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>
Documents STORYKIT_PORT env var for running multiple instances
in parallel worktrees without port conflicts.
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>
All acceptance criteria verified. Always show story name/id in TODO
panel regardless of story count. Archive story.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add GET /workflow/upcoming endpoint that reads .story_kit/stories/upcoming/
and returns story IDs with names parsed from frontmatter. Add UpcomingPanel
component wired into Chat view with loading, error, empty, and list states.
12 new tests (3 backend, 9 frontend) all passing.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add TodoPanel that displays unchecked acceptance criteria from current
story files. Backend parses `- [ ]` lines from markdown, frontend
shows them in a panel with refresh. Includes 4 Rust unit tests,
3 Vitest tests, 3 Playwright E2E tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Spike proved: spawning claude -p in a PTY from Rust gets Max subscription
billing. Multi-agent concurrency confirmed with session resumption.
Includes AgentPool REST API, claude-code provider, and spike documentation.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
# Conflicts:
# .ignore
Reverts port changes made during the spike back to default (3001/5173).
Adds two new stories for multi-worktree support: dynamic port management
(story 32) and worktree diff inspection with editor integration (story 33).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Proves that spawning `claude -p` in a pseudo-terminal from Rust gets Max
subscription billing (apiKeySource: "none", rateLimitType: "five_hour")
instead of per-token API charges. Concurrent agents run in parallel PTY
sessions with session resumption via --resume for multi-turn conversations.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Drop story 28, renumber 30-33 to 28-31, add story 31 (View Upcoming
Stories), and extend .ignore for .claude/ and .story_kit/ directories.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add end-to-end coverage tracking: backend collects vitest coverage,
records metrics with threshold/baseline tracking, and blocks acceptance
on regression. Frontend displays coverage in gate/review panels with
a "Collect Coverage" button. Includes 20 Rust tests, 17 Vitest tests,
and 14 Playwright E2E tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add workflow engine with acceptance gates, test recording, and review
queue. Frontend displays gate status (blocked/ready), test summaries,
failing badges, and warnings. Proceed action is disabled when gates
are not met. Includes 13 unit tests (Vitest) and 9 E2E tests
(Playwright) covering all five acceptance criteria.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
