- Add AgentPromptTemplate and AgentPromptsConfig types to ProjectSettings
- Create agent-prompts module with 7 built-in prompt templates and role resolver
- Wire engine agents (executor, reviewer, merger, triage) to use resolved prompts
- Add 25 test cases covering template resolution, role assignment, and validation
- Export new types from @fusion/core package
- Document agentPrompts configuration and built-in templates in AGENTS.md
- Add thinkingLevel field to createTask and updateTask in core store
- Accept thinkingLevel and planningModel fields in dashboard task routes
- Send thinkingLevel and planningModel in frontend API calls from task forms
- Add ThinkingLevel selector to ModelSelectorTab component with tests
- Wire up planning model and thinking level in QuickEntryBox, TaskForm, and NewTaskModal
- Add unit tests for store, routes, and ModelSelectorTab coverage
- Add changeset and update AGENTS.md documentation
- Add planningModelProvider and planningModelId fields to core Task type
- Update backend API validation to accept planning model fields on create/update
- Update frontend API client and TaskForm to handle planning model
- Add planning model selector row to ModelSelectorTab component
- Wire up planning model in TaskDetailModal edit mode with save support
- Update AGENTS.md with planning model override documentation
- Add comprehensive tests for ModelSelectorTab and API routes
- Bump schema version from 10 to 11
- Add spawn settings (maxSpawnedAgentsPerParent, maxSpawnedAgentsGlobal) to ProjectSettings type
- Implement AgentStore access and spawned agent tracking in TaskExecutor
- Add spawn_agent tool with child agent execution in isolated worktrees
- Wire up child termination on parent session end and system prompt generation
- Add comprehensive test suite (554 lines) covering spawning, limits, termination, and error handling
- Document agent spawning architecture, IPC protocol, and usage in AGENTS.md
- Refactor QuickEntryBox to use an actions dropdown (⋯) for advanced controls (deps, models, save)
- Move dependency picker and model selection (plan/executor/validator) into nested dropdown menus
- Add Plan (lightbulb) and Subtask (list) quick-action buttons to the input bar
- Update ListView and QuickEntryBox tests for new dropdown-driven UI
- Add CSS styles for dropdown menus, nested submenus, and action buttons
- Update AGENTS.md and README.md docs for the new QuickEntryBox layout
- Add phase field to workflow step definitions (pre-merge vs post-merge) with persistence and API
- Execute pre-merge steps in executor before merge; post-merge steps in merger after successful merge
- Pre-merge failures block merge and keep task in in-review; post-merge failures are logged only
- Expose phase controls and phase-aware results in the dashboard UI
- Add changeset for the published @gsxdsm/fusion package
- Add model provider/model selection fields to WorkflowStepManager component
- Add dropdowns for choosing executor model per workflow step definition
- Wire executor to use per-step model overrides when configured
- Add comprehensive tests for WorkflowStepManager (340 lines)
- Add CSS styles for model selection UI in workflow step editor
- Update AGENTS.md and README.md with model override documentation
- Add changeset for published package bump
- Add ModelOnboardingModal component with provider selection, API key input, and model verification flow
- Add API key authentication support to SettingsModal with clear-key functionality
- Trigger onboarding from App.tsx when modelOnboardingComplete setting is false
- Add comprehensive tests for ModelOnboardingModal and SettingsModal authentication
- Document model onboarding flow and API key auth in AGENTS.md and README
- Add CSS styles for onboarding modal, provider cards, and auth section
- Add generateSubtasksFromPlanning function to generate subtasks from planning session key deliverables
- Add POST /planning/start-breakdown and POST /planning/create-tasks API routes
- Add startPlanningBreakdown and createTasksFromPlanning frontend API functions
- Extend PlanningModeModal with Break into Tasks UI and subtask editing (drag-and-drop, dependency validation)
- Add comprehensive tests for generateSubtasksFromPlanning with edge cases
- Document planning mode multi-task creation feature in AGENTS.md
- Document nested model menu behavior in QuickEntryBox in AGENTS.md
- Add README section describing the model selection nested menu pattern
- Add regression tests for nested model menu submenu open/close behavior
- Add drag-and-drop and arrow-button reordering for workflow steps in TaskForm
- Add CSS styles for reorder controls and drag states
- Add comprehensive tests for reorder behavior in TaskForm, NewTaskModal, and TaskDetailModal
- Simplify planning.ts by removing redundant JSON parse/stringify logic
- Update AGENTS.md and README with workflow step ordering documentation
- Remove unused changeset and dashboard README section
- Fix executor bug where tasks paused during execution with a graceful session exit were silently dropped instead of moved back to todo
- When session.dispose() resolves the prompt without throwing, the paused-aborted flag now triggers moveTask(todo) so the scheduler can resume after unpause
- Add executor test suite covering pause via graceful exit, pause via abort error, and pause during session disposal
- Document corrected pause/unpause behavior for in-progress tasks in README and AGENTS.md
- Add fn init command for initializing new kb projects
- Add auto-migration check at CLI startup
- Add /api/setup-state and /api/complete-setup dashboard endpoints
- Add SetupState and CompleteSetupInput types to dashboard API
- Add migration and rollback documentation to AGENTS.md
- Create changeset for multi-project migration feature
- Add Project Overview page with responsive grid and health metrics
- Add Project selector dropdown for quick context switching
- Add Project drill-down with back navigation to overview
- Add Setup wizard with auto-detection and manual entry flows
- Add Global activity feed with project attribution badges
- Add Project health polling (active tasks, agents, completion counts)
- Add Empty states and loading skeletons for better UX
- Add Keyboard navigation support (arrow keys, enter, escape)
- Add LocalStorage persistence for wizard state and view preferences
- Add Project Overview page with responsive grid and health status cards
