- Expand fn agent import to accept directories, .tar.gz/.tgz/.zip archives, single .md manifests, and legacy .sh manifests
- Update /api/agents/import to handle agents array, source path, or manifest string inputs with dry-run previews and legacy fallback parsing
- Refresh AgentImportModal and dashboard API typing for new preview metadata, directory uploads, and improved error handling
- Add coverage for CLI import paths, dashboard import routes, modal behavior, and assignment route timeout stability
- Add a minor @gsxdsm/fusion changeset documenting Agent Companies import support
- Add a new NodeConnection utility that validates inputs, tests /api/health endpoints, normalizes URLs, and classifies connection failures
- Add CentralCore methods to test node connectivity and connect/register remote nodes, with duplicate-name checks and node:connection:test event emission
- Export NodeConnection types and APIs from @fusion/core for external consumers
- Add comprehensive unit coverage for NodeConnection and CentralCore connection flows, and increase dashboard assignment test setup timeout to reduce build/test flakiness
- Add aiSessionTtlMs and aiSessionCleanupIntervalMs project settings with defaults and bounds for cleanup scheduling
- Extend AiSessionStore cleanup to expire stale in-progress sessions, emit deletion events, and support start/stop scheduled cleanup loops
- Wire server startup/shutdown to load cleanup settings and manage the scheduled ai_sessions sweep lifecycle
- Align planning, subtask breakdown, and mission interview in-memory session retention to a 7-day TTL with shared deletion-driven cleanup
- Update schema/tests/docs for migration v15 ai_sessions indexing and end-to-end cleanup/TTL behavior stability
- Add dashboard routes for /agents/org-tree and /agents/resolve/:shortname with scoped store wiring and 404 handling
- Add /agents/:id/chain-of-command endpoint to return reporting hierarchy from self to top manager
- Extend dashboard app API with OrgTreeNode export plus fetchOrgTree, fetchChainOfCommand, and resolveAgent helpers
- Add route tests covering org-tree, resolve, and chain-of-command success and not-found scenarios
- Add a shared SSE event buffer utility and wire it into planning, subtask, mission interview, and task stream routes
- Support Last-Event-ID replay semantics and robust event serialization so clients can recover missed stream events
- Add a resilient client-side reconnect wrapper and surface reconnecting state in planning, subtask breakdown, and mission interview modals
- Expand test coverage across API routes, SSE buffering behavior, reconnect handling, and mission/planning stream flows
- Add GET /api/memory and PUT /api/memory routes with project-scoped file access and validation
- Add fetchMemory and saveMemory dashboard API helpers for memory file operations
- Extend the Settings modal Memory section with inline FileEditor loading, dirty tracking, save action, and read-only behavior when memory is disabled
- Add SettingsModal tests covering memory load, loading state, save flow, and empty-content handling
- Add planning model selection UI to PlanningModeModal initial view with model loading, favorites wiring, and default/custom badge state
- Extend startPlanningStreaming client API to send optional planningModelProvider/planningModelId overrides
- Propagate planning model overrides through /planning/start-streaming and createSessionWithAgent so agent creation uses selected model settings
- Add frontend and backend tests covering modal selection behavior, request forwarding, and end-to-end planning model flow
- Add a shared interview Q&A formatter for planning history across question types
- Append formatted interview context to generated subtask descriptions when history exists
- Include the same interview context in multi-task planning log entries for created tasks
- Expand planning tests to cover formatter behavior and subtask description context handling
- Include complete planning sessions in active session queries and background tracking
- Add create-task fallback to recover completed planning data from persisted ai session records
- Validate and reconstruct summary/initial plan data from stored JSON before creating tasks
- Expand tests for modal resume flow, session-store filtering, and route fallback behavior
- Define canonical agent permission types and export permission helpers from @fusion/core
- Add permission normalization and access-state computation with role defaults plus explicit grants
- Extend AgentStore with getAccessState and add unit tests for permission logic and store behavior
- Add dashboard routes for GET /api/agents/:id/access and PATCH /api/agents/:id/permissions with request validation and serialization
- Add a minor changeset for @gsxdsm/fusion documenting the new agent permission endpoints
- Define and export agent config revision types in @fusion/core for revision metadata and snapshots
- Persist config revisions in AgentStore with type-safe snapshot diffing when agent runtime config changes
- Add dashboard routes to list agent config revisions and fetch individual revision details
- Add focused tests for core revision persistence flows and dashboard agent revision route behavior
- Update Claude usage window normalization to set resetAt when API omits reset timestamps
- Derive fallback resetAt as now plus the computed window duration while preserving existing resetMs/resetText behavior
- Expand usage tests to assert fallback resetAt is present and approximately 5 hours in the future in both affected scenarios
- Harden core AgentStore lifecycle behavior and heartbeat runtime integration paths
- Align dashboard agent APIs, server routes, and agent UI flows with the updated contract
- Tighten CLI agent/message command routing and validate payload handling semantics
