- Add --attachment flag to `multica issue create` CLI command
- Fix CreateComment response to include linked attachments instead of empty array
- Include attachments inline in GetIssue API response (matching Jira/ClickUp pattern)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add file attachment support to `multica issue comment add`. The CLI
uploads files via multipart form to /api/upload-file, collects the
returned attachment IDs, and passes them when creating the comment.
Usage: multica issue comment add <issue-id> --content "..." --attachment file1.png --attachment file2.pdf
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): add `multica update` command
Detects whether multica was installed via Homebrew (by resolving the
binary symlink and checking if it lives under a Homebrew prefix).
- Brew installs: runs `brew upgrade multica` automatically.
- Non-brew installs: prints instructions for installing via brew or
downloading from GitHub releases.
- Checks latest version from the GitHub releases API and skips
the update if already up to date.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): use fully-qualified tap name in brew upgrade
Use `brew upgrade multica-ai/tap/multica` instead of `brew upgrade multica`
to avoid any potential name collision with core formulae.
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(agents): reply as thread instead of top-level comment
When an agent responds to a user comment, the reply is now nested under
the triggering comment (parent_id) instead of appearing as a separate
top-level comment. Also enables on_comment trigger by default for newly
created agents.
- Add trigger_comment_id column to agent_task_queue (migration 028)
- Pass triggering comment ID through EnqueueTaskForIssue → task → createAgentComment
- Include parent_id in WebSocket broadcast for agent comments
- Default agent creation includes both on_assign and on_comment triggers
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): add --parent flag to comment add for threaded replies
The agent posts comments via the CLI, so the correct fix is giving it a
--parent flag rather than wiring trigger_comment_id through the task
infrastructure. The agent reads the comment list, decides which comment
to reply to, and passes --parent <comment-id>.
- Add --parent flag to `multica issue comment add`
- Update agent runtime instructions to explain --parent usage
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(daemon): pass trigger_comment_id to agent execution context
The agent now knows which comment triggered its task and gets an explicit
instruction to reply to it using --parent. The trigger_comment_id flows
from the DB through the claim response, daemon Task struct, and into
issue_context.md where the agent sees it.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(comments): agent replies to thread root, matching frontend behavior
When the triggering comment is itself a reply (has parent_id), resolve
to the thread root so the agent's reply stays in the same flat thread.
This matches the frontend where all replies share the top-level parent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(cli): show parent_id and full IDs in comment list
The table output now includes a PARENT column and shows full comment IDs
(not truncated) so agents can see thread structure and use --parent.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(daemon): instruct agents to always use --output json
Agents now see explicit guidance to use --output json for all read
commands, ensuring they get structured data with full IDs and parent_id
for proper threading.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(daemon): differentiate comment-trigger vs assign-trigger context
When triggered by a comment, the agent now gets clear instructions:
- Primary goal is to read and respond to the comment
- Do NOT change issue status just because you replied
- Only change status if explicitly requested
This prevents the agent from seeing "In Review" and stopping, since
it now understands the task is to reply, not to re-evaluate the issue.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(daemon): split workflow by trigger type in CLAUDE.md/AGENTS.md
The Workflow section in the agent's runtime config now shows a
comment-reply workflow when triggered by a comment (read comments,
find trigger, reply, don't change status) vs the full assignment
workflow (set in_progress, do work, set in_review).
Previously the agent always saw the assignment workflow, causing it
to check the issue status, see "In Review", and stop without reading
or replying to the triggering comment.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(daemon): remove duplicate workflow from issue_context.md
Workflow instructions now live only in CLAUDE.md/AGENTS.md (runtime_config.go).
issue_context.md keeps just the task data: issue ID, trigger type, and
triggering comment ID.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(task): skip duplicate comment on completion for comment-triggered tasks
When triggered by a comment, the agent posts its own reply via CLI
with --parent. The task completion path was also creating a comment
from the agent's stdout output, resulting in duplicates. Now only
assignment-triggered tasks auto-post output as a comment. Error
messages from FailTask are still posted regardless of trigger type.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Allow running multiple daemon instances against different servers (e.g.
production and local dev) simultaneously. Each profile gets isolated
config, PID file, log file, health port, and workspaces root.
Usage:
multica login --profile dev --server-url http://localhost:8080
multica daemon start --profile dev
Default profile (no --profile flag) behavior is unchanged.
