- Add creator ownership verification on chat session endpoints (get, archive, send, list messages)
- Add CancelTaskByUser handler with ownership check instead of unrestricted CancelTask
- Show user messages optimistically before server response
- Remove unused streamingContent from chat store and sendMessage mutation import
- Make QueryProvider devtools flag a prop instead of reading process.env in core package
- Add proper FK constraint on chat_session.creator_id → user(id)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add `multica project` CLI commands (list, get, create, update, delete,
status) so agents can manage projects. Also add --project flag to
`issue create` and `issue update` for associating issues with projects.
When a user has multiple workspaces but no default configured,
`agent list` and `issue list` would fail with a cryptic server-side
"workspace_id is required" error. Now the CLI validates early and
suggests using --workspace-id, MULTICA_WORKSPACE_ID env, or
`multica config set workspace_id`.
Closes#532
Implement the Master Agent chat feature allowing users to chat with agents
directly from a floating window, separate from the issue-based workflow.
Backend:
- New chat_session and chat_message tables (migration 033)
- Make issue_id nullable on agent_task_queue for chat tasks
- REST API: create/list/get/archive sessions, send/list messages
- EnqueueChatTask in TaskService with session_id persistence
- WS events: chat:message, chat:done
- Daemon: chat task type with separate prompt builder
- ClaimTaskByRuntime populates chat context (session, message, repos)
Frontend:
- ChatSession/ChatMessage types + API client methods
- core/chat: TanStack Query options, mutations with optimistic updates, WS updaters
- features/chat: Zustand store, ChatFab (floating button), ChatWindow with
real-time streaming via task:message events
- Mounted in dashboard layout (bottom-right corner)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add owner_id to agent_runtime table to track who registered each runtime.
Backend: new delete endpoint with role-based permissions (owner/admin can
delete any, members only their own), list filtering by owner (?owner=me),
and agent dependency check before deletion.
Frontend: Mine/All filter toggle in runtime list, owner display in list
items and detail view, delete button with AlertDialog confirmation.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(search): implement full-text search for issues
Add pg_bigm-based full-text search across issue titles and descriptions,
with API endpoint, CLI subcommand, and web Cmd+K search dialog.
- Migration 032: pg_bigm extension + GIN indexes on title/description
- Server: GET /api/issues/search?q=... with pagination and total count
- CLI: `multica issue search <query>` with table/json output
- Web: Cmd+K command palette using cmdk, with debounced search
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(search): address review feedback on search implementation
1. Escape LIKE special characters (%, _, \) in handler to prevent
matching anomalies from user input.
2. Wire AbortController signal into searchIssues fetch so in-flight
requests are actually cancelled on new input.
3. Fix offset=0 falsy check — use !== undefined instead of truthiness.
4. Merge results + count into single query using COUNT(*) OVER()
window function, eliminating the duplicate DB round-trip.
5. Exclude done/cancelled issues by default; add include_closed
parameter to API, CLI (--include-closed), and web client.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(search): default web search to include all statuses
Pass include_closed: true in the web Cmd+K search so results include
done and cancelled issues by default, matching the reviewer's request.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(search): add comment search with snippet extraction
Extend search to cover issue comments in addition to title/description.
Results are deduplicated at the issue level, with match_source and
matched_snippet fields indicating where and what matched.
