Set reuseExistingServer:true in playwright config so acceptance gates
don't fail when port 41700 is already occupied by a prior test run.
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>
- Add `hiddenRosterAgents: ReadonlySet<string>` to LozengeFlyContext:
- Derived from pipeline: any agent currently assigned to a work item
- `flyingOutAgents` state keeps badge hidden for 500 ms during the
fly-out animation so the returning clone lands before the badge reappears
- Union of both sets exposed as `hiddenRosterAgents` in context
- Update AgentPanel: wrap each RosterBadge in a collapsing div
controlled by `hiddenRosterAgents`. The div transitions max-width
0→300px / opacity 0→1 so the roster gap closes/opens smoothly.
- Add tests covering:
- `hiddenRosterAgents` is empty when no agents are assigned
- Badge hidden immediately when agent appears in pipeline
- Badge hidden during fly-out (0–499 ms) and visible after (≥500 ms)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Sonnet 4.6 is too slow for small stories — agents burn through turns
without completing. Reverting coders, QA, and mergemaster to Sonnet 4.5.
Supervisor and coder-opus remain on Opus.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The --directory flag does not exist in Claude Code CLI. It was added in
c169cfc but caused every agent spawn to exit immediately with "unknown
option", resulting in Session: None errors. The process cwd (set via
cmd.cwd()) already correctly pins agents to the worktree directory.
Co-Authored-By: Claude Opus 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>
