Make start_agent non-blocking by deferring worktree creation. The agent
spawn now returns immediately while worktree setup happens asynchronously,
improving responsiveness of the start_agent MCP call.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add missing closing brace for spawn_watchdog function
- Remove leftover <<<<<<< HEAD conflict marker in test module
- Restore conflict marker test data that was incorrectly stripped
- Add missing completed_at field in inject_test_agent_with_handle
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Remove leftover conflict markers and add missing closing brace for
watchdog_detects_orphaned_running_agent test function.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds log_buffer ring buffer and slog! macro for in-memory server log
capture, plus get_server_logs MCP tool for agents to read recent logs.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The agent pool allowed the same agent (e.g. "qa") to run concurrently
on multiple stories because start_agent() only checked whether that
story+agent combo was already active. It did not check whether the
agent was busy on a different story.
Two concurrent QA runs each spawn cargo clippy + cargo test + vitest,
causing extreme CPU load (load average >33 on M1 Mac).
Fix: before registering a new agent as Pending, scan all active entries
for any Running or Pending entry with the same agent_name. If one is
found, return an error explaining that the story will be picked up when
the agent becomes available.
The existing auto_assign_available_work() mechanism already scans
pipeline directories (3_qa/, 4_merge/, etc.) for unassigned stories
and uses find_free_agent_for_stage() — which respects single-instance
limits — to assign work when an agent slot opens up. So the queuing
behaviour is naturally provided: the story stays in its directory,
and auto-assign picks it up when the previous run completes.
Adds two regression tests:
- start_agent_rejects_when_same_agent_already_running_on_another_story
- start_agent_allows_new_story_when_previous_run_is_completed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add log_buffer module: bounded 1000-line ring buffer with push/get_recent API
- Add slog! macro: drop-in for eprintln! that also captures to ring buffer
- Replace all eprintln! calls across agents, watcher, search, chat, worktree, claude_code with slog!
- Add get_server_logs MCP tool: accepts count (1-500) and optional filter params
- 5 unit tests for log_buffer covering push/retrieve, eviction, filtering, count limits, empty buffer
- 262 tests passing, clippy clean
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The test_plan field was a gate from the old interactive web UI workflow
where a human would approve a test plan before the LLM could write code.
With autonomous coder agents, this gate is dead weight — coders sometimes
obey the README's "wait for approval" instruction and produce no code.
Removes: TestPlanStatus enum, ensure_test_plan_approved checks in fs/shell,
set_test_plan MCP tool + handler, test_plan from story/bug front matter
creation, test_plan validation in validate_story_dirs, and all related tests.
Updates README to remove Step 2 (Test Planning) and renumber steps.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The worktree doesn't have .story_kit/work/ so agents had no access to
the story requirements. Read the story file from the project root and
prepend it to the prompt. Without this, coders would start, read
CLAUDE.md, have nothing to implement, and exit with no code.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
model = "sonnet-4.6" is not a valid Claude CLI model identifier,
causing all coder/qa/mergemaster agents to get 404 errors from the
API and exit immediately with no work done. Change to
"claude-sonnet-4-6". Also disable automatic worktree cleanup on
archive so agent work can be inspected post-mortem.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When an agent process exits normally, the server now automatically runs
acceptance gates (uncommitted changes check + cargo clippy + tests) and
advances the pipeline based on results. This replaces the previous model
where agents had to explicitly call report_completion as an MCP tool.
Changes:
- Add run_server_owned_completion() free function in agents.rs that runs
gates on process exit, stores a CompletionReport, and advances pipeline
- Wire it into start_agent's spawned task (replaces simple status setting)
- Remove report_completion from MCP tools list and handler (mcp.rs)
- Update default_agent_prompt() to not reference report_completion
- Update all agent prompts in project.toml (supervisor, coders, qa,
mergemaster) to reflect server-owned completion
- Add guard: skip gates if completion was already recorded (legacy path)
- Add 4 new tests for server-owned completion behavior
- Update tools_list test (26 tools, report_completion excluded)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
On agent completion, the server automatically runs script/test and
advances stories through the pipeline: coder → qa → mergemaster →
archive. Failed gates restart the agent with failure context. Agents
no longer need to call pipeline-advancing MCP tools.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Add notify-based filesystem watcher for .story_kit/work/ that
auto-commits changes with deterministic messages and broadcasts
events over WebSocket. Push full pipeline state (Upcoming, Current,
QA, To Merge) to frontend on connect and after every watcher event.
Strip dead UI: remove ReviewPanel, GatePanel, TodoPanel,
UpcomingPanel and all associated REST polling. Replace with 4
generic StagePanel components driven by WebSocket. Simplify
AgentPanel to roster-only.
Delete all 11 workflow HTTP endpoints and 16 request/response types
from the server. Clean dead code from workflow module. MCP tools
call Rust functions directly and need none of the HTTP layer.
Net: ~4,100 lines deleted, ~400 added.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add `qa` agent entry to `.story_kit/project.toml` with a detailed
prompt covering code quality scan, test verification, manual testing
support, and structured report generation
- Add `move_story_to_qa` function in `agents.rs` that moves a work item
from `work/2_current/` to `work/3_qa/` and auto-commits (idempotent)
- Add `request_qa` MCP tool in `mcp.rs` that moves the story to
`work/3_qa/` and starts the QA agent on the existing worktree
- Add unit tests for `move_story_to_qa` (moves, idempotent, error cases)
- Update `tools_list_returns_all_tools` test to expect 27 tools
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Move current/ to .story_kit/current/ (out of stories/)
- Type-aware routing for bugs, spikes, stories
- close_bug_to_archive() for bug lifecycle
- All path references updated across agents.rs, workflow.rs, mcp.rs
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- 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>
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>
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>
- Add base_branch detection to WorktreeInfo (from project root HEAD)
- Expose base_branch in AgentInfo API response
- Add {{base_branch}} template variable to agent config rendering
- Show git difftool command with copy-to-clipboard in AgentPanel UI
- Add diff command instruction to coder agent prompts
- Add AgentPanel tests for diff command rendering and clipboard
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Fix CLAUDECODE env var blocking nested Claude Code sessions
- Add drain-based event_log for reliable get_agent_output polling
- Add non-SSE get_agent_output fallback (critical for MCP tool calls)
- Preserve worktrees on agent stop instead of destroying work
- Reap zombie processes with child.wait() after kill
- Increase broadcast buffer from 256 to 1024
- Engineer supervisor and coder prompts in project.toml
- Point .mcp.json to test port 3002
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 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>
