- Add comprehensive e2e test for steering comments injection in executor
- Verify system prompt steering comments are correctly injected
- Test covers executor initialization and prompt construction
- Add logic to auto-create refinement task when steering comment is added to done task
- Add 117 lines of unit tests covering auto-refinement trigger conditions
- Include changeset for minor version bump
- Validate that tasks cannot depend on themselves in TaskStore.addDependency()
- Add comprehensive tests for self-dependency validation
- Fix mock isolation issues in store tests
- Add async generateTitle() using AI to create concise task titles from descriptions\n- Update createTask() to generate titles asynchronously when not provided\n- Add dynamic import pattern for @kb/engine to enable testability\n- Update store tests with comprehensive coverage for AI title generation\n- Add changeset for the title generation fix
- Define 5 built-in workflow step templates (Documentation Review, QA Check, Security Audit, Performance Review, Accessibility Check)
- Add API endpoints GET /api/workflow-step-templates and POST /api/workflow-step-templates/:id/create
- Add templates tab to Workflow Step Manager with one-click add functionality
- Include high-quality agent prompts for each template category
- Add changeset for the new feature
- Add Step types to core data model (command, validation, approval steps)
- Update AutomationStore CRUD operations for step management
- Refactor CronRunner for sequential step execution with per-step config
- Add Dashboard API routes for step CRUD and step-aware schedule updates
- Create ScheduleStepsEditor component for visual step configuration
- Add StepTypeBadge component for step type visualization
- Update ScheduleCard and ScheduleForm to display and manage steps
- Add comprehensive test coverage for stores, runner, and components
- Add changeset for patch release
- Add core data model for workflow step definitions with AI-assisted prompt refinement
- Create API routes for CRUD operations and prompt refinement via /api/workflow-steps
- Add WorkflowStepManager dashboard UI for defining and managing workflow steps
- Integrate workflow step selection into NewTaskModal for per-task enablement
- Execute workflow steps sequentially in executor after task_done() with readonly tools
- Run workflow step agents before moving tasks to in-review, failing on step errors
- Add comprehensive tests for store, API routes, components, and executor integration
- Add GlobalSettingsStore with file-based storage in ~/.pi/kb/settings.json
- Implement two-tier hierarchy: global (user prefs) and project (.kb/config.json)
- Update TaskStore to merge settings with project overriding global
- Add API endpoints: GET/PUT /api/settings/global and GET /api/settings/scopes
- Add scope indicators (🌐 global, 📁 project) to settings modal sidebar
- Implement scope-aware save: only save active scope, reject global-only fields
- Add frontend API functions for global settings operations
- Add tests for GlobalSettingsStore, settings routes, and SettingsModal scopes
- Create changeset for the new settings hierarchy feature
- Update AGENTS.md with settings hierarchy documentation
- Add model preset types and settings fields with API validation
- Create model preset utility helpers for size-based auto-selection
- Add settings UI for managing model presets (create, edit, delete)
- Integrate preset selection into NewTaskModal with custom override option
- Add inline preset selection to InlineCreateCard component
- Persist modelPresetId in task store and preserve through archive/unarchive
- Add changeset and update AGENTS.md with feature documentation
- Extend core Settings types with planningProvider, planningModelId, validatorProvider, validatorModelId fields
- Add model selectors in Settings UI for planning and validator models
- Use planning model for triage task specification generation
- Use validator model for specification review in triage
- Use validator model for code reviews in executor agent
- Update AGENTS.md with model hierarchy documentation
- Add morning, afternoon, evening, and night preset schedules to core automation types
- Update ScheduleForm with preset selection dropdown and time handling
- Add color coding for different schedule types in ScheduleCard
- Add tests for new schedule preset functionality
- Include changeset for release tracking
- Add taskStuckTimeoutMs setting to detect tasks with no activity
- Create StuckTaskDetector to poll in-progress tasks every 30s
- Integrate heartbeat tracking into executor via step callbacks
- Implement recovery flow: abort stuck sessions, retry with preserved progress
- Export detector and wire into dashboard for real-time monitoring
- Add comprehensive tests and documentation to AGENTS.md
- Add archiveAllDone method to TaskStore with filtering and batch archive
- Add POST /tasks/archive-all-done API endpoint with tests
- Add useTasks hook support and API function for archiveAllDone
- Add Archive All button to done column header in Board UI
- Wire up onArchiveAllDone through Board component hierarchy
- Add batch status API types (BatchStatusRequest, BatchStatusResponse, etc.)
