* fix(daemon): reclaim disk on long-open issues + correct cancelled-status check
Two related fixes for GitHub #1890 (self-hosted disk space growth):
- The GC's done/cancelled branch compared `status.Status` against `"canceled"`
(single l), but the issue schema and the rest of the daemon use `"cancelled"`
(double l). Cancelled issues therefore never matched and only fell out via the
72h orphan TTL, which itself doesn't fire because cancelled issues are still
reachable. Aligning the spelling lets cancelled-issue task dirs be reclaimed
on the normal TTL path.
- Add a third GC mode, artifact-only cleanup, for the common case the report
flagged: an issue stays open for days while many tasks complete on it, so
per-task `node_modules`, `.next` and `.turbo` directories accumulate without
ever becoming GC-eligible. The new branch fires when `.gc_meta.completed_at`
is older than `MULTICA_GC_ARTIFACT_TTL` (default 12h), the env root is not
currently in use by an active task, and the issue is still alive. It removes
only directories whose basename matches `MULTICA_GC_ARTIFACT_PATTERNS`
(default narrow: `node_modules,.next,.turbo`); source, `.git`, `output/`,
`logs/` and the meta file are preserved so subsequent tasks can still resume
the workdir. Patterns containing path separators are dropped, `.git` subtrees
are never descended into, symlinked matches are not followed, and every
removal target is verified to live inside the task dir.
Bookkeeping: `Daemon` now tracks active env roots with a refcounted set so the
GC loop never reclaims a directory that is mid-execution; `runTask` claims the
predicted root early plus the prior workdir on reuse paths. The cycle log is
extended with bytes reclaimed and per-pattern counts so self-hosted operators
can see what was freed.
Docs: extend the daemon configuration table in CLI_AND_DAEMON.md with the new
GC env vars and add a Workspace garbage collection section explaining the
three modes and the artifact-pattern contract.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): protect active env root from full GC removal too
Address GPT-Boy's PR #1931 review: the active-root guard only fired in the
artifact-cleanup branch, leaving a real race on the full-removal paths. A
follow-up comment on a long-done issue dispatches a task that reuses the prior
workdir, but `CreateComment` does not bump issue.updated_at — so the issue
still satisfies the done+stale GCTTL window and `gcActionClean` would
`RemoveAll` the directory mid-execution. The orphan-404 path is similarly
exposed when a token's workspace access is in flux.
Move the `isActiveEnvRoot` check to the top of `shouldCleanTaskDir` so all
three delete actions (clean, orphan, artifact) skip an in-use env root in one
place, and drop the now-redundant guard from the artifact branch.
Add tests covering the three at-risk paths: active root + done/stale issue,
active root + 404 issue past orphan TTL, active root + no-meta orphan past
TTL.
Also align two stale comments noted in the same review: cleanTaskArtifacts now
documents that symlinks are skipped entirely (the previous note implied the
link itself was removed), and GCOrphanTTL no longer claims that 404s are
cleaned immediately — the implementation gates them on the same TTL.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* refactor(repos): drop unused description + tighten create-project layout
Two related changes that touch the workspace-repos surface together.
1. Remove the per-repo `description` field everywhere it was threaded.
The only place it ever surfaced was a markdown table column the daemon
wrote into the agent runtime config, where most rows just read "—"
anyway. Agents already discover project structure by running
`multica project` / `multica issue` against the CLI, so the human-
readable description string carried no real value while taking up an
extra Settings input row and propagating through six layers (settings
UI → workspace.repos jsonb → handler RepoData → daemon RepoData →
repocache.RepoInfo → execenv.RepoContextForEnv).
- Settings → Repositories drops the description input; the URL field
now spans the whole row.
- WorkspaceRepo TS type loses `description`; backend RepoData /
RepoInfo / RepoContextForEnv all collapse to URL only.
- Daemon's runtime_config Repositories block changes from a
`| URL | Description |` markdown table to a simple bullet list.
- Tests updated; jsonb residue in existing workspaces is dropped at
normalize time, so no migration needed.
2. Tighten the Create Project modal footer: pull the Status / Priority /
Lead / Repos pills onto the same row as the Create Project button
(Linear-style single-row footer) instead of stacking them above it,
and swap the Repos pill icon from `FolderGit` to a real GitHub mark
(lucide-react v1 dropped brand icons, so the mark lives inline as a
small SVG component in this file).
I tried promoting Repos to its own "Resources" strip above the footer
to separate the resources abstraction from project metadata, but with
a single pill it looked too sparse — leaving a TODO comment in the
footer to revisit once we add Linear / Notion / Figma / Slack
resource types.
* fix(daemon test): drop residual Description field on RepoData literals
* fix(repos): drop Description residue surfaced after rebase on #1929
Project-resource github_repo lift path (#1929) and registerTaskRepos
both still constructed RepoData{...Description: ...} after the rebase.
Two test sites in daemon_test.go and execenv_test.go also reintroduced
the field. Strip them so the Description-removal change builds and
tests pass with the latest main.
* feat(projects): project github_repo resources override workspace repos
When an issue's project has at least one github_repo resource, the daemon
claim handler now sends only those as resp.Repos — workspace-level repos
are hidden to avoid mixing two repo lists in the agent prompt. With no
project github_repos (or no project), behavior is unchanged: workspace
repos are surfaced as before.
Lifts each project github_repo's url (and label, when present) into a
RepoData entry so `multica repo checkout` and the meta-skill render the
same URLs. The full structured list still ships at
.multica/project/resources.json for skills that want everything.
Adds TestProjectReposReplaceWorkspaceReposInMetaSkill covering the
rendering side. Docs updated to spell out the new precedence.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): allow project repo URLs through the checkout allowlist
When ClaimTaskByRuntime narrows resp.Repos to project github_repo URLs,
the daemon receives URLs that may not exist in the workspace's
GetWorkspaceRepos response. The existing checkout flow rejected those
with ErrRepoNotConfigured because the allowlist (and cache) was built
only from workspace-bound repos.
Adds registerTaskRepos in daemon.runTask: before agent spawn, merge
task.Repos into a new task-scoped allowlist (separate from the
workspace-scoped one so a workspace refresh doesn't wipe project URLs)
and kick off a background cache sync. ensureRepoReady now treats either
allowlist as valid.
Tests:
- TestRegisterTaskReposAllowsProjectOnlyURL — project-only URL is
checkout-able and does not trigger a workspace-repos refresh
- TestRegisterTaskReposSurvivesWorkspaceRefresh — task URLs persist
across refreshWorkspaceRepos
- TestClaimTask_ProjectGithubReposOverrideWorkspaceRepos — claim
handler returns only project repos when present, no workspace leakage
- TestClaimTask_ProjectWithoutRepos_FallsBackToWorkspaceRepos — fall
back to workspace repos when project has no github_repo resources
Docs updated to spell out the daemon-side allowlist behavior.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* fix(task): rerun starts a fresh session, skip poisoned resume
When a task ended in a known agent fallback ("I reached the iteration
limit and couldn't generate a summary.", "Put your final update inside
the content string. Keep it concise.") the (agent_id, issue_id) resume
lookup would still pick that session, so a manual rerun inherited the
poisoned state and reproduced the same bad output.
Two complementary guards:
1. Daemon classifies poisoned terminal output and routes it through the
blocked path with failure_reason set ('iteration_limit' /
'agent_fallback_message'). GetLastTaskSession excludes failed tasks
with those reasons, so even comment-triggered tasks no longer resume
them. Tasks that failed mid-flight (timeout, runtime_recovery, etc.)
are still resumable, preserving MUL-1128's auto-retry contract.
2. Manual rerun marks the new task force_fresh_session=true. The daemon
claim handler skips the resume lookup entirely when the flag is set,
capturing the user-intent signal that "the prior output was bad" even
when poisoned classification misses a future fallback wording.
Auto-retry of orphaned mid-flight failures (MaybeRetryFailedTask →
CreateRetryTask) does not take this path, so it keeps resuming.
Tests: classifyPoisonedOutput unit test; integration tests assert the
SQL filter excludes poisoned classifiers, RerunIssue flips the flag,
and the normal enqueue path leaves it false.
Co-authored-by: multica-agent <github@multica.ai>
* fix(daemon): cap poisoned-output matcher to short trimmed text
GPT-Boy review on MUL-1630: the previous strings.Contains match would
classify any output that quoted the marker substring — including a
review/analysis that simply discussed the marker itself. Real fallback
messages are short single-sentence affairs, so cap the candidate at
~one paragraph and trim whitespace before matching. Adds regression
tests covering a long quoting review and a marker buried in a long
real conclusion; both must stay classified as completed.
