mirror of
https://github.com/multica-ai/multica.git
synced 2026-07-06 22:09:44 +02:00
feat/react-grab-dev-overlay
326 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Hzzzzzx
|
b4c9e4423c |
test: enable -race detector in Go test pipeline (WOR-61) (#4274)
* test: enable -race detector in Go test pipeline (WOR-61) Add the -race flag to all three Go test invocation sites so the existing concurrency regression harness (workdir_race_test.go for #3999, runtime_gone_test.go, runtime_profile_drift_test.go) actually exercises the race detector. The daemon package alone has 28+ goroutine launch points with no automated race coverage before this change. Sites updated: - Makefile:299 (make test, local) - .github/workflows/ci.yml:101 (CI backend job) - .github/workflows/release.yml:55 (release verify job) go test already runs a vet subset by default, so no separate -vet flag is added. No production code touched. Co-authored-by: multica-agent <github@multica.ai> * test(execenv): serialize runtimeGOOS-mutating test (WOR-61) TestInjectRuntimeConfigIssueMetadataCodexFormattingUnchanged called t.Parallel() while mutating the package-level runtimeGOOS to drive the windows/linux branches, racing with the other parallel tests that read runtimeGOOS in buildMetaSkillContent. The -race flag enabled in the prior commit surfaced it as 3 WARNING: DATA RACE reports and 11 "race detected" failures in CI (only the execenv package failed). Drop t.Parallel() and add the "// Not parallel: mutates the package-level runtimeGOOS." comment already used by the six sibling writer tests across execenv_test.go and reply_instructions_test.go. This is test-isolation only; no production code, no mutex/atomic, no signature change. Verified locally: go test -race -count=1 ./internal/daemon/execenv/ -> ok 2.276s go test -race -count=1 ./internal/daemon/... -> all 3 pkgs ok Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: hzz <331380069@qq.com> Co-authored-by: multica-agent <github@multica.ai> |
||
|
LinYushen
|
0d0edac32f |
feat(daemon): discover local skills from ~/.agents/skills (MUL-3333) (#4244)
* feat(daemon): discover local skills from ~/.agents/skills (MUL-3333)
Upgrade local skill discovery and import from a single provider root to an
ordered multi-root scan: the runtime's own skill directory (e.g.
~/.claude/skills) first, then the cross-tool universal root ~/.agents/skills.
- Rename localSkillRootForProvider -> localSkillRootsForProvider, returning
ordered roots [provider, universal] with a kind classifier.
- listRuntimeLocalSkills iterates the roots, gives each root its OWN visited
set (so a cross-root symlink alias is not collapsed), dedupes strictly by
Key with the provider root winning, and sorts once after the merge.
- loadRuntimeLocalSkillBundle walks the same priority order and only falls
through to the next root on os.IsNotExist; any other stat error is returned
so import never silently resolves a different same-key skill.
- Add a Root ("provider" | "universal") field to the local skill summary
(daemon + handler structs and the TS RuntimeLocalSkillSummary type) so the
UI can label a skill's origin without a future schema break.
Backward compatible: every skill visible today keeps its Key, SourcePath and
FileCount; the universal root only surfaces additional, non-conflicting skills.
Out of scope (follow-up issues): execution-time injection of ~/.agents/skills
into runtimes (e.g. Codex seedUserCodexSkills) and workspace-relative
.agents/skills discovery.
Tests cover universal-root discovery + import, provider-wins conflict
priority, both-roots merge, missing/both-missing roots, nested layouts,
IsNotExist fallback, the no-fallthrough-on-read-error guarantee, and the
per-root visited cross-root symlink alias. Docs updated in en/zh/ja/ko.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): fall through to next root when a same-key dir has no SKILL.md
loadRuntimeLocalSkillBundle previously only fell through to the next root on
os.IsNotExist for the skill DIRECTORY. A provider-root directory that shares a
skill's key but contains no SKILL.md (so listRuntimeLocalSkills descends past
it and surfaces the universal-root skill instead) made load stop on the
invalid provider dir and error — list and load disagreed, and the import the
user picked from the list could not be fetched.
Make the validity predicate match list: a root "has" the skill at a key only
when it is a directory containing a SKILL.md. A missing entry, a non-directory,
or a directory without a SKILL.md all mean "this root doesn't have it" and we
continue to the next root. Only a genuine non-IsNotExist stat error or an
unreadable existing SKILL.md (permission/IO) is returned, so we still never
silently substitute a different-content same-key skill from a lower-priority
root (Eve review #1, preserved by the existing read-error guard test).
Adds regression tests for the provider-dir-without-SKILL.md and provider-non-dir
fall-through cases.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
|
||
|
Bohan Jiang
|
e3a829f05e |
feat(daemon): disk-usage cross-root aggregation + migration FK/readiness fixes (MUL-3404) (#4290)
Bundles the MUL-3404 disk-usage feature with the two Preflight BLOCK fixes. - feat(daemon): `disk-usage --all-profiles` aggregates across every workspace root (default + each ~/.multica/profiles/* root, incl. the Desktop app's), with a per-root breakdown and combined grand total; the cross-root hint now also fires when the current root is non-empty. - fix(db): drop DB-level foreign keys/cascades from the new autopilot_subscriber and comment.source_task_id migrations (resolved in the app layer — autopilot delete now removes subscribers in a transaction); the autopilot_subscriber down-migration relabels reason='autopilot' to 'manual' instead of deleting. - fix(server): readiness verifies every required migration is applied, not just the lexically-last one, so an out-of-order migration can't be masked. MUL-3404. |
||
|
Bohan Jiang
|
e7daf876bd |
fix(daemon): reclaim autopilot_run workdir on terminal status (MUL-3403) (#4287)
* fix(daemon): reclaim autopilot_run workdir on terminal status (MUL-3403) Autopilot run workdirs are never reused — there is no PriorWorkDir path that hands a later run the same directory, so every run gets a fresh one. Yet GC waited the full GCTTL (default 24h) before reclaiming a terminal run's dir. Combined with one fresh dir per run, high-frequency autopilots piled up hundreds of stale dirs (508 dirs / 22GB in the field report). Drop the TTL gate so a terminal run (completed/failed/skipped/ issue_created) is reclaimed immediately, mirroring gcDecisionQuickCreate. Existing safety constraints are untouched: active-env-root short-circuit, 404 -> orphanByMTime, non-404 error -> skip, and the local_directory override all still apply. Co-authored-by: multica-agent <github@multica.ai> * docs(daemon): fix GetAutopilotRunGCCheck comment — completed_at is not a TTL anchor The endpoint comment still claimed the daemon uses completed_at as the TTL anchor for terminal runs. GC now decides purely on terminal status (the workdir is never reused, so a terminal run is reclaimed on sight); completed_at is returned for the API contract / diagnostics only. Addresses the review nit on #4287. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
1279f22d1c |
MUL-3325: add background task safety brief (#4257)
* fix(daemon): add background task safety brief Co-authored-by: multica-agent <github@multica.ai> * fix(agent): force Claude background tools foreground Co-authored-by: multica-agent <github@multica.ai> * fix(agent): narrow Claude async launch detection Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
LinYushen
|
77ac17ef49 |
Make custom runtimes appear immediately (#4234)
* Make custom runtimes appear immediately * Scope daemon profile refresh by authorized runtimes * Relay runtime profile refresh hints * Localize runtime profile close label |
||
|
Multica Eve
|
6bb8cac9ea |
MUL-3332: daemon picks up new custom runtime profiles without restart (#4225)
* MUL-3332: daemon picks up new custom runtime profiles without restart The workspaceSyncLoop's already-tracked branch refreshed only settings and repos via refreshWorkspaceRepos and never re-fetched runtime profiles, so a custom runtime profile created via the web UI / CLI did not become a registered runtime row until the daemon restarted (or a runtimeGone recovery happened to fire). Detect server-side profile drift each sync tick by hashing the workspace's profile list with profileSetSignature(), caching the digest on workspaceState.profileSetSig, and triggering reregisterWorkspaceAfterRuntimeGone when the live signature differs from the cached one. Steady-state syncs cost exactly one extra GetRuntimeProfiles round trip; only real drift fans out to a Register call. The fetch is best-effort: a 404 / network blip preserves the cached signature so a transient failure cannot loop the daemon into spurious re-registrations. Tests in runtime_profile_drift_test.go cover digest stability under reorder, field-by-field drift detection (add / enable-flip / command_name / protocol_family / fixed_args / visibility), the no-drift hot path (no re-register), the new-profile drift path (single re-register + index update + sig converges), and best-effort fetch error handling. Co-authored-by: multica-agent <github@multica.ai> * MUL-3332: split orphan recovery from profile drift; converge to zero Addresses two blocking review concerns on #4225 (raised by GPT-Boy): 1. Profile drift must not kill running tasks on existing runtimes. The first cut reused reregisterWorkspaceAfterRuntimeGone, which after re-register calls /recover-orphans for every returned runtime ID. The server's RecoverOrphanedTasksForRuntime hard-fails every dispatched/running/waiting_local_directory row on that runtime — the correct response when a runtime row was actually deleted server-side, but a catastrophic false positive on profile drift: a built-in runtime still actively executing the user's tasks would have its work killed just because the user added an unrelated sibling custom profile. Fix: extract applyRegisterResponseInPlace as the shared in-place state converger between the two paths, and stop calling /recover-orphans from the drift path. reregisterWorkspaceAfterRuntimeGone keeps the /recover-orphans call because in that path the rows really were gone. 2. Disabling the only profile on a custom-only daemon must converge. The first cut hit registerRuntimesForWorkspace's len(runtimes)==0 guard and bailed out, so the disabled profile's runtime stayed alive in local tracking and on the server (still polling, still heartbeating, still online for the full 150 s stale-heartbeat window). Fix: introduce ErrNoRuntimesToRegister as a sentinel, have registerRuntimesForWorkspace return profileSig even on the empty case (so the drift path can cache the converged-empty signature), and have the drift refresh's error handler take a convergeWorkspaceRuntimesToZero branch that clears local runtimeIDs / runtimeIndex entries and Deregisters the orphaned IDs so the server marks them offline immediately. The same Deregister step also runs on partial drift (a built-in survives, the disabled profile's runtime drops) so the user sees the dropped runtime go offline within the next sync tick instead of after the 150 s sweep. Tests: - TestRefreshWorkspaceRuntimeProfiles_DriftWithRunningRuntimeSkipsOrphanRecovery (mixed built-in + custom, add another profile, asserts zero /recover-orphans calls). - TestRefreshWorkspaceRuntimeProfiles_DisableConvergesCustomOnlyDaemon (custom-only daemon, disable only profile, asserts local state cleared, signature converges to empty digest, Deregister called with the orphaned ID, no recover-orphans, follow-up tick is no-op). - TestRefreshWorkspaceRuntimeProfiles_DisableOneOfManyDeregistersDroppedID (partial drift: only the dropped ID is Deregistered, surviving built-in is left alone and not orphan-recovered). - TestRefreshWorkspaceRuntimeProfiles_NewProfileTriggersReregister extended to also assert no /recover-orphans calls. - TestRegisterRuntimes_SkipsProfileNotOnPath strengthened to assert the ErrNoRuntimesToRegister sentinel and that profileSig is still returned on the empty path. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
LinYushen
|
1f5cb51d4e |
MUL-3284: Web UI + CLI (custom runtime PR3) (#4177)
* MUL-3284 PR3 (CLI): multica runtime profile subcommands + local path override
- cmd_runtime_profile.go: `multica runtime profile` group — list / create /
update / delete against /api/workspaces/{id}/runtime-profiles, plus set-path
/ unset-path for a per-machine command override. protocol-family validated
client-side via agent.IsSupportedType / agent.SupportedTypes; visibility
validated; update only sends changed flags (protocol_family immutable);
delete surfaces the server 409 body when agents are still bound.
