- accept_story MCP tool moves current/ to archived/
- move_story_to_archived helper with idempotent behavior
- start_agent auto-moves upcoming/ to current/
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- report_completion MCP tool for agents to signal done
- Rejects if worktree has uncommitted changes
- Runs acceptance gates (clippy, tests) automatically
- Stores completion status on agent record
- 10 new tests
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Integrate Claude Code provider into the chat UI alongside regular
Ollama/Anthropic providers. Updates AgentPanel and Chat components.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add REST and MCP endpoints for creating, listing, and removing worktrees.
Includes worktree lifecycle management and cleanup operations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Server detects .story_kit/ in cwd or parent directories at startup and
automatically opens the project. MCP tools work immediately without
manual project-open step. Falls back to cwd when no .story_kit/ found.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Agent worktrees now get a .mcp.json written with the correct port from
the running server. AgentPool receives the port at construction and
passes it through to create_worktree, which writes .mcp.json on both
new creation and reuse.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add wait_for_agent MCP tool that blocks until an agent reaches a terminal
state (completed, failed, stopped). Returns final status with session_id,
worktree_path, and git commits made by the agent.
- Subscribe-before-check pattern avoids race conditions
- Handles lagged receivers, channel closure, and configurable timeout
- Default timeout 5 minutes, includes git log of agent commits in response
- 11 new tests covering all paths
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Use --resume <session_id> with claude -p so the web UI claude-code-pty
provider maintains full conversation context across messages, identical
to a long-running terminal Claude Code session.
Changes:
- Capture session_id from claude -p stream-json system event
- Pass --resume on subsequent messages in same chat session
- Thread session_id through ProviderConfig, ChatResult, WsResponse
- Frontend stores sessionId per chat, clears on New Session
- Unset CLAUDECODE env to allow nested spawning from server
- Wait for clean process exit to ensure transcript flush to disk
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Use --resume <session-id> with claude -p to maintain conversation
context across messages in the web UI claude-code-pty provider.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Replace single [agent] config with multi-agent [[agent]] roster system.
Each agent has name, role, model, allowed_tools, max_turns, max_budget_usd,
and system_prompt fields that map to Claude CLI flags at spawn time.
- AgentConfig expanded with structured fields, validated at startup (panics
on duplicate names, empty names, non-positive budgets/turns)
- Backwards-compatible: legacy [agent] format auto-wraps with deprecation warning
- AgentPool uses composite "story_id:agent_name" keys for concurrent agents
- agent_name added to AgentEvent variants, AgentInfo, start/stop/subscribe APIs
- GET /agents/config returns roster, POST /agents/config/reload hot-reloads
- POST /agents/start accepts optional agent_name, /agents/stop requires it
- SSE route updated to /agents/:story_id/:agent_name/stream
- Frontend: roster badges, agent selector dropdown, composite-key state
- Project root initialized to cwd at startup so config endpoints work immediately
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add POST /workflow/stories/create endpoint that auto-assigns story
numbers, generates correct front matter, and writes to upcoming/.
Add slugify_name and next_story_number helpers with full test coverage.
Add frontend createStory API method and types.
Update README to recommend creation API for agents.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add git worktree isolation for concurrent story agents. Each agent now
runs in its own worktree with setup/teardown commands driven by
.story_kit/project.toml config. Agents stream output via SSE and support
start/stop lifecycle with Pending/Running/Completed/Failed statuses.
Backend: config.rs (TOML parsing), worktree.rs (git worktree lifecycle),
refactored agents.rs (broadcast streaming), agents_sse.rs (SSE endpoint).
Frontend: AgentPanel.tsx with Run/Stop buttons and streaming output log.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add configurable port via STORYKIT_PORT env var (default 3001). Server
prints machine-readable STORYKIT_PORT=<port> on startup and writes
.story_kit_port file for discovery. Frontend proxy and WebSocket read
VITE_STORYKIT_PORT env var instead of hardcoding port 3001.
7 new tests (4 backend, 3 frontend) all passing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The security/sandboxing story was renumbered from 34 to 35 but the
old 34_agent_security_and_sandboxing.md was never deleted. Story 34
is now Per-Project Agent Configuration and Role Definitions.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add name and test_plan front matter to 31 story files that were
missing it. Upcoming stories get test_plan: pending, current and
archived get test_plan: approved.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
