointing skill
discovery and memory back at the source. `.env` is now overlay-owned and
DERIVED (writeDerivedHermesEnv): it preserves the source's credentials/settings
but strips any `HERMES_HOME` assignment and pins `HERMES_HOME` to the overlay
last (single-quoted, literal), written 0600 via atomic replace. It is written
even when the source has none, so Hermes' project-`.env` fallback (override=True
only when no user `.env` loaded) can't relocate the home either.
2. Root derivation was lexical-only, diverging from `get_default_hermes_root`,
which compares `env_path.resolve()` with `native_home.resolve()`. A HERMES_HOME
symlinked into `<native>/profiles/<x>` was treated as its own root, so
`-p default`/`-p <sibling>` resolved wrong. `hermesRootFromHomeFor` now resolves
symlinks (Path.resolve(strict=False)-style best effort) for the containment
decision while keeping the returned root unresolved, matching Hermes.
Regressions: source `.env` with HERMES_HOME replayed through the override=True
dotenv order (bound skill + task memory stay on the overlay; creds preserved);
minimal overlay `.env` created when the source has none; and a symlinked profile
home resolving `-p default`/`-p <sibling>` to the native root.
The daemon pins each agent CLI's symlink-resolved absolute path at startup to
block PATH-redirect of a task launch. A version manager (Homebrew Cask, nvm/fnm)
upgrading in place deletes the pinned versioned directory and repoints the stable
name, leaving the daemon on a path that no longer exists — every codex task, model
list, and version detection then hard-fails with "executable not found" until the
daemon restarts.
resolveAgentEntry now self-heals a vanished pin by re-resolving the recorded
command once, version-detecting and min-version-gating the candidate before
adopting it, and publishing {path, version} atomically so callers key policy off
the binary that actually runs. Coalesced with singleflight; a live heal wins over
a reappearing stale path; custom runtimes and custom-only hosts are untouched.
Applied at task launch, model listing, and registration.
MUL-4486
* feat(daemon-claim): machine-level batch task claim endpoint (MUL-4257)
Collapse the per-runtime /tasks/claim poll fan-out into a single machine-level
batch claim to cut /api/daemon claim request volume.
Server:
- agent.sql: = ANY(runtime_ids) batch variants of the claim queries
(ListQueuedClaimCandidatesByRuntimes, PromoteDueDeferredTasksForRuntimes,
ReclaimStaleDispatchedTasksForRuntimes); runtime.sql: GetAgentRuntimes(= ANY)
so a whole machine's runtimes are resolved/promoted/reclaimed/listed in a
constant number of queries instead of N.
- service.ClaimTasksForRuntimes: claim up to max_tasks across a runtime set,
preserving per-(issue,agent) serialization, the concurrency cap, the
empty-claim cache short-circuit, and every dispatch side effect. Batch
promote replays the per-row side effects (task:queued + empty-cache Bump).
- handler.ClaimTasksByRuntime (canonical POST /api/daemon/tasks/claim, with a
transitional /claim alias): validates daemon_id (required; must match the
mdt_ token) and rejects runtimes bound to a different daemon (group-ownership
check mirroring the WS path); resolves+authorizes each runtime_id; claims;
and finalizes each task through the SAME FinalizeTaskClaim as the per-runtime
endpoint (atomic token + delivered_comment_ids receipt), requeueing the exact
claim and omitting it on failure. buildClaimedTaskResponse is extracted from
the per-runtime handler and returns the delivered-comment ids plus a
structured *claimBuildFailure so both paths share identical payload building
and failure semantics (workspace-isolation, chat-input load/empty).
- max_tasks: negative -> 400, zero -> empty (never coerce to 1), positive
capped at 32. runtime_ids parsed with non-panicking util.ParseUUID.
Daemon:
- Client.ClaimTasks posts daemon_id + runtime set + free-slot count to the
canonical path under a short request-scoped timeout, bounding the
head-of-line coupling the per-runtime pollers avoid (MUL-1744).
Tests: service batch drain / max_tasks cap / deferred-promote receipt /
finalize-failure rollback+requeue; handler routing + token, cross-workspace
skip, cross-daemon skip, daemon_id required, owner-missing cancel,
max_tasks=0/negative, invalid-uuid skip, comment delivery receipt, stale-reclaim
replacement receipt; client posts/parses (daemon_id + canonical path).
Follow-up: cut the daemon pollLoop over to a single batched poller (flips the
MUL-1744 isolation contract; needs its concurrency tests redesigned).
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon-ws): generic WS request/response transport for daemon RPC (MUL-4257)
Add a generic daemon->server request/response layer over the existing WS
control connection, the transport for WS-first claim (HTTP fallback):
- protocol: daemon:rpc_request / daemon:rpc_response envelopes with a
correlation request_id + method + body, and an rpc-v1 capability gate.
- daemonws.Hub: SetRPCHandler + goroutine-dispatched handleRPCFrame (bounded
by a per-connection in-flight cap) that echoes the request_id; missing
handler / saturation return non-2xx so the daemon falls back to HTTP.
Read limit raised to 64KB for rpc requests carrying a runtime set.
- hub tests: round-trip, handler-error->non-2xx, no-handler->503.
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon-ws): WS-first task claim over the generic RPC transport (MUL-4257)
Bind claim to the WS request/response layer, with HTTP fallback:
- server: handler.DaemonRPCHandler adapts a daemon:rpc_request (method
tasks.claim) to the existing HTTP ClaimTasksByRuntime via a synthetic
in-process request carrying the WS connection's identity (daemon_id +
workspace + capabilities), so all auth / payload-building / finalization is
reused unchanged. Wired via daemonHub.SetRPCHandler. ClientIdentity now
captures X-Client-Capabilities so capability gating matches the HTTP path.
- daemon: wsRPCClient correlates responses by request_id over the shared WS
connection; attached to the live connection's write channel (guarded so a
Call racing teardown never sends on a closed channel) and detached on
disconnect. rpc_response frames are routed in the read loop.