- Add batch GitHub client wrappers for efficient PR/issue status fetching
- Create useBatchBadgeFetch hook for coordinated dashboard fetching
- Update Board component to batch fetch badge statuses on mount
- Update TaskCard to merge batch, WebSocket, and task data with freshness comparison
- Add batch status REST endpoint at POST /api/tasks/batch/status
- Add Zen to COLOR_THEMES array in core types
- Add Zen theme CSS styles with dark and light variants
- Add Zen theme option to ThemeSelector component
- Add tests for Zen theme selection in ThemeSelector
- Update index.html theme initialization to include Zen
- Add changeset for the new theme
- Add AutomationStore and core automation types for cron-based scheduling
- Implement CronRunner engine for executing scheduled automations
- Add REST API routes for CRUD operations on automations
- Create UI components: ScheduleCard, ScheduleForm, and ScheduledTasksModal
- Integrate scheduled tasks into dashboard App.tsx and CLI dashboard command
- Add comprehensive tests for store, runner, API, and UI components
- Include changeset for the new scheduled tasks feature
- Update default VITEST_MAX_WORKERS from 8 to 16 in all packages
- Affects CLI, Core, Dashboard, and Engine vitest configs
- Improves test execution parallelism on multi-core machines
- Environment variable override still supported via VITEST_MAX_WORKERS
- Fix SSE hook cleanup to prevent memory leaks and stale connections
- Cap agent log memory and optimize batch log processing
- Memoize Board, Column, and TaskCard with custom comparator to reduce re-renders
- Stabilize column task arrays and preserve pagination across live updates
- Add TaskCardBadge component for PR/issue state display
- Remove deprecated GitHub polling code and archive functionality from core store
- Add ArchiveEntry type and archive.jsonl storage format for compact task archives
- Implement archiveTask() with optional cleanup and archiveTaskAndCleanup() convenience method
- Add restoreFromArchive() to reconstruct tasks from archive entries when directory is missing
- Implement cleanupArchivedTasks() for bulk cleanup of all archived task directories
- Add comprehensive tests for archive, cleanup, and restore operations (385+ lines)
- Add readArchiveLog(), findInArchive(), and unarchiveTask() API methods
- Document archive storage pattern and restoration behavior in AGENTS.md
- Include changeset for patch release noting archive cleanup feature
- Remove dist-dependent workspace type resolution from all tsconfig files
- Add clean-checkout typecheck regression test to CI suite
- Update package.json type definitions for core, engine, dashboard, and cli packages
- Update README with typecheck testing documentation
- Clean up unused test files and component dependencies
- Extend task creation types, store persistence, and API payloads to accept executor and validator model overrides
- Add inline model selection to the dashboard create card with default normalization, retryable model loading, and focus-safe interactions
- Wire the list-view create flow through InlineCreateCard and style the dropdown to stay usable within the viewport on mobile and desktop
- Add store, route, app, list-view, and inline-create tests covering override submission, partial selections, and inline creation behavior
- Document the new creation-time model selection flow and include a published package changeset
- Add a focused GitHub badge poller with shared rate-limit, freshness, and cleanup handling
- Wire a dedicated badge websocket server and routes to stream PR and issue badge snapshots
- Add a shared useBadgeWebSocket hook and update TaskCard to subscribe only when visible while preserving partial badge state
- Cover polling, websocket, and task card flows with tests and document the realtime badge channel
- Add the Factory theme to shared theme types and the dashboard theme selector
- Validate persisted color themes against shared constants in useTheme and the pre-hydration init script
- Introduce reusable design tokens for typography, spacing, radius, shadows, and transitions in dashboard styles
- Add Factory-specific dark and light styling overrides for cards, buttons, columns, and theme swatches
- Strengthen theme tests to cover all supported themes, Factory previews, and stylesheet token contracts
- Add Ayu and One Dark to COLOR_THEMES and validThemes arrays
- Add CSS theme variables for both themes in styles.css
- Update ThemeSelector UI to include new theme options
- Extend Theme type to include ayu and one-dark values
- Update tests for ThemeSelector and useTheme hooks
- Add changeset for minor version bump
- Add breakIntoSubtasks flag to core Task model and persist to store
- Plumb subtask flag through dashboard API routes with validation
- Add subtask toggle UI to inline task creation card
- Update triage agent to handle automatic subtask breakdown when enabled
- Add comprehensive tests for store, API routes, and UI components
- Include changeset for patch release documenting the new feature
- Fix moveTask to clear status/error/worktree/blockedBy when moving from in-progress to todo/triage
- Add error message display in TaskCard for failed tasks with truncation
- Add prominent error alert in TaskDetailModal for failed tasks
- Refactor usage tracking: move from app/components to dashboard/src/
- Add usage.ts and usage.test.ts for centralized usage tracking
- Remove UsageIndicator and useUsageData from app/ directory
- Update styles.css for error display components
- Update executor tests for error handling
- Add changeset for patch release
- Remove createdAt and updatedAt columns from ListView component
- Update TaskCard to remove date display and related styles
- Update TaskDetailModal to remove date fields
- Update ListView tests to reflect new column layout
- Fix column index in dependencies test after column removal
- Remove unused usage tracking module (usage.ts and usage.test.ts)
- Clean up related CSS styles for date columns
- Add PlanningModeModal component with interactive task planning UI
- Implement backend planning API with /api/planning endpoints
- Add PlanningSession class for managing planning state
- Integrate planning mode into dashboard with header button
- Add comprehensive tests for planning components and API routes
- Include AI agent structure for future planning automation
- Update README with Planning Mode documentation
- Add refineTask() to TaskStore with validation for feedback and requirements
- Add POST /tasks/:id/refine API endpoint with tests
- Add refine UI to TaskDetailModal for submitting feedback
- Add kb_task_refine tool to pi extension for AI-driven refinement
- Add 'kb task refine' CLI command for manual task refinement
- Include validation constraints: max 2000 chars feedback, max 5000 chars requirements
- Create gh-cli utility module with auth detection and command execution
- Refactor GitHubClient to use gh CLI commands with REST API fallback
- Refactor PR Monitor to use gh CLI for PR operations
- Add listIssues() and getIssue() methods to GitHubClient
- Remove in-app GitHubRateLimiter (gh CLI handles rate limiting)
- Update all tests for gh CLI implementation
- Update AGENTS.md and extension docs for gh CLI auth preference
- Add worktreeNaming setting type with 'random' | 'task-id' | 'task-title' options
- Update executor to generate worktree names based on setting value
- Create worktree-names.ts utility module with generateWorktreeName function
- Add comprehensive executor tests for all naming strategies
- Update AGENTS.md documentation with setting description and usage
- Include changeset for patch release