- internal/cli/config.go: ProfileCommandOverrides map[string]string on
CLIConfig (omitempty), through the existing marshal/unmarshal so set/unset
round-trips without dropping other fields.
- internal/daemon: Config.ProfileCommandOverrides, loaded from CLIConfig;
appendProfileRuntimes now prefers an override path when set AND executable,
else falls back to exec.LookPath(command_name), else skips+logs as before.
- Tests: cmd_runtime_profile_test.go (registration, create/update/delete incl.
bad-family + missing-flag + 409 surfacing, set/unset path round-trip,
relative-path rejection, config preservation); cli/config round-trip;
daemon prefers-override / falls-back-when-not-executable.
Verified: go build ./..., go vet, go test ./cmd/multica/... ./internal/daemon/...
./internal/cli/... all pass.
Co-authored-by: multica-agent <github@multica.ai>
* MUL-3284 PR3 (Web): custom runtime profiles in the Runtime page
Single-list integration — no new page, no tabs/grouping. Built-in protocol
families and custom profiles render mixed in one catalog, each row badged
built-in vs custom (progressive disclosure).
- packages/core: RUNTIME_PROFILE_PROTOCOL_FAMILIES (single-source 13-family
whitelist, matches server agent.SupportedTypes + migration 120 CHECK) and
RuntimeProtocolFamily / RuntimeProfile types; api client
list/get/create/update/deleteRuntimeProfile against
/api/workspaces/{id}/runtime-profiles; runtimes/profiles.ts query +
mutation hooks and a 409 "agents still bound" conflict parser.
- packages/views/runtimes: runtime-profile-catalog (mixed built-in+custom
rows), runtime-profiles-dialog (header "+ Add runtime" → step 1 pick
protocol family → step 2 display_name/command_name/description; edit form
for custom; admin-gated), delete-runtime-profile-dialog (confirm + graceful
409), runtimes-page / runtime-list integration.
- i18n: new strings added to all four locales (en, zh-Hans, ja, ko).
- a11y: dialogs are focus-trapped, Esc-closable, labelled; full
create/edit/delete flow is keyboard + screen-reader operable.
Iron rule honored: no generic per-agent args UI here (those stay on Agent
config). fixed_args is not surfaced as a general args field.
Verified: turbo typecheck + lint + test pass for @multica/core, @multica/views,
@multica/web; the @multica/web production build succeeds.
Co-authored-by: multica-agent <github@multica.ai>
* MUL-3284 PR3: hide fixed_args from Web + CLI (not yet wired to launch)
Review fix. fixed_args was surfaced as a working feature, but the daemon does
not splice it into the agent launch command — exposing it promised admins a
no-op. Per the call, remove it from every user-facing surface while keeping the
underlying column/struct "carried but not exposed".
- Web (runtime-profiles-dialog.tsx + runtime-profile-catalog.ts): drop the
detail row, the create body field, the update patch field, and the form
textarea; remove the parseFixedArgs/fixedArgsToText helpers and the
fixedArgs form value. Left a NOTE pointing at the daemon TODO.
- i18n: removed the fixed_args strings from all four locales (en/zh-Hans/ja/ko).
- CLI (cmd_runtime_profile.go): removed the `--fixed-arg` flag from create and
update and stopped sending `fixed_args`; updated the "no fields" message.
Test now asserts the CLI never sends fixed_args.
Untouched (the carried-but-not-exposed layer): the runtime_profile.fixed_args
column, the server handler's accept/return, and the daemon's RuntimeProfile
field — all keep the existing TODO(MUL-3284) to wire it into the launch path
(with a test proving args reach the backend) before any UI/CLI re-exposes it.
Verified: turbo typecheck+lint+test pass for @multica/core and @multica/views;
go build/vet/test pass for ./cmd/multica/.
Co-authored-by: multica-agent <github@multica.ai>
* MUL-3284 PR3: stop exposing profile visibility=private (server forces workspace)
Double-review (Eve) caught a fixed_args-shaped hole: visibility=private was a
user-facing toggle (Web form + detail + CLI), but the three server read paths
(ListRuntimeProfiles, daemon ListEnabledRuntimeProfilesForWorkspace,
DaemonRegister) never enforce it — so a "private" profile's name/command would
leak to other members and could be registered by other machines' daemons
(lateral data leak). Same "don't paint a pie" fix as fixed_args: hide the
control everywhere and force the stored value.
- Server (runtime_profile.go): drop `visibility` from the create + update
request structs; CreateRuntimeProfile always stores 'workspace'
(runtimeProfileDefaultVisibility); UpdateRuntimeProfile no longer accepts it;
removed validRuntimeProfileVisibility. The column + response field stay
(always 'workspace') as the carried-but-not-exposed layer.
- Web (runtime-profiles-dialog.tsx): removed the visibility form fieldset,
the VisibilityOption component, the detail row, the visibility state, and the
create/update submit fields.
- i18n: removed the profile visibility strings from all four locales
(profiles.detail.visibility, profiles.visibility.*, profiles.form.visibility_*).
Top-level runtime/agent visibility strings are untouched.
- CLI (cmd_runtime_profile.go): removed `--visibility` from create/update and
the VISIBILITY list column; removed validateVisibility; stopped sending the
field.
- Tests: new TestCreateRuntimeProfile_ForcesWorkspaceVisibility (POST
visibility:"private" -> response and DB row are 'workspace'); CLI create test
now asserts visibility is never sent.
Follow-up MUL-3308 tracks implementing real creator-visibility (and wiring
fixed_args to the launch path); TODOs left in server/Web/CLI point to it.
Verified: turbo typecheck+lint+test pass (@multica/core, @multica/views);
go build/vet pass; go test ./cmd/multica/... and the full ./internal/handler/
suite pass against a migrated Postgres 17.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
|
||
|
LinYushen
|
52e76e7b23 |
MUL-3284: server API + daemon (custom runtime PR2) (#4149)
* MUL-3284: add runtime_profile schema (custom runtime PR1) Schema-only foundation for custom runtimes. Additive migration 120: - New workspace-level `runtime_profile` table: the shared, team-visible definition of a custom runtime (e.g. an in-house Codex wrapper). protocol_family is CHECK-constrained to the exact backend list in agent.New() (server/pkg/agent/agent.go). The only args column is `fixed_args` (args every agent on the runtime must inherit); there is deliberately no generic per-agent args field — those stay on agent.custom_args. - `agent_runtime.profile_id` (nullable, FK -> runtime_profile ON DELETE CASCADE): NULL = built-in runtime, non-NULL = a registered instance of a custom profile. - Partial unique index agent_runtime_workspace_daemon_profile_key on (workspace_id, daemon_id, profile_id) WHERE profile_id IS NOT NULL. The legacy UNIQUE (workspace_id, daemon_id, provider) constraint is left INTACT so the existing registration upsert (ON CONFLICT (workspace_id, daemon_id, provider) in runtime.sql) keeps resolving its arbiter and the server stays green. Converting that key to a partial (WHERE profile_id IS NULL) index and making the upsert profile-aware is PR2's registration work, not this migration. Verified up + down against Postgres 17: full `migrate up` applies 120; schema shows the table, column, partial index and intact legacy constraint; functional checks pass (partial index blocks dup (ws,daemon,profile), allows same profile on another daemon; CHECK and display_name uniqueness reject bad input; legacy ON CONFLICT still resolves; profile delete cascades to instances); down/up round-trip is clean. Co-authored-by: multica-agent <github@multica.ai> * MUL-3284: drop DB FKs/cascade from runtime_profile migration (review fix) Per review (house rule: no new database foreign keys / cascades; relational integrity lives in the application layer): - runtime_profile.workspace_id: drop REFERENCES workspace ON DELETE CASCADE -> plain UUID NOT NULL. - runtime_profile.created_by: drop REFERENCES "user" ON DELETE SET NULL -> plain UUID. - agent_runtime.profile_id: drop REFERENCES runtime_profile ON DELETE CASCADE -> plain UUID. CHECK constraints, UNIQUE (workspace_id, display_name), the workspace index, and the partial unique index agent_runtime_workspace_daemon_profile_key are unchanged. The legacy UNIQUE (workspace_id, daemon_id, provider) constraint remains untouched. Behavioral consequence: the database no longer auto-removes a profile's agent_runtime instance rows on profile delete. That cleanup moves into PR2's profile-delete path. Up-migration comments document this; down-migration comment no longer references FKs/cascade. Re-verified on Postgres 17: migrate up applies 120; no FK constraints exist on the new columns; partial index still blocks dup (ws,daemon,profile_id); CHECK and display_name uniqueness still reject bad input; deleting a profile now leaves the runtime row orphaned (proving cascade is gone); down/up round-trip clean with the legacy constraint intact. Co-authored-by: multica-agent <github@multica.ai> * MUL-3284 PR2 (server): runtime_profile CRUD + profile-aware registration Server/DB half of the custom-runtime feature. - Migration 121: convert the legacy UNIQUE (workspace_id, daemon_id, provider) constraint on agent_runtime into a partial unique index scoped to built-in rows (WHERE profile_id IS NULL). With 120's partial index on profile_id this lets one daemon host the built-in provider AND custom profiles of the same protocol family without collision. - Queries: runtime_profile CRUD; ListEnabledRuntimeProfilesForWorkspace (daemon-facing); CountAgentsByProfile + DeleteAgentRuntimesByProfile for the app-layer cascade; profile-aware UpsertAgentRuntimeWithProfile; the built-in UpsertAgentRuntime ON CONFLICT now spells out WHERE profile_id IS NULL so it targets the right partial index. sqlc regenerated. - agent.SupportedTypes / IsSupportedType: single-source protocol_family whitelist, in lockstep with agent.New and the migration 120 CHECK. - Handlers + routes: runtime_profile CRUD (member-read, admin-write) with protocol_family whitelist validation, display_name uniqueness (409), and fixed_args validation (no generic per-agent args — iron rule); a daemon-token endpoint GET /api/daemon/workspaces/{id}/runtime-profiles; DeleteRuntimeProfile does the app-layer cascade (delete instance rows then profile, in one tx) and refuses (409) while active agents are bound. - DaemonRegister accepts an optional per-runtime profile_id: validates the profile belongs to the workspace and is enabled, registers via the profile-aware upsert, and skips legacy hostname merge for custom rows. AgentRuntimeResponse now carries profile_id. Verified on Postgres 17: migrate up through 121; built-in + custom codex coexist on one daemon; both upsert arbiters are idempotent; delete-by-profile cascade removes only the custom instance; migrate down reverses 121 then 120 and replays clean. go build ./... and go vet pass; handler test package compiles. Daemon-side wiring (fetch profiles, PATH-resolve command_name, register with profile_id, exec uses command_name) lands in a follow-up commit on this branch. Co-authored-by: multica-agent <github@multica.ai> * MUL-3284 PR2 (daemon): pull profiles, PATH-resolve, register, exec command Daemon-side half of custom runtime profiles, against the server contract on this branch. - client.go: GetRuntimeProfiles(workspaceID) -> GET /api/daemon/workspaces/{id}/runtime-profiles (mirrors GetWorkspaceRepos); RuntimeProfile / RuntimeProfilesResponse types. - types.go: Runtime gains profile_id (parsed from the register response so runtimeIndex carries it). - daemon.go: * appendProfileRuntimes — called inside registerRuntimesForWorkspace before the empty-runtimes guard. Best-effort fetch (older server 404s are logged and swallowed; never fails registration). Per enabled profile: resolve command_name via PATH (exec.LookPath, behind a `lookPath` test hook), skip+log when absent, best-effort version probe, record the resolved absolute path keyed by profile_id, and append a registration entry {name, type=protocol_family, version, status:online, profile_id}. A custom-only host (no built-in agents) still registers. * profileCommandPaths map (guarded by d.mu) + recordProfileCommandPath / customCommandPathForRuntime helpers. * runTask: looks up the claimed task's RuntimeID -> profile command path and overrides the executable path, synthesizing an AgentEntry so a custom runtime runs even when the host has no built-in agent of the same provider. provider (=protocol_family) is unchanged so agent.New still selects the right backend. - Tests: GetRuntimeProfiles