- Migration 033: pg_bigm GIN index on comment.content
- SQL: EXISTS subquery for comment matching, correlated subquery for
snippet extraction, 3-tier ranking (title > description > comment)
- Server: SearchIssueResponse with match_source and matched_snippet
- Web: show comment icon + snippet below issue title when matched
- CLI: MATCH column shows source and truncated snippet
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(search): redesign search dialog to match Linear's spacious style
- Widen dialog from sm (384px) to xl (576px) with top-20% positioning
- Larger search input with icon, generous padding, and ESC hint
- Use cmdk primitives directly for full style control
- Taller result list (400px / 50vh), spacious result items (py-2.5)
- Rounded-lg items with accent highlight on selection
- Cleaner border separator between input and results
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(issues): add sub-issue support
- Backend: Add ListChildIssues SQL query, add parent_issue_id to UpdateIssue,
add GET /api/issues/{id}/children endpoint
- Frontend: Display parent issue breadcrumb and link in issue detail sidebar,
show child issues list with status icons, add "Create sub-issue" action in
dropdown menu and sidebar, pass parent_issue_id through create issue modal
- Update test mocks for new API method
* fix(issues): add parent validation, cycle detection, and improve child refresh
- CreateIssue: validate parent issue exists in the same workspace
- UpdateIssue: validate parent exists, prevent self-referencing, detect
circular parent chains (up to 10 levels deep)
- Frontend: derive child issues from store when available instead of
refetching on every global issue count change
1. Separate ReportTaskUsage endpoint (POST /api/daemon/tasks/{id}/usage)
so usage is captured independently of complete/fail — fixes usage loss
for failed/blocked tasks.
2. Add usage tracking for all four providers:
- Claude: already done (stream-json message.usage)
- OpenCode: extract from step_finish.part.tokens
- OpenClaw: extract from step_end.data token fields
- Codex: extract from turn/completed and task_complete usage fields
3. Remove usage from CompleteTask payload — all usage goes through the
dedicated endpoint now.
Extract token usage from Claude Code's stream-json output in real-time
during task execution, replacing the inaccurate global JSONL log scanner.
- New `task_usage` table: tracks (task_id, provider, model) level usage
- Agent SDK: parse `message.usage` from assistant messages, accumulate
per-model and return in Result
- Daemon: convert agent usage to entries, send with CompleteTask
- Server: store usage on task completion, expose workspace-level
aggregation APIs (GET /api/usage/daily, GET /api/usage/summary)
* refactor: remove agent triggers config field
Remove the triggers field from agent configuration. The on_assign,
on_comment, and on_mention behaviors are now always enabled (hardcoded),
as decided in the Agentflow design discussion (MUL-372).
Changes:
- Database: migration 032 drops triggers column from agent table
- Backend: remove triggers from create/update agent APIs and response
- Backend: simplify trigger-checking logic to always-enabled
- Frontend: remove TriggersTab UI and AgentTrigger types
- Tests: remove trigger config unit tests (no longer configurable)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor: also remove agent tools config field
Remove the tools field from agent configuration alongside triggers.
The tools field was a placeholder — stored in the DB and shown in the
UI but never passed to the daemon or used at runtime.
- Database: migration 032 now also drops tools column
- Backend: remove tools from create/update agent APIs and response
- Frontend: remove ToolsTab UI, AgentTool type, and tools tab
- Update landing page copy
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(test): remove tools/triggers columns from test fixtures
The test fixtures still referenced the dropped tools and triggers
columns when inserting agent rows, causing CI failures.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Support Google login that links to existing accounts by email.
When a user who registered via email OTP signs in with Google using
the same email, they are linked to the same account.
Backend:
- Add POST /auth/google endpoint that exchanges Google auth code for
tokens, fetches user profile, and calls findOrCreateUser()
- Updates user name and avatar from Google profile on first Google login
Frontend:
- Add "Continue with Google" button on login page (shown when
NEXT_PUBLIC_GOOGLE_CLIENT_ID is configured)
- Add /auth/callback page to handle Google OAuth redirect
- Add loginWithGoogle to auth store and API client
Keep branch additions (errSilent, exactArgs, examples template blocks)
that were added in the CLI help UX improvement.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add EXAMPLES section to leaf and sub help templates (gh CLI style)
- Add example to attachment download command
- Simplify attachment download description
- Show help output when required args are missing (error first, then help)
- Replace cobra.ExactArgs with custom exactArgs that prints help on failure
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(cli): overhaul help output to match gh CLI style
- Add gh-style grouped help with CORE/RUNTIME/ADDITIONAL COMMANDS sections
- Use UPPERCASE section headers (USAGE, FLAGS, EXAMPLES, LEARN MORE)
- Format commands as "name: description" with automatic alignment
- Add ENVIRONMENT VARIABLES and EXAMPLES sections to root help
- Apply consistent templates to root, subcommand, and leaf commands
- Update descriptions from "Manage X" to "Work with X" for gh parity
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(execenv): add explicit instruction for agents to always use multica CLI
Agents were using curl/wget to access Multica attachment URLs directly,
which fails due to authentication. Add a prominent "Important" section
to the generated CLAUDE.md template that explicitly prohibits direct
HTTP access and instructs agents to escalate missing CLI functionality
to their workspace owner.
