Replace simple text buttons with macOS-style window preview cards for
Light/Dark/System theme selection, using pure CSS miniature window mockups.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add inline pickers on board cards for priority, assignee, and due date
- Add custom trigger prop to PriorityPicker, AssigneePicker, DueDatePicker for styling control
- Replace due date quick options with Calendar-based DueDatePicker in issue detail sidebar
- Use PickerWrapper to stop event propagation from pickers to Link/drag handlers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Redesign card layout: priority label, description line, subtle shadow, configurable properties
- Wider columns (280px) with rounded background, count badge, and card spacing
- Add SortableContext for within-column drag reordering with fractional position indexing
- Fix collision detection to prefer card targets over column droppables for reliable down-drag
- Add hidden columns panel on right side with show/hide toggle
- Consolidate header into Filter popover (status + priority) and Display popover (ordering + card properties)
- Auto-switch to manual sort when cards are dragged to preserve drag ordering
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Write skills to provider-native paths so agents discover them
automatically instead of relying on manual path references in
CLAUDE.md/AGENTS.md.
- Claude: write to {workDir}/.claude/skills/ (native discovery)
- Codex: write to per-task CODEX_HOME/skills/ with auth/config
seeded from ~/.codex/ (symlink auth.json, copy config files)
- Fallback: keep .agent_context/skills/ for unknown providers
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The parser read `payload.msg` but Codex JSONL files store token data at
`payload.info`. Also adds model tracking from `turn_context` events,
`last_token_usage` fallback, and `cache_read_input_tokens` field support.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Redesign the skill detail panel to use a directory tree + file viewer
layout, similar to a file browser. SKILL.md and supporting files are
shown in a collapsible tree on the left; selecting a file renders its
content on the right with markdown preview (including YAML frontmatter
parsing) and an edit toggle.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace the subtle inline badge with two always-visible source cards
that show URL formats for ClawHub and Skills.sh, highlighting the
detected source as the user types. Import button now shows
source-specific loading text.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* 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>
Add a Repositories section to workspace settings where admins can
add/remove GitHub repo URLs with descriptions. Agents use these repos
to clone and work on code.
- Add WorkspaceRepo type and export from shared/types
- Update API client updateWorkspace to accept repos
- Add repos section in workspace-tab.tsx with add/remove UI
- Fix test helpers to include repos field
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add a `repos` JSONB column to the workspace table for storing
associated repository URLs and descriptions. This enables the daemon
to clone repos and set up git worktrees for agent task execution.
Structure: [{"url": "https://github.com/org/repo", "description": "..."}]
- Migration 014: adds repos column with default '[]'
- UpdateWorkspace query: supports updating repos
- Workspace API: returns repos in GET, accepts in PUT
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace the frozen context snapshot pattern with a CLI-driven approach:
agents now use `multica` CLI commands to fetch issue details, comments,
and workspace context on demand, always getting the latest data.
- Remove buildContextSnapshot and snapshot generation from enqueue
- Claim endpoint now returns fresh agent name + skills from DB
- Daemon resolves provider from local runtimeIndex, not snapshot
- Prompt instructs agent to use `multica issue get` / `comment list`
- Meta skill (CLAUDE.md/AGENTS.md) documents all available CLI commands
- Skills still injected as filesystem files (static agent config)
- Simplify daemon types: remove TaskContext/IssueContext/RuntimeContext
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 all Claude Code skills (ui-ux-pro-max, shadcn, frontend-design,
web-design-guidelines) from the .agents directory.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove the frontend-only knowledge base page, sidebar nav entry, and
unused BookOpen import. Fix setup-worktree to always generate unique
ports via init-worktree-env.sh instead of skipping when .env.worktree
already exists with default ports.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Previously the entire view was replaced with "No matching issues" text.
Now the board columns or list view render even when empty.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
These fields were unused in practice. Removed from frontend types,
issue detail UI, backend handlers, daemon prompt/context, protocol
messages, SQL queries, and tests. DB columns retained with defaults.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Adapt runtime features (usage tracking, ping, heartbeat) to main's
multi-workspace architecture. Update frontend imports from @multica/types
to @/shared/types after the package consolidation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add a new "Runtimes" sidebar tab to manage local agent runtimes with three
main capabilities: runtime status overview, token usage tracking (reading
Claude Code and Codex CLI local JSONL logs via daemon), and an interactive
connection test that sends a ping through the daemon to verify end-to-end
agent CLI connectivity.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Support importing skills from external sources (clawhub.ai and skills.sh)
via a new POST /api/skills/import endpoint. The backend auto-detects the
source from the URL, fetches skill metadata and files, and creates the
skill in the workspace. The frontend CreateSkillDialog now has two tabs:
Create (manual) and Import (paste URL with source auto-detection badge).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The login page was changed to email+OTP but tests still expected
the old name+email+password form.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