Daemon.ClaimTasksWSFirst issues tasks.claim over WS and falls back to the
HTTP claim endpoint on any transport failure (no conn / buffer full /
timeout) — wired into the poller at the poller cutover.
- tests: handler tasks.claim RPC end-to-end (claims + dispatches) + unknown
method 404; daemon wsRPCClient round-trip / timeout / unavailable /
server-error / detach-fails-pending (all under -race).
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): cut claim poller over to machine-level ClaimTasksWSFirst (MUL-4257)
Replace the per-runtime HTTP poll loop with a single batch poller: each cycle
acquires all free execution slots (slot-before-claim) and issues ONE
ClaimTasksWSFirst across every runtime the daemon hosts (WS-first, HTTP
fallback), dispatching each returned task to its runtime. Wakeups (targeted /
catch-up / runtime-set change) collapse to one nudge. Removes runRuntimePoller
+ runtimePollOffset. The WS handshake now advertises the same capabilities as
HTTP (+ rpc-v1) so WS-built claim payloads keep skill-ref / coalesced-comment
gating.
Trades per-runtime isolation (MUL-1744) for one request, bounded by the short
per-request WS timeout / client timeout. Tests: batch poller claims across
runtimes + skips-at-capacity + pollLoop shutdown drain (replacing the
per-runtime poller tests); heartbeat isolation + runtime-set watcher kept.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon-ws): WS RPC disconnect-race panic + batch stale-comment-plan repair (MUL-4257)
Two PR #5193 review blockers:
1) WS RPC send-on-closed-channel race, both ends:
- server: give each connection a cancelable ctx (cancelled on readPump
teardown) and run the RPC handler under it, so a slow claim stops on
disconnect; guard c.send with sendMu/sendClosed (trySend) so a late RPC
response goroutine never writes to the closed channel. Heartbeat ack routed
through the same guard.
- daemon: wsRPCClient.deliver now sends under the mutex, serialized with
attach(nil)'s close+delete, so a delivered response can't hit a channel
the detach path just closed.
- regressions (-race): daemon deliver-vs-detach; server
disconnect-during-handler-response.
2) batch claim now runs the stale-comment-plan repair: extracted the
per-runtime handler's repair (trigger deleted, only coalesced survive ->
cancel + replay survivors) into shared repairStaleCommentPlanIfNeeded, called
by both claim paths. Prevents the batch path (now the default poller) from
finalizing+dispatching a task with no comment input and silently dropping the
surviving user comment. Regression: batch omits the stale task, cancels it,
and rebuilds the survivor into a new trigger plan.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon-ws): server-side RPC deadline + legacy claim fallback (MUL-4257)
Two review blockers:
1) WS RPC timeout/fallback (GPT-Boy): the daemon's WS wait didn't cancel
server-side claim, so a slow WS claim could commit after the daemon fell
back to HTTP, leaking dispatched tasks and breaking the free-slot bound.
Fix: RPC envelope carries TimeoutMs; the server bounds the handler ctx by it
(so ClaimTasksByRuntime's tx is cancelled/rolled back at the deadline), and
the daemon waits budget + grace so a claim that committed before the deadline
still reports back. A committed-then-unreported claim degrades to the same
stale-reclaim safety net as HTTP, never a double effective claim. Regression:
server-side TimeoutMs cancels the handler.
2) Backward compat (Terra-Boy): a new daemon against a server without the batch
route (/api/daemon/tasks/claim 404) couldn't claim. Fix: ClaimTasksWSFirst
falls back to the legacy per-runtime ClaimTask loop on a batch 404 and caches
'batch unsupported' (reset on WS reconnect to re-probe after a server
upgrade). Regression: server exposing only the legacy route.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon-ws): no double-claim on WS teardown/detach (MUL-4257)
Sol-Boy review blocker: on reconnect, teardown failed the pending RPC (→ HTTP
fallback) but then flushed the queued tasks.claim frame to the still-alive
socket, so the server committed the WS claim on top of the HTTP one — double
claim, WS batch orphaned to stale reclaim, breaking the free-slot bound.
- Teardown now closes the connection FIRST, so runWSWriter discards the queued
RPC frame (write error path) instead of delivering it.
- A detach while a claim's frame is already in flight now returns a distinct
errWSRPCUncertain; ClaimTasksWSFirst does NOT HTTP-fall-back on uncertain (the
WS claim may have committed) — it skips the cycle and lets reclaim / the next
poll recover. Genuine 'not sent' / timeout still fall back (safe: the
server-side deadline guarantees no uncommitted claim by budget+grace).
- Regression: detach during an in-flight WS claim asserts zero HTTP claims
(at most one path claims); plus the existing detach/deliver-race and
server-timeout tests.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon-ws): cancelable RPC frames close the backpressure double-claim (MUL-4257)
Sol-Boy review blocker: the client's response budget starts at enqueue, but
the socket write is async (10s write deadline). A backpressured writer could
hold a tasks.claim in the local queue past the client timeout — the daemon
HTTP-fell-back, then the writer woke and delivered the stale WS frame, so the
server committed it too: same free slots claimed twice. No detach occurs, so
the prior errWSRPCUncertain fix did not cover it.
- WS frames are now cancelable (wsOutbound{sent,canceled} under a mutex). The
writer calls beginWrite() before WriteMessage and skips cancelled frames.
- On give-up (timeout / detach / ctx), Call cancels the queued frame: if it was
still pending the cancel wins and the frame is guaranteed never delivered
(errWSRPCUnavailable → safe HTTP fallback); if the writer already began
sending it the cancel loses and the outcome is errWSRPCUncertain (no
fallback). The decision is atomic, so at most one transport claims.
Tests: wsOutbound cancel-before-write vs write-before-cancel; Call timeout
cancels an unsent frame (writer then drops it) vs uncertain when already sent;
plus the updated detach and existing timeout/race tests.