request shape; profile runtime appended + path recorded (custom-only host); profile skipped when command not on PATH; profiles-fetch-404 is best-effort; customCommandPathForRuntime bookkeeping. - agent: lockstep test pinning SupportedTypes to agent.New and the migration 120 protocol_family CHECK. Iron rule honored: profile carries no generic per-agent args. fixed_args are parsed and carried but intentionally NOT wired into the launch command yet (optional/best-effort; explicit TODO(MUL-3284) in appendProfileRuntimes). Verified: go build ./... clean; go vet ./internal/daemon/... clean; go test ./internal/daemon/... pass (existing + 5 new); full go test ./internal/handler/ suite passes against a migrated Postgres 17; agent lockstep test passes. Co-authored-by: multica-agent <github@multica.ai> * MUL-3284 PR2: profile delete runs full archived-agent cascade (fix 500) Review fix. DeleteRuntimeProfile previously guarded only on ACTIVE agents, but agent.runtime_id is ON DELETE RESTRICT — a profile whose runtimes had only ARCHIVED agents passed the guard, then DeleteAgentRuntimesByProfile hit the FK and the handler 500'd. Now it mirrors the mature runtime-delete cascade (DeleteAgentRuntime): in one transaction it enumerates the profile's runtime rows, refuses (409) any with active agents or active squads led by archived agents, then for each runtime pauses autopilots pinned to its archived agents, drops archived squads led by them, and hard-deletes the archived agents before removing the runtime rows and the profile. No code path can now fall through to a raw FK error. - queries: ListAgentRuntimeIDsByProfile (sqlc regen). Reuses the existing per-runtime teardown queries (CountActiveSquadsWithArchivedLeadersByRuntime, ListArchivedAgentIDsByRuntime, PauseAutopilotsByAgentAssignees, DeleteSquadsByArchivedAgentsOnRuntime, DeleteArchivedAgentsByRuntime). - tests: TestDeleteRuntimeProfile_ArchivedAgentCascade (archived-only profile deletes cleanly: 204, runtime + archived agent + profile gone) and TestDeleteRuntimeProfile_ActiveAgentBlocks (active agent → 409, survives). Verified against Postgres 17: both new tests pass; full handler suite, daemon tests, and agent lockstep test pass; go vet clean. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
18a58e80c0 |
MUL-3316: fix(execenv): switch agent prompt to --content-file to prevent heredoc flag swallowing (#4182) (#4191)
* fix(execenv): switch agent prompt to --content-file to prevent heredoc flag swallowing (#4182) The Linux/macOS reply template recommended --content-stdin with a quoted HEREDOC. That pattern is safe for the trivial single-flag comment-add case that BuildCommentReplyInstructions emits, but as soon as a model wraps extra flags around the heredoc on multica issue create / update — assignee, project — the bash heredoc/flag boundary is fragile in two ways the model cannot see: - A 'BODY \\' terminator with a trailing token is not recognised as the heredoc end, so flag lines after it are swallowed into the description (OXY-78: residual flag text leaked into the description, command exit 0). - A clean terminator turns the trailing '--assignee ...' line into a separate failing shell statement, while the create itself already exited 0 with no assignee (OXY-76: assignee silently dropped, no residual text). In both cases the CLI never receives the swallowed flags, the API request omits the fields, and the daemon has no visibility. The created issue lands with assignee_id: null / project_id: null. This commit: * Switches the Linux/macOS branch of BuildCommentReplyInstructions to --content-file with a 3-step recipe (write file, post, rm) so the body never reaches the shell and all flags live on one shell-token line. There is no heredoc boundary for flags to leak across. * Adds a parallel cleanup step (Remove-Item) to the Windows branch so the cross-platform template is one shape. * Rewrites the runtime_config.go ## Comment Formatting non-Windows section to mandate --content-file and explicitly ban --content-stdin HEREDOC for agent-authored comments, citing #4182. * Reorders the Available Commands menu lines for issue create / update / comment add to put --content-file / --description-file ahead of the stdin variant and add a per-line note pointing at #4182. * Updates and renames the affected tests (TestBuildCommentReplyInstructionsCodexLinux, TestBuildCommentReplyInstructionsNonCodexLinux, TestInjectRuntimeConfigLinuxCommentFormattingEmphasizesFile, TestInjectRuntimeConfigIssueMetadataCodexFormattingUnchanged) so the new file-first contract is pinned and the old HEREDOC mandate is in the banned-strings lists. This converges Linux/macOS with the long-standing Windows file-only path, so the cross-platform guidance is now one shape. It also strictly improves on the previous MUL-2904 guardrail by eliminating shell exposure of the body entirely (no body ever reaches the shell, so backtick / $() / $VAR substitution cannot corrupt it). Closes GitHub multica-ai/multica#4182. No CLI or backend changes — --content-file / --description-file already exist. Co-authored-by: multica-agent <github@multica.ai> * docs(prompt): correct stale BuildPrompt comment to file-first (#4182) --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> Co-authored-by: CC-Girl <cc-girl@multica.ai> |
||
|
Bohan Jiang
|
f9c193e06b |
fix: fail closed on agent task auth tokens (#4142)
Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
YOMXXX
|
34d4cd3a28 |
feat(openclaw): support connecting to existing OpenClaw gateway (#3260) [MUL-3158] (#3664)
* feat(openclaw): support connecting to existing OpenClaw gateway (#3260) When the daemon host is a lightweight dev machine or CI coordinator, the heavy agent work (LLM inference, code execution, tool use) often belongs on a more powerful remote server already running an OpenClaw gateway. Multica historically hard-coded `openclaw agent --local`, forcing every turn to execute in-process on the daemon host. This change adds an opt-in gateway routing mode controlled per-agent via `runtime_config`: { "mode": "gateway", "gateway": { "host": "...", "port": 18789, "token": "...", "tls": false } } - Backend: ExecOptions gains OpenclawMode + OpenclawGateway; buildOpenclawArgs drops `--local` when mode == "gateway". Per-task openclaw-config.json wrapper pins gateway.{host,port,auth.{mode,token},tls} so users do not need to edit the daemon host's `~/.openclaw/openclaw.json` to point at a different endpoint. - Daemon: AgentData carries the raw runtime_config; decoding is fail-soft (malformed JSON falls back to local mode rather than blocking dispatch). - API: gateway.token is masked to "***" on every GET; PATCH replays the sentinel back, and the update handler restores the persisted token so the round-trip never destroys the secret. Defense-in-depth masking on WS broadcasts, plus String/MarshalJSON masking on the in-memory struct to block stray `%+v` / json.Marshal leaks. - UI: openclaw-only "Routing" tab on the agent detail page with mode selector + structured endpoint form. Token uses a "saved — submit a new value to rotate" UX and matching backend preserve hook. Empty `runtime_config` keeps the historical embedded behaviour, so existing agents are unaffected. * fix(openclaw): address #3664 review — drop dead gateway field, gate pin on mode Per Bohan-J's review: - Remove the dead ExecOptions.OpenclawGateway field (+ its String/MarshalJSON and the daemon.go construction block). It carried the plaintext bearer token but was never read — buildOpenclawArgs only consumes OpenclawMode and the live gateway path runs through execenv.OpenclawGatewayPin — so this narrows the secret's footprint. - Gate the gateway pin on mode=="gateway" in decodeOpenclawRuntimeConfig: a {"mode":"local","gateway":{...,"token"}} payload no longer writes the token into the 0o600 per-task wrapper that --local makes openclaw ignore. - Warn on an unrecognized non-empty mode (e.g. "gatway") instead of silently falling back to local. - Run preserveMaskedGatewayToken in CreateAgent too, so a literal "***" at create time can't persist as a real bearer token. - Document the gateway host:port trust boundary (SSRF note for shared daemon hosts). Adds regression tests for the local-mode pin drop and the unknown-mode warning. |
||
|
Bohan Jiang
|
f415099c4a |
MUL-3263: support managed MCP config for Cursor (#4081)
* feat: support managed MCP config for Cursor Co-authored-by: multica-agent <github@multica.ai> * fix: address Cursor MCP review feedback Co-authored-by: multica-agent <github@multica.ai> * docs: include Cursor in skills MCP support Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
c8ab73d38d |
MUL-3244: Bind quick-create attachments to created issues (#4062)
* fix: bind quick-create attachments to created issues Co-authored-by: multica-agent <github@multica.ai> * test: use real image markdown in quick-create attachment test Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Liu Guanzhong
|
4594c776e1 |
feat(agent): add CodeBuddy as first-class CLI backend (#3186)
* feat(agent): add codebuddyBackend struct and buildCodebuddyArgs Introduces the codebuddy agent backend skeleton with args builder that mirrors claudeBackend's protocol flags (stream-json, bypass permissions, blocked args filtering) for the codebuddy CLI fork. * feat(agent): implement codebuddyBackend.Execute with stream-json parsing * feat(agent): wire codebuddy into New() factory and launchHeaders * feat(agent): add codebuddy dynamic model discovery from --help * feat(agent): add codebuddy thinking/effort discovery and providerThinkingEnums * feat(daemon): add codebuddy CLI probe, env vars, and args support * fix(agent): use len(models)==0 for default model instead of loop index * fix(agent): increase codebuddy --help timeout to 35s for slow CLI startup * fix(agent): address codebuddy PR review feedback - Wire codebuddy into execenv: reuse claude's CLAUDE.md, .claude/skills, and ~/.claude/skills paths since CodeBuddy is a Claude Code fork - Replace hardcoded 20-min timeout with runContext for zero-timeout = no-deadline semantics matching all other backends - Restore runContext regression tests lost in rebase merge - Mirror claude.go execution model: concurrent stdin write to prevent pipe deadlock, sync.Once for stdin closure, keep stdin open for control_request auto-approval mid-run - Add control_request handling with auto-approve behavior - Add RequestID/Request fields to codebuddySDKMessage - Add codebuddy to metrics knownRuntimeProviders - Add codebuddy to provider-logo.tsx (reuses ClaudeLogo) - Consolidate --help discovery: shared codebuddyHelpOutput cache eliminates duplicate cold-start invocations --------- Co-authored-by: krislliu <krislliu@tencent.com> |
||
|
Multica Eve
|
9439a85aa6 |
MUL-3242: fix daemon workdir provisioning race
Fixes GitHub issue #3999 by moving the daemon StartTask transition behind workdir provisioning and extending the active env-root guard through completion metadata writes. |
||
|
Bohan Jiang
|
8151f60c6c |
fix(daemon): drop stale resume session when workdir is not reused (#4027)
CLI backends key their session stores to the cwd (Claude Code looks sessions up under ~/.claude/projects/<encoded-cwd>/), so a prior session id can only resolve when the task runs in the exact workdir the session was recorded against. When the prior workdir no longer exists (GC'd after the issue went done, daemon reinstall, manual cleanup), execenv.Reuse falls back to a fresh Prepare but the stale session id was still passed to the backend: claude exited within a second and the run failed before doing any work — permanently, because the failed run records no session_id and the next claim serves the same stale pointer again. Gate ResumeSessionID on the workdir actually being reused, and correct PriorSessionResumed so the runtime brief uses the cold-path wording when the session is dropped. Fixes multica-ai/multica#3854 (MUL-3221) Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
ac75c97797 |
fix(desktop): disable auto-start/stop toggles for a daemon the app can't control (WSL2) (#3940)