Co-authored-by: multica-agent <github@multica.ai>
* fix(migrations): rename 065 force_fresh_session → 066 to clear collision
main introduced 065_project_resources after this branch was cut, so
both files shared the 065_ prefix. The readiness check
(server/cmd/server/health.go → migrations.LatestVersion) takes the
last entry by lexical order, which is 065_project_resources, leaving
this branch's 065_force_fresh_session unguarded — a deploy that
applied project_resources but not force_fresh_session would still
report ready, and the next enqueue / rerun / claim would crash on
"column force_fresh_session does not exist".
Renaming to 066_force_fresh_session puts it strictly after
project_resources so readiness blocks until it's applied.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(projects): typed project resources + agent runtime injection
Adds a `project_resource` table that lets a project carry typed pointers
(github_repo today, more later) and surfaces them at agent runtime.
Server
- migration 065: project_resource (resource_type TEXT + resource_ref JSONB)
- sqlc CRUD + handler at /api/projects/{id}/resources
- claim handler attaches project_id/title + resources to issue tasks
Daemon
- TaskContextForEnv carries project context
- writes .multica/project/resources.json into workdir
- adds "## Project Context" block to CLAUDE.md / AGENTS.md / GEMINI.md
via type-dispatched formatter so new resource types just add a case
CLI
- multica project create --repo <url> attaches repos in one step
- multica project resource add/list/remove
Frontend
- Project create modal: Repos pill (workspace repos + ad-hoc URL)
- Project detail sidebar: collapsible Resources section with attach/remove
Docs
- New "Project Resources" chapter explaining the abstraction and
exactly what code to touch when adding a new resource type
Co-authored-by: multica-agent <github@multica.ai>
* fix(projects): transactional resources[] on create + generic CLI ref + test fix
Addresses review feedback on PR #1926:
1. CI red: TestProjectResourceLifecycle delete step called withURLParam
twice, which replaced the chi route context and dropped the project id.
Switched to the existing withURLParams helper from daemon_test.go.
2. POST /api/projects now accepts resources[] and attaches them in the
same transaction as the project. Invalid refs roll back the whole
create — no more half-attached projects on failure. Web modal + CLI
`project create --repo` both use the new bundled payload.
3. CLI `project resource add` now accepts a generic --ref '<json>' flag
so a new resource_type works without a CLI change. Per-type
shortcuts (--url for github_repo) remain as a convenience but are no
longer the only way in. Docs updated to drop the CLI from the
"files you must touch" list.
Adds two new server handler tests:
- TestCreateProjectAttachesResources (resources[] happy path)
- TestCreateProjectRollsBackOnInvalidResource (transactional rollback)
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
* feat(daemon): add Co-authored-by trailer for Multica Agent to git commits
Install a prepare-commit-msg hook in worktree bare repos that appends
"Co-authored-by: multica-agent <github@multica.ai>" to every commit
made by agents. Uses git interpret-trailers for proper formatting and
skips duplicates.
* feat(settings): add Co-authored-by toggle in workspace Labs settings
Add a workspace-level toggle to enable/disable the Co-authored-by
trailer for agent commits. Default is enabled (on).
Backend:
- Include workspace settings in daemon register response
- Store settings in daemon workspaceState
- Thread CoAuthoredByEnabled through WorktreeParams to conditionally
install the prepare-commit-msg hook
- Parse co_authored_by_enabled from workspace settings JSONB
Frontend:
- Replace empty Labs tab placeholder with a Git section containing
a Switch toggle for the Co-authored-by trailer setting
- Optimistically update the workspace query cache on toggle
* chore(daemon): skip squash commits in Co-authored-by hook
Test commit to verify the prepare-commit-msg hook appends the
Co-authored-by trailer automatically.
Co-authored-by: multica-agent <github@multica.ai>
---------
Co-authored-by: multica-agent <github@multica.ai>
The description rule in buildQuickCreatePrompt() instructed the agent to
"always provide a rich, self-contained description" and "spell out what
needs to be done", which caused the agent to fabricate detailed product
specs, implementation phases, and design decisions from a one-line input.
Replace with a faithfulness-first rule: enrich with factual context
(fetched PR details, linked resources) but never invent requirements,
design decisions, or constraints the user did not express.
Fixes MUL-1605
* feat(quick-create): enrich issue title and description with URL context
Update the quick-create agent prompt to fetch context from URLs in user
input (GitHub PRs, issues, web pages) before creating the issue. The
agent now produces semantically rich titles (e.g. "Review PR #123:
Refactor auth to OAuth2" instead of "review PR #123") and includes
summarized link content in the description so issues are self-contained.
* refactor(quick-create): let agent decide when to fetch URL context
Replace prescriptive URL enrichment instructions (hardcoded gh/WebFetch
commands) with goal-oriented guidance. The agent now uses its own
judgment to decide whether fetching referenced URLs would produce a
meaningfully better title/description, rather than being told exactly
which tools to use.
* fix(quick-create): always generate rich description for agent execution
The description was previously optional ("omit if simple request"). Since
quick-create issues are executed by agents, richer context leads to
better execution — update the prompt to always produce a substantive
description with actionable context.
* fix(quick-create): remove Chinese text from prompt, use English only
Replace Chinese examples in priority mapping and assignee matching with
language-agnostic English equivalents, per project coding rules.
* fix(quick-create): remove language-related hints from prompt
Agent doesn't need to be told about language handling — remove
"(in any language)" and "or equivalent in any language" qualifiers.
Keep prompt purely in English with no language-related content.
* fix(execenv): default-disable Codex native multi-agent in per-task config
Recent Codex app-server releases enable features.multi_agent by default,
exposing spawn_agent / wait / close_agent tools that let a parent thread
spawn nested subagents. The daemon currently models only the parent thread,
so the parent's turn/completed is treated as task completion even when
spawned children are still running — leading to premature task completion
and dropped child output.
Disable features.multi_agent by default in the per-task CODEX_HOME/config.toml
so Multica's task lifecycle is the only orchestration layer in play. Strip
both the dotted-key form (features.multi_agent) at TOML root and the
multi_agent key inside a [features] table; siblings and unrelated tables
are preserved. Honor MULTICA_CODEX_MULTI_AGENT=1 as an opt-out for users
who explicitly want Codex native subagents inside a Multica task.
The user's global ~/.codex/config.toml is never modified — only the daemon's
isolated per-task copy.
Also widen managedBlockRe to consume `\n*` rather than `\n?` so reruns
don't accumulate blank lines when both the sandbox and multi-agent managed
blocks coexist.
* fix(execenv): inject managed multi_agent inside existing [features] table
Per PR review (codex_multi_agent.go:77-83 vs :112-115): when the user's
config.toml already has a top-level `[features]` table, writing
`features.multi_agent = false` at the TOML root implicitly redefines the
same `features` table. The strict TOML parser used by Codex (`toml-rs`)
rejects that with `table 'features' already exists`, so Codex would fail
to load the per-task config and refuse to start the thread. Verified the
strict-parser failure with pelletier/go-toml/v2; the previous
BurntSushi/toml-based regression test was permissive enough to miss it.
Detect a root-level `[features]` header and place the managed block
inside that table (`multi_agent = false` with marker comments). When no
such header exists, keep the existing root-level dotted-key form. The
managed-block regex matches both layouts so reruns and layout
transitions stay idempotent. A `[features.experimental]` sub-table
without a bare `[features]` header still uses the root dotted-key form,
which is spec-valid (no explicit redefinition).
Tests now use pelletier/go-toml/v2 to actually parse the output and
assert features.multi_agent decodes to false; the regression case from
the PR review is covered explicitly.
* fix(execenv): recognize feature table header variants
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Two coordinated fixes for a quick-create case where the agent ended up
creating duplicate issues. Repro: user pasted an image into the
quick-create prompt; the front-end uploaded it and embedded the URL as
markdown in the user input; the agent saw the URL, assumed it was an
attachment, and ran `multica issue create … --attachment "https://…"`.
The CLI POSTed the issue first, then failed to read the URL as a file
(`os.ReadFile("https://…")`) and exited 1. The agent treated exit 1 as
"create failed" and retried — but the first issue already existed, so
the workspace ended up with two of them.
CLI (`server/cmd/multica/cmd_issue.go`):
- `runIssueCreate` pre-validates `--attachment` BEFORE POSTing. URLs are
warned about and skipped (they are never local files); local-path
read errors fail before the issue is created so no half-baked issue
lands. Once the POST succeeds, post-create upload failures only
print a stderr warning and the issue metadata is still emitted —
never a non-zero exit, so callers cannot mistake "attachment upload
hiccup" for "create failed" and retry.
- `runIssueCommentAdd` already uploads attachments BEFORE the comment
is created, so its failure mode is fine; it just gets the same
URL-skip behaviour for consistency.
Quick-create prompt (`buildQuickCreatePrompt`):
- Tells the agent NOT to pass `--attachment` for prompt-embedded image
URLs (they are already part of the description as markdown).