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add gh-style grouped help with CORE/RUNTIME/ADDITIONAL COMMANDS sections
- Use UPPERCASE section headers (USAGE, FLAGS, EXAMPLES, LEARN MORE)
- Format commands as "name: description" with automatic alignment
- Add ENVIRONMENT VARIABLES and EXAMPLES sections to root help
- Apply consistent templates to root, subcommand, and leaf commands
- Update descriptions from "Manage X" to "Work with X" for gh parity
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When a reply in a thread explicitly mentions only non-agent entities
(members or issues), do not inherit agent mentions from the parent
comment. This prevents false agent triggers when a user is directing
their reply at other people (e.g. "cc @Someone") rather than requesting
work from agents mentioned in the thread root.
Fixes MUL-324
The assignee was unconditionally skipped in the mention path, assuming
on_comment would handle it. But on_comment is suppressed for terminal
statuses (done/cancelled), so an explicit @mention of the assignee had
no effect. Now only skip the assignee dedup when on_comment will
actually fire (non-terminal status).
1. Update CLAUDE.md template to document --limit, --offset, --since
params and guide agents to use pagination when comments are large
2. Add GetJSONWithHeaders to API client; CLI now prints "Showing X of Y
comments" to stderr when paginating
3. Cap --since without --limit at 500 server-side to prevent unbounded
result sets
Add --limit, --offset, and --since flags to `multica issue comment list`
to prevent context window overflow when issues have many comments.
The API endpoint now accepts limit, offset, and since (RFC3339) query
parameters. When paginating, the response includes an X-Total-Count
header with the total number of comments.
- Add --config flag to skill create/update (accepts JSON string)
- Add --runtime-config flag to agent create/update (accepts JSON string)
- Add --yes flag to skill delete with confirmation prompt
- Improve agent skills set error message (guide users to --skill-ids '')
- Validate --days range (1-365) in runtime usage
- Include last known status in ping/update timeout errors
When a member-started thread root @mentions the assignee agent, replies
in that thread should trigger on_comment — the thread is a conversation
with the agent, not a member-to-member chat.
Previously isReplyToMemberThread only checked the reply content for
assignee mentions. Now it also checks the parent (thread root) content.
This fixes a gap where path 1 (on_comment) suppressed the trigger and
path 2 (on_mention) skipped the assignee, leaving no trigger path.
When a top-level comment @mentions an agent (non-assignee), subsequent
replies in the same thread now also trigger that agent via on_mention.
Previously only the current comment's mentions were checked, so replies
without an explicit re-mention would silently skip the agent.
Extends enqueueMentionedAgentTasks to accept the parent comment and
merge its parsed mentions (deduplicated) into the trigger set, reusing
all existing guards (self-trigger, assignee skip, visibility, dedup).
Closes MUL-177
* fix(agent): instruct agents to use download_url for attachments
Agents were not aware of the signed vs unsigned URL distinction in
attachments, causing failures when trying to read images. Added an
Attachments section to the generated CLAUDE.md/AGENTS.md template that
tells agents to always use `download_url`. Also increased signed URL
expiry from 5 to 30 minutes to better accommodate agent processing time.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): add `multica attachment download` command
Adds a dedicated CLI command for downloading attachments by ID. The
command fetches attachment metadata from the API (which returns a fresh
signed URL), downloads the file, and saves it locally. This eliminates
the need for agents to understand signed vs unsigned URLs.