* feat(daemon): report OS in /health response The desktop app reads daemon liveness over HTTP but starts/stops it via the native CLI, which acts on the host process namespace. On Windows with the daemon in WSL2, /health is reachable via localhost forwarding yet the daemon's process is unreachable — so the app needs a signal to tell a daemon it manages from one it merely sees. Expose runtime.GOOS as `os` so the desktop can compare it against its own host OS. MUL-3154, #3916 Co-authored-by: multica-agent <github@multica.ai> * fix(desktop): disable auto-start/stop for an unmanageable daemon When the daemon runs in an environment the app can't drive — e.g. Linux in WSL2 behind a Windows desktop, reachable only via localhost forwarding — the Auto-start/Auto-stop toggles silently did nothing: the lifecycle CLI acts on the host process namespace and never reaches the daemon's PID. Detect it by comparing the daemon's reported OS (new /health `os` field) against the host OS, and only when a daemon is actually running. When they differ: disable both toggles with an explanatory note, skip the version-match restart on auto-start, and skip the no-op stop on quit. Fails safe — a missing `os` (older daemon) or a matching OS keeps the toggles live, so native Mac/Windows/Linux daemons are unaffected. MUL-3154, #3916 Co-authored-by: multica-agent <github@multica.ai> * fix(desktop): centralize externally-managed guard at the lifecycle boundary Review follow-up. The first cut only disabled the Settings toggles, but the same unmanageable daemon (WSL2 etc.) could still be Stop/Restart-ed from the Runtime card and from automatic lifecycle entries (logout, user switch, reauth, first-workspace restart) — each of which would shell out to a native CLI that can't reach the daemon's process. Move the guard into the main-process lifecycle functions so every entry point is covered by construction: stopDaemon() and restartDaemon() no-op for an externally-managed daemon, and ensureRunningDaemonVersionMatches() treats it as up-to-date (no misleading restart). The per-branch checks in the auto-start handler and before-quit are removed — the boundary now covers them. The Runtime card hides Stop/Restart and shows a 'Managed outside the app' hint, mirroring the Settings tab. Adds a component test for the card's two states. MUL-3154, #3916 Co-authored-by: multica-agent <github@multica.ai> * fix(desktop): preflight the lifecycle guard against live /health Review follow-up. The guard read a cached lastExternallyManaged, which only fetchHealth() updates — but not every lifecycle entry polls before calling stop/restart. syncToken()'s user-switch branch calls restartDaemon() directly after its own fetchHealthAtPort(), without refreshing the cache; on a fresh launch / account switch (no poll yet) the cache is still the initial false, so restartDaemon() would shell out to the native CLI and hit the very WSL/native PID-namespace problem this PR avoids. Make stopDaemon()/restartDaemon() preflight against a live /health read each call instead of trusting the poll cache. The decision is extracted to a pure daemonLifecycleUnreachable(readDaemonOS, hostOS) so a unit test can prove the *live* value (not a cache) drives it. lastExternallyManaged is removed — the UI already reads the per-status externallyManaged field, so it had no other consumer. MUL-3154, #3916 Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Chenyu-24601
|
8b94764c47 |
feat(daemon): configurable OpenClaw binary path / state dir via CLIConfig.Backends (MUL-3157)
Summary: - Add CLI config schema for OpenClaw backend binary path and state dir overrides. - Apply those overrides during daemon LoadConfig using the existing env-var based probe/spawn path. - Cover backward compatibility, precedence, partial overrides, and fail-soft config loading. Verification: - go test ./internal/cli ./internal/daemon - go vet ./internal/cli ./internal/daemon - GitHub CI passed |
||
|
Bohan Jiang
|
24b162cdbc |
feat(daemon): surface the real task initiator to the agent runtime (MUL-2645) (#3899)
* feat(daemon): surface the real task initiator to the agent runtime (MUL-2645)
In a multi-person workspace the agent runtime only ever saw the runtime
OWNER identity: the brief's `## Requesting User` is sourced from
runtime.OwnerID and the task-scoped token is owner-bound, so every
requester (whoever commented, @mentioned, or chatted) appeared to the
agent as the owner. Agents that route by initiator for permission,
privacy, or audit all misjudged.
Resolve the real task initiator at claim time and surface it distinctly
from the owner:
- comment / mention trigger -> triggering comment's author (member or agent)
- chat task -> chat session creator (sessions are creator-only)
- on-assign / autopilot / quick-create -> no attributable initiator (omitted)
Adds initiator_{type,id,name,email} to the claim response, the daemon
Task, and TaskContextForEnv, rendered into the brief as a new
`## Task Initiator` section. The section documents the privacy boundary:
the agent's credentials stay owner-scoped, so this is an attested
identity for the agent's own routing/privacy logic, not act-as. No DB
migration — both paths are derivable from existing rows.
Tests: brief rendering (member/agent/omit/sanitize) + email guard unit
tests, and claim-handler tests for the comment and chat paths.
Co-authored-by: multica-agent <github@multica.ai>
* fix(chat): store real sender as task initiator, not chat_session creator (MUL-2645)
Review fix (Niko, PR #3899). v1 resolved the chat task initiator from
chat_session.creator_id at claim time. That is correct for web chat and
Lark p2p (creator == sender), but WRONG for Lark group chats: the group
session creator is deliberately the installer (stable identity across
member churn), not the message sender. So in a Lark group, every member
who triggered the agent showed up in the brief as the installer/owner —
the exact bug this issue is about, still live at that entry point.
Capture the real sender at enqueue time instead of deriving it from the
session creator at claim time:
- migration 117: agent_task_queue.initiator_user_id (FK user, ON DELETE
SET NULL); NULL for non-chat and pre-migration rows.
- EnqueueChatTask now takes an explicit initiatorUserID. Web chat passes
the authenticated request user; the Lark dispatcher threads the inbound
sender (binding.MulticaUserID) through scheduleRun -> flushChatRun. The
debouncer keeps the latest scheduled flush per session, so in a multi-
sender silence window the LATEST sender wins (documented + tested).
- claim handler resolves the initiator from task.initiator_user_id and
drops the creator_id fallback entirely.
The Lark group session creator stays the installer (unchanged) — only the
task initiator is corrected, keeping the two concepts cleanly separate.
Tests: dispatcher group regression (initiator = sender, not installer),
latest-sender-wins, p2p initiator assertion; the chat claim handler test
now sets creator != initiator and asserts the stored sender wins.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
|
||
|
liujianqiang-niu
|
5be7d1bc17 |
MUL-3136 fix(openclaw): parse config path from last non-empty line of CLI output
Fix OpenClaw config discovery when `openclaw config file` prints Doctor warning UI before the actual config path. The daemon now uses the last non-empty stdout line as the path while preserving the existing tilde expansion, absolute-path validation, stat checks, and fail-closed behavior. Tests: go test ./internal/daemon/execenv |
||
|
Bohan Jiang
|
1ddf89a8f2 |
feat(daemon): enable Antigravity (agy) per-agent model selection (MUL-3125) (#3894)
* feat(daemon): wire agy --model and model discovery for Antigravity agy 1.0.6 added a --model flag and an `agy models` catalog command, which were the #1 blocker in the earlier agy-backend review (MUL-3125). The antigravity backend already shipped but deliberately dropped opts.Model because agy 1.0.1 had no way to select a model. - buildAntigravityArgs now passes --model <display name> when opts.Model is set; the value is the exact `agy models` display string (spaces + parens), passed as a single exec arg so no shell quoting is needed. - Block --model in custom_args so it can't override the managed value. - ListModels("antigravity") enumerates via `agy models` (no static fallback: agy silently no-ops on unrecognised models, so a stale guess would turn a typo into a successful empty run). - ModelSelectionSupported now returns true for every built-in provider; the hook stays for any future model-less runtime. - Daemon probe reads MULTICA_ANTIGRAVITY_MODEL for the daemon-wide default. Co-authored-by: multica-agent <github@multica.ai> * docs(providers): mark Antigravity model selection as supported Antigravity gained --model in agy 1.0.6 (MUL-3125). Update the provider matrix + prose (en/zh/ja/ko) from "managed internally / no --model" to dynamic discovery via `agy models`, and refresh the now-stale picker comments. Flag the display-string (not slug) shape and agy's silent no-op on unrecognised values. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): reject unknown Antigravity model at spawn (MUL-3125) agy exits 0 with empty output on an unrecognised --model, so a stale/typo'd value would surface as a 'completed' but empty task. Validate opts.Model against the `agy models` catalog in Execute before spawning: a non-empty model the CLI does not advertise fails fast with an actionable error listing the real choices. opts.Model is the single funnel for agent.model and the MULTICA_ANTIGRAVITY_MODEL default, so this one check covers every source (UI free-text, API, persisted value, env) — addressing Elon's review that a UI-only guard is bypassable. Validation is fail-OPEN: if the catalog can't be discovered we pass the value through and let agy resolve it, so a discovery hiccup never blocks a run. Pure antigravityModelError() is unit-tested (valid / unknown / near-miss / empty-model / empty-catalog); verified live against real agy 1.0.6. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
0xMomo
|
ef75f80d9d |
fix(daemon): clean stale agent branches during repo gc (MUL-2550) (#3039)
* fix(daemon): 清理陈旧 agent 分支 Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): 串行化 bare repo gc Co-authored-by: multica-agent <github@multica.ai> * test(daemon): adapt health repo cache mock Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): gate gc maintenance on stale-branch deletion Address review feedback on the bare-repo GC change: - Only run `reflog expire` + `git gc --prune=30.days` when we actually deleted a stale agent branch this cycle. Previously the heavy step ran every GC tick on every cached repo even when there was nothing to reclaim, turning a stale-ref cleanup into a periodic full-repo maintenance job under the per-repo lock. - Split git command timeouts: `gc --prune=30.days` now gets a 10-minute budget instead of sharing the 30s ceiling that was scoped for the original `worktree prune` call. Light commands stay at 30s. - Drop the redundant `gc --auto` — `gc --prune=30.days` already performs the maintenance `gc --auto` would have triggered. - Narrow the agent-namespace ref query from `refs/heads/agent` to `refs/heads/agent/` so the pattern can't surface a literal `agent` branch outside the daemon namespace. Tests: - New TestPruneWorktree_IgnoresLiteralAgentBranch pins the trailing- slash narrowing. - New TestPruneWorktree_SkipsMaintenanceWhenNothingDeleted uses an unreachable, backdated loose object as a sentinel to verify that `gc --prune` runs only when a stale agent branch was reaped. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: 0xNini Code Dev <agent@multica.local> Co-authored-by: multica-agent <github@multica.ai> Co-authored-by: 0xNini <0xnini@iMac-Pro.local> Co-authored-by: J <j@multica.ai> |
||
|
Bohan Jiang
|
3808049361 |
fix(codex): set semantic thread names (#3887)
Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
NanamiKite
|
2e34016f1f |
fix(daemon): interrupt local agent on server-side terminal task states (#3878)
shouldInterruptAgent now treats every terminal task status (completed/failed/cancelled, via isAgentTaskTerminal) plus a 404 task-not-found as an interruption signal, so the daemon stops a local agent once the backend has finalized the task — e.g. the runtime offline sweeper flipping running -> failed during a disconnect/reconnect. Previously only `cancelled`/404 interrupted, so the agent ran to completion and its CompleteTask call failed against a non-running row, wasting compute and adding log noise. Closes #3877 |
||
|
HMYDK
|
4190de3d64 |
fix(skills): quote description values in built-in SKILL.md YAML frontmatter (#3852)
Built-in SKILL.md description values contained unquoted ': ' sequences, which strict YAML parsers (e.g. Codex) reject — silently dropping the skill at load. - Quote all eight built-in skill descriptions. - ensureSkillFrontmatter() re-synthesizes frontmatter that has a name but fails YAML validation, so malformed imports are repaired instead of dropped. - Unify frontmatter delimiter parsing into a single frontmatterParts helper. - Add strict-YAML regression tests over the built-in skills, plus unit tests for the recovery branch and delimiter variants. Closes #3851. |