Co-authored-by: multica-agent <github@multica.ai>
* fix(batch-claim): return partial success instead of dropping committed claims (MUL-4257)
Sol-Boy review blocker: ClaimTasksForRuntimes reclaims (step 2) and claims per
agent (step 6) in independent transactions, but a step-4 candidate-SELECT error
or a mid-loop ClaimTask error did 'return nil, err' — discarding tasks already
committed as dispatched. The handler 500s; the daemon sees a definite (non-
uncertain) 500 and HTTP-falls-back, claiming a SECOND batch into the same free
slots while the first batch waits for stale reclaim — the double-claim this PR
removes.
- Both error paths now prefer partial success: if any task has already
committed (claimed non-empty), return it (nil error) so the handler finalizes
and returns 200; the errored candidates stay queued for the next poll. The
remaining error is logged. Only a genuinely empty result still returns the
error (safe: no committed claim to lose, HTTP fallback just re-fails).
Regression (internal/service, DB-backed, fault-injected):
- PartialSuccessOnSecondAgentClaimFailure: fail the 2nd ClaimTask's Begin →
the first agent's committed task is returned, not dropped.
- PartialSuccessOnCandidateQueryFailureAfterReclaim: a stale dispatched task is
reclaimed, then the candidate SELECT fails → the reclaimed task is returned.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): correct unread — archived sessions + mount-race auto-read (MUL-4360)
Reland of #5315, which was reverted by #5332 as collateral in an unrelated
release-wide revert (to unwind 162/163 migration BLOCK from other PRs), not for
any defect in this code — Howard/Preflight assessed these changes WARN /
non-blocking. Restores all three fixes verbatim off current main:
- backend: ListAllChatSessionsByCreator derives unread_count=0 / has_unread=false
for status='archived' rows via a CASE gate. last_read_at is untouched, so
unarchiving restores the true unread state. Single source of truth for every
unread surface (quick-chat FAB, sidebar Chat tab, chat-window header, mobile);
installed desktop clients benefit with no app update.
- frontend: the archive mutation onMutate optimistically zeroes the row's unread
so no badge counts a just-archived session in the frame before the refetch
lands. Unarchive does not fabricate a count — the true state returns from the
server refetch.
- frontend: auto-mark-read is deferred a tick and cancelled on cleanup, so a
session that is only momentarily active on mount (persisted activeSessionId
restored for one frame, then cleared by the URL->store effect) is not marked
read; only a session that stays active past the tick is.
Verification: sqlc regenerate produces no drift; go test ./internal/handler
-run 'TestListChatSessions_ArchivedSessionReportsZeroUnread|TestSetChatSessionArchived_ClearsChannelBinding'
passes against a real Postgres; vitest mutations.test.tsx (3) and
use-chat-controller.test.tsx (8) pass; core + views typecheck clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): converge archived unread on chat:session_updated realtime event (MUL-4360)
Howard's #5333 review found a real cross-tab gap: the chat:session_updated
handler patched status but never unread, and chatSessionsOptions is
staleTime: Infinity, so a session archived in one tab kept its unread badge lit
in another tab/device forever — the same stuck-badge bug, one surface over.
Extract the inline handler into applyChatSessionUpdatedToCache and force
unread_count=0 / has_unread=false when payload.status === "archived", mirroring
the archive mutation's optimistic patch and the backend deriving unread=0 for
archived rows. Unarchive does NOT fabricate a count — the true unread returns
from the server refetch (last_read_at untouched). No sessions-list
invalidation; minimal field patch as reviewed.
Adds use-realtime-sync.test.ts coverage: an archived event zeroes a cached
unread row; an active event does not resurrect unread; a rename-only event
leaves unread untouched.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
Fixes#5300. The daemon hardcoded optionId="approve_for_session" when auto-approving Hermes' session/request_permission, but Hermes' ACP edit-approval offers only ["allow_once","deny"] and rejects anything else, silently blocking every file write. handleAgentRequest now selects an option the agent actually offered — a safe session/single-use grant, else an offered reject_once to deny just that action, else a JSON-RPC error — never a permanent allow_always or a whole-turn cancelled. Includes regression + branch-coverage tests.
* fix(labels): sweep resource-label junctions on bulk deletes (MUL-4479)
Runtime, runtime-profile, and workspace deletion hard-delete their agents
and skills without clearing agent_to_label / skill_to_label. Migration 173
dropped the junction foreign keys, so these rows are no longer cascade-cleaned;
once resource labels are enabled, every labelled agent/skill removed through one
of these bulk paths leaves a permanent, invisible orphan junction row.
Clear the junctions in the same transaction as the owner delete, before the
owning rows disappear:
- DeleteAgentRuntime / ArchiveAgentsAndDeleteRuntime / DeleteRuntimeProfile:
DeleteAgentLabelAssignmentsByRuntime, ahead of the archived-agent hard-delete.
- DeleteWorkspace: DeleteAgentLabelAssignmentsByWorkspace +
DeleteSkillLabelAssignmentsByWorkspace, ahead of the workspace cascade.
Adds regression tests for all four delete paths.
Follow-up to #5345 (Elon review). Resource labels must stay disabled until this
lands.
Co-authored-by: multica-agent <github@multica.ai>
* fix(labels): make workspace cleanup atomic
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Co-authored-by: Eve <eve@multica-ai.local>
The 162_resource_labels down migration recreated issue_label_workspace_name_lower_idx
with a plain CREATE UNIQUE INDEX, which takes a blocking lock on the existing
issue_label table during a rollback to v0.3.43 and violates the online-migration
rule that every CREATE INDEX must be CONCURRENTLY.
CREATE INDEX CONCURRENTLY cannot run in a transaction or a multi-command migration,
so the rebuild is split out of 162.down:
- 171.down now rebuilds the legacy index as a single CREATE UNIQUE INDEX CONCURRENTLY
(the natural inverse of 171.up, which drops it).
- 174 (new, no-op up) deletes the agent/skill label rows in its down so they are gone
before 171.down rebuilds the workspace-wide unique index. Down migrations apply
high->low, so 174.down -> 171.down -> 162.down runs in the required order.
- 162.down keeps only the transaction-safe structural teardown.
Validated on an isolated Postgres: full up->down->up chain with a colliding
issue/agent label pair; the concurrent rebuild succeeds after the rows are deleted,
restores the valid pre-162 unique index, and a negative control (rebuild before the
delete) fails on the exact collision.