Changes:
- New `multica attachment download <id>` CLI command
- New `GET /api/attachments/{id}` backend endpoint
- `DownloadFile` helper on APIClient
- Updated CLAUDE.md template to document the command
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): sanitize filename and add download size limit
- Use filepath.Base on attachment filename to prevent path traversal
- Add 100MB size limit to DownloadFile (matches upload limit)
- Include response body in download error messages for debugging
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Devv <devv@Devvs-Mac-mini.local>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The integration tests hardcoded the old default JWT secret while .env
sets a different JWT_SECRET, causing all authenticated requests to fail
with 401. Use auth.JWTSecret() so tests stay in sync with the server.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(agent): replace hard delete with archive/restore
Replace agent deletion with soft archive pattern. Archived agents
are preserved in the database with all historical references intact
but cannot be assigned, mentioned, or trigger tasks.
Backend:
- Add archived_at/archived_by columns to agent table (migration 031)
- Replace DELETE /api/agents/{id} with POST /api/agents/{id}/archive
- Add POST /api/agents/{id}/restore endpoint
- ListAgents excludes archived by default (?include_archived=true to include)
- Skip archived agents in task triggers (on_assign, on_comment, on_mention)
- Block assignment to archived agents
- Cancel pending tasks on archive
- New events: agent:archived, agent:restored (replacing agent:deleted)
Frontend:
- Agent type includes archived_at/archived_by fields
- Mention autocomplete and assignee picker filter out archived agents
- Agent list shows archived agents with muted styling
- Agent detail shows archive banner with restore button
- Delete button replaced with Archive button and updated confirmation dialog
- API client: archiveAgent/restoreAgent replace deleteAgent
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(agent): self-review fixes for archive feature
- Fix: workspace store now fetches agents with include_archived=true
so archived agents are actually visible in the frontend (the archived
UI was dead code before — ListAgents excludes archived by default)
- Fix: add error logging for CancelAgentTasksByAgent in ArchiveAgent
- Fix: add idempotency guards — return 409 Conflict when archiving
an already-archived agent or restoring a non-archived agent
- Fix: revert unnecessary extra GetAgent query in ReconcileAgentStatus
(archived agents won't have running tasks after CancelAgentTasksByAgent)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(daemon): support direct download update for non-Homebrew installs
Previously, CLI auto-update only worked for Homebrew installations. Non-brew
binaries would fail with "not installed via Homebrew". Now the daemon and
`multica update` fall back to downloading the release binary directly from
GitHub Releases when Homebrew is not detected.
Also fixes:
- Daemon restart now uses the current executable's absolute path instead of
searching PATH, ensuring the updated binary is used
- Brew installs preserve the symlink path so the new Cellar version is picked up
- Daemon startup logs now include the CLI version
- Update UI auto-clears "restarting" status after 5s to show the new version
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): remove dead DetectNewBinaryPath and guard against nil latest version
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The runtime detail page was showing the agent CLI version (claude/codex)
as "CLI Version" because metadata.version stored the agent version from
agent.DetectVersion(). The multica CLI version was never sent.
Fix: daemon now sends cli_version in the registration request, server
stores it as metadata.cli_version alongside the existing agent version,
and frontend reads metadata.cli_version.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(runtime): support CLI update from web runtime page
Add the ability to update the CLI daemon from the web Runtime detail page.
When a newer version is available on GitHub Releases, an update button
appears. Clicking it sends an update command through the server to the
daemon via the heartbeat mechanism (same pattern as ping). The daemon
executes `brew upgrade`, reports the result, and restarts itself with the
new binary.
Changes across all three layers:
- Frontend: version display, GitHub latest check, UpdateSection component
- Server: UpdateStore (in-memory), heartbeat extension, 3 new endpoints
- CLI: shared update logic, daemon handleUpdate + graceful restart
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(runtime): handle 'running' status in ReportUpdateResult
The daemon sends {"status":"running"} when it starts executing the
update, but ReportUpdateResult treated any non-"completed" status as
failure — immediately marking the update as failed before brew upgrade
even ran.