- Hardens the "no retry" rule: even on a non-zero exit, do not retry
`issue create` — the issue may already exist.
GitHub #1839: when an issue is reassigned from agent A to agent B, B
often only reads the issue body and misses context A added in comments
(e.g. which repo to clone). The assignment-triggered workflow injected
into CLAUDE.md / AGENTS.md said "Read comments for additional context
or human instructions" — vague enough that agents routinely skipped
it. The comment-triggered branch already gives an explicit
`multica issue comment list` invocation, so behavior diverged.
Promote step 3 to a concrete CLI call, mark it mandatory, and surface
the most common failure mode (stale instructions on reassignment) so
the agent recognizes when it matters. Reorder so comments are read
*before* flipping status to `in_progress`, matching how a human would
catch up on a thread before claiming work.
* feat(quick-create): default assignee to picker agent when user didn't name one
The quick-create prompt previously told the agent to OMIT --assignee
when the user's input didn't name a person. That left almost every
quick-created issue unassigned, which doesn't match user intent — the
user opened quick-create with a specific agent picked, so that agent
is the obvious owner.
Both prompt surfaces (BuildPrompt for the dispatched message, plus
the workflow block in injected CLAUDE.md / AGENTS.md) now instruct
the agent: if the input doesn't name an assignee, pass
`--assignee "<your name>"`. The picker agent's name is interpolated
into the prompt at task-build time so the agent has a literal value
to use rather than guessing its own name. The "explicitly named
assignee → resolve via members" branch is unchanged.
* refactor(execenv): drop duplicated quick-create field rules from CLAUDE.md/AGENTS.md
The quick-create field rules (title / description / priority / assignee
fallback / project / status) lived in two places — the per-turn user
message built by BuildPrompt, and the workflow block injected into
CLAUDE.md / AGENTS.md by buildMetaSkillContent. Same content, two
sources, easy to update one and forget the other (the assignee-default
change in this PR had to touch both).
Quick-create is one-shot, so the per-turn user message is always
present and is the natural single source of truth. The injected
file's quick-create section now keeps only the hard guardrails:
"do exactly one issue create, no issue get / status / comment add,
exit on CLI error". Those guardrails stay in BOTH surfaces because
they're the safety net for providers that don't propagate the user
message into resumed-session context.
renderQuickCreateContext (issue_context.md) was already
guardrails-only — no change needed there.
The agent-facing CLAUDE.md/AGENTS.md injected by InjectRuntimeConfig was
missing every doorway to non-core issue properties:
- `multica issue label list/add/remove` — the only way to label a newly
created issue from the agent. Without it, agents either give up
("no command for that, please add it manually") or hallucinate flag
names like `multica issue create --label foo` and fail.
- `multica issue subscriber list/add/remove` — same story for the
subscribe-on-behalf flow.
- `multica label list/create` — agents need to discover existing label
ids before they can attach one (we don't auto-create labels here).
- `issue create` flag list dropped `--project`, `--due-date`,
`--attachment` even though the CLI has supported them for a while.
- `issue update` flag list dropped `--status`, `--assignee`,
`--project`, `--due-date`, `--parent`, leaving agents thinking they
could only edit title/description/priority via update.
Also splits `issue status` from `issue update` in the doc so the agent
sees the shortcut, and notes the `issue create` body intentionally
does NOT accept labels/subscribers (use the post-create commands).
Codex Desktop writes one [[skills.config]] entry per known skill into
~/.codex/config.toml. File-backed entries get path = "...", but
plugin-backed entries (e.g. name = "superpowers:brainstorming") only get
a name. Codex CLI 0.114's TOML deserializer treats path as required, so
it rejects the plugin entries with "missing field path" and fails
thread/start.
The daemon copies ~/.codex/config.toml verbatim into each task's
isolated codex-home, which propagated those broken entries into the
per-task config and blocked every Codex agent run for affected users.
Strip the whole [[skills.config]] array on copy. Multica writes the
agent's currently assigned skills directly to codex-home/skills/ and
Codex auto-discovers them from there, so the user-level skill registry
is redundant for a per-task run.
Closes#1753
* feat(server): add quick-create issue async task path
Adds POST /api/issues/quick-create which validates the picked agent's
reachability up front (not archived, has runtime, runtime online) then
queues an issue-less agent task whose context JSONB carries the user's
natural-language prompt + requester + workspace. Daemon claim resolves
the workspace from the context, and the prompt builder switches to a
quick-create template instructing the agent to translate the prompt
into a single multica issue create call.
Task completion writes a success inbox item to the requester pointing at
the newly-created issue (located by querying the agent's most recent
issue in the workspace since task start, so we don't depend on agent
stdout shape). Failures write an action_required inbox item carrying the
original prompt + agent id so the frontend can offer "Edit as advanced
form" without losing input.
* feat(views): quick-create issue modal + inbox failure CTA
Adds a streamlined create-issue UI bound to the c shortcut: pick an
agent, type one line, submit. The modal closes immediately and the
agent translates the prompt into a multica issue create call in the
background. Shift+c keeps the legacy advanced form for users who want
every field. The "Advanced" button inside the new modal seeds the
shared issue-draft store with the prompt + picked agent so switching
mid-flow doesn't lose input.
Last-used agent persists per (user, workspace) via a workspace-aware
zustand store so frequent users skip the picker on every open.
Inbox renders quick_create_done items with a status pin to the new
issue and quick_create_failed items with an "Edit as advanced form"
CTA that re-seeds the legacy modal with the original prompt.
ApiError now carries the parsed JSON body so the modal can branch on
the structured agent_unavailable code without parsing the error
message.
* fix(quick-create): execenv injection, claim race, private-agent permission
Addresses GPT-Boy review on #1786:
1. execenv was rendering the assignment-task issue_context.md / runtime
workflow even for quick-create, telling the agent to call
`multica issue get/status/comment add` against an empty IssueID.
Adds QuickCreatePrompt to TaskContextForEnv, plus a quick-create
branch in renderIssueContext + the runtime_config workflow that
instructs the agent to run a single `multica issue create` and
exit, with explicit "do NOT call issue get/status/comment add"
guards.
2. ClaimAgentTask serialized only on issue_id / chat_session_id, so
concurrent quick-creates on the same agent (both NULL on those
columns) ran in parallel — making the success-inbox lookup race
over "most recent issue by this agent". Adds a third OR clause
that treats "all four FKs NULL" as a serialization key for the
same agent, so quick-create tasks on a given agent run one at a
time.
3. QuickCreateIssue handler bypassed the private-agent ownership rule
that validateAssigneePair enforces elsewhere — a user could POST a
private agent_id they didn't own and trigger it. Now routes the
picked agent through validateAssigneePair before the runtime
liveness check.
4. Clarifies the quick-create-store namespacing comment to match the
actual workspace-aware StateStorage convention used by the other
issue stores (per-user is browser-profile-local).
* fix(quick-create): branch Output section + deterministic origin lookup
Addresses GPT-Boy's second-pass review on #1786:
1. The runtime_config.go Output section forced "Final results MUST be
delivered via multica issue comment add" for every non-autopilot
task — quick-create still got this conflicting instruction even
though there's no issue to comment on. Switched the Output block
to a three-way switch so quick-create gets a tailored "stdout is
captured automatically; do NOT call comment add" branch matching
the autopilot variant.
2. Completion lookup was "most recent issue created by this agent
since task.started_at", which races against concurrent issue
creates by the same agent (assignment task running alongside
quick-create when max_concurrent_tasks > 1). Replaced with a
deterministic origin link:
- Migration 060 extends issue.origin_type CHECK to allow
'quick_create'.
- Daemon sets MULTICA_QUICK_CREATE_TASK_ID env var when running a
quick-create task.
- multica issue create CLI reads the env var and stamps the new
issue with origin_type=quick_create + origin_id=<task_id>.
- Server CreateIssue handler accepts (origin_type, origin_id)
from trusted callers (only "quick_create" is allowed; the pair
is rejected unless both fields are provided together).
- notifyQuickCreateCompleted now calls GetIssueByOrigin keyed on
(workspace_id, "quick_create", task.ID) — no more time-window
racing against parallel agent activity.
The old GetRecentIssueByCreatorSince query is removed.
Follow-ups to #1765 review nits:
- Tighten the per-turn prompt and AGENTS.md workflow instructions so
that "exit with no output" only applies when the trigger is from
another agent AND no actual work was produced this turn. If the
agent did real work, the standard "post results as a comment" rule
still applies — a result reply is not a noise comment.
- Add TestAgentExplicitMentionStillTriggers as a positive control
documenting the boundary the structural fix preserves: suppressing
implicit parent-mention inheritance for agent authors does NOT
block deliberate handoffs. An agent that explicitly @mentions
another agent in its own content still enqueues a task for the
mentioned agent and does not self-trigger.