Closes MUL-42
* fix(cli): daemon reads server_url from config file
The daemon only checked CLI flags and env vars for server_url, ignoring
the persisted config in ~/.multica/config.json. Now falls back to the
config file when neither flag nor env var is set.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): reset workspace data when server_url changes on login
When logging in to a different server, stale workspace_id and
watched_workspaces from the previous server caused 404 errors in the
daemon. Now both browser and token login paths clear workspace data
when the server URL changes.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): reset workspace data on every login, not just server change
A different user logging in on the same machine would inherit stale
workspace data. Always clear workspace_id and watched_workspaces on
login so autoWatchWorkspaces repopulates them fresh.
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(cli): support app_url in CLI config for browser login
The login flow opens the frontend URL for browser-based auth, but
previously app_url could only be set via environment variables.
Add app_url to CLIConfig so it can be persisted with `multica config set`.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(cli): persist app_url to config during browser login
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(server): distinguish agent vs human CLI actions via X-Agent-ID/X-Task-ID headers
Extract resolveActor helper in handler to centralize agent identity resolution
from X-Agent-ID header with X-Task-ID cross-validation. Fix DeleteComment,
DeleteIssue, and UpdateComment handlers that previously hardcoded "member" as
actor type. Forward MULTICA_TASK_ID as X-Task-ID header from CLI client.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(server): add debug logging and test coverage for resolveActor
Add slog.Debug on agent/task validation failures for easier debugging.
Add TestResolveActor with 5 cases covering member fallback, valid agent,
non-existent agent, valid task, and mismatched task.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
When agents use the multica CLI during task execution, their comments,
issue updates, and issue creations were attributed to the daemon's user
(via JWT) instead of the agent. Pass MULTICA_AGENT_ID env var from the
daemon, send X-Agent-ID header from the CLI client, and use it in
handlers to set the correct author/actor identity.
Previously, `multica login` only saved server_url to config when it was
empty. A stale value (e.g. from a prior session pointing at a different
host) was never overwritten, causing subsequent API calls to hit the
wrong server.
Agents now decide which repo to use based on issue context and check out
repos on demand via `multica repo checkout <url>`. Workspace repos are
cached locally as bare clones for fast worktree creation.
Key changes:
- Add repocache package for bare clone management (clone, fetch, worktree)
- Add `multica repo checkout` CLI command that talks to local daemon
- Add POST /repo/checkout endpoint on daemon health server
- Pass workspace repos metadata through register + task claim responses
- Remove pre-created worktrees from execenv (workdir starts empty)
- Update CLAUDE.md template to instruct agents to use `multica repo checkout`
- Pass MULTICA_DAEMON_PORT, WORKSPACE_ID, AGENT_NAME, TASK_ID env vars to agent
* refactor: decouple task lifecycle from issue status, add daemon health server
- Remove automatic issue status changes from StartTask (in_progress),
CompleteTask (in_review), and FailTask (blocked) in task service.
Issue status is now fully managed by the agent via `multica issue status`.
- Update agent prompt and meta skill to instruct agents to manage issue
status themselves (in_progress → done/in_review/blocked).
- Add daemon health HTTP server on 127.0.0.1:19514 with /health endpoint
exposing pid, uptime, agents, and workspaces. Fail fast if port is taken
(another daemon already running).
- Update `multica status` to check both server and daemon health.
- Add Save button to repos section in workspace settings UI.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* refactor(daemon): simplify prompt, fix runtime config path, improve task error logging
- Slim down BuildPrompt to a minimal hint; detailed workflow now lives in CLAUDE.md/AGENTS.md
- Write CLAUDE.md to workDir root instead of .claude/CLAUDE.md
- Fix git-exclude pattern (.claude → CLAUDE.md)
- Decouple task queue reconciliation from issue status changes (agents manage status via CLI)
- Add diagnostic logging when CompleteTask/FailTask fail due to unexpected task state
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(task): use task_completed/task_failed inbox notification types
FailTask was sending "agent_blocked" which conflates agent crash with
issue-level blocked status. Align notification types with the new
decoupled model: task_completed and task_failed. Update frontend types
and labels accordingly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tests for truncateID, formatAssignee, resolveAssignee (6 cases),
and validIssueStatuses.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Make truncateID use rune counting instead of byte length for unicode safety
- Refactor workspaceGet and workspaceMembers to use newAPIClient helper
for consistent server-URL validation
- Add --output flag to issueStatusCmd for JSON output support
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Expose workspace details (including context field) and member listing
via the CLI so agents can dynamically query workspace context instead
of relying on static snapshots.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- resolveAssignee now reports actual API errors instead of silently
falling through to "not found" when both member/agent fetches fail
- Comment content truncation uses rune count for correct CJK handling
- Remove unnecessary _ = aType discard
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add `multica issue` command group with subcommands for full issue
lifecycle management: list, get, create, update, assign, status,
and comment operations. Includes assignee resolution by name across
both workspace members and agents.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove unused ListWorkspaces/Workspace from daemon client, add log when
default workspace is set implicitly, document token reload limitation.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- `multica workspace list` — list all user workspaces from API (with
watching indicator)
- `multica watch <id>` — add workspace to daemon watch list (top-level)
- `multica unwatch <id>` — remove from watch list (top-level)
- `multica watches` — show current daemon watch list (top-level)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add `multica workspace watch/unwatch/list` CLI commands
- Daemon watches multiple workspaces from config's `watched_workspaces`
- Registers runtimes per workspace, polls all runtime IDs in round-robin
- Hot-reload: daemon detects config file changes every 5s and
adds/removes workspaces without restart
- Remove `--workspace-id` flag from daemon (workspace selection is now
purely config-driven via `multica workspace watch`)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
The daemon now reads the auth token from ~/.multica/config.json (set by
`multica auth login`) instead of requiring a browser-based pairing flow.