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
* fix(codex): bound app-server startup RPCs
Co-authored-by: multica-agent <github@multica.ai>
* test(codex): de-flake bounded-handshake test
The single 500ms handshake bound was shared by the successful preamble
RPCs, so a slow fork/exec of the /bin/sh fake app-server could make
initialize spuriously time out under parallel load. Raise the test bound
to 3s (still below the 5s semantic timeout and 10s harness ceiling) and
loosen the elapsed assertion to match.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
Co-authored-by: J <j@multica.ai>
Moving an issue to `cancelled` used to auto-cancel every in-flight agent task
on that issue. Users have no expectation that clicking "cancel" stops running
agent runs, so this implicit coupling is removed from UpdateIssue and
BatchUpdateIssues. Deleting an issue still cancels its tasks (the owning row
disappears); a plain status change never does. Reassignment already didn't
cancel tasks (#4963 / MUL-4113), so this makes status-cancel consistent.
- Status-table-driven regression tests cover every active state the cancel
query sweeps (queued / dispatched / running / waiting_local_directory /
deferred) on both the single and batch paths.
- Updated the multica-working-on-issues skill (SKILL.md + source map) and
corrected stale comments in task.go and agent.sql that described the removed
coupling as current.
MUL-4465
* feat(skills): search runtime local skills
* feat(skills): highlight matched substrings in runtime local skill search
Reuse the shared HighlightText (the same component the global search
command uses) to highlight matched substrings in a result's name,
provider, description, and path, so styling stays consistent across the
app. Narrow the search to the fields the row actually renders and drop
`key`, so every match maps to something visible. While a query is active,
lift the description's 2-line clamp so a match past the first two lines
stays on screen instead of being clipped.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): zero unread for archived chat sessions across all badges (MUL-4360)
Archiving a chat session flips status but deliberately does not advance
last_read_at, and ListAllChatSessionsByCreator counted unread
unconditionally. So an archived session that had unread replies kept
reporting has_unread=true / unread_count>0 — a stuck badge the user can
never clear (archived sessions are read-only and hidden from history, so
there is no mark-as-read entry). MUL-4372 fixed only the quick-chat FAB
surface; the sidebar Chat tab badge and the chat-window "other unread"
header still counted it.
Fix at the source: derive unread_count = 0 for status='archived' rows in
ListAllChatSessionsByCreator. Because has_unread is server-derived as
unread_count > 0, and all surfaces (FAB, sidebar via
countUnreadChatMessages, chat-window header, and mobile) read this one
payload, every badge drops archived sessions with no per-surface filter.
last_read_at is left untouched so unarchiving restores the true unread
state. Installed desktop clients benefit without an app update.
Also zero unread optimistically in the archive mutation so no badge
counts a just-archived session in the frame before the refetch lands
(FAB already filtered archived; this keeps sidebar/header consistent).
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): stop auto-mark-read from clearing a transiently-active session on mount (MUL-4360)
The chat page persists `activeSessionId`, so on a bare `/chat` navigation it
restores the last-open session as active for one frame before its URL→store
effect (which runs AFTER useChatController's effects, since the hook is called
first) clears it back to null. The auto-mark-read effect fired in that gap and
marked the restored-but-never-opened session read — its unread badge vanished
though the right pane still showed "select a chat" and the user never opened it.
This is why the sidebar count dropped (e.g. 2 → 1) just by entering the tab.
Defer the read by a tick and cancel it on cleanup: a session that is only
momentarily active (restored on mount, then cleared) has its pending read
cancelled when activeSessionId changes; only a session that stays active past
the tick — a real select, deep link, or refresh — is marked read. A live-store
re-check in the timer is a belt-and-suspenders guard.
Adds the previously-missing auto-mark-read coverage: a stable-active session is
read after the tick; a momentarily-active one is not.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: coderbaozi <YHbaozi1988@163.com>
Co-authored-by: abun <103836393+coderbaozi@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
#5307 renamed 161_attachment_task_id -> 164 (and 162_..._index -> 165) to
resolve a prefix collision. schema_migrations keys on the full stem, so any DB
that applied the migration under its old 161 number does not have "164" in the
ledger and the runner re-applies the renamed file. The bare `ADD COLUMN task_id`
then aborts with 42701 ("column already exists"), blocking every later
migration — this is exactly what crashed the dev deploy of main (bf288349f) at
container startup, before it ever reached 166_project_dates.
Add `IF NOT EXISTS` so the re-run is a harmless no-op on already-migrated DBs
(dev/staging/prod) with no manual schema_migrations surgery, while staying
identical on a fresh DB. Sibling 165 already uses CREATE INDEX ... IF NOT EXISTS
for the same reason; this brings 164 in line. The down file already uses
DROP COLUMN IF EXISTS.
Verified on a throwaway DB reproducing the dev drift (forget 164/165 in the
ledger, keep the column+index): old file reproduces the 42701 crash, the fixed
file self-heals and completes. Migration lint + concurrent migrate tests pass.
Refs #5307
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Projects become schedulable planning objects alongside their issues: add
optional start_date / due_date, mirroring issue.start_date / issue.due_date.
This is only the first slice of #5227 — labels, metadata, and the editable
metadata UI are still out of scope.
- migration 166: two nullable DATE columns on `project` (calendar days, no
FK/index — matches the issue end-state after migration 112)
- sqlc CreateProject / UpdateProject carry the dates; UpdateProject uses
narg so an explicit null clears
- handler: parse YYYY-MM-DD (400 on bad format), rawFields-presence clear on
update, and the hand-scanned SearchProjects query returns the columns
- CLI: `project create/update --start-date/--due-date` (empty clears on update)
- frontend + mobile types/zod schemas: the two new schema fields are
nullable().default(null) so a project from an older backend (frontend
deploys before backend) parses to null instead of degrading the batch to
the empty fallback; added a search schema drift test
- projects skill / CLI docs
Part of #5227
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
The GitHub-token rule only matched classic tokens (ghp_/gho_/ghu_/ghs_/ghr_),
even though its comment claims to cover fine-grained tokens. Add coverage for
GitHub fine-grained PATs (github_pat_), Slack app-level (xapp-) / config (xoxe-),
Google API keys (AIza...), and Stripe live secret/restricted keys (sk_live_/rk_live_).