When an agent replied in a thread whose root mentioned another agent,
the reply inherited the parent mention and re-triggered the other agent.
This caused 'No reply needed' ping-pong loops between co-assigned agents.
Structural fix:
- In enqueueMentionedAgentTasks, suppress parent-mention inheritance
when authorType == 'agent'. Explicit @mentions in the agent's own
comment still work for deliberate handoffs.
Defense-in-depth (prompt):
- Strengthen per-turn prompt and AGENTS.md workflow instructions to
explicitly forbid posting 'No reply needed' noise comments.
Regression test:
- TestAgentReplyDoesNotInheritParentMentions covers both the fix
(agent reply does not re-trigger) and the positive control
(member reply still inherits mentions).
Also updates TestBuildPromptCommentTriggeredByAgent to match the
new prompt wording.
* fix(comments): preserve newlines from agent CLI writes
Agents (e.g. Codex) routinely emit `multica issue comment add --content
"para1\n\npara2"` because Python/JSON-style string literals are their
default. Bash does not expand `\n` inside double quotes, so the literal
4-char sequence flowed through the CLI into the database and rendered
as text in the issue panel — comments came out as one wall of prose.
Three coordinated fixes so the platform behavior no longer depends on
whether a given model has strong bash-quoting intuition:
- CLI: decode `\n / \r / \t / \\` in `--content` and `--description` for
`issue create / update / comment add` (callers needing a literal
backslash still have `--content-stdin`).
- Agent prompt: rewrite the comment-add example in the injected runtime
config to require `--content-stdin` + HEREDOC for any multi-line body,
and call out the same rule for `--description`. The previous wording
flagged stdin only for "backticks, quotes", which models read as
irrelevant to plain paragraphs.
- Renderer: add `remark-breaks` to the shared Markdown plugin chain so a
bare `\n` becomes a visible line break instead of a CommonMark soft
break — protects against models that emit single newlines for
formatting.
Tests: pin the new CLI helper, and pin the runtime-config guidance so
the multi-line wording cannot decay back into a footnote.
* fix(comments): address review feedback on newline-rendering PR
- Cover the issue panel: ReadonlyContent (used by every comment card and
the issue description) has its own react-markdown wiring; add
remark-breaks there too so the renderer fix actually applies to the
surface the bug was reported on, not just the chat panel. Pinned by
ReadonlyContent line-break tests.
- Make the prompt's `--description` guidance executable: add
`--description-stdin` to `issue create` / `issue update`, refactor
comment-add to share a single `resolveTextFlag` helper, and have the
injected runtime config name the real flag instead of an imaginary
"stdin / a tempfile" path. Pinned by the runtime-config guidance test.
- Document the unescape contract on each affected flag's help text and
pin the precise boundary in tests: `\n / \r / \t / \\` are decoded;
`\d / \w / \s / \u / \0` and other unrecognised escapes pass through
verbatim, so regex literals and Windows paths survive intact unless
they embed a literal `\n` / `\r` / `\t`. Callers that need the literal
sequence have `--content-stdin` / `--description-stdin` as the escape
hatch.
Merge the two symlink removal branches in exposeSharedCodexPluginCache —
they shared the same os.Remove + recreate path with only the error label
differing. The branch is now keyed off Lstat's ModeSymlink bit, with
Readlink reused only to fast-path an already-correct link. Behaviour is
unchanged; just less duplicated code.
Expose the shared Codex plugin cache inside each per-task CODEX_HOME before launch so plugin-provided skills are available on the first session.
Refresh agent-assigned workspace skills for both newly prepared and reused Codex environments, and cover plugin cache plus reuse behavior with focused execenv tests.
Follow-up to #1686. Locks in two nits flagged during review:
1. agent.Result.Status doc comment now lists "cancelled" alongside the
existing values, so the enum surface matches actual usage.
2. New TestExecuteAndDrain_ContextCancelled_ReportsCancelled exercises
the path added in #1686: when the parent context is cancelled before
the backend produces a Result, executeAndDrain must return
Status="cancelled" (not "timeout"). A regression here would silently
restore the misleading log line we just fixed.
When the server cancels a task (e.g. assignee changes during execution,
explicit user cancel, or workspace_isolation check fail), the daemon's
cancellation poll fires runCancel() on the run context. The drainCtx
derived from runCtx then signals Done(), but executeAndDrain() was
returning Status: "timeout" regardless of *why* the context ended.
The "agent finished status=timeout" log line is then misleading — it
suggests an actual deadline timeout when really the task was cancelled
by upstream. We spent hours misdiagnosing a healthy handoff as a
broken timeout because of this.
Distinguish context.Canceled from context.DeadlineExceeded in
executeAndDrain, and add a "cancelled" case to runTask so the status
propagates through the existing log path.
No behaviour change for genuine timeouts; no behaviour change for
the cancelled-by-poll discard path in handleTask. Only the daemon
log line and TaskResult.Status get the more accurate label.
PR #1632 updated the Pi project-level skill dir from
.pi/agent/skills/ to .pi/skills/, but missed two references:
- server/internal/daemon/execenv/runtime_config.go:20 — the comment
block here lists project-level paths for every other provider, so
using Pi's global path was inconsistent and misleading.
- docs/docs-rewrite-plan.md:88 — planning doc still listed the old
path in the Skills row.
Follow-up to #1632.
* feat(daemon): harden agent mention-loop instructions
Two agents that mention each other via `mention://agent/<id>` can fall into
an infinite reply loop — each says "I'm done" in prose but keeps
`@mentioning` the other, which re-enqueues their run. Adding hard caps on
agent-to-agent turns conflicts with Multica's design principle of giving
agents the same authorship freedom as humans, so this change hardens the
instructions that the harness injects instead.
- Replace the terse "mentions are actions" blurb with a full Mentions
protocol: `side-effecting` warning, explicit "when NOT to mention"
(replying to another agent, sign-offs, thanks) and "when a mention IS
appropriate" (human escalation, first-time delegation, user asked).
- Add a pre-workflow decision step for comment-triggered runs: decide
whether a reply is warranted at all, decide whether to include any
`@mention`, and clarify that the post-a-comment rule is mandatory *if*
you reply — silence is a valid exit for agent-to-agent threads.
- Thread the triggering comment's author kind + display name
(`TriggerAuthorType` / `TriggerAuthorName`) from the claim endpoint
through the daemon task type, per-turn prompt, and CLAUDE.md workflow.
When the author is another agent, both surfaces now name that agent
and warn against sign-off mentions.
- Soften the old closing line that told agents to `always` use the
mention format — the word generalized to member/agent mentions and
encouraged the very behavior that causes loops.
Refs GH#1576, MUL-1323.
* fix(daemon): remove MUST-respond conflict and sanitize trigger author name
Addresses two blocking points on PR #1581:
1. buildCommentPrompt told the agent "You MUST respond to THIS comment"
and unconditionally appended the reply command — directly conflicting
with the new agent-to-agent silence-as-valid-exit workflow. Models
were likely to keep following the older must-reply rule and fall back
into the loop this PR is trying to close.
Rewrite the header as "Focus on THIS comment — do not confuse it
with previous ones" (keeps the anti-stale-comment signal) and change
BuildCommentReplyInstructions to open with "If you decide to reply,
post it by running exactly this command" so the reply command is
available but conditional across both prompt surfaces.
2. Raw agent/user display names were being embedded directly into the
high-priority prompt and CLAUDE.md via TriggerAuthorName. Agent and
member names are only validated as non-empty at write time, so a
name containing newlines, backticks, or fake mention markup would
turn the field into a cross-agent prompt-injection surface.
Add execenv.SanitizePromptField — strip control runes, collapse
whitespace, drop markdown structural characters (backtick, asterisk,
brackets, pipe, angle brackets, hash, backslash), truncate to 64
runes — and apply it at both embed sites (per-turn prompt and
CLAUDE.md). Defense-in-depth at the consumption layer so this works
for already-stored names without a migration.
Tests: TestSanitizePromptField covers the policy; TestBuildPromptSanitizesAgentName
plants an attack payload in TriggerAuthorName and checks the rendered prompt
does not leak the newline-anchored injection or the fake mention markup.
TestBuildPromptCommentTriggered*{,ByMember} updated to lock in the
conditional reply-command framing.
* refactor(daemon): trim redundant CLAUDE.md preamble and drop name sanitizer
Per PR #1581 feedback:
1. Remove the `if ctx.TriggerAuthorType == "agent"` preamble block in
runtime_config.go. It duplicated what workflow steps 4 and 5 already
say ("Decide whether a reply is warranted", "Never @mention the
agent you are replying to as a thank-you or sign-off"), so the
signal lands the same without the extra ~7 lines of CLAUDE.md. The
per-turn prompt preamble in prompt.go stays — that surface has no
numbered workflow below it and would otherwise lose the
silence-as-exit signal.