- Add Project Selector dropdown in header for quick context switching
- Add project drill-down navigation with task board/list views
- Add Setup Wizard components for first-run project registration
- Add global activity feed with project attribution and filtering
- Add project-aware task fetching to backend API
- Add project health polling and status badges
- Update ActivityLogModal with project filter and useActivityLog hook
- Add project subcommands: list, add, remove, show, set-default, detect
- Add --project flag support for all task commands
- Create project-context.ts utilities for project resolution
- Add defaultProjectId to GlobalSettings type
- Implement project auto-detection from cwd
- Update CLI argument parsing for global --project flag
- Add multi-project CLI documentation to AGENTS.md
- Optimize backup tests using fake timers instead of real timeouts
- Enable parallel file execution in core, engine, CLI, and dashboard packages
- Add inline test helpers to reduce dependencies in dashboard routes tests
- Update executor tests with exact command matching and improved assertions
- Update AGENTS.md with test optimization patterns (fake timers, unique temp dirs)
- Add MigrationOrchestrator with automatic project detection and registration
- Add FirstRunExperience with setup wizard for new users
- Add backward compatibility layer for single-project workflows
- Integrate migration hook into CLI entry point
- Add comprehensive tests for migration and first-run functionality
- Update AGENTS.md with multi-project migration and dashboard documentation
- Add Project Overview page with responsive grid and health status cards
- Add Project Selector dropdown in header for quick project switching
- Add Setup Wizard for registering new projects with auto-detection
- Implement project drill-down: click project to view its tasks
- Add global activity feed with cross-project activity log
- Add project health monitoring with real-time status polling
- Add deep linking support for tasks via ?task= URL parameter
- Add useTasks hook with project context filtering
- Add ntfy notification deep link to open tasks in dashboard
- Fix terminal error message formatting for agent failures
- Unify comment style across codebase (// instead of /** */)
- Add comprehensive tests for multi-project components
- Enable parallel file execution in core, engine, CLI, and dashboard packages via vitest.config.ts
- Optimize backup tests using fake timers instead of real setTimeout delays
- Add test optimization patterns to AGENTS.md documentation (fake timers, parallel execution)
- Add changeset documenting the test speed improvements
- Include test fixes for SettingsModal, engine tests, and git worktree mocks from KB-637
- Add ProjectRuntime interface with InProcessRuntime and ChildProcessRuntime implementations
- Implement HybridExecutor for multi-project task orchestration
- Add IPC protocol for host-worker communication in child-process mode
- Implement health monitoring with automatic restart for child processes
- Add comprehensive tests for hybrid-executor and project-runtime
- Update AGENTS.md with multi-project runtime documentation
- Add changeset for hybrid-executor-runtime release
- Add CentralCore API for cross-project coordination (project registry, health tracking)
- Add CentralDatabase with SQLite storage for projects, activity log, and concurrency
- Export central infrastructure types: RegisteredProject, ProjectHealth, GlobalConcurrencyState
- Add central integration tests for multi-project workflows
- Update AGENTS.md with CentralCore usage documentation
- Add core AI summarization service with model selection hierarchy
- Modify task store to support title generation callback pattern
- Add POST /api/ai/summarize-title endpoint with rate limiting
- Wire up summarization in dashboard task creation flow
- Add AI Summarization settings UI section in dashboard
- Add comprehensive tests for summarization service and API
- Document auto-summarization settings in AGENTS.md
- Add formatTaskIdentifier helper to format task references with title or description fallback
- Update notification messages to include task identifier context
- Show truncated description (200 chars) prefixed with task ID when no title
- Add comprehensive tests for formatTaskIdentifier function
- Add changeset for notification improvements and update AGENTS.md
- Rename all KB_* environment variables to FUSION_* prefix across CLI and dashboard
- Update CLI runtime files (native-patch.ts) and build configuration
- Update dashboard server, badge-pubsub, GitHub webhooks, and terminal service
- Update test files to use new FUSION_API_KEY and related env vars
- Update documentation in README, AGENTS.md, STANDALONE.md, and dashboard README
- Update changeset files with new environment variable names
- Add backup settings to ProjectSettings with schedule, retention, and directory config
- Create BackupManager with create, list, cleanup, and restore operations
- Add CLI backup commands: --create, --list, --restore, --cleanup
- Implement backup validation and automation sync for scheduled backups
- Add dashboard backup settings UI with stats and 'Backup Now' button
- Add backup API routes for settings management and manual operations
- Include comprehensive backup tests and changeset for patch release
- Document backup configuration and recovery in AGENTS.md
- Add SQLite database foundation with WAL mode, transactions, and JSON column helpers
- Implement auto-migration system from legacy file-based storage with .bak backup strategy
- Migrate TaskStore to SQLite with full test coverage (256 tests)
- Migrate AutomationStore to SQLite with full test coverage (48 tests)
- Add SQLite Storage Architecture documentation to AGENTS.md
- Include changeset for patch release
- 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
- 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 backend subtask breakdown session management and API endpoints
- Create SubtaskBreakdownModal component for generating AI-suggested subtasks
- Integrate subtask breakdown into QuickEntryBox and NewTaskModal flows
- Add frontend API client functions for breakdown sessions and subtask creation
- Add tests for SubtaskBreakdownModal and backend routes
- Create changeset documenting the subtask breakdown feature
- 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