Publishable Stripe keys (pk_live_) are intentionally NOT redacted (public).
Adds regression tests for every new shape, including a positive test that
pk_live_ stays unredacted.
`161_attachment_task_id` and `162_attachment_task_id_index` (from #5164)
merged after prefixes 161/162/163 were already taken on main by #5277,
#5279, and #5296, leaving two migrations on each of 161 and 162. That trips
TestMigrationNumericPrefixesStayUniqueAfterLegacySet, so the backend job now
fails on every open PR. Renumber to the next free prefixes (164/165); the
file contents are unchanged.
Note for already-migrated databases: any DB that applied 161/162 has those
versions recorded in schema_migrations. After this rename, reconcile the
ledger (rename the recorded versions to 164/165) or reset the dev DB —
otherwise the migrator re-runs the renamed files and the ADD COLUMN fails
because the column already exists.
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Archiving a channel-bound chat session now severs its
channel_chat_session_binding in the same tx as the status flip. The web
send path already treats status='archived' as read-only, but the channel
engine (Feishu/Slack) resolves inbound traffic through the binding without
checking session status, so an archived-but-still-bound session kept
receiving agent replies and a stuck, uncleared unread badge. Dropping the
binding makes the next inbound message fork a fresh session; unarchive does
NOT recreate it (a later session may already own the channel).
The FAB unread badge counted status=all sessions without excluding
archived, so residual unread on an archived session (archive does not
mark-read) held the badge even though the session is hidden and read-only.
Extract countUnreadChatSessions() and exclude archived. This matches what
mobile already computes (active-only list), restoring count parity.
Tests: backend archive-clears-binding + unarchive-does-not-recreate;
frontend countUnreadChatSessions archived-exclusion cases.
MUL-4372
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* feat(chat): support images/files in agent chat replies (MUL-4287)
Agents can now attach images/files to their chat replies, matching how
comment attachments already work. The write-side gap was that the assistant
chat_message is synthesized server-side from the completion callback's text
output and never bound any attachments.
Backend:
- migration 150: nullable attachment.task_id (+ partial index), the transient
handle that ties an agent's in-run upload to the reply it produces.
- POST /api/upload-file accepts task_id: gated to the task's own agent, in
this workspace, on a chat task; tags the row with task_id + chat_session_id.
- CompleteTask (chat branch) binds the task's still-unclaimed attachments to
the assistant message via BindChatAttachmentsToMessage (rejects rows already
owned by an issue/comment/chat_message). An empty-output reply that produced
files still creates a message so the images have an owner. FailTask binds
nothing.
CLI:
- `multica attachment upload <path>` uploads a file for the current chat task
(task from MULTICA_TASK_ID or --task) and prints id / markdown_url / a
ready-to-paste markdown snippet.
Prompt:
- web/mobile chat prompt tells the agent how to attach a file to its reply.
Mobile:
- chat:done handler now always invalidates the messages list so attachments
(absent from the event payload) refetch; mirrors web's self-heal.
- chat bubbles render standalone attachment cards via the existing
CommentAttachmentList (dedup vs inline references), matching web.
Web/desktop needed no change — they already render message.attachments inline
and via AttachmentList, and self-heal on chat:done.
Tests: upload permission/isolation, bind-on-complete, empty-output+attachments,
FailTask no-bind, null task_id untouched, already-owned not stolen, CLI output
contract, mobile refetch-on-done.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): address review blockers on chat reply attachments (MUL-4287)
Two final-review blockers on PR #5164:
1. Mobile inline dedup only checked raw `url`, so an attachment referenced
inline via `markdown_url` (exactly what the CLI snippet emits) rendered
twice — once inline, once as a standalone card. Reuse the core
`contentReferencesAttachment` helper so dedup covers every real reference
form (stable /api/attachments/<id>/download path, url, download_url,
markdown_url), matching web's AttachmentList. Extracted the filter into a
pure `lib/attachment-dedup.ts` so it is unit-testable, and added a
regression test covering `content` containing `attachment.markdown_url`
(plus the other URL forms and same-identity sibling dedup).
2. CLI `attachment upload` emitted `![...]` image markdown for every file,
producing a broken-image snippet for non-images. Emit image markdown only
for image/* content types and a plain link otherwise, with a CLI contract
test for both.
Approved scope otherwise unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): renumber attachment_task_id migration 150 -> 157 after main merge (MUL-4287)
Merged latest main; main renumbered its migrations and now occupies 150-156,
so 150_attachment_task_id collided with 150_agent_task_coalesced_comments and
would fail TestMigrationNumericPrefixesStayUniqueAfterLegacySet. Renamed to the
next unique prefix (157). No content change; migrate up applies cleanly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): render agent-produced files as attachment cards, not raw links
The chat upload command handed the agent a bare `[name](url)` markdown
snippet. Pasted mid-sentence it renders as a plain text link (not a card),
and the referenced URL hides the auto-bound standalone attachment — so a
file the agent produced could end up showing as nothing.
Return the block-level `!file[name](url)` card syntax instead (images keep
`` inline), and markdown-escape the filename so names with `[`/`]`
don't truncate the label. The prompt and CLI help now state the file
auto-attaches below the reply and the snippet is optional, only for placement.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): soften message-list scroll fade (32px → 16px)
The 32px edge fade washed out full-bleed content (HTML / image previews)
at the list edges. Halve the fade distance so it barely grazes previews
while still hinting at more content above/below.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): renumber attachment_task_id migration 157 -> 158
main landed 157_agent_task_delivered_comments while this branch was open,
colliding on prefix 157 and failing TestMigrationNumericPrefixesStayUniqueAfterLegacySet.