||
|
Wes
|
5e7587ad07 | Optimize daemon runtime wakeups (#3859) | ||
|
Xinmin Zeng
|
270d177475 |
fix: broken "Add a computer" command on Multica Cloud + two CLI amplifiers (MUL-3087) (#3817)
* fix(server): recognize official cloud by frontend host in daemon setup config The 'Add a computer' dialog builds its command from /api/config's daemon_server_url/daemon_app_url, falling back to 'multica setup' when both are empty. The official cloud is meant to omit them, but the omission only fired when MULTICA_PUBLIC_URL=https://api.multica.ai. When that env is unset the server URL defaults to the frontend origin and the old guard (which required serverURL host == api.multica.ai) didn't match, so the dialog emitted 'multica setup self-host --server-url https://multica.ai' — pointing the daemon backend at the frontend (no /health, no WebSocket proxy). Identify the official cloud by its frontend host alone (multica.ai / app.multica.ai) so a missing or misconfigured MULTICA_PUBLIC_URL can no longer leak the broken self-host command. Regression from #3474. * fix(cli): probe before persisting self-host config to preserve auth on failure setup self-host wrote a fresh CLIConfig{ServerURL, AppURL} (a full overwrite that drops the saved token) and only then probed the server, returning early on failure. A failed probe therefore logged the user out and left them unconnected, with no recovery in the same command. Probe first via persistSelfHostConfigIfReachable: an unreachable server leaves the existing config — and its token — untouched (failed setup = no-op). The prober is injected so both branches are unit-tested. * fix(daemon): serve health before preflight so daemon start readiness is accurate The CLI's 'daemon start' polls the health endpoint for 15s expecting status=running, but the daemon only began serving health after preflightAuth, whose initial workspace sync detects every configured agent's version by exec'ing it (~20s cold with 8 agents). Health served too late, so a perfectly healthy daemon printed 'may not have started successfully'. Start the health server right after resolveAuth (which still fails fast on a missing token) and before the slow preflight, so readiness reflects the daemon core being up rather than agent-version detection finishing. * fix(daemon): gate /health readiness so daemon start can't report a false start Serving health before preflightAuth fixed the false-negative (a healthy daemon printed "may not have started"), but health still returned status:"running" unconditionally — before preflight (PAT renew + workspace sync + runtime registration) had completed. `daemon start` and the desktop treat "running" as ready, so a slow or *failing* preflight could be misreported as a started daemon: setup prints "connected", then the process exits or hangs in agent-version detection with no runtime registered. That is harder to diagnose than the original false-negative. Split liveness from readiness: bind/serve the health port early (so callers see a live "starting" daemon instead of connection-refused), but report status:"starting" until d.ready is set after preflight, then "running". - daemon.go: add d.ready (atomic.Bool); set it true after the background loops launch, before pollLoop. - health.go: healthHandler reports "starting" until ready, else "running". - cmd_daemon.go: `daemon start` waits for "running" with a deadline raised to 45s (covers cold-start agent detection) and a clearer "still starting" message; new daemonAlive() helper treats both "running" and "starting" as a live daemon, so the already-running guard, restart, and stop act on a starting daemon and don't double-spawn or race its listener; `daemon status` shows "starting" distinctly. Older CLIs/desktop that only know "running" safely treat "starting" as not-ready (status != "running"), so no boundary break. Tests: health reports starting-then-running; daemonAlive truth table. Co-authored-by: multica-agent <github@multica.ai> * fix(desktop): handle daemon "starting" health status in lifecycle The daemon now reports /health status:"starting" until preflight completes (liveness/readiness split). That made "starting" a new external contract of /health, but the Desktop daemon-manager only knew "running", so the readiness fix would have moved the CLI's false-negative into a Desktop start regression: - `daemon start` now blocks up to 45s waiting for readiness, but the Desktop spawned it via execFile({ timeout: 20_000 }). On a cold start (the ~20s agent detection this PR targets) Electron killed the CLI supervisor at 20s and reported a start failure, even though the detached daemon child kept booting — the UI flashed "stopped" then "running". Raise the timeout to 60s (must exceed the CLI's 45s startupTimeout). - The Desktop treated only raw status === "running" as a live daemon, so a daemon that was still "starting" (booting on its own or started via the CLI) showed as "stopped", and startDaemon() would spawn a second one — which the new CLI rejects as "already running", surfacing as a start error. Add daemonStatusAlive() (shared, pure, unit-tested) mirroring the Go daemonAlive() and use it for liveness: fetchHealth() surfaces a daemon-reported "starting" as state "starting" regardless of our own currentState; startDaemon()'s already-running guard and the restart-on-user-switch guard treat "starting" as an existing daemon. version-decision stays gated on "running" (readiness, not liveness) — unchanged. Verified: desktop typecheck, eslint, full vitest suite (193 tests) all pass. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
3708fb0f07 |
fix(daemon): inactivity-based agent run timeout, no wall-clock guillotine (MUL-3064)
Active long-running sessions are no longer killed by a fixed wall-clock deadline. Liveness is delegated to the idle watchdog (MULTICA_AGENT_IDLE_WATCHDOG, default 30m) with a larger in-flight-tool budget (MULTICA_AGENT_TOOL_WATCHDOG, default 2h). MULTICA_AGENT_TIMEOUT is an opt-in absolute cap (default 0 = no cap). The server-side 2.5h sweeper is unchanged as a coarse backstop. Fixes #3745. |
||
|
Multica Eve
|
63b847ee48 |
Honor agent identity in assignment workflow (#3802)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Naiyuan Qing
|
b9334dd59f |
fix: anchor comment triggers to thread roots (#3746)
Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
d6a556bdbf |
fix(execenv): refresh skills in place on reuse instead of accumulating duplicate dirs (#3716)
Re-dispatching the same agent on the same issue reuses the persistent workdir via execenv.Reuse(), where the standard-provider skill refresh re-wrote skills without clearing the prior dispatch's output, so allocateCollisionFreeSkillDir dodged Multica's own directories into issue-review-multica-N. On reuse, reclaim the platform-owned managed skill directories the prior manifest recorded (removeReusedManagedSkillDirs) and roll back the remaining sidecar files (CleanupSidecars) before refreshing, so each skill lands at its canonical slug every dispatch. Mirrors the Codex hydrateCodexSkills wipe; scoped to reuse, which never runs for local_directory tasks. Fixes #3684 (MUL-2963). |
||
|
Naiyuan Qing
|
1544e3b68a |
feat(skills): built-in agent skills (WIP) MUL-2759 (#3456)
* feat(skills): introduce built-in agent skills (WIP) Inject platform-authored, version-bundled skills into every agent on top of its workspace-bound skills, so agents learn how to operate Multica correctly without users needing to know the internals or agents needing to read source. Mechanism: skills are embedded into the server binary and appended to the agent payload at task-claim time (handler/daemon.go), reusing the existing SkillData wire + daemon-side writeSkillFiles. The daemon needs no changes, and because it travels over an existing wire field, older daemons pick the skills up the moment the server ships. First skill: multica-mentioning — how to build a working @mention (look up the UUID, match type to id source, know what each mention type triggers). WIP: injection mechanism + first skill only; more skills to follow in dependency order (skill -> agent -> squad). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(skills): make multica-mentioning the standard template + add eval Add the contract-skill frontmatter the other built-in skills will copy: user-invocable:false (it triggers from context, not as a slash command) and allowed-tools fencing it to the multica CLI it teaches. These keys survive to agent machines untouched (ensureSkillFrontmatter only ever adds a missing name). Add a Go eval in builtin_skills_test.go (a _test.go so it never ships to agent machines via the skill-files walk): - Enforces the template invariants on every built-in skill, present and future: multica- prefix, name+description present, description within 1024 chars, body within the 500-line L2 budget, no eval file leaking into the shipped payload. - Couples the mentioning skill's documented contract to the real util.ParseMentions: its Incorrect examples must parse to nothing (a name where a UUID belongs fails silently) and its Correct example must fire. A drift in the mention regex now breaks CI instead of silently turning the skill into a lie agents act on. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * feat(skills): add working-on-issues built-in skill Co-authored-by: multica-agent <github@multica.ai> * feat(skills): verify linked PRs in issue workflow skill Co-authored-by: multica-agent <github@multica.ai> * feat(skills): add skill import and discovery built-ins Co-authored-by: multica-agent <github@multica.ai> * feat(skills): add skill authoring built-in Co-authored-by: multica-agent <github@multica.ai> * docs(skills): align builtin skill workflows Co-authored-by: multica-agent <github@multica.ai> * docs(skills): use structured skill search Co-authored-by: multica-agent <github@multica.ai> * fix(skills): make built-in skill bundle launch-ready Co-authored-by: multica-agent <github@multica.ai> * fix(skills): align built-ins with additive skill binding Co-authored-by: multica-agent <github@multica.ai> * feat(skills): add creating agents built-in skill Co-authored-by: multica-agent <github@multica.ai> * Add built-in squads skill Co-authored-by: multica-agent <github@multica.ai> * refactor(skills): rewrite built-in skills as source-traced contracts Rewrite the built-in agent skills to the inbuilt-skill-authoring standard: state source-traced product facts with the source-code link logic as the core, not prescriptive how-to coaching. - creating-agents: drop the Decision-flow / Do-don't-consequences methodology; replace with field/behavior contracts (validation, persisted shape, daemon claim-time consumption, env gating, skill binding). - skill-discovery: stop teaching repo/github_stars as selection signals — searchClawHubSkills never populates them (always null); rank by install_count + source/url + description. Add file:line citations. - mentioning: drop the unbacked "member mention sends a notification" claim (no such path in the comment handler); state that only agent/squad mentions enqueue work. Tighten the parser-failure wording. - working-on-issues: refresh citations drifted by the main merge; describe the PR response `state` enum accurately; trim status coaching. - skill-importing: correct response type to SkillWithFilesResponse; document the reserved SKILL.md supporting-file rule; add line-accurate citations. - squads: correct the "leader cannot be archived" overstatement (not rejected at create/update; fails closed later at routing/dispatch); refresh source-map attributions and test list. Each skill now ships references/<skill>-source-map.md as its evidence layer (line-accurate citations live there, not pinned in the test, so a future main merge cannot rot them into stale lies). builtin_skills_test.go: replace coaching/line-number pins with drift-resistant contract anchors, forbid the coaching phrasing, and require every skill to ship its source-map. The ParseMentions behavior coupling is preserved. