- task_done() marks all remaining steps as done and signals completion
- No more filesystem side channel for completion detection
- Removes all .DONE references from executor and prompts
- task_list: returns all non-done tasks (ID, column, description, deps)
- task_get: returns full task detail including PROMPT.md content
- Agent calls task_list to scan for duplicates, task_get to verify
- Add duplicate check instructions to specification prompt
- Read existing tasks before writing spec to detect duplicates
- Agent outputs DUPLICATE: {id} instead of PROMPT.md when duplicate found
- Parse agent output for duplicate flag and auto-close duplicate tasks
- Log duplicate relationship before deleting the duplicate task
- Extract tool parameter schemas to module-level constants for reuse
- Add Static<typeof schema> type annotations to tool execute callbacks
- Import Static type from @mariozechner/pi-ai
- Remove inline parameter schema definitions from tool objects
- Add markdown-body base styles in dashboard styles.css
- Remove backdrop and enable scroll on task detail prompt rendering
- Add TaskDetailModal unit tests with vitest jsdom environment
- Update vitest config with globals and jsdom support
- Clean up unused test files and legacy concurrency module
- Add agent-active CSS with animated purple border glow using in-progress theme color
- Apply agent-active class conditionally in TaskCard component
- Add TaskCard agent-active unit tests
- Move TaskCard tests to __tests__ directory
- Add atomic writes for config.json with config lock in store
- Simplify safeReadTaskJson to readTaskJson, removing truncation recovery logic
- Remove withRetry workaround from fetchTaskDetail in dashboard API
- Remove related retry logic from executor and dashboard command
- Update store tests to cover atomic write behavior
- Fix server-side error handling in GET /tasks/:id with retry on transient failures
- Add client-side retry logic for fetchTaskDetail in dashboard
- Add unit tests for routes and API error/retry behavior
- Remove outdated core store tests and vitest config
- Update documentation for error handling improvements
Extract TypeBox schemas to module-level constants and use Static<typeof schema>
to explicitly type execute callback params, resolving all TS7006 implicit-any
errors in the four create*Tool methods.
- Route now returns 404 only for ENOENT, 500 for transient errors
- store.getTask() retries once after 50ms on non-ENOENT failures
- Added route tests for success, 404, and 500 cases
- Updated vitest config to include src/**/*.test.* files
- Add per-task write lock in TaskStore to prevent concurrent write corruption
- Implement defensive JSON parsing with recovery for task.json files
- Use atomic writes (write-to-temp + rename) for task.json updates
- Add vitest config and tests for lock, parsing, and atomic write behavior
- Remove concurrency module from engine, consolidating store safety in core
- Create AgentSemaphore class in engine/src/concurrency.ts with configurable maxConcurrent
- Integrate semaphore into TriageProcessor and TaskExecutor to gate agent spawning
- Wire semaphore into merge path and dashboard engine components
- Add comprehensive tests for concurrency, executor, and triage integration
- Update JSDoc and types for maxConcurrent configuration option
- Reorder JSX and update layout in TaskCard component
- Update dashboard styles for new TaskCard layout
- Add TaskCard unit tests with vitest
- Add vitest config and test dependencies to dashboard package
Replaces CLI-based progress reporting (hai task update/log/create)
with custom tools registered on the worker's pi session. No PATH
dependency, no shell overhead, works in any worktree.
- task_update(step, status) — update step lifecycle
- task_log(message) — log actions and decisions
- task_create(description) — create tasks for out-of-scope work
- review_step unchanged (already a tool)
- System prompt and execution prompt updated to reference tools
- Add serialized merge queue to prevent concurrent git merge operations
- Enqueue in-review tasks on startup so pre-existing tasks are not missed
- Add periodic retry interval to re-attempt failed merges automatically
- Re-check autoMerge setting and task column before each merge attempt
- Clean up merge retry interval on SIGINT for graceful shutdown