- Expand test coverage across core, dashboard, engine, and CLI for route, heartbeat, and instruction regressions
- Add shared plugin types and manager modules for splash screen, status bar, and network handling
- Export plugin initialization from the dashboard entrypoint and configure Capacitor splash/status-bar defaults
- Add unit tests covering plugin initialization and each manager's behavior across supported scenarios
- Document the plugin manager architecture and add required Capacitor plugin dependencies
- Add AgentApiKey and AgentApiKeyCreateResult types and export them from @fusion/core
- Implement AgentStore API key create/list/revoke methods with SHA-256 token hashing and JSONL persistence
- Add comprehensive AgentStore coverage for CRUD behavior, revocation semantics, persistence, and concurrent key creation
- Add dashboard routes and API tests for POST/GET/DELETE agent key endpoints with 404/validation handling
- Add a minor @gsxdsm/fusion changeset for the new agent API key feature
- Add assignedAgentId to core task types, database schema migration, and TaskStore persistence flows
- Implement dashboard assignment API routes for setting and clearing task-to-agent assignments
- Expand core and dashboard test coverage for persistence, migration behavior, and assignment route handling
- Add a changeset for the published CLI package to document the assignment core update
- Add dashboard /api/nodes CRUD, health-check, and metrics routes backed by CentralCore with request validation
- Extend project updates and frontend API types to support node assignment via nodeId
- Add dashboard API client helpers for node list/register/update/delete/health/metrics operations
- Implement fn node list/add/remove/show/health commands with validation, confirmation, and table/JSON output
- Add route and CLI/bin tests plus a minor @gsxdsm/fusion changeset for node management support
- Add Capacitor dependencies and dashboard scripts for sync, open, run, and mobile preparation
- Add a typed dashboard capacitor.config.ts with dist/client webDir and FUSION_BACKEND_URL server override
- Add Vitest coverage for Capacitor config shape, app identity, webDir, cleartext mode, and env URL behavior
- Ignore generated iOS/Android platform directories and document the end-to-end mobile workflow in the dashboard README
- Add flex-column base layout for .mailbox-modal and make .mailbox-content grow/scroll correctly
- Introduce a dedicated <=768px mailbox mobile CSS section for header, tabs, detail view, and FAB spacing
- Add MailboxModal regression tests that assert required CSS rules and detail-view structural hooks
- Increase batch GitHub issue import route test timeout to 30s for slower retry paths in CI
- Add HeartbeatTriggerScheduler class with timer, assignment, and on-demand trigger types
- Wire timer-based periodic wakeups using per-agent heartbeatIntervalMs config
- Add agent:assigned event in AgentStore for assignment-triggered wakeups
- Enhance POST /api/agents/:id/runs with WakeContext and 409 conflict on concurrent runs
- Integrate trigger scheduler into InProcessRuntime lifecycle (start/stop)
- Add enabled field to AgentHeartbeatConfig for per-agent trigger control
- Update AGENTS.md with heartbeat trigger scheduling documentation
- Add instructionsPath and instructionsText fields to Agent type and AgentStore
- Create agent-instructions resolver module in engine with priority-based resolution
- Wire custom instructions into executor, triage, reviewer, and merger agents
- Add PATCH /agents/:id/instructions API endpoint with file and text support
- Add instructions editor UI to dashboard agent detail config tab
- Add comprehensive tests for instructions resolver and AgentStore integration
- Add changeset for published package bump
- Wire heartbeatMonitor into ServerOptions and pass through to API routes
- Add POST /api/agents/:id/runs route to trigger heartbeat execution with optional source/triggerDetail
- Update API client startAgentRun to accept optional source and triggerDetail parameters
- Add Run Heartbeat button to AgentsView and enhance AgentDetailView RunsTab with execution details and polling
- Add route handler tests for agent runs and UI static analysis tests
- Support run history display with status, duration, trigger type, and result details
- Add planningModelProvider/planningModelId fields to task model and API batch-update endpoint
- Wire triage engine to use per-task planning model override with settings hierarchy fallback
- Add planning model selector to TaskDetailModal Model tab
- Add comprehensive tests for triage engine planning model resolution and dashboard API/routes
- Add backend API endpoint for time-range filtered agent log retrieval (GET /api/agents/:id/logs)
- Add fetchAgentRunLogs API function in dashboard client
- Make RunsTab run cards clickable with inline log viewer accordion
- Make AgentRunHistory run rows clickable to expand and view logs
- Enhance AgentDetailView with collapsible log sections and time-range filtering
- Add comprehensive tests for store, routes, and component click behavior
- 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 companies.sh type definitions and parser in @fusion/core with comprehensive tests
- Create CLI `kb agent-import` command to import agents from companies.sh
- Add POST /api/agents/import dashboard endpoint with dry-run support
- Build AgentImportModal component with search, preview, and batch import UI
- Add dashboard route tests for the agent import API endpoint
- Create changeset for @gsxdsm/fusion minor bump
- Remove hardcoded/planned stub responses from planning createSession and related functions
- Wire AI agent into planning session for interactive Q&A-based task planning
- Update JSDoc to remove stub references and reflect actual implementation