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * docs(skills): close field-role and citation gaps found in review Independent review of the rewritten built-in skills surfaced two real gaps and some citation drift; this fixes them. - creating-agents: add the three missing field rows (visibility, max_concurrent_tasks, mcp_config) to the field-contract table — mcp_config is runtime-consumed (TaskAgentData, daemon.go), visibility is access-control (default private), max_concurrent_tasks is a scheduler cap (default 6). Mark custom_args/runtime_config JSON validation as CLI-side (the server marshals as-is). Correct the CLI body-builder note (description/instructions use a non-empty check, the rest use Changed). Source-map: fix the env query name (UpdateAgentCustomEnv), the conformance test name, and add the new field defaults + the McpConfig runtime-payload line. - mentioning: the @squad mention private gate is canAccessPrivateAgent, not canEnqueueSquadLeader (that wrapper is the assignment/child-done path). - working-on-issues: cite notifyParentOfChildDone at its func def (:51), not the doc comment (:15). - skill-importing: config.origin is set only when the source supplied an origin — note it may be absent; cite createSkillWithFiles at its definition (skill_create.go:72), not the call site. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * Add built-in skills for autopilots runtimes and resources Co-authored-by: multica-agent <github@multica.ai> * feat(runtime): list skill descriptions in the brief Skills index The brief's `## Skills` section emitted bare skill names only, discarding the one-line description that SkillContextForEnv already carries. For Claude-family providers the frontmatter description is loaded natively; for providers without native skill discovery (hermes/default) the brief's list is the only signal they ever see, so a bare name gave them nothing to decide when to load a skill. Emit `name — description` when a description is present, falling back to the bare name when it is empty. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * refactor(skills): drop CLI-only rule from working-on-issues The "Platform data goes through the CLI" section duplicated the runtime brief's `## Important: Always Use the multica CLI` section verbatim (and the attachment-via-CLI note duplicated the brief's `## Attachments`). The CLI-only rule is universal and must be known before any skill loads, so the brief is its single source of truth; the skill copy was pure redundancy and a drift risk. Remove it and the matching intro clause. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * refactor(skills): remove discovery guidance from built-ins * docs(skills): remove stale skill-necessity records The per-skill necessity records had drifted to 3 of 8 shipped skills plus a record for `multica-skill-authoring`, which is not a shipped built-in skill. Per-skill "why it exists / when to use it" already lives co-located with each skill (frontmatter `description` + `references/<skill>-source-map.md`) where it cannot drift from the skill, and the doc's methodology duplicated the workspace's inbuilt-skill-authoring protocol. Remove the file rather than keep a parallel listing that every new skill has to remember to update. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * feat(runtime): add source-authority escape hatch to the brief The brief already tells agents to run `--help` for command discovery, but nothing stated the trust precedence when a skill, the brief, or a doc seems to contradict actual behavior. Add one line to the Available Commands escape-hatch note: trust the live CLI (`--help`/`--output json`) and the checked-out source over source-traced prose that can lag the code, and verify on any conflict or confusion. Kept in the always-on brief (universal, needed before any skill loads) rather than duplicated into each skill; per-skill source-map pointers remain the specific layer. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * fix(runtime): scope the source-authority escape hatch to the CLI The previous version told agents the "checked-out source is the deeper authority" for verifying behavior. That over-claims: the repos in a task's brief come from GetWorkspaceRepos + project github_repo resources (per-workspace config, see daemon.registerTaskRepos), not the Multica platform source. A generic agent's checked-out source is its own app, not Multica's code, so it cannot verify a Multica skill/brief claim against it. The only universally available authority for Multica behavior is the live CLI (`--help` / `--output json` / observed command behavior). Re-scope the line accordingly and state plainly that the platform's source is not in the workdir. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Co-authored-by: multica-agent <github@multica.ai> * revert(runtime): drop the source-authority escape-hatch line Reverts the brief addition from |
||
|
Multica Eve
|
10afd1af1b |
feat(server): introduce pkg/taskfailure classifier and switch in-flight failure_reason writes (MUL-2946) (#3693)
Lift MUL-1949's offline backfill failure_reason taxonomy into a shared in-flight classifier so the agent_task_queue.failure_reason column is written with refined values (provider_auth_or_access, context_overflow, provider_capacity_or_rate_limit, …) at write time rather than waiting on SQL backfill to re-classify after the fact. PR1 of the Grafana board plan in MUL-2328 — the upcoming PR2 reuses pkg/taskfailure.AllReasons() to pre-warm the Prometheus failure_reason label set. * server/pkg/taskfailure: new package with the canonical 21 Reason constants (7 platform-side + 14 agent_error.* sub-reasons), AllReasons() returning a defensive copy, IsAgentError() prefix check, and Classify(rawError) Reason mirroring the SQL CASE rules from MUL-1949 (db-boy's analysis). 100% statement coverage. * server/internal/daemon/daemon.go: route the 'agent_error' coarse fallback paths (StartTask error, runTask early-return error, CompleteTask permanent rejection, reportTaskResult default branch) and the executeAndDrain default error case (chained after classifyPoisonedError) through taskfailure.Classify so blocked / timeout / unknown-status results all carry a refined reason on the wire. * server/internal/service/task.go: FailTask classifies errMsg when the daemon-supplied failureReason is empty, eliminating the legacy COALESCE(.., 'agent_error') landing. * server/internal/daemon/poisoned.go: alias FailureReasonIterationLimit and FailureReasonAPIInvalidRequest to the canonical taskfailure constants. agent_fallback_message and codex_semantic_inactivity are pre-existing operational reasons not in the canonical 21 — kept as literals for now and revisited in a follow-up PR. Backfill SQL from MUL-1949 stays as the authoritative offline source of truth; this PR keeps the in-flight classifier in lock-step with the SQL CASE expression so historical and future rows share the same taxonomy. No behavior change for the platform-side reasons (queued_expired, runtime_offline, runtime_recovery, timeout, etc.) which already align with the canonical set. Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
44feb3d06d |
fix(skill): canonicalize reserved SKILL.md path check across daemon + API (#3660)
A skill_file row whose path is the skill's own SKILL.md (persisted by older builds or direct create/update API calls) collides with the primary content the daemon writes itself, failing task prep with errPathPreExists on every non-codex local runtime (#3489). #3526 guarded this with strings.EqualFold(path, "SKILL.md") at the daemon write site and the three API ingress points, but the stored path is not canonicalized: "./SKILL.md" or "sub/../SKILL.md" slip past the exact-match guard while filepath.Join still resolves them onto the same SKILL.md, so prep can still break. Extract one canonical helper, skill.IsReservedContentPath, that cleans the path before the case-insensitive compare, and use it at all four sites (execenv writeSkillFiles, skill create, update, single-file upsert). Add a daemon-side regression test for writeSkillFiles ignoring a bundled SKILL.md (exact + "./" spellings) — the load-bearing fix previously had only API-layer coverage — plus a unit test for the helper. Existing poisoned rows are intentionally left in place (skipped at prep) per the decision on MUL-2928. MUL-2928 Follow-up to #3526; supersedes #3560. Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
MSandro
|
996eb07dc5 |
fix(daemon): skip duplicate SKILL.md in supporting files to prevent task prep failures (#3526)
Fixes #3489 MUL-2928 |
||
|
Bohan Jiang
|
888186b183 |
fix(daemon): make comment-posting guardrail provider-agnostic (MUL-2904) (#3654)
* fix(daemon): make comment-posting guardrail provider-agnostic (MUL-2904) Agents inlining a backtick-wrapped token into `multica issue comment add --content "..."` had the shell run it as a command substitution, silently deleting the token; the stored comment never matched the model's intent, so it retried forever — spamming OKK-497 with duplicate comments. The corruption is shell-driven, not provider-driven, so extend the "never inline --content; use --content-file / quoted-HEREDOC --content-stdin" rule from Codex-only to ALL providers: - BuildCommentReplyInstructions: collapse the Linux/macOS non-Codex inline branch into the unified quoted-HEREDOC stdin template. - buildMetaSkillContent: rename "Codex-Specific Comment Formatting" -> "Comment Formatting" and emit it for every provider; strengthen the Available Commands entry and the assignment step-6 examples to steer away from inline --content. - Windows behavior unchanged (file-only; avoids PowerShell ASCII drop). Tests: flip the non-Codex Linux reply test into a MUL-2904 regression, broaden the stdin-emphasis test across providers, and pin the provider-agnostic guardrail. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): keep Windows assignment brief file-only (address review) Review catch on #3654: the previous commit added platform-agnostic prose recommending "--content-file or --content-stdin" in the Available Commands entry and the assignment-triggered step-6 example. The assignment path has no BuildCommentReplyInstructions OS override, so on Windows an agent following step 6 literally would pipe its final comment through PowerShell and drop non-ASCII bytes (#2198 / #2236 / #2376) — contradicting this PR's own Windows file-only rule in the ## Comment Formatting section. Make the platform-agnostic surfaces defer to the OS-aware ## Comment Formatting section (the single source of truth) instead of naming stdin. The flag synopsis still lists all three modes. Add TestInjectRuntimeConfigWindowsAssignmentBriefStaysFileOnly: a Windows assignment-triggered brief must not contain any prescriptive "... or --content-stdin" recommendation. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Qi Yijiazhen
|
91c1e51411 |
feat(editor): add / slash-command palette for invoking agent skills (#3159)
* feat(editor): add / slash-command palette for invoking agent skills Adds a `/` trigger in the chat box that opens a popover listing the active agent's skills. Selecting an item inserts a `[/label](slash://skill/<id>)` token; the daemon extracts those IDs in `buildChatPrompt` and emits an "Explicitly selected skills:" block using the canonical names from the agent's skill registry — labels are display-only and never trusted. Built on Tiptap's `Mention` extension so the suggestion lifecycle, keyboard routing, and IME handling mirror the existing `@` mention UX. Item list is sourced from the React Query workspace cache (no per-keystroke fetch). Gated behind a new `enableSlashCommands` prop so only `chat-input` opts in; other `ContentEditor` consumers (issue editor, comments) are unaffected. Read-only markdown surfaces render the token as a `.slash-command` pill via a custom link renderer + sanitize-schema/url-transform allowlists. Closes #3108 * fix(i18n): add slash_command editor copy for ko/ja The PR added slash_command popover empty-state keys to en + zh-Hans only; locales/parity.test.ts requires every locale to cover every EN key, so ko and ja failed CI. Add the two keys (no_skills_configured, no_results) matching existing skill terminology (스킬 / スキル). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Naiyuan Qing <145280634+NevilleQingNY@users.noreply.github.com> Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Bohan Jiang
|
0f9d9d1494 |
fix(skills): align Go/TS frontmatter coercion for non-scalar values (#3614)
The Go SKILL.md frontmatter parser unmarshalled into a {Name,Description}
string struct, so a non-scalar value (a list/map written where a scalar
belongs) made the whole decode fail and dropped even a valid sibling
`name`. The TS parser instead kept the name and JSON-encoded the value,
so the file-viewer (TS) and the import path (Go) could disagree about
the same SKILL.md.