2. Delete execenv.SanitizePromptField + its test. Workspace agents are
created by trusted team members, so the cross-agent name-injection
surface it defended isn't realistic in the current trust model.
3. Drop TriggerAuthorType/Name from execenv.TaskContextForEnv and stop
populating them in daemon.go — they're no longer read by the
execenv package. The same fields on daemon.Task stay because
prompt.go still needs them to label the triggering author in the
per-turn prompt.
Tests simplified to match the leaner shape: CLAUDE.md regression
guards now assert that the anti-loop phrases live in the numbered
workflow, and the sanitizer-specific tests are removed.
* feat(daemon/gc): tighten GC defaults + flex duration suffix
Driven by user feedback in #1539 (40 GB VPS filling within 24h of heavy
AI-coding usage): the existing TTLs were sized for desktop/laptop
deployments and are too lenient for small-disk, long-running daemons.
- GCTTL: 5d → 24h. Done/canceled issues almost never need a multi-day
grace period in AI-coding workflows.
- GCOrphanTTL: 30d → 72h. Covers crash-leftover and pre-GC directories
without a month-long wait.
- Issue-deleted orphans (API returns 404) are now cleaned on the next GC
cycle regardless of mtime. The issue row is gone; there is nothing
left to protect.
- parseFlexDuration: accept a `d` (day) suffix in addition to the stdlib
time.ParseDuration syntax. MULTICA_GC_TTL=5d now works; previously only
120h was accepted.
* fix(daemon/gc): address review — 404 safety + decimal/overflow in duration parser
Two issues flagged in PR review:
1. 404-immediate-clean is unsafe. The /gc-check endpoint returns 404 for
both "issue deleted" AND "daemon token has no access to the workspace"
(anti-enumeration, see requireDaemonWorkspaceAccess). Clean-on-404
would let a scoped-down daemon token wipe taskDirs whose issues are
still live. Restore the mtime gate against GCOrphanTTL. With the new
72h default we still shrink the original 30d window dramatically
without the cross-workspace hazard. Lock the behavior in with a new
test that asserts a recent 404 is skipped.
2. parseFlexDuration mishandled decimals and swallowed Atoi errors:
"0.5d" → 7m12s (regex matched only the "5d"), "1.5d" → 1h7m12s,
and 20+ digit day values Atoi-errored silently to 0. Match the full
decimal number with `\d*\.\d+|\d+` and parse with ParseFloat so
fractional days and oversized inputs both go through
time.ParseDuration correctly — fractions as sub-hour durations,
overflow as a returned error.
Review follow-up on PR #1557: the server-side change started returning
500 when the store write failed, but the daemon's handleLocalSkillList /
handleLocalSkillImport were discarding the ReportLocalSkill*Result error
return. Net effect was a silent drop — the daemon moved on, the request
stayed in "running" on the server, and the user saw the same "daemon did
not respond within 30 seconds" timeout the store refactor was supposed
to kill.
Fix: route both report calls through reportLocalSkillResultWithRetry,
which retries on 5xx + network errors with 0 / 0.5s / 2s / 4s backoff
(total ~6.5s, well inside the 60s server-side running timeout), stops
on 4xx (request expired / cross-workspace rejection — retry won't help),
bails on context cancel, and logs Error on exhaustion so ops has a
footprint to grep for.
Tests (server/internal/daemon/local_skill_report_test.go, 6 new cases):
- 500 twice then success -> 3 attempts, second retry lands
- 404 -> exactly 1 attempt (permanent, no retry)
- import 502 then success -> 2 attempts
- All-500 -> burns through all backoff slots then gives up with ERROR log
- Context cancel mid-backoff -> exactly 1 attempt, cancellation logged
- Smoke: report paths hit /api/daemon/runtimes/<rt>/local-skills{,import}/<req>/result
localSkillReportBackoffs is var-assignable so tests can swap in zero-delay
schedules without paying real sleep latency.
* feat(runtimes): remove Test Connection / runtime ping feature
The Test Connection action invoked a real single-turn agent run to verify
runtime connectivity. In practice it was expensive (reuses none of the
normal task exec env, so it also gave misleading results) and low value —
daemon heartbeat + Online status already covers the "is the runtime
alive" question. Dropping the whole end-to-end probe path:
- deletes server handler and in-memory PingStore
- drops pending_ping from the heartbeat response and daemon poll loop
- removes daemon.handlePing, PendingPing, ReportPingResult
- removes the CLI `multica runtime ping` command
- removes the PingSection UI block and RuntimePing types / api methods
* docs: fix runtime CLI subcommand list in product-overview
* fix: pass model to Hermes ACP session/new and add hermes to InjectRuntimeConfig
- hermes.go: include opts.Model in session/new params so Hermes uses
the configured model instead of its default (fixes local LLM failures)
- runtime_config.go: add "hermes" to the AGENTS.md provider list so
Hermes receives the Multica runtime instructions and skill discovery
Fixes: https://github.com/multica-ai/multica/issues/1195
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(hermes): drop false native-skill claim and add regression tests
The previous change added 'hermes' to the 'skills discovered automatically'
branch of buildMetaSkillContent, but resolveSkillsDir has no Hermes case so
skills still land in the .agent_context/skills/ fallback. AGENTS.md ended up
claiming native discovery while the files were somewhere else, which would
mislead Hermes (and future debuggers).
- Move 'hermes' to the fallback branch alongside 'gemini' so AGENTS.md points
Hermes at .agent_context/skills/ — matching where writeContextFiles actually
writes them.
- Extract buildHermesSessionParams so the session/new payload is unit-testable.
- Add regression tests covering:
* buildHermesSessionParams includes/omits 'model' correctly
* InjectRuntimeConfig('hermes') writes AGENTS.md with the fallback hint
* writeContextFiles('hermes') writes skills to .agent_context/skills/
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: CC-Girl <cc-girl@multica.ai>
* fix(skills): unify Add Skill UX + surface every local skill with real file count
Iterating on the local-skill import flow that just landed. Three fixes
shipped together because they all surfaced while testing the same code
path on the Skills page.
UX — fold runtime import into the existing "+ Add Skill" dialog
- Drop the standalone HardDrive icon button + the empty-state
"Import From Runtime" buttons. Adding a skill is now a single entry
point: the "+" header button (or empty-state button) opens one dialog
with three tabs: Create / Import URL / From Runtime.
- Extract the runtime-import body into RuntimeLocalSkillImportPanel so
it can mount inline as a tab. The standalone Dialog wrapper stays for
the per-runtime "Import this skill" flow on the agent skills tab,
which preselects runtime + skill and benefits from its own modal.
- Cap the dialog at max-h-[85vh] with a scrollable tabs body so the
From-Runtime tab (runtime selector + skill list + name/description
form) no longer overflows the screen on shorter displays.
- Filter the runtime selector to runtimes the caller owns. Other users'
runtimes were listed but the import endpoint rejects them anyway,
matching the Runtimes page's "Mine" default.
- The selected-runtime label in the trigger now shows the runtime name
(`Claude (MacBook-Air.local) (claude)`) instead of the raw UUID — the
shadcn SelectValue needs explicit children when items don't render
the bare value as their label.
- Drop the placeholder Sparkles icon to the left of the skill name /
description inputs in the detail header — it was decorative noise.
Daemon — surface every installed local skill and report the right count
- listRuntimeLocalSkills used filepath.WalkDir, which silently dropped
every symlinked skill via the os.ModeSymlink early return. Skill
installers like lark-cli ship every skill at ~/.agents/skills/<name>
and symlink each one into ~/.claude/skills/, so users with dozens of
skills only saw the few they had cloned in place. Switch to ReadDir
+ os.Stat (which follows symlinks) on the runtime root.
- collectLocalSkillFiles also failed for symlinked skill dirs because
filepath.WalkDir does not descend into a symlinked root, so every
such skill reported 0 files. Resolve the skill dir via EvalSymlinks
before walking.
- Bundle file count purposely excludes SKILL.md (it travels in the
bundle's `Content` field to avoid duplication on import). The summary
now adds 1 back so the user-facing count matches the real file total
— every skill has SKILL.md, we just required it to be parseable.
Tests
- New TestListRuntimeLocalSkills_FollowsSymlinkedSkillDirs seeds a
shared installer dir, symlinks one skill into the runtime root, and
asserts both regular and symlinked skills come back with the right
source path (~/.claude/...) and metadata.
- TestListRuntimeLocalSkills_Claude updated to expect file_count = 2
(one supporting file + SKILL.md) and a comment explains the +1 split.
* test(skills): drive new Add Skill dialog flow in skills-page test
Old test asserted the standalone "Import From Runtime" button. The PR
folded that into the unified "+ Add skill" dialog as the third tab, so
the test now opens the dialog, switches to the "From Runtime" tab, and
asserts the same end state.