- Add comprehensive tests for AI-powered planning (planning.test.ts, routes.test.ts)
- Add mock agent setup to routes test for planning endpoint coverage
- 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 POST /tasks/:id/spec/rebuild API endpoint to regenerate task specifications
- Add rebuildTaskSpec client function in dashboard API layer
- Add respecify button to task detail modal for triggering spec rebuilds
- Add comprehensive tests for the spec/rebuild endpoint covering success, error, and edge cases
- Add GET /agents/:id/children API endpoint to fetch child agents of a parent
- Create fetchAgentChildren API function with tests in dashboard client
- Implement useAgentHierarchy hook with recursive tree loading and expand/collapse
- Add tree view mode to AgentsView with hierarchical agent display
- Enhance AgentDetailView with parent info and expandable children section
- Add tree view CSS styles for connection lines and expand/collapse indicators
- Add POST /api/missions/:missionId/start backend endpoint to start planning missions
- Add startMission() frontend API function in dashboard api.ts
- Add Start button in MissionManager component for planning missions
- Add integration tests for the startMission endpoint covering success, error, and edge cases
- Fix TaskChangesTab overcounting changes for done tasks by handling missing commit SHA gracefully
- Add /api/tasks/:id/diff endpoint with fallback for done tasks without merge commit info
- Add comprehensive tests for both TaskChangesTab component and diff route edge cases
- Document done-task Changes tab fallback behavior in README
- Add onKeyDown handler to CustomModelDropdown portal container for keyboard event forwarding
- Wrap SettingsModal empty state assertions in waitFor for async test stability
- Extract rate limiter state for proper test isolation in routes tests
- Add reconcileProjectStatuses to CentralCore mock for consistent test setup
- Improve /api/ai/summarize-title rate limiting with per-test isolation
- Add reconcileProjectStatuses() method to CentralCore that scans all registered projects and updates stale health records
- Integrate reconciliation into the GET /api/projects dashboard route so statuses are refreshed on read
- Add comprehensive tests for CentralCore reconciliation logic (144 lines)
- Add route-level tests verifying reconciliation runs before response (61 lines)
- Add backend file operations (copy, move, delete, rename, download) in file-service.ts with workspace root protection
- Add API routes for file operations including directory download as zip via archiver
- Add client API functions in api.ts for all file operation endpoints
- Add context menu UI in FileBrowser component with operations dialog for confirming destructive actions
- Add CSS styles for context menu including danger items and dividers
- Add 33 FileBrowser context menu tests and 485+ file-service tests
- Fix pre-existing test failures in routes-diff, mission-e2e, and theme sync tests
- When the Claude usage API omits resets_at for the 5-hour session window, fall back to using the full window duration as resetMs
- This enables pace calculation and reset text display even without an explicit reset timestamp
- Update existing test to verify fallback behavior (resetMs = 5h, resetText = 'resets in 5h')
- Add new test for pace calculation with fallback reset time
- Add MissionSummary type and getMissionSummary method to MissionStore
- Include mission summary data in GET /missions API endpoint
- Update frontend types and API client for mission summary
- Display mission status summary with progress bar on MissionManager list cards
- Add CSS styles for progress bar and summary display
- Update MissionManager tests for summary display
- Remove isClaudeWeeklyWindow() suppression logic so absolute reset timestamps display for all provider windows
- Populate resetAt field in Codex (reset_at / reset_after_seconds), Gemini (resetTime), Minimax (remains_time), and Zai (nextResetTime) providers
- Enable fallback relative text generation for all windows when resetText is null but resetAt exists
- Add tests for resetAt extraction across Codex, Gemini, Minimax, and Zai providers
- Update UsageIndicator component tests to reflect that all windows now show absolute reset dates
- When a slice is activated and has autoAdvance enabled, automatically triage all features in that slice
- Add auto-triage logic to mission-store activateSlice method
- Add comprehensive tests for auto-triage behavior covering edge cases
- Fix module import paths across mission-related files (mission.ts, extension.ts, mission-integration.test.ts, mission-routes.ts, scheduler.ts)
- Add defaultOn field to WorkflowStep model, API endpoints (GET/POST/PATCH), and WorkflowStepManager UI
- Add skip-default-steps checkbox to TaskForm and NewTaskModal for explicit opt-out of default workflow steps
- Pre-select default workflow steps on new task creation forms automatically
- Add CSS styling for skip-default-steps toggle row
- Add comprehensive tests for WorkflowStepManager, TaskForm, and NewTaskModal components
- Add route tests for PATCH workflow-step endpoint and default selection logic
- Update README and task-structure reference docs
When tasks fail and retry, the old worktree lingered on disk and the new
worktree got a random name causing worktrunk to report it as unassigned.
Now: retry clears worktree/branch fields, removes old worktree from disk,
and createWorktree returns the actual branch name (including -2 suffixes)
so task.branch always matches reality.
Also fixes pre-existing test failures: Terminal WebSocket mock sessions
missing lastActivityAt, and TerminalModal keyboard overlap tests leaking
cached _initialViewportHeight between tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