Decode into a generic map and coerce per key on the Go side, mirroring
the TS coercion (scalars -> literal form, sequences/mappings -> JSON), so
both sides produce identical results and a structured value never
discards a sibling key. Rename ParseFrontmatter -> ParseSkillFrontmatter
to remove the cross-language name clash with the TS parseFrontmatter
(which returns {frontmatter, body}), and drop the unused TS
parseSkillFrontmatter export.
Add parity tests for sequence/mapping values plus name-only,
description-only, leading-blank-line and triple-dash-in-body edge cases
on both sides.
Follow-up to #3543 / MUL-2842.
Co-authored-by: J <j@multica.ai>
Co-authored-by: multica-agent <github@multica.ai>
|
||
|
YOMXXX
|
801c201d4c |
fix(skills): parse multi-line YAML frontmatter in SKILL.md (#3495) (#3543)
Three independent line-based frontmatter parsers only handled single-line `description: value`, so a YAML block scalar (`description: |`) collapsed to the literal "|" and the rest of the description was dropped before it ever reached the database. Replace all three with real YAML decoders that understand block scalars, folded scalars and quoted values: - server/internal/skill: shared ParseFrontmatter via gopkg.in/yaml.v3, used by both the handler import path and daemon local-skill discovery - packages/core/skills: shared parseFrontmatter via the yaml package - file-viewer renders multi-line frontmatter values (whitespace-pre-wrap) Both parsers fall back to empty values on malformed YAML, preserving the previous non-fatal behaviour. |
||
|
Naiyuan Qing
|
3c8645e546 |
feat(cli): add squad member set-role (#3583)
Co-authored-by: multica-agent <github@multica.ai> |
||
|
Naiyuan Qing
|
4ae4722ef0 |
fix(comments): preserve direct parent on replies (#3579)
Co-authored-by: multica-agent <github@multica.ai> |
||
|
Naiyuan Qing
|
973a43923f |
fix(comments): revert since-delta to issue-wide, steer to parent thread first (#3535)
#3509/#3523 scoped the comment-trigger since-delta count to the triggering
thread, so an agent resuming a busy issue only saw "+N in this thread" and
lost visibility of new comments in other threads. Revert the count to
issue-wide (every thread), keeping the trigger-comment + agent-own
exclusions, and reshape the warm-path hint to:
- report the issue-wide new-comment volume,
- steer the agent to read the triggering (parent) thread FIRST
(`--thread <trigger> --since`, or `--tail 30` for full context),
- demote the issue-wide `--since` catch-up to an only-if-needed fallback
("don't read them all blindly").
Also fixes the now-stale "scoped to the triggering thread" wording in the
resumed-session no-delta hint (it's issue-wide zero now).
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: multica-agent <github@multica.ai>
|
||
|
Multica Eve
|
d1c7d478e1 |
MUL-2785: clarify thread-scoped comment delta (#3523)
Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Multica Eve
|
9616d78e47 |
MUL-2785: optimize resumed comment reads (#3509)
* feat(comments): skip default thread read on resumed comment sessions Co-authored-by: multica-agent <github@multica.ai> * fix(comments): scope since delta to trigger thread Co-authored-by: multica-agent <github@multica.ai> * chore(comments): address thread delta review nits Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: Eve <eve@multica-ai.local> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Naiyuan Qing
|
3187bbf90c |
feat(comments): re-add since-delta + cold-start thread read + parent-root write normalization (#3494)
* feat(comments): since-delta new-comment hint + default-on comment session resume (#3432) * feat(db): add unresolved comment count + list filter queries Add CountUnresolvedComments (excludes the agent's own comments) and ListUnresolvedCommentsForIssue. Both are additive — existing callers stay on the unfiltered queries — so old clients are unaffected. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(handler): support unresolved-only comment listing Wire an additive `unresolved` query param into ListComments. Defaults off so an old CLI that never sends it gets unchanged behavior; only true/1 enable it. Rejects combining unresolved with thread/recent (whole-issue filter vs navigation models). Includes filter + count query tests. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(handler): plumb unresolved count + thread root into claim, gate comment resume Populate trigger_parent_id (thread root of the trigger comment) and unresolved_count (excludes the agent's own comments) on comment-triggered claim responses. Both fields are omitempty so old daemons ignore them. Gate comment-triggered session resume behind MULTICA_RESUME_COMMENT_SESSION (default off): resumed comment turns can inherit the prior turn's "Done." final message, so this stays an explicit rollout switch. The runtime-match and poisoned-session guards still apply regardless of the flag. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(daemon): inject unresolved-comments hint + resolve step into agent brief Add a shared BuildUnresolvedCommentsHint helper rendered on both the per-turn prompt and the CLAUDE.md workflow (kept in sync per PR #2816). It ships only the count and the relevant CLI call — never comment bodies — so the server stays cheap. Thread case points at --thread <root>; issue case points at --unresolved. Suppressed when the count is 0. Also add a workflow step telling the agent to `multica comment resolve <thread-root>` once a thread is fully handled, so the unresolved set converges. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(cli): add comment list --unresolved and comment resolve command Add an --unresolved filter to `issue comment list` (wired to the server's unresolved param, rejected when combined with --thread/--recent) and a top-level `comment resolve <id>` command that POSTs to the existing /api/comments/{id}/resolve endpoint, letting an agent close threads it has fully handled. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(comments): since-delta new-comment hint + default-on comment resume Simplifies the comment-triggered agent flow down to what's actually needed: - New-comment awareness is now a pure time delta: the claim response carries new_comment_count + new_comments_since (anchored on the prior run's started_at, never completed_at so a long run can't miss comments). The per-turn prompt and CLAUDE.md workflow render one line — "N new comment(s) since your last run, --since <ts>" — via a shared BuildNewCommentsHint so the two surfaces can't drift. Cold start (no prior run) falls back to a plain read. - Comment-triggered tasks resume the prior session by default (same runtime), dropping the MULTICA_RESUME_COMMENT_SESSION rollout gate. The "Focus on THIS comment" prompt guard defends against inheriting the prior turn's "Done." marker; GetLastTaskSession still excludes poisoned sessions. - Drops the resolved-based machinery from the first draft: CountUnresolvedComments / ListUnresolvedCommentsForIssue queries, the `comment list --unresolved` flag, the `multica comment resolve` command, and the resolve workflow step. - Removes the verbose cursor-pagination paragraph from the comment prompt; the --thread/--recent/--since flags stay in the CLI/API, just no longer explained inline every turn. Compatibility: new claim fields are omitempty (old daemons ignore them). Comment resume is default-on and affects even old daemons, which already consume prior_session_id. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(comments): collapse reply parent_id to thread root on write Comment threads are a 2-level model (root + flat replies, like Linear/Slack), enforced today only by the UI and the agent path — the CreateComment handler stored whatever parent_id it was handed, and the agent-side flatten walked just one level, so a reply-to-a-reply could land at depth 3+. Add GetThreadRoot (a recursive walk to the parent_id=NULL root) and run both write paths (handler.CreateComment, service.createAgentComment) through it, so every stored reply's parent_id IS its thread root. Readers can now treat parent_id as the thread root without re-walking. The agent-drift guard still compares the raw parent_id to the trigger comment before normalization. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(comments): cold-start reads triggering thread, warm keeps --thread pointer The since-delta rework dropped the thread-first read on the COLD path: a first-time agent fell back to the flat `comment list` dump (oldest-first, cap 2000), burying the trigger's context in ancient chatter. Point cold start at the triggering conversation instead via a shared BuildColdCommentsHint (`--thread <trigger> --tail 30` + a --recent pointer for cross-thread background). On the WARM path, --since is a pure time delta and can miss the triggering thread's pre-anchor history, so BuildNewCommentsHint now also emits a --thread pointer. Both surfaces (per-turn prompt + CLAUDE.md workflow) render via the shared helpers so they cannot drift (PR #2816 rule). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
Bohan Jiang
|
fa076d38f2 |
MUL-2778 feat(agent): wire mcp_config through OpenClaw runtime (#3450)
* MUL-2778 feat(agent): wire mcp_config through OpenClaw runtime The MCP config tab (#3419) lets admins save mcp_config on an agent, and recent work (#3439) plumbed it through the three ACP runtimes. OpenClaw still ignored the field, leaving the Tab silently inert for any OpenClaw-backed agent. Translate the agent's Claude-style `{"mcpServers": {...}}` into the per-task OpenClaw wrapper's `mcp.servers` block — OpenClaw resolves MCP via its own config schema rather than ExecOptions, so the existing OPENCLAW_CONFIG_PATH preparer is the right seam. Fail closed on malformed JSON / entries missing `command` or `url`, matching the fail-closed posture the preparer already uses for the agents.list step. Null / absent mcp_config leaves the wrapper free of an `mcp` key so the user's global mcp.servers flows through untouched; an explicit empty managed set (`{}` / `{"mcpServers":{}}`) is honoured as "admin saved no servers" mirroring `hasManagedCodexMcpConfig`. Strict-mode replacement (drop user-only servers entirely) would require OpenClaw to do a per-key replace rather than a deep merge at `mcp.servers`; the comment documents that caveat rather than relying on undocumented behaviour. Also adds `openclaw` to `MCP_SUPPORTED_PROVIDERS` so the MCP Tab actually surfaces in the agent overview pane, and pins the new visibility case with a renderPane test. Co-authored-by: multica-agent <github@multica.ai> * MUL-2778 fix(agent): make openclaw mcp_config strict-replace via sanitized snapshot Elon flagged on #3450 that the previous wiring let user-only mcp.servers leak through the wrapper's `$include` of the live user config: deep-merge at `mcp.servers` keeps user-only names, and the strict-empty case (`{ "mcpServers": {} }`) silently inherited user globals. Switch the strict-replace path to write a sanitized snapshot of the user's fully resolved config (via `openclaw config get --json`) with the `mcp` block stripped, then have the wrapper `$include` the snapshot instead of the live user file. With the user's `mcp` gone from the $include resolution, the wrapper's `mcp.servers` is the only definition the embedded OpenClaw sees — managed only, including the explicit empty set. The snapshot lives in envRoot at 0o600 alongside the wrapper so the GC reaper sweeps it with the rest of the task scratch, and no extra OPENCLAW_INCLUDE_ROOTS entry is needed (same-dir $include). Fail-closed on `config get --json` errors so the daemon never silently falls back to the leaky $include path. The inherit branch (null mcp_config) still uses the live user file directly — no extra CLI roundtrip and no snapshot is written. New tests pin the contract Elon's review required: - TestPrepareOpenclawConfigStrictReplacesUserMcpServers: user has global_one + shared, managed has shared + managed_only → wrapper has exactly {shared (managed value), managed_only}; global_one does NOT leak; snapshot file has the user's `mcp` stripped while preserving gateway / providers / API keys. - TestPrepareOpenclawConfigStrictEmptyManagedSetDropsUserMcp: empty managed set drops user's global_one (both `{}` and `{"mcpServers":{}}` cases). - TestPrepareOpenclawConfigNullMcpConfigKeepsUserInclude: null path inherits the live user config, writes no snapshot, makes no extra CLI call. - TestPrepareOpenclawConfigFailsClosedOnResolvedConfigError: errors during `config get --json` surface; no stale wrapper or snapshot. - TestPrepareOpenclawConfigManagedSetFreshInstall: fresh install with managed mcp_config skips the snapshot dance entirely. Also tightens en + zh-Hans MCP Tab copy to mention OpenClaw goes via the per-task wrapper, and to use OpenClaw's own `transport` field rather than Claude's `type` for HTTP/SSE entries. Co-authored-by: multica-agent <github@multica.ai> * MUL-2778 fix(agent): narrow openclaw snapshot strip to mcp.servers only Elon's third-round must-fix: the previous strict-replace snapshot deleted the entire `mcp` block, which wiped out non-server settings under `mcp` like `sessionIdleTtlMs`. Those are documented OpenClaw config keys (https://docs.openclaw.ai/gateway/configuration-reference#mcp) outside the MCP Tab's scope — the agent's saved mcp_config only manages server definitions, so other `mcp.