Also stub useAuthStore so the runtime panel's "Mine"-only filter sees
the seeded runtime owner (user-1).
* fix(daemon): list nested skills, not just depth-1 entries
Per #1480 review (MUL-1246): switching listRuntimeLocalSkills from
filepath.WalkDir to flat ReadDir lost coverage for nested skill
layouts. opencode stores skills as e.g. `release/reporter/SKILL.md`,
and loadRuntimeLocalSkillBundle accepts that slash-delimited key, so
the import dialog could no longer surface skills the load endpoint
was perfectly happy to fetch.
Replace the flat ReadDir with a recursive enumerator that:
- Follows symlinks at every level (so installer-style symlinked skill
trees still work — that was the original reason for moving off
WalkDir).
- Short-circuits at every SKILL.md: a directory that qualifies as a
skill is registered, and its children are NOT scanned for further
skills. Stale nested SKILL.md files inside a parent skill's bundle
stay part of that bundle.
- Caps recursion at maxLocalSkillDirDepth=4 (covers opencode's depth=2
with headroom) and tracks visited resolved paths so a cyclic symlink
can't loop forever.
New regression test seeds both a top-level skill (with a decoy
SKILL.md inside its templates dir) and a depth-2 nested skill, and
asserts the walker registers exactly two keys — "top" and
"release/reporter" — with the inner templates SKILL.md correctly
ignored.
* feat: identify clients via X-Client-Platform/Version/OS
Adds client identification headers (and matching WS query params) across
all first-party clients so the server can split logs/metrics/gating by
caller without parsing User-Agent.
- HTTP: X-Client-Platform, X-Client-Version, X-Client-OS
- WS: client_platform, client_version, client_os query params
- Platform ∈ {web, desktop, cli, daemon}; OS ∈ {macos, windows, linux}
Wired through the shared TS ApiClient/WSClient via a new identity option
on CoreProvider. Web reads its version from package.json/env; Desktop
captures version + OS synchronously in preload via sendSync IPC. Go CLI
and daemon clients populate the same headers using runtime.GOOS
(normalized darwin → macos).
Server-side adds a ClientMetadata middleware that stashes the headers in
request context; the request logger and logger.RequestAttrs surface them
on every access log and handler-level log. Realtime hub logs the same
fields on websocket connect.
CORS allowlist extended for the new headers.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* test: address client-identity PR nits
- Memoize the CoreProvider identity object on Web and Desktop, and key
WSProvider's effect on identity primitives instead of the object
reference, so unrelated parent re-renders no longer tear down and
reconnect the WebSocket.
- Add direct header-injection tests for the CLI and daemon Go HTTP
clients (X-Client-Platform/Version/OS) and a normalizeGOOS unit test
on both packages.
- Add a TS test for WSClient that asserts client_platform/client_version/
client_os land on the upgrade URL and never leak the auth token.
- Add a hub test that dials the WS endpoint with client_* query params
and asserts the "websocket connected" log entry surfaces them as
structured attributes.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat(server): orphan-task recovery + auto-retry + manual rerun (MUL-1128)
When the daemon process crashed mid-task the issue was stuck at
in_progress for up to 2.5h: the in-flight task timeout was the only
mechanism that ever moved the row, and the runtime heartbeat sweeper
only fires after the runtime stays offline for 45s — a quick restart
beats both windows.
This change implements the A+B plan from the issue thread:
A. lifecycle hygiene
- migration 055 adds attempt / max_attempts / parent_task_id /
failure_reason / last_heartbeat_at to agent_task_queue
- new daemon-auth endpoint POST /runtimes/{id}/recover-orphans:
daemon calls it on every register so the server fails any
dispatched/running tasks the previous process left behind
- new daemon-auth endpoint POST /tasks/{id}/session: persists the
agent's session_id + work_dir mid-flight so a crash doesn't
lose the resume pointer (claude+codex emit MessageStatus with
SessionID; daemon forwards on the first one it sees)
- FailAgentTask / FailStaleTasks / FailTasksForOfflineRuntimes
now set failure_reason ('agent_error' / 'timeout' /
'runtime_offline')
B. auto-retry with resume context
- TaskService.MaybeRetryFailedTask spawns a fresh queued attempt
carrying parent's session_id/work_dir when the failure reason
is infrastructure-shaped (timeout, runtime_offline,
runtime_recovery) and attempt < max_attempts; skips autopilot
- wired into the runtime sweeper paths and TaskService.FailTask
so the user transparently sees a new in_progress run instead of
a stuck row
- new user-auth POST /api/issues/{id}/rerun + multica issue rerun
CLI for the manual escape hatch
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(server): address PR review for orphan-task recovery (MUL-1128)
Three review-must-fix items on top of the A+B implementation:
1. recover-orphans now funnels through TaskService.HandleFailedTasks,
the same shared post-failure pipeline used by the runtime sweeper.
This guarantees task:failed events are emitted, agent status is
reconciled, and issues stuck in_progress with no remaining active
task are reset to todo even when no auto-retry is created
(max_attempts exhausted, autopilot, non-retryable reason).
2. RerunIssue now uses CancelAgentTasksByIssueAndAgent, scoped to the
issue's current assignee. The previous implementation called
CancelAgentTasksByIssue, which would collateral-cancel parallel
@-mention agents on the same issue.
3. GetLastTaskSession now considers both completed and failed tasks
(mirroring GetLastChatTaskSession), ordering by the most recent
timestamp. With UpdateAgentTaskSession pinning session_id/work_dir
mid-flight, an auto-retry or manual rerun of a daemon-crash failure
now actually resumes the prior conversation context instead of
starting fresh — matching the stated B-branch behaviour.
go build / go vet pass; the existing service and agent test suites pass.
runtime_sweeper / handler integration tests require a local DB with the
055 migration (and the pre-existing 050 first_executed_at column).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* fix(cli): detach daemon from parent console on Windows
CREATE_NEW_PROCESS_GROUP alone leaves the daemon attached to the
parent console, so closing the launching cmd/PowerShell window fires
CTRL_CLOSE_EVENT down the inherited console and takes the daemon
with it. Add DETACHED_PROCESS so the child has no console at all;
stdout/stderr are already redirected to the log file before spawn.
* fix(cli): make `multica update` work while the binary is running on Windows
On Windows, a running .exe is opened without FILE_SHARE_WRITE, so the
previous os.Rename(tmp, exe) always failed with "Access is denied" —
every `multica update` on Windows hit this, because the CLI is
updating its own running binary.
Windows does allow renaming the running .exe (just not overwriting
it), so the new Windows-only replaceBinary moves the running binary
to `.old` first, installs the new one, and restores the original if
installation fails. A best-effort CleanupStaleUpdateArtifacts runs
at CLI/daemon startup to reclaim the leftover `.old` file once the
old process has exited.
Unix keeps the plain rename-over semantics (the old inode stays valid
for the running process).
* fix(cli): stop daemon via HTTP /shutdown instead of console ctrl events
With DETACHED_PROCESS the Windows daemon shares no console with the
stop caller, so `GenerateConsoleCtrlEvent(CTRL_BREAK_EVENT, pid)`
silently never reaches it — the old code would report "stop sent"
while the daemon kept running. Replace the platform-specific
stopDaemonProcess with a cross-platform POST to the daemon's HTTP
/shutdown endpoint, which cancels the same top-level context the
self-restart path already uses. Fall back to `process.Kill()` if
the HTTP call fails.
Also drops the now-unused stopDaemonProcess / CTRL_BREAK_EVENT
wiring, adds handler tests, and updates the DETACHED_PROCESS comment.
Phase 0 hotfix for the cross-workspace contamination reported in MUL-1027
/ #1235: an agent running for workspace A ended up commenting on (and
renaming) a two-day-old issue in workspace B.
#1249/#1259 fixed resolution for autopilot tasks and consolidated the
task-workspace resolver, and #1294 populated workspace_id in the claim
response for run_only autopilot tasks. Those closed the known fallthroughs
but the failure mode is still broader: whenever the daemon or server fails
to supply a workspace, the CLI silently falls back to
`~/.multica/config.json`, which is user-global, not workspace-scoped. On a
host running daemons for multiple workspaces, a single gap in workspace
propagation is enough to leak writes across workspaces.
This PR adds three coordinated guards so no single layer's bug can cause a
cross-workspace write:
1. `server/cmd/multica/cmd_agent.go` — `resolveWorkspaceID` detects the
agent execution context (`MULTICA_AGENT_ID` / `MULTICA_TASK_ID` env,
both daemon-only markers) and in that context refuses to fall back to
the user-global CLI config. Human / script usage (no agent env) is
unchanged: flag → env → config fallback chain still applies.