Fix: use a switch statement to handle "running" as a no-op (status is
already "running" from PopPending), and also timeout running updates
after 120 seconds in case brew upgrade hangs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(mentions): support @mentioning issues in comments
- Extend MentionItem type to include "issue" alongside "member"/"agent"
- Add issue search (by identifier and title) to mention suggestion dropdown
- Render issue mentions with CircleDot icon in autocomplete popup
- Issue mentions serialize as [MUL-117 Title](mention://issue/id) (no @ prefix)
- Markdown renderer shows issue mentions as clickable links to /issues/:id
- Backend mentionRe regex updated to match issue mention type
* feat(mentions): auto-expand issue identifiers and add mention format to agent instructions
1. Path A — CLAUDE.md template (runtime_config.go):
Add a "## Mentions" section teaching agents the mention serialization
format for issues, members, and agents. All agents automatically
receive this via the auto-generated CLAUDE.md.
2. Approach 2 — Server-side auto-conversion (internal/mention/):
New ExpandIssueIdentifiers() utility that scans comment content for
bare issue identifiers (e.g. MUL-117) and replaces them with
[MUL-117](mention://issue/<uuid>) mention links. Skips code blocks,
inline code, and existing markdown links. Integrated into both:
- handler.CreateComment (HTTP API path)
- service.createAgentComment (agent task output path)
When clicking an inbox notification, the issue detail now scrolls to and
briefly highlights the relevant comment. Also adds a floating "Jump to
bottom" button on issue pages with long timelines.
Backend: store comment_id in inbox notification details for new_comment
and reaction_added events. Frontend: pass highlightCommentId through to
IssueDetail, add id attributes to comment elements, and track scroll
position for the jump-to-bottom button.
Add two new CLI commands so agents can access execution history:
- `multica issue runs <issue-id>` lists all task executions for an issue
- `multica issue run-messages <task-id>` lists messages for an execution
Also adds --since query param support to the ListTaskMessages backend
handler for incremental message fetching.
Tests verify:
- Stale running tasks: task:failed event has WorkspaceID set
- Agent status reconciliation: agent returns to "idle" after sweep
- Stale dispatched tasks: same correctness for dispatch timeout path
The runtime sweeper was publishing task:failed events without a
WorkspaceID, causing them to be silently dropped by the WS listener.
This meant frontends never received notification when stale/orphaned
tasks were failed by the sweeper — the live log card kept showing
"Agent is working" and the agent status remained "working" indefinitely.
- Look up workspace_id from issue table for each swept task
- Set WorkspaceID on published events so they reach the correct WS room
- Reconcile agent status after sweeping so agents return to "idle"
@all is a broadcast to all workspace members — it should not trigger
the assignee agent's on_comment. Previously @all was treated as
"includes everyone" and allowed the trigger.
Changes:
- commentMentionsOthersButNotAssignee now checks HasMentionAll() early
and returns true (suppress) when @all is present
- Fix authRequestWithAgent test helper that was making a duplicate HTTP
request (one as member, one as agent)
Tests: 5 new @all unit test cases, 2 new @all integration test cases.
End-to-end tests through the full HTTP router + real database:
TestCommentTriggerOnComment (6 subtests):
- Top-level comment without mentions → triggers agent
- Top-level comment mentioning only others → suppresses trigger
- Top-level comment mentioning assignee → triggers agent
- Reply to agent thread without mentions → triggers agent
- Reply to member thread without mentions → suppresses trigger (Bohan's bug)
- Reply to member thread mentioning assignee → triggers agent
TestCommentTriggerOnAssignNoStatusGate:
- Assigning agent to in_progress issue → triggers (no todo restriction)
TestCommentTriggerOnMentionNoStatusGate:
- @mentioning agent on done issue → triggers (no status gate)
TestCommentTriggerCoalescing:
- Rapid-fire comments → only 1 task created (dedup)