If not authenticated, it logs a message and exits.
Workspace ID is auto-resolved from the user's workspaces when not
explicitly set via flag/env.
Removed: daemon.json, pairing session flow, --config-path flag,
PairingSession type, PersistedConfig, LoadWorkspaceIDFromDaemonConfig.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
ReposRoot was a daemon-level config that locked all tasks to a single
git repo. Replace with RepoPath in TaskContext so the server can specify
the repo per task. When not provided, daemon falls back to directory mode.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace bare HTML with a styled card layout featuring dark/light mode
support, Multica brand icon, and auto-close behavior.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add state parameter to CLI browser login flow for CSRF protection — CLI
generates a random state, frontend passes it through, CLI verifies on
callback. Also restrict cli_callback to http: scheme only.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Prevent open redirect / JWT theft by only allowing localhost/127.0.0.1
as cli_callback hostname
- URL-encode the callback URL in the login query string
- Simplify resolveAppURL to use os.Getenv directly (no phantom flag)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
`multica auth login` now opens the browser for email verification,
receives the JWT via localhost callback, and exchanges it for a PAT.
The legacy PAT-paste flow is preserved via `--token` flag.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(auth): add email verification login flow with 401 auto-redirect
Replace the old OAuth-based login with email verification codes:
- Backend: send-code / verify-code endpoints, verification_codes table (migration 009), rate limiting, Resend email service
- Frontend: two-step login UI (email → 6-digit OTP), auth store with sendCode/verifyCode
- SDK: ApiClient gains onUnauthorized callback; 401 responses auto-clear token and redirect to /login
- Fix login button staying disabled due to global isLoading state
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(auth): add brute-force protection, redirect loop guard, and expired code cleanup
- VerifyCode: increment attempts on wrong code, reject after 5 failed tries (migration 010)
- onUnauthorized: skip redirect if already on /login to prevent infinite loops
- SendCode: best-effort cleanup of expired verification codes older than 1 hour
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(auth): add master verification code for non-production environments
Allow code "888888" to bypass email verification in non-production
environments to simplify development and testing workflows.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* feat(auth): add personal access tokens for CLI and API authentication
Add full-stack PAT support: users create tokens in Settings, CLI authenticates
via `multica auth login`. Server stores SHA-256 hashes only. Auth middleware
extended to accept both JWTs and PATs (distinguished by `mul_` prefix).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace raw fmt/log calls with structured slog logger (Go) and
console-based logger (TypeScript). Add request logging middleware.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Rename the binary and all references from multica-cli to multica for a
cleaner command-line experience.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1. Add Client.SendHeartbeat/Register methods — no more direct postJSON calls
2. Use url.Values for query params to prevent URL injection
3. Unexport helpers (envOrDefault, durationFromEnv, sleepWithContext)
4. CLI resolveWorkspaceID falls back to daemon.json
5. Implement agent stop (PUT /api/agents/{id} with status=offline)
6. Add --output flag to agent get for consistent UX
7. Add server/multica to .gitignore for stray builds
8. Inject version/commit via -ldflags in Makefile build target
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extract daemon logic from cmd/daemon/ into internal/daemon/ package and
create a new unified CLI entry point at cmd/multica/ using cobra. The CLI
supports `daemon` as a long-running subcommand plus ctrl subcommands for
agent/runtime management, config, status, and version.
Server, migrate, and seed binaries remain unchanged.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