2. `server/internal/handler/daemon.go` — `ClaimTaskByRuntime` now
captures the runtime's workspace from `requireDaemonRuntimeAccess` and
enforces `resolved_task_workspace == runtime_workspace` after the
existing issue/chat/autopilot branches. On mismatch or empty, the
handler explicitly cancels the just-dispatched task (via
`TaskService.CancelTask`, which also reconciles agent status) and
returns 500. Without the explicit cancel, `ClaimTaskForRuntime` had
already transitioned the task to 'dispatched' and the agent status to
'working', so a plain 500 would leave both stuck for the ~5 min
stale-task sweep window.
3. `server/internal/daemon/daemon.go` — `runTask` refuses to spawn the
agent when `task.WorkspaceID` is empty (defense-in-depth against
server bugs and reused workdirs).
Tests:
- `cmd/multica/cmd_agent_test.go`:
`TestResolveWorkspaceID_AgentContextSkipsConfig` — five subtests
covering the full fallback matrix (outside agent context still reads
config; agent context uses env; agent context with empty env returns
empty; task-id-only marker also counts; requireWorkspaceID surfaces the
agent-context error message).
- `internal/handler/daemon_test.go`:
`TestClaimTaskByRuntime_TaskWorkspaceMismatch_CancelsAndRejects` —
constructs a data-inconsistent task (runtime_id in workspace A,
issue_id in workspace B) and asserts the handler returns 500 AND
leaves the task in 'cancelled' state (not 'dispatched').
Phase 1/2 follow-ups (prompt injection of workspace slug, session lookup
workspace filter, cross-workspace audit of agent-facing endpoints,
observability) are out of scope for this PR and tracked separately.
* feat(agent): add Kimi CLI as agent runtime
Adds support for Moonshot AI's Kimi Code CLI (https://github.com/MoonshotAI/kimi-cli)
as a new agent runtime, alongside Claude, Codex, OpenCode, OpenClaw, Hermes,
Gemini, Pi, Cursor and Copilot.
Kimi Code CLI implements the standard Agent Client Protocol (ACP) via the
`kimi acp` subcommand, so the new `kimiBackend` reuses the existing
hermesClient JSON-RPC transport in the agent package — only the binary,
client identity, log prefix, and tool-name extraction differ.
Wiring:
- server/pkg/agent: new kimiBackend + kimi_test.go; registered in New(),
LaunchHeader map, and the supported-types coverage test.
- server/internal/daemon/config.go: probes `kimi` (overridable via
MULTICA_KIMI_PATH / MULTICA_KIMI_MODEL).
- server/internal/daemon/execenv: writes AGENTS.md as the runtime context
file (Kimi reads AGENTS.md natively via /init), and writes skills under
`.kimi/skills/` so they are auto-discovered by the project-level skill
loader.
- packages/views/runtimes: ProviderLogo gains a Kimi mark.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* feat(agent/kimi): support per-agent model selection via ACP set_model
Wire Kimi into the model dropdown introduced in #1399:
- ListModels gets a 'kimi' case that drives the same ACP
initialize + session/new handshake as Hermes; both share a new
discoverACPModels helper and parseACPSessionNewModels parser
so future ACP backends only need a small provider entry.
- kimiBackend now issues session/set_model after session/new when
opts.Model is non-empty, mirroring the Hermes flow. Failures
fail the task instead of silently falling back to Kimi's
default model — silent fallback would hide that the dropdown
pick wasn't honoured.
Verified: go build ./..., go test ./pkg/agent/... ./internal/daemon/... ./internal/handler/..., pnpm typecheck and pnpm test (138 passed).
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
* refactor(agent): address code review feedback on Kimi runtime
- Share ACP provider-error sniffer between hermes and kimi. Previously
only hermes promoted stderr-observed 4xx/5xx into a failed task;
kimi would report "completed + empty output" when the Moonshot
upstream rejected a request (expired token, rate limit, …). Rename
hermesProviderErrorSniffer → acpProviderErrorSniffer and parameterise
the provider name; wire it into kimiBackend.Execute the same way.
- Rename extractHermesSessionID → extractACPSessionID (shared by all
ACP backends) so the name matches parseACPSessionNewModels.
- Drop the redundant second argument to kimiToolNameFromTitle; the
Message struct has only one relevant field (Tool), so passing it
twice was a dead fallback. Document that the function normalises
residual capitalised kimi titles not caught by hermesToolNameFromTitle.
- Remove kimi-only cmd.WaitDelay override; the hermes baseline is
fine for both and divergence adds noise.
- Add TestKimiBackendSetModelFailureFailsTask: fake `kimi acp` binary
that returns a JSON-RPC error for session/set_model, asserts that
the task result surfaces status=failed with the model name + upstream
message and preserves the session id.
- Fix stale agent listings in agent.go / daemon/config.go doc comments
(missing cursor, gemini, copilot).
All: `go build ./...`, `go vet ./...`, `go test ./pkg/agent/...
./internal/daemon/... ./internal/handler/...` green.
* fix(agent/kimi): pass --yolo so Shell tools don't hang on approval
Kimi's default config has `default_yolo = false`. Every Shell/file-mutating
tool call causes kimi acp to send a `session/request_permission` request
and block (up to 300s) waiting for a response. The daemon's hermesClient
only handles `session/update` notifications — permission requests go
unanswered, the tool call times out, and the UI loop eventually dies
("UI loop timed out"). Observed with the first real kimi task: agent sat
as Live for ~7 minutes before the daemon killed it.
The fix mirrors hermes' HERMES_YOLO_MODE=1 override: pass `--yolo` to
`kimi` so it auto-approves everything. `--yolo` is a top-level flag on
the `kimi` CLI (not a flag on `kimi acp`), so it must come before the
`acp` subcommand in argv. Added to kimiBlockedArgs so user custom_args
can't strip it.
While here, fix a related bug that made kimi tool names show up empty
in the daemon log ("tool #1: "): hermesToolNameFromTitle's fallback
returned `kind` when neither title-with-colon nor kind matched a known
tool. Kimi's ACP `tool_call` emits bare titles like "Shell" or "Read
file" with no `kind` at all, so we'd drop the title on the floor before
kimiToolNameFromTitle ever got a chance to map it. Now: preserve the
title when kind is unclassified; hermes titles always carry a colon so
this branch never fires for hermes.
Tests:
- TestKimiBackendPassesYoloFlag — fake binary that records its argv,
asserts --yolo comes before acp.
- TestHermesToolNameFromTitle rows for bare kimi-style titles.
- Existing suite green: go build, go vet, full pkg/agent + daemon +
handler test packages.
* fix(agent/acp): auto-approve session/request_permission from agent
The previous attempt (`kimi --yolo acp`) was a no-op. Inspected the
kimi-cli source: the `acp` Typer subcommand takes no parameters, so
flags on the root `kimi` command are dropped before `acp_main()` runs
— it's impossible to opt into YOLO mode through CLI flags for ACP.
The real fix is on our side: respond to session/request_permission.
ACP is bidirectional. When kimi runs a Shell or file-write tool, it
sends `session/request_permission` (agent → client, JSON-RPC request
with id + method) and waits up to 300s for a response. Our existing
hermesClient.handleLine only dispatched: (id + result/error) →
handleResponse, and (no id + method) → handleNotification. A request
with BOTH id and method fell through and got silently dropped — kimi
timed out, UI loop died, task sat stuck for 7 minutes.
Add handleAgentRequest: for session/request_permission, echo the id
and respond with outcome=selected, optionId=approve_for_session. The
daemon is headless; there's no user to prompt. `approve_for_session`
lets the agent remember the action so subsequent identical calls
(every Shell, every file write) skip the round-trip entirely. For any
other agent → client method, reply with standard -32601 method-not-
found so the agent doesn't block.
Also:
- Add writeMu so request() (main goroutine) and handleAgentRequest
(reader goroutine) don't interleave JSON frames on stdin.
- Revert the `--yolo acp` flag — it's a no-op, and carrying it in
kimiBlockedArgs gives the wrong impression that it does something.
Comment in kimi.go now points at handleAgentRequest as the real fix.
Tests:
- TestHermesClientAutoApprovesPermissionRequest: inject a
session/request_permission, assert the reply echoes the id and
carries {outcome: selected, optionId: approve_for_session}.
- TestHermesClientReplesMethodNotFoundForUnknownAgentRequest: confirm
unknown agent → client methods get JSON-RPC -32601 instead of silence.
- TestKimiBackendInvokesACPSubcommand replaces the yolo-flag assertion
with a negative assertion: no dead --yolo / --auto-approve / -y on
argv, since they'd pretend to do something they can't.
All: go build ./..., go vet ./..., go test ./pkg/agent/... green.