Bump this PR's migration to the next free prefix (158). Rename only; the
migration body (nullable attachment.task_id + partial index) is unchanged.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): pin attachment upload to the token's task; build index concurrently
Two code-review findings on the chat-attachment path (MUL-4287):
- Isolation/privacy: POST /api/upload-file only checked the form task_id
belonged to the caller's agent, not that it matched the task-scoped token's
authoritative X-Task-ID. A run authorized for task A could tag an attachment
onto task B (another chat task of the same agent, possibly another user's
session), binding it into that reply on completion. Require the form task_id
to equal the server-set X-Task-ID; add a same-agent/other-task 403 regression.
- Migration: split the task_id lookup index into its own migration (159) built
with CREATE INDEX CONCURRENTLY (repo convention) — it cannot share a
multi-command file with the ADD COLUMN in 158.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(chat): enforce task-token source on attachment upload; drop transient task_id FK (MUL-4287)
Addresses the two remaining Preflight BLOCKERs on PR #5164.
Security (file.go): the task_id upload path compared the form task_id to
X-Task-ID but did not require X-Actor-Source=task_token. A normal JWT/mul_ PAT
leaves that header empty and the middleware does NOT strip a client-forged
X-Task-ID; resolveActor's fallback accepts a valid X-Agent-ID+X-Task-ID pair.
So a member who learned a task ID could forge both and inject an attachment
onto another chat task's assistant reply (cross-session/privacy leak). Now the
branch requires X-Actor-Source=task_token first (mirrors chat_history.go's
load-bearing boundary), then pins to the middleware-injected X-Task-ID. Tests
now go through the real task-token headers and add a forged-JWT-403 regression.
Migration (158): task_id is a transient binding handle (written once at upload
against an already-validated task, read only during that task's own
completion; durable owner is chat_message_id). There is no app-layer path that
hard-deletes agent_task_queue rows, and orphan uploads are already reaped by
attachment.chat_session_id's ON DELETE CASCADE — so an FK here would only add a
cascade dependency the app never relies on plus write overhead on the hot
attachment table. Drop the FK; task_id is now a plain UUID column. Added a
regression test that an unbound task-tagged upload is reaped on chat_session
delete. Index (159, CONCURRENTLY) unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(mobile): align !file card preprocess with web parser + CLI escaped labels (MUL-4287)
Howard final-review blocker: mobile's `!file[...]` preprocess didn't keep up
with the CLI's file-card output, so agent-produced non-image files rendered
nowhere on mobile.
- `FILE_LINE_RE` used `[^\]]+` for the label, so the CLI's escaped-bracket
output `!file[a\]b.pdf](url)` (cmd_attachment.go escapeMarkdownLabel) never
matched — the line stayed literal AND `standaloneAttachments` still hid the
fallback card (the URL is in `content`), so the file showed nowhere.
- Align the matcher with web's `packages/ui/markdown/file-cards.ts`: label
allows backslash-escaped metacharacters (ReDoS-safe class), and the URL is
restricted to the same allowlist (site-relative /uploads + /api/attachments/
<UUID>/download, plus absolute http(s)); disallowed schemes stay plain text.
- Unescape the label to the real filename, then re-escape only the chars that
would break a markdown LINK label (mobile emits `[📎 name](url)`, re-parsed
by the renderer — unlike web's HTML data-filename), so a raw `]` never
truncates the link text.
No dedup change: once the inline `!file` renders, hiding the standalone card is
correct. Added focused unit tests covering the escaped-label case, parens/
backslash unescape, the site-relative URL form, and disallowed-scheme rejection.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
* fix(comments): clarify 409 when a comment-triggered task posts a top-level comment (MUL-4417)
A comment-triggered task that posted a parentless top-level comment on its
own issue got a 409 whose message named the required parent id but never
said top-level comments are disallowed. Agents misread it as the issue being
locked and deleted good replies trying to reset. Keep the guard (agents must
reply under their trigger comment), but make the error self-explanatory and
document the constraint in the CLI --parent help. Add handler-level tests
pinning the rejected top-level case and the allowed reply-under-trigger case.
Refs GH #5266.
Co-authored-by: multica-agent <github@multica.ai>
* fix(comments): tighten 409 wording and assert the fix hint (MUL-4417)
Review nits on #5292: drop the inaccurate "while it is active" phrasing and
the redundancy from the 409 message so it matches the actual allow-set
(trigger or coalesced comment); collapse the incident narration to one line;
and assert the actionable parent_id (--parent) hint in the regression test so
the guidance can't be dropped silently.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J (Multica agent) <agent-j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Detect the bundled Codex CLI under the relocated ChatGPT.app on macOS, while keeping the legacy Codex.app path so older installs still resolve.
Closes#5205
Fix garbled `multica login -h` output: the --token line printed a raw NUL and a hijacked value placeholder. Change the NoOptDefVal sentinel to a printable value and drop backticks from the usage string. Add a regression test that renders the flag help through pflag's real path and asserts no control bytes plus the standard --token string[="prompt"] form.
Co-authored-by: YYClaw <197375+yyclaw@users.noreply.github.com>
Co-authored-by: J <j@multica.ai>
* fix(agents): let workspace members view runtime capabilities (MUL-4427)
The Agent capabilities redesign (#5277) reused the runtime local-skills
discovery endpoint on Agent detail surfaces, but the endpoint kept the
owner-only gate from the original import flow. Viewing an agent bound to
someone else's runtime returned 403, which the Skills / MCP tabs rendered
as 'try again when the runtime is online' even though the runtime was
online.
- Discovery (list + poll) now requires workspace membership only; the
payload is the deliberately redacted inventory built for this display.
- Import (init + poll) stays owner-only: it copies skill file contents
off the owner's machine.
- The failed notice no longer blames runtime connectivity, and a 403
(new client against an older backend) gets an honest permission
message.
* test(settings): stub Intl.supportedValuesOf in timezone picker tests
The preferences-tab timezone tests drove a ~600-option Base UI Select
through userEvent in jsdom; on slow CI runners the clear-preference case
exceeded even its extended 20s per-test timeout (PR #5281 frontend job).
