- Include user comments as context during AI triage spec generation and spec review
- Invalidate stale spec approvals when new user comments are added after approval
- Add lastApprovedAt tracking to task metadata for approval freshness detection
- Add comprehensive tests for comment-aware triage, review, and stale approval logic
- Add changeset for published package and update README with feature documentation
- Add valid board transitions from todo to in-review and in-review to todo (retry)
- Clear transient fields (agentId, worktree, branch, prInfo, mergeRetries, etc.) on in-review→todo transition
- Add Retry button to TaskDetailModal for in-review tasks
- Add tests for retry transition and transient field cleanup in store
- Clear prInfo, issueInfo, and modelPresetId in unarchiveTask to avoid stale badge/model data
- Clear prInfo, issueInfo, and modelPresetId in moveToDone after successful merge
- Add regression tests for transient field clearing in both code paths
- Fix existing tests to use public API instead of private methods
- Add scanOrphanedBranches utility to worktree-pool for detecting fusion/* branches with no matching task
- Add cleanupOrphanedBranches to SelfHealingManager with dry-run support and task re-registration
- Wire branch cleanup into deleteTask and archiveTask so branches are removed when tasks are deleted or archived
- Add comprehensive tests for scanning, cleanup, and integration with delete/archive flows
- Add mission store methods for pausing, stopping, and resuming missions with proper state transitions
- Implement feature triage flow that evaluates and classifies mission features
- Add scheduler blocked-task check to prevent scheduling when dependencies are unmet
- Create dashboard mission management UI with pause/stop/resume controls
- Add mission API routes for triage, pause, stop, and resume operations
- Add e2e tests for mission routes and unit tests for mission store and scheduler
- 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
Introduces ai_sessions table (schema v9), AiSessionStore, and background
session support for mission interviews, planning, and subtask breakdown.
Adds BackgroundTasksIndicator component, SSE-based progress streaming,
and dashboard API routes for session management.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add getFusionDir() method to TaskStore for resolving agent database path
- Update in-process-runtime to use getFusionDir() instead of hardcoded path
- Update dashboard routes AgentStore initialization to use getFusionDir()
- Add changeset for published package patch bump
- Fix resolveBaseBranch to use stored branch name and consistent fusion/ prefix
for both explicit deps and blockedBy paths (was using kb/ for blockedBy)
- Add main branch checkout verification in merger before squash merge to prevent
feature code from landing on wrong branch lineage
- Align all branch prefix references from stale kb/ to fusion/ across executor,
merger, store, and routes
- Fix executor test OOM by mocking merger fully, adding fake timers to retry
tests, and switching vitest pool to vmThreads
- Update all test assertions to use fusion/ branch prefix
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add defaultOn boolean to WorkflowStep type and store persistence
- Auto-apply default-on workflow steps when creating tasks
- Refactor AgentDetailView and AgentListModal components for cleaner rendering
- Add CSS styles for agent detail and list modal improvements
- Update TaskCard to display workflow step status badges
- Add comprehensive tests for defaultOn store logic and TaskCard behavior
- Add executionMode field to WorkflowStep type with 'agent' | 'api' options and validation
- Extend TaskStore CRUD with execution mode support and validation for prompt/description
- Add API validation layer in dashboard routes for workflow step create/update/delete
- Enhance WorkflowStepManager component with inline editing, validation feedback, and improved UX
- Add comprehensive tests for store CRUD validation and API route validation
- Clean up dashboard styles by removing unused CSS rules and dead test assertions
- Extend WorkflowStep type with optional modelProvider, modelId, validatorModelProvider, validatorModelId fields
- Add API endpoints (PATCH /api/workflow-steps/:id) to update model overrides on workflow steps
- Update executor to use per-step model overrides when running workflow step agents
- Add AgentDetailView support for displaying workflow step model configuration
- Add store and executor tests for new model override behavior
- Clarify in dashboard README that agent log entries are never truncated
- Add maxLength safeguards in store (getAgentLog), routes, useAgentLogs, and useMultiAgentLogs hooks
- Add tests for store, AgentLogViewer component, useAgentLogs hook, useMultiAgentLogs hook, and dashboard routes
- All tests verify that log text and detail fields are preserved in full without per-entry truncation
- Change MIN_DESCRIPTION_LENGTH threshold from 140 to 200 in ai-summarize.ts
- Update shouldAutoSummarize logic and tests for new 200-char threshold
- Update UI copy in SettingsModal and API/routes references
- Update store tests to reflect the new threshold value
- Remove obsolete dashboard activity-log mobile layout test files and unused CSS