* fix(agent/acp): surface kimi tool input/output via content blocks
Kimi-cli emits tool_call and tool_call_update ACP frames with the
input/output inside a `content` array of ContentToolCallContent
blocks (shape: {type:"content", content:{type:"text", text:"..."}}),
not in the hermes-style `rawInput` map / `rawOutput` string. Our
parser only looked at rawInput/rawOutput, so the daemon recorded
empty Input and Output for every kimi tool — the execution-history
UI showed blank terminal panels even for commands that ran fine.
Add extractACPToolCallText() and a fallback in handleToolCallStart /
handleToolCallUpdate: when rawInput is nil / rawOutput is empty, pull
the text out of the content blocks. rawInput / rawOutput still take
precedence so hermes' behaviour is untouched. Terminal /
FileEditToolCallContent blocks are skipped (we have nothing to render
them as — kimi only emits TerminalToolCallContent when the client
advertises terminal capability, which we don't).
Tests:
- TestHermesClientHandleToolCallStartKimiContent — content array →
Input.text populated.
- TestHermesClientHandleToolCallCompleteKimiContent — multi-block
content → Output concatenated with newline separator.
- TestHermesClientHandleToolCallRawOutputTakesPrecedence — hermes
rawOutput still wins when both are present.
- TestExtractACPToolCallText — unit coverage for the helper
(single/multiple text blocks, terminal-block skip, empty input).
* fix(agent/acp): buffer streaming tool args so Input isn't empty in UI
kimi-cli streams tool args token-by-token via tool_call_update frames
— the initial tool_call carries an empty content block and each
subsequent in_progress update carries the cumulative JSON so far
(`{`, `{"comma`, `{"command": "echo`, …). The final completed update
then carries the tool's stdout, not the args. Observed per kimi-cli
acp/session.py::_send_tool_call{,_part,_result} and confirmed by
driving a real Shell call end-to-end: 10 in_progress frames, last
with `{"command": "echo hello world"}`, then completed with `hello
world\n`.
Our previous handleToolCallStart emitted MessageToolUse on the first
tool_call frame, capturing the empty content — so every kimi tool
appeared in the execution-history UI with a blank input. Output was
correct (fix 4335c198) but command was missing.
Changes:
- hermesClient now tracks pending tool calls per toolCallId. Hermes
path is unchanged — rawInput is present at tool_call time, so
emit-immediately-then-flag-emitted still fires on the initial frame.
- kimi path defers MessageToolUse until status=completed / failed.
tool_call_update in_progress frames update the buffered argsText
(cumulative, so overwrite); on completion we parse the accumulated
JSON into Message.Input. Malformed JSON falls back to `{"text": …}`
so non-JSON tool args still render.
- Orphan completion frames (no matching tool_call seen — e.g. daemon
restarted mid-task) synthesise ToolUse from the update's own
title/kind/rawInput so the UI still gets a header.
- extractACPToolCallText now also renders FileEditToolCallContent
blocks as a compact header ("--- path / +++ path / (edited: N → M
bytes)"). kimi emits these for Write / StrReplaceFile / Patch when
the tool's display block is a DiffDisplayBlock.
Tests:
- TestHermesClientKimiStreamingToolCall: empty tool_call + 5 streaming
in_progress + completed. Asserts no emission until complete, then
[ToolUse(Input.command="echo hi"), ToolResult(Output="hi\n")].
- TestHermesClientKimiMalformedArgsFallback: non-JSON argsText → falls
back to Input.text.
- TestHermesClientHandleToolCallCompleteOrphan: completed frame
without a start → ToolUse synthesised from update's rawInput.
- TestExtractACPToolCallText: diff + new-file-diff cases.
All agent / daemon / handler test packages green.
---------
Co-authored-by: Eve <8b0578a3-cf72-4394-9e38-b328eca92463@users.noreply.multica.ai>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Eve <eve@multica.ai>
Co-authored-by: Lambda <f252c2c5-7d1d-4f3c-b394-a61abfe673fc@users.noreply.multica.ai>
Adds a first-class `model` field on agents so users can pick the LLM model from the create / settings UI instead of editing `custom_env` / `custom_args`. Each provider's dropdown is populated from the live CLI when possible (`opencode models`, `pi --list-models`, `openclaw agents list --json`, `cursor-agent --list-models`, hermes ACP `session/new` → `SessionModelState`), with a static catalog for providers that don't enumerate.
Daemon resolves the runtime model as `agent.model → MULTICA_<PROVIDER>_MODEL → ""` — empty passes through so each backend's CLI picks its own default, avoiding static-guess drift.
Per-provider honouring:
- Claude / Codex / OpenCode / Cursor / Gemini / Pi / Copilot — CLI `--model` / thread payload.
- OpenClaw — `opts.Model` is mapped to `--agent <name>` (the CLI rejects `--model`).
- Hermes — `session/set_model` ACP RPC; stderr is sniffed for provider-level errors so HTTP 4xx from the configured LLM surfaces instead of "empty output"; explicit-model failures mark the task `failed`.
Supporting changes: migration 050 adds `agent.model`; daemon ↔ server heartbeat piggyback carries a model-discovery request; new REST endpoints under `/api/runtimes/{id}/models`; `multica agent create --model` / `update --model`; shared `ModelDropdown` in `packages/views/agents` (searchable, creatable, provider-grouped, default-badge, runtime-supported gate).
Agents were silently finishing tasks without ever posting results to the
issue — their final reply stayed in terminal/log output only. See MUL-1124.
Root cause: the injected CLAUDE.md / AGENTS.md put "post a comment with
results" inside the body of step 4 (a nested clause in the default workflow
description), so skill-driven flows jumped straight from "do the work" to
`status in_review`.
- Hoist posting the result comment into its own explicit, numbered step in
both assignment-triggered and comment-triggered workflows, with the exact
`multica issue comment add` invocation inlined.
- Add a hard warning at the top of the Output section that terminal / chat
text is never delivered to the user.
- Add regression test covering both workflow branches.
* fix(agent/comments): re-emit trigger comment id every turn + server-side parent_id guard
Resumed Claude sessions keep prior turns' tool calls in context, so a
comment-triggered task could reuse the PREVIOUS turn's --parent UUID
instead of the current trigger's. The reply landed in the wrong thread
(MUL-1125): backend stored exactly what the agent sent, but the agent
pulled a stale UUID from its own conversation memory.
Two layers of defense:
1. Extract BuildCommentReplyInstructions so daemon.buildCommentPrompt
and execenv.InjectRuntimeConfig emit the same "use this exact
--parent, do not reuse values from previous turns" block. The
per-turn prompt now carries the current TriggerCommentID, which it
previously relied on CLAUDE.md for (and CLAUDE.md isn't re-read
mid-session).
2. Handler-side guard in CreateComment: when an agent posts from inside
a comment-triggered task (X-Agent-ID + X-Task-ID, task has
TriggerCommentID), require parent_id == task.TriggerCommentID or
return 409. Assignment-triggered tasks are untouched.
* fix(agent/comments): scope parent_id guard to the task's own issue
Two issues from CI + GPT-Boy's review:
1. Guard was too broad: the CLI stamps X-Task-ID on every request, so an
agent legitimately commenting on a different issue while its current
task was comment-triggered would get 409'd with the wrong issue's
trigger comment id. Narrow the guard to fire only when the request's
issue matches the task's own issue — cross-issue agent activity
stays unblocked.
2. The integration test tried to insert a second queued task for the
same (agent, issue), which hits the idx_one_pending_task_per_issue_agent
unique index. Replace the assignment-triggered-task sub-case with a
cross-issue regression test (the scenario we now need to cover anyway):
post on issue B while X-Task-ID points at a comment-triggered task on
issue A, expect 201.
Fixes#1332.
Two regressions introduced in #910 (2026-04-14, "OpenClaw backend P0+P1
improvements") that together block all openclaw users:
1. `openclaw agent` does not accept `--model` or `--system-prompt`, so
any agent configured with a Model field crashed in ~700ms with
`exit status 1`. Remove both forwards, and add them to
openclawBlockedArgs so custom_args can't reintroduce the crash.
Model is bound at registration time via `openclaw agents
add/update --model`.
2. AgentInstructions were written to `{workDir}/AGENTS.md` by
execenv.InjectRuntimeConfig, but openclaw loads bootstrap files
from its own workspace dir — the file was never read, so every
agent's Instructions field was silently discarded. Populate
opts.SystemPrompt for the openclaw provider in runTask and
prepend it to the `--message` payload in the backend so the
model actually receives the instructions.
Other providers surface instructions through their native runtime
config file (CLAUDE.md / AGENTS.md / GEMINI.md) and are intentionally
left unchanged to avoid double injection.
Extract buildOpenclawArgs so arg construction is directly testable;
add unit tests covering the removed flags, the SystemPrompt prepend,
and custom_args filtering.