Stub the IANA enumeration down to the curated COMMON_TIMEZONES fallback
— everything the tests pick lives there too — and drop the now-unneeded
20s overrides. File test time drops from ~35s to under 1s.
---------
Co-authored-by: Lambda <lambda@multica.ai>
* feat(github): fan out PR/check_suite webhooks to all bound workspaces (MUL-4343)
One GitHub App installation can be bound to several workspaces (#4855), but
pull_request and check_suite webhooks were still routed to a single workspace
via resolveWorkspaceForRepo (workspace.repos registry + oldest-binding
fallback). Every workspace but one silently received nothing for a shared repo,
with no way to opt in.
Deliver each repo event to every workspace bound to the installation. Repo
scope is whatever GitHub authorized the installation for; we no longer gate on
the workspace.repos registry (that list means "code the agent clones", not a
webhook subscription). Each workspace independently mirrors the PR, auto-links
against its own issue prefix + github toggles, records check suites against its
own PR mirror, and gets its own realtime broadcast.
- Extract mirrorPullRequestForWorkspace / recordCheckSuiteForWorkspace and loop
over all installation bindings instead of resolving one workspace.
- Remove the now-dead resolveWorkspaceForRepo / repoIdentityFromURL routing.
- Replace the registry-routing tests with PR + check_suite fan-out tests.
Co-authored-by: multica-agent <github@multica.ai>
* test(github): out-of-order fan-out test + drop dead query + document multi-workspace delivery (MUL-4343)
Addresses review feedback on the webhook fan-out change:
- Add TestWebhook_CheckSuite_OutOfOrderFansOutToBoundWorkspaces: a check_suite
that arrives before the PR must stash a pending row per bound workspace, and
each workspace must drain its own row when the PR fans out.
- Remove the now-unused ListWorkspacesWithRepos query (its only caller was the
deleted resolveWorkspaceForRepo) and regenerate sqlc; fix the stale
"picks the target workspace via the repos registry" comment on
ListGitHubInstallationsByInstallationID.
- Document multi-workspace event delivery in the GitHub integration docs
(en + zh), including an explicit self-host upgrade note: delivery is now
keyed on the GitHub connection, so a workspace that relied on the
code-repository list alone (without connecting GitHub) must connect the
installation to keep receiving events. This is an intentional, documented
behavior change — the PR description's earlier "single-binding behavior is
unchanged" claim was inaccurate and has been corrected.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Two daemon-side fixes to the persisted task transcript:
- Wait for the drain goroutine to flush the final message batch before every
terminal return (result, timeout, idle-watchdog, upstream cancel), so a
consumer reading the transcript at completion can't see a truncated tail.
Bounded (10s, then cancel + 12s) so a backend that never closes its message
channel cannot stall the terminal transition.
- Share the message seq counter across a resume-failure retry so the retry's
rows keep ascending seq values instead of restarting at 1 and interleaving
with the failed attempt's rows.
Server-initiated cancellation read timing is tracked separately in #5219.
Closes#5209
MUL-4369
* feat(chat): task-owned direct-chat input batches + explicit no_response outcome (MUL-4351)
Direct (web/mobile) chat no longer uses the last-assistant-row as an implicit
input cursor. Each direct send now owns an immutable input batch:
- agent_task_queue.chat_input_task_id makes a task the owner of the user
messages it must consume; the send path creates the task + user message +
attachment bindings + session touch in one transaction, and the daemon is
notified only after commit. A claim reads exactly that batch, so a message
that arrives mid-run belongs to the next task and is never absorbed.
- Auto-retry inherits the root input owner and is queued at a bumped priority,
created inside FailTask's transaction so no newer chat task can jump ahead.
- CompleteTask writes exactly one assistant outcome inside the completion
transaction: a normal message, or a visible no_response outcome (with a
non-empty English fallback) when the final output is empty. The write failing
rolls the completion back and the handler returns 5xx so the daemon retries;
the status CAS keeps it idempotent. chat:done carries message_kind.
- Web/desktop/mobile render no_response as a localized 'no text reply' state
(keeping the tool timeline), suppress Copy, keep it unread, and keep the
session-list preview non-blank.
- Legacy/channel tasks (chat_input_task_id NULL) keep the trailing-message
selector, so a rolling deploy never replays Slack/Lark history.
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): scope no_response to direct tasks; don't cancel task on input read error (MUL-4351)
Addresses PR review (Niko):
- writeChatCompletionOutcome only writes a no_response row for task-owned
direct tasks (chat_input_task_id set). Legacy/channel (Slack/Lark) tasks keep
the prior behavior: empty output writes no assistant row, so chat:done carries
empty content and the channel outbound silently drops it — the no_response
fallback body never reaches an external channel.
- The daemon claim distinguishes a genuine zero-input batch from a failed
input read: on ListChatInputMessages / ListChatMessages error it returns 5xx
and preserves the dispatched task for redelivery instead of cancelling a valid
task on a transient DB error.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
Testing surfaced two problems with the per-thread fan-out:
1. Authorization (blocker): CreateComment rejected any agent comment on the
task's issue whose parent_id != task.TriggerCommentID, so replies to the
OTHER coalesced threads were denied ('parent_id must equal this task's
trigger comment id') and those threads never got a reply. Allow the trigger
comment OR any comment the task coalesced (taskCoversReplyParent: trigger ∪
coalesced_comment_ids); every other parent on the issue is still rejected,
so this stays scoped to the set the run was actually given to answer.
2. Ordering: the agent answered the newest (triggering) comment first. The
fan-out instruction now numbers the targets and explicitly requires posting
OLDEST thread first, the newest/triggering thread last, so replies land in
chronological order. commentReplyThreads already lists oldest-first.
Tests: TestTaskCoversReplyParent (allow-list) and chronological-order
assertions in the cross-thread prompt test.
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): bound daemon.log size with rotation (MUL-4330)
The background daemon redirected its stdout/stderr into daemon.log opened
O_APPEND and never rotated it, so the file grew without limit until it was
too large to open. Every structured log line already flows through slog
(including agent subprocess stderr, forwarded via newLogWriter), so the
daemon's logger is effectively the sole author of the file's volume.