- Add changeset for patch bump
- Add state to tasks: persisted in DB, gates scheduler pickup to prevent immediate retry of transient failures
- Introduce shared recovery-policy module with bounded exponential backoff (1s → 60s, max 5 attempts)
- Wire recovery policy into executor, scheduler, and triage so all agents respect the same retry cadence
- Persist retry state (attempt count, next eligible time) in task metadata via store and DB schema
- Add DB migration for new retry columns and update schema tests
- Update README with recovery policy documentation
- Refactor dashboard Header component and styles, consolidate header tests
- Fix session-files route tests to align with updated route signatures
- Derive readable refinement titles from source task title or first line of description instead of raw task ID
- Fall back to task ID only when both title and description are empty/whitespace
- Collapse internal whitespace in description-derived labels for clean output
- Update PROMPT.md heading to match the new readable refinement title
- Add comprehensive tests for title precedence, whitespace handling, and edge cases
- Document refinement naming behavior in README
- Add changeset for @gsxdsm/fusion patch release
- Stop merging steeringComments into comments array in rowToTask to prevent duplication
- Add regression tests verifying comments and steeringComments remain separate
- Add changeset for the comments deduplication fix
- Fix SSE event relay to properly broadcast task store events to dashboard clients
- Use named heartbeat events instead of SSE comments for reliable keep-alive
- Add missing event emission in core task store for state changes
- Add comprehensive tests for SSE pipeline, event emission, and UI hooks
- Remove broken useTerminal hook and AgentLogViewer tests, fix flaky test suites
- Fix addSteeringComment to skip auto-refinement and write directly to steeringComments array
- Update formatCommentForInjection to accept SteeringComment type instead of raw string
- Export SteeringComment type from @fusion/core for executor usage
- Add tests verifying steering comments are persisted to task store
- Fix executor import to use exported SteeringComment type
- Add 'branch' field to Task and ArchivedTaskEntry types with DB migration
- Executor stores branch name on task after worktree assignment
- Merger reads branch from task metadata instead of relying on worktree state
- Implement non-destructive conflict recovery in prepareForTask with reset/clean
- Add tests for branch storage, merger branch reading, and worktree recovery
- Add step synchronization when loading task from database
- Sync steps array from PROMPT.md file to keep task metadata in sync
- Add test coverage for getTask step sync behavior
- Remove terminal session functionality (useTerminalSessions hook and tests)
- Clean up unused terminal-related components and CSS
- Implemented multi-tab support in TerminalModal component
- Each tab maintains independent WebSocket connection and xterm instance
- Tab management: create, switch, close tabs with keyboard shortcuts (Ctrl+Tab)
- Added Plus button to create new tabs
- Added close button on tabs (except last remaining tab)
- Updated keyboard shortcuts text in status bar
- Connection status indicator per tab
- Per-tab scrollback buffers preserved when switching tabs
- Auto-cleanup of all sessions when modal closes
- Added comprehensive tests for multi-tab functionality
fix: update scheduler filesystem path from .kb to .fusion for task validation
style: clean up TaskDetailModal styling with reusable CSS classes
test: add comprehensive tests for file-service operations with mocked filesystem
- Store missionId alongside sliceId when MissionStore links a feature to a task
- Clear both linkage fields together when features are unlinked from tasks
- Preserve mission linkage fields through TaskStore reads, writes, and updates
- Expand mission and task store coverage for mission linkage persistence and cleanup
- fix TaskStore.getOrCreateForProject to resolve projects through BackwardCompat and support legacy .fusion/.kb detection
- add regression tests for exact-name project lookup, legacy cwd fallback, and fresh-schema task create/update persistence
- sync the tasks schema definition with missionId support so fresh databases match runtime migrations
- add project overview and selector styles for the multi-project dashboard UI
- Implement automatic PROMPT.md regeneration in updateTask() when title or description changes
- Add comprehensive tests for PROMPT.md sync behavior in store.test.ts
- Create changeset for the PROMPT.md sync fix
- Remove multi-project migration changeset (superseded)
- Update dashboard components and styles for setup wizard and provider icons
- Add MigrationOrchestrator with filesystem scanning and auto-registration
- Add FirstRunExperience with setup wizard state management
- CLI integration with automatic migration hook on first run
- Backward-compatible single-project mode support
- \"--project\" flag support for CLI multi-project targeting
- KB_SKIP_MIGRATION environment variable for recovery
- Graceful fallback when central database unavailable
- New fn init command to initialize kb projects
- Interactive first-run setup wizard API in dashboard
