- Add agent log persistence layer with JSONL append/read and event emission in core store
- Add server-side SSE log streaming endpoint and REST route for fetching logs
- Create AgentLogViewer component and useAgentLogs hook for real-time log display
- Integrate log viewer into TaskDetailModal
- Fix pre-existing build and test errors
- Create build script (packages/cli/build.ts) using Bun.build compile target
- Update asset resolution in dashboard server for bundled context
- Add npm scripts to wire up the build process
- Add build-exe tests to verify compiled binary output
- Fix pre-existing build errors in engine and core packages
- Document build and compile workflow in README
- Add Static type import from pi-ai in triage.ts
- Add aiMergeTask import from merger.js in executor.test.ts
- Add WorktreePool import from worktree-pool.js in executor.test.ts
- Add blockedBy field to Task type and core store
- Update scheduler to set blockedBy when deferring tasks due to file-scope overlap
- Render file-scope overlap badge on TaskCard in dashboard
- Add tests for blockedBy store logic, scheduler deferral, and TaskCard badge
- Simplify and refactor existing executor, triage, and CLI command code
- Expand MIME type support for text file uploads
- Add --attach flag to CLI task create command
- Surface attachments to triage agent with image content support
- Reference attachments in executor prompt for task execution context
- Add drag-and-drop file upload on dashboard task cards
- Update Scheduler to read settings dynamically from the store instead of using static config
- Make TriageProcessor poll interval dynamic so it responds to settings changes
- Update dashboard.ts wiring to pass dynamic settings through to engine components
- Add scheduler and triage processor tests for dynamic settings behavior
- Remove unused InlineCreateCard and stale test files
- Add wasWorktreeLimited flag to only log worktree limit on first occurrence
- Reset flag when worktrees free up so the message reappears on next saturation
- Add tests verifying single log on repeated maxed passes
- Add test verifying log reappears after slots free and re-saturate
- Set task status to 'failed' on execution failure in engine executor
- Add failed indicator styling on TaskCard component
- Add POST /tasks/:id/retry API endpoint and client function
- Add retry button in TaskDetailModal for failed tasks
- Add tests for failed indicator, retry endpoint, and modal behavior
- Release worktree back to pool when recycleWorktrees setting is enabled
- Skip worktree removal when released to pool, preserving it for reuse
- Fall through to force-remove behavior when pool is unavailable or recycling is disabled
- Remove duplicate entries from adjective and noun word lists in worktree-names.ts
- Add tests to verify all adjectives are unique
- Add tests to verify all nouns are unique
- Ensure generated worktree names remain distinct
- Refactor merger.js mock to use importOriginal and spread actual exports
- Preserve aiMergeTask export while still mocking findWorktreeUser
- Add missing listTasks mock to merger worktree pool integration test
- Set status to queued in scheduler for file-scope-deferred tasks
- Normalize queued badge display in TaskCard component
- Add TaskCard unit tests for queued status rendering
- Add scheduler tests for file-scope-deferred task queuing
- Move logo.svg to correct public directory
- Import Static type utility from pi-ai
- Extract taskGetParams schema to a named constant
- Add explicit type annotations to task_get execute callback params
- Improve type safety for triage tool parameter handling
- Count triage tasks with status 'specifying' as active agent slots in scheduler
- Rewrite scheduler tests to focus on concurrency slot accounting
- Add tests for specifying-only, mixed, and no-specifying scenarios
- Use direct schedule() invocation pattern to avoid timer complexity in tests
- Add worktree-names module with adjective-animal name generator (generateWorktreeName)
- Update executor to assign humanized random worktree names and support dependency worktree reuse
- Remove task-ID fallback paths from merger and store; add shared worktree cleanup via findWorktreeUser
- Remove worktree pool module and related scheduler/integration tests
- Update dashboard worktree label tests and add JSDoc documentation for worktree naming
- Add recycleWorktrees setting to control worktree pooling behavior
- Implement WorktreePool class with acquire/release/prepareForTask lifecycle
- Integrate pool into executor: acquire warm worktrees, skip init command for pooled entries
- Integrate pool into merger: release worktrees to pool instead of removing on task completion
- Add comprehensive unit and integration tests for pool, executor, and merger interactions
- Add re-entrance guard to schedule() preventing concurrent passes from starting conflicting tasks
- Extract pathsOverlap() to module-level export for direct unit testing
- Add comprehensive scheduler test suite with overlap and concurrency coverage
- Add JSDoc explaining why the guard is needed and how inProgressScopes stays consistent
- Add executor logic to resolve and reuse dependency worktrees for warm build caches
- Add reuseWorktree method that creates a new branch in an existing worktree
- Add findWorktreeUser helper to check if a worktree is shared across tasks
- Update executor and merger cleanup to skip worktree removal when still in use
- Add comprehensive tests for worktree reuse and conditional cleanup paths
- 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
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.
- 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
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 autoMerge boolean to Settings model with default false
- Add auto-merge toggle UI to the In Review column header
- Implement server-side auto-merge behavior in dashboard command
- Fix pre-existing build errors in types, executor, and dashboard server
- Update README with auto-merge documentation
- Add groupOverlappingFiles toggle to Settings types and store with default enabled
- Parse File Scope sections from PROMPT.md to extract per-task file lists
- Implement overlap detection in scheduler to group tasks sharing files
- Add groupOverlappingFiles toggle to the Settings UI modal
- Update README and remove obsolete triage overlap logic
Triage prompt now explicitly:
- Checks for test framework before writing spec
- Creates a prerequisite task if no test framework exists
- Adds it as a dependency on the current task
- Forbids typecheck-only or manual-only testing steps