*` tuning the user set must survive. Replace the blanket `delete(resolved, "mcp")` with a stripUserMcpServers helper that: - deletes only `mcp.servers` when `mcp` is an object - drops the parent `mcp` key only when the object is empty after the strip (so we don't emit `mcp: {}` placeholders) - leaves non-object `mcp` values untouched (we only know how to strip servers from the documented shape) Pinned with TestPrepareOpenclawConfigStrictPreservesNonServerMcpKeys: user resolved has both `mcp.sessionIdleTtlMs: 300000` and `mcp.servers.global_one`; after the strict path runs the snapshot keeps the TTL and drops the servers map, and the wrapper's `mcp.servers` is exactly the managed set with no leak. Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Naiyuan Qing
|
d90732750f |
Revert "feat(comments): since-delta new-comment hint + default-on comment ses…" (#3455)
This reverts commit
|
||
|
Bohan Jiang
|
ee4ec3b76d |
MUL-2784 fix(daemon): cleanup sidecar tree (.agent_context / .multica / provider skills) after local_directory tasks (#3444)
* fix(daemon): cleanup .agent_context / .multica / provider skill sidecars after local_directory tasks (MUL-2784) PR #3438 (MUL-2753) only restored CLAUDE.md / AGENTS.md / GEMINI.md to their pre-task bytes; the sidecar tree writeContextFiles seeds (.agent_context/, .multica/, .claude/skills/, .github/skills/, .opencode/skills/, skills/, .pi/skills/, .cursor/skills/, .kimi/skills/, .kiro/skills/, .agents/skills/, fallback .agent_context/skills/) was explicitly deferred to this follow-up. In local_directory mode the agent's workdir is the user's repo, so each task accumulates one more layer of those directories in the user's tree. Plan A: track every file/dir Prepare creates inside workDir in a sidecarManifest written to envRoot/.multica_sidecar_manifest.json (daemon scratch — never in the user's workdir). On local_directory teardown CleanupSidecars walks the manifest, removes the recorded files, then rmdir-iterates the recorded directories in reverse. Pre-existing files and directories are deliberately NOT recorded, so a user-installed .claude/skills/my-own-skill/ sibling — or any unrelated file the user keeps under .claude/, .github/, etc. — is preserved bit-for-bit. Non-empty rmdir fails ENOTEMPTY and is silently skipped, which is the signal that the user owns the directory. Daemon wiring lives next to the existing CleanupRuntimeConfig defer in runTask: runtime brief first, sidecars second. Cloud-mode runs still write a manifest for symmetry but never trigger the cleanup (the GC loop wipes envRoot wholesale). Tests (sidecar_manifest_test.go) cover the round-trip invariant per the issue's acceptance criteria: - empty workdir → Prepare → Cleanup → empty workdir, byte-exact, for every file-based provider (claude, codex, copilot, opencode, openclaw, hermes, pi, cursor, kimi, kiro, antigravity, gemini), - user's .claude/skills/my-own-skill/ (and equivalents per provider) survives Cleanup intact, - unrelated user files under .claude/, .github/, etc. survive, - three repeated cycles do not accumulate any orphan state, - project_resources branch (.multica/project/resources.json) is also reversible, - recordWriteFile refuses to record pre-existing files, - recordMkdirAll refuses to record pre-existing dirs, - Cleanup is a no-op when the manifest file is missing. Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): refuse to overwrite pre-existing sidecar paths; pick collision-free skill slugs (MUL-2784 review) Addresses PR #3444 review (Elon): **Must-fix #1**: recordWriteFile used to overwrite pre-existing target files unconditionally and only skip the manifest record. That destroys user bytes at write time AND leaves the corrupted contents in place at cleanup time — the byte-exact contract the issue requires is violated on both halves. Fixed by making recordWriteFile detect any pre-existing entry (regular file, symlink, directory) via Lstat and return a sentinel errPathPreExists without touching the path. The user's bytes are preserved verbatim. For per-skill collisions (user's .claude/skills/issue-review/ vs Multica's "Issue Review"), writeSkillFiles now allocates a collision-free sibling slug via allocateCollisionFreeSkillDir: first attempt is the natural slug, then `<base>-multica`, `<base>-multica-2`, …, bounded at 64 attempts. Provider-native discovery still picks the skill up (every subdir under skillsParent is a distinct skill) and the user's path stays bit-for-bit intact. For Multica-only namespace files (.agent_context/issue_context.md, .multica/project/resources.json), the writer swallows errPathPreExists and continues — the runtime brief already carries every fact those files would, so a collision degrades to brief-only mode rather than destroying user content. **Must-fix #2**: Added byte-exact collision matrix tests covering every file-based provider (claude / codex / copilot / opencode / openclaw / hermes / pi / cursor / kimi / kiro / antigravity / gemini): - TestPrepareThenCleanupSidecarsSameSlugCollisionPerProvider: seeds user's `<provider>/skills/issue-review/SKILL.md` plus a private notes.md sibling, runs Prepare → Inject → Cleanup, asserts workdir snapshot is byte-identical to seed. - TestPrepareThenCleanupSidecarsIssueContextCollisionPerProvider: seeds user's `.agent_context/issue_context.md`, asserts round-trip preserves it. - TestPrepareThenCleanupSidecarsProjectResourcesCollisionPerProvider: same for `.multica/project/resources.json`. - TestPrepareThenCleanupSidecarsMultiSkillCollisionFreeAllocation: end-to-end check that the Multica skill lands at the collision-free sibling and Cleanup removes only the Multica side. - TestAllocateCollisionFreeSkillDir: directed unit test pinning the slug-bumping sequence. - TestRecordWriteFileRefusesToOverwritePreExistingFile (was TestRecordWriteFileSkipsPreExistingFile): flipped to assert the user's bytes survive and errPathPreExists is returned. - TestRecordWriteFileRefusesToOverwriteSymlinkOrDir: covers the Lstat path for non-file entries. **Should-fix**: CleanupSidecars used to swallow ANY non-ENOENT rmdir error as "user content present," silently dropping real I/O failures (EACCES, EPERM, EBUSY). Now it re-reads the directory after a failed rmdir via the new dirHasEntries helper — non-empty → silently skip (ENOTEMPTY, the intended branch); empty → genuine error, captured into firstErr and surfaced. Plus directed tests: - TestCleanupSidecarsSurfacesRealRmdirErrors - TestDirHasEntries Local verification: - go test ./internal/daemon/execenv/... — all green - go test ./internal/daemon/... — all green - go vet ./... — clean Co-authored-by: multica-agent <github@multica.ai> * fix(daemon): surface original rmdir error when post-rmdir ReadDir also fails (MUL-2784 review) Addresses remaining PR #3444 review blocker (Elon): dirHasEntries used to return true when ReadDir failed with anything other than ENOENT, which made CleanupSidecars treat every locked / faulted directory as ENOTEMPTY and silently drop the original rmdir error. The v1 fix from the previous round closed the EACCES-on-empty-dir branch but missed the case where the chmod also blocks ReadDir — exactly the failure mode the review called out. Helper change: dirHasEntries now returns (hasEntries, ok bool): - (false, true) — dir exists and is empty (or missing, race-safe) - (true, true) — dir has user content (the ENOTEMPTY branch) - (_, false) — ReadDir failed (EACCES, ENOTDIR, EIO, …); the caller cannot tell ENOTEMPTY from a real error and MUST surface the original rmdir error CleanupSidecars switches on (ok, hasEntries): - !ok → surface the ORIGINAL rmdir error (not the ReadDir failure — that's diagnostic plumbing and would distract from the root cause) - ok && hasEntries → swallow silently (intended ENOTEMPTY branch; preserve user content) - ok && !hasEntries → surface the rmdir error (empty dir + EACCES / EPERM / EBUSY → genuine cleanup failure) Tests: - TestDirHasEntries: extended with a regular-file sub-case (ReadDir returns ENOTDIR) asserting (false, false). The v1 helper returned (true) here, hiding the bug. - TestCleanupSidecarsSwallowsMissingAndNonEmptyDirs: renamed from TestCleanupSidecarsSurfacesRealRmdirErrors. The old name claimed to test the surfacing path but never actually exercised it. - TestCleanupSidecarsSurfacesEACCESOnEmptyRecordedDir: chmod parent to 0o555 so rmdir(recorded) fails EACCES while ReadDir(recorded) still succeeds (empty). Asserts firstErr is non-nil and references both the recorded path and the rmdir branch. Skipped when running as root (chmod is bypassed for uid 0). - TestCleanupSidecarsSurfacesEACCESWhenReadDirFailsToo: the must-fix case — chmod parent 0o555 AND chmod recorded 0o000 so BOTH rmdir and ReadDir fail. The surfaced error must be the ORIGINAL rmdir failure, not the ReadDir one. Skipped on uid 0. Local verification: - go test ./internal/daemon/execenv/... — all green - go test ./internal/daemon/... — all green - go vet ./... — clean Co-authored-by: multica-agent <github@multica.ai> --------- Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |
||
|
Bohan Jiang
|
90a737fc7e |
fix(daemon): retry terminal task callbacks on transient errors (MUL-2780) (#3443)
CompleteTask / FailTask used to be fire-once. A 1-second upstream 502 burst would drop the call, then the immediate fail-fallback also 502'd, leaving the task stuck in `running` forever and showing the agent as "still working" in the UI. Add a bounded retry around the two terminal callbacks: 4s, 8s, 16s, 32s, 64s backoff schedule (5 retries, ~124s ceiling), retrying only on transient errors (5xx, 408, 429, transport-level) and bailing immediately on permanent 4xx. Also fix a latent bug where a transient complete failure would silently downgrade a successful run to a fail: the fallback now triggers only on permanent errors. Server-side CompleteTask / FailTask are already idempotent on "already terminal", so replays from a retry are safe even if the prior 502'd response was actually persisted. Co-authored-by: J <j@multica.ai> Co-authored-by: multica-agent <github@multica.ai> |