Route the foreground daemon's slog output — both the injected component
logger and the package-global slog default — through a size-based rotating
writer (lumberjack) that keeps the active daemon.log small (20MB default,
5 gzip-compressed backups, 30d), all env-overridable. Raw crash output
(Go runtime panics, pre-logger errors) now goes to a separate daemon.err.log
so the child's inherited fds never hold daemon.log open, which would block
rotation's rename on Windows.
The Desktop app spawns the daemon via this same launcher and its log tail
already handles size-shrink, so both CLI and Desktop are covered.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): address log-rotation review — foreground output, Windows handles, bounded err log (MUL-4330)
Resolves the blocking review items on the daemon.log rotation change:
1. Windows first-upgrade rotation: a foreground managed daemon now re-points
its own stdout/stderr to daemon.err.log at startup (SetStdHandle) before
building the rotator, releasing any daemon.log handle an older self-update
launcher inherited (Go opens files without FILE_SHARE_DELETE, which would
otherwise block rename-on-rotate). No-op on Unix, where an open fd never
blocks rename.
2. `daemon logs -f` vs rotation: Unix uses `tail -F` (reopen by name); Windows
opens the reader with FILE_SHARE_DELETE so it can't block the rotator's
rename, and reopens the file on size-shrink to follow across rotation.
3. Self-update handoff no longer briefly runs two rotators on one file: the old
process closes its rotator and moves remaining handoff logs (incl. the slog
default) to the crash sink before the successor starts.
4. daemon.err.log is now bounded: it rolls to a single ".1" backup once past
5MB at open time, so a crash loop can't move the growth problem to it. It is
also surfaced in the troubleshooting docs.
5. Explicit `--foreground` in a terminal keeps live stdout/stderr logging (a
documented debugging path); only detached/background children rotate into
daemon.log. Decided by whether stderr is a terminal.
Also: rotation env knobs now reject 0/negative (0 means 100MB / keep-all in
lumberjack), preventing an accidental unbounded config. Adds unit tests for
the err-log rolling and positive-int parsing; Windows/Linux(arm64) cross-builds
and `GOOS=windows go vet` pass.
Co-authored-by: multica-agent <github@multica.ai>
* docs: sync zh/ja/ko troubleshooting with daemon.log rotation + daemon.err.log (MUL-4330)
Co-authored-by: multica-agent <github@multica.ai>
* test(handler): bump the agent's own runtime version in quick-create parent test (MUL-4330)
TestQuickCreateIssueParentTrustBoundary bumped an arbitrary `LIMIT 1`
agent_runtime, but the handler version-checks agent.RuntimeID — the runtime
bound to the request's agent. In the shared handler test workspace, other
tests register additional runtimes, so the two diverge and the agent's real
runtime keeps the seed's empty cli_version, tripping the daemon-version gate
(422 daemon_version_unsupported) before the parent_issue_id assertions run.
Bump the runtime tied to the agent instead, making the setup deterministic.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): route coalesced replies per root thread (MUL-4348)
When a busy agent coalesces multiple @mentions into one run, the run used
a single --parent (the newest trigger), so questions raised in separate
root threads were answered in one merged comment while the other threads
were left unanswered.
Group the trigger + coalesced comments by root thread server-side in the
prompt builder (commentReplyThreads). When the run spans >=2 distinct
threads, emit a per-thread reply plan (BuildMultiThreadCommentReplyInstructions)
that instructs one reply per thread with the exact --parent, explicitly
overriding the general 'one comment per run' rule. Multiple @mentions from
the SAME thread collapse to a single group upstream, so same-thread
follow-ups keep the ordinary single --parent=trigger path and can never be
split into duplicate replies. Single-thread / non-coalesced runs are
unchanged.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): sync workflow-brief reply step with per-thread fan-out (MUL-4348)
Review of #5202 found the cross-thread fan-out was injected only into the
per-turn prompt (buildCommentPrompt), while the persistent workflow brief
(writeWorkflowComment step 7) still emitted the single --parent=trigger
cookbook for every comment task. A cross-thread run therefore got two
slightly conflicting reply instructions, so the fan-out guarantee rested on
prompt wording/precedence rather than structure.
Carry the computed thread targets on TaskContextForEnv.CommentReplyTargets
(populated from the same commentReplyThreads() the prompt uses, so the two
surfaces cannot drift). When >=2 targets, the workflow reply step now emits
the per-thread fan-out plan too; same-thread follow-ups collapse to a single
group upstream and keep the single-parent cookbook, so they still can never
be split. Also clarified the multi-thread cookbook to show a distinct file
per reply (reply-1.md / reply-2.md).
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): reply under the specific mentioning comment per thread (MUL-4348 review nit #1)
Non-trigger threads previously replied under the thread root, while the
trigger's thread replied under the trigger comment — asymmetric, and it put
the answer at the top of the thread instead of next to the actual question
when the mention was a mid-thread reply. Reply under the NEWEST triggering
comment in each thread instead (inputs are chronological, so last-write-wins
per thread), making every thread consistent and nesting each answer beside
its question.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
* fix(lark): tolerate binding token clock skew
Clamp binding-token expiry against the database clock while preserving the 15-minute TTL cap. Return the persisted expiry so binding cards reflect the value enforced by Postgres.
* docs(lark): correct stale table name in binding token TTL comments
Post-#124 the table is channel_binding_token (with the
channel_binding_token_ttl_cap CHECK); update the two comments in
types.go and binding_token_test.go that still named the pre-generalization
lark_binding_token table.
---------
Co-authored-by: Bohan-J <bohan.optimism@gmail.com>
Discover the Codex model list and per-model reasoning efforts from the installed CLI (codex debug models --bundled), with a verified static fallback for old/offline installs. Server gates token syntax; the daemon validates the exact (model, effort) pair.
Closes#5197
MUL-4354
Track actual claim-time delivery, support legacy daemons, and repair comment
batches across claim, retry, edit, and delete races.
MUL-4348
Co-authored-by: Eve <eve@multica-ai.local>
Co-authored-by: multica-agent <github@multica.ai>