- Fix TaskStore sliceId persistence and bidirectional linking between tasks and features
- Add comprehensive mission integration tests for hierarchy, status rollup, and events
- Enhance E2E tests with reorder, cascade delete, and error handling coverage
- Add scheduler integration tests for mission slice activation
- Fix duplicate mission commands in CLI help text
- Add changeset for missions launch
- Consolidate steeringComments and comments into unified comments field using TaskComment type
- Remove SteeringComment type, migrate all comments to TaskComment format
- Update addComment to delegate to addTaskComment with auto-refinement for done tasks
- Merge legacy steeringComments data into comments during database migration
- Update dashboard API endpoint from /steer to /comments
- Update executor to use unified comments field for real-time injection
- Update PR comment handler to use addTaskComment method
- 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
- Merge steeringComments and comments into unified comments field in Task type
- Update TaskStore to use single comments array instead of separate steeringComments
- Add database migration to convert existing steeringComments to comments
- Update executor to inject all comments into AI execution context
- Update dashboard SteeringTab to use unified comments API
- Update CLI task steer command to use comments field
- Update PR comment handler to add comments via unified API
- Add modifiedFiles and baseCommitSha fields to task schema for tracking changes
- Capture list of modified files during task execution in the executor
- Add GET /tasks/:id/diff API endpoint to retrieve file list and patches
- Create TaskChangesTab component with expandable file diffs
- Integrate Changes tab into TaskDetailModal for in-progress, in-review, and done tasks
- Add CSS styles for diff viewer with syntax highlighting
- Update API client with fetchTaskDiff function and Project Management types
- 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 database migration to merge steeringComments into comments field
- Update SQLite schema and queries to use unified comments column
- Refactor TaskStore to handle single comments field instead of dual fields
- Update dashboard components (SteeringTab, TaskCard) for unified comments
- Update engine executor and PR comment handler for new field structure
- Remove deprecated steeringComments from types and interfaces
- Add modifiedFiles and baseCommitSha tracking during task execution
- Create GET /tasks/:id/diff API endpoint for file list and patches
- Build TaskChangesTab component with expandable file diffs
- Integrate Changes tab into TaskDetailModal for in-progress, in-review, and done tasks
- Add database columns and types for diff tracking
- Update executor to capture modified files during agent sessions
- Add project API methods and types (fetchProjects, registerProject, fetchProjectHealth, etc.)
- Add ProjectCard component with health metrics, status badges, and pause/resume actions
- Add server-side project management routes for multi-project orchestration
- Add ActivityFeed component with grouped entries and project badges
- Add SetupWizard component with 5-step project creation flow
- Fix TypeScript errors in server routes for listProjects and getGlobalConcurrencyState
The database was never properly closed on SIGINT/SIGTERM — WAL files were left
in a partially-written state causing "database disk image is malformed" errors.
Adds WAL checkpoint on close, synchronous=NORMAL pragma, SIGTERM handlers, and
a store.close() method that flushes all pending writes before exit.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add baseCommitSha field to tasks for diff computation baseline
- Track modified files in executor and store in database
- Add /api/tasks/:id/diff endpoint to serve unified diffs
- Add getTaskDiff() API client function in dashboard
- Create TaskChangesTab component with file list and diff viewer
- Integrate Changes tab into TaskDetailModal with proper styling
- Add changeset for the new diff viewer feature
- Rename data directory from .kb to .fusion across core, CLI, dashboard, and engine
- Update all path references in source files, tests, and CLI output
- Remove deprecated central-core infrastructure (central-core, central-db, central-integration)
- Remove obsolete test files (PlanningModeModal.test.tsx, ScheduleForm.test.tsx)
- Add changeset for the directory rename breaking change
- Add inline role editing to AgentListModal with clickable role icons
- Add handleRoleChange and handleRoleKeyDown handlers for role updates
- Persist view toggle (board/list) with localStorage alongside role editing
- Restore task prefix from FN back to KB for generated task IDs
- Restore branch naming from fusion/ back to kb/ for task branches
- Update branch name references in executor, merger, scheduler, and CLI
- Add touch gesture detection support to TaskCard component
- Update worktree grouping labels to use KB prefix
- Change default task prefix from KB to FN across all packages
- Rename branch naming pattern from kb/{id} to fusion/{id}
- Update all test assertions and fixtures to use new prefixes
- Add changeset for the breaking change
- Resolve merge conflicts in TaskCard.test.tsx touch gesture tests
- 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
