- Add MemoryInsights class in @fusion/core for AI-powered memory audit generation
- Add post-run hook to CronRunner for triggering memory summarization after scheduled tasks
- Wire memory background processing in both dashboard and serve commands
- Add memoryAuditEnabled and memoryAuditSchedule settings for configurable automation
- Fix startup ordering: sync automation before cronRunner.start() to prevent race conditions
- Add comprehensive tests for memory-insights and dashboard/serve integration
- Update contributing.md and settings-reference.md with documentation
- Add fn node list command to list all registered nodes with status and URL
- Add fn node show command to display detailed node information including system metrics
- Add fn node health-check command to trigger and verify node health status
- Add fn node remove command to unregister nodes from the mesh
- Add fn mesh status command to show mesh topology with peer connections
- Add comprehensive tests for all node and mesh CLI commands
- Update bin.ts to wire up new node and mesh subcommands
- Update memory with CLI mock pattern for testing
The cachedMaxConcurrent variable driving the AgentSemaphore was only
updated during unpause transitions and merge retry timers. Changing
maxConcurrent in the dashboard had no effect on the semaphore until one
of those events fired, causing fewer tasks to run than configured.
Also adds HeartbeatMonitor and HeartbeatTriggerScheduler wiring to both
serve and dashboard commands, with tests.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Require gh-authenticated paths for task pr-create and dashboard PR routes
- Switch dashboard command and extension GitHub tools to use the gh auth client instead of token-based auth
- Update CLI and dashboard tests to cover gh-only createPr and import behavior
- Refresh README guidance and add a changeset removing the GitHub token requirement for PR flows
- Update CLI build and runtime paths to emit and reference fn-named binaries across default and cross-target builds
- Adjust Bun binary bootstrap stubs and native patch temp/symlink prefixes to use fn naming consistently
- Update CI, release, and test-release workflows to validate and collect fn-prefixed artifacts
- Align CLI build and package config tests with fn binary expectations and add a patch changeset for @gsxdsm/fusion
- Rename all pi extension tool registrations from kb_* to fn_* across task, mission, and agent tool families
- Update extension and skill-sync tests plus Fusion skill docs/workflows to assert and document the new fn_* tool names
- Align product-identity strings across core, dashboard, and CLI references, including GitHub import examples, User-Agent headers, and terminal TERM_PROGRAM
- Add a @gsxdsm/fusion minor changeset describing the extension tool-prefix rename
- Wrap dashboard auth storage with API-key provider helpers derived from model registry providers
- Normalize provider display names and bridge set/clear/has API-key operations to AuthStorage credentials
- Expand route and onboarding tests for mixed OAuth/API-key states and API-key-authenticated setup paths
- Stabilize assignment-trigger heartbeat timing test by replacing fixed delays with waitFor assertions
- Add a core exporter that generates COMPANY.md, per-agent AGENTS.md files, and optional SKILL.md stubs with stable slug/link handling
- Export new Agent Companies exporter APIs from @fusion/core and extend manifest kinds to include skill entries
- Add fn agent export with project-aware agent loading, optional company metadata flags, and export summary/error output
- Add POST /api/agents/export route with request validation, agent ID filtering, custom/default output directory support, and exporter integration
- Add focused tests for core exporter behavior, CLI export command, and dashboard route handling
- Wrap TaskExecutor task:updated async listener logic in a top-level guard and log uncaught listener failures
- Add explicit catch handling for ProjectManager activity logging and dashboard stuck-detector settings-triggered checkNow calls
- Document async EventEmitter guard conventions in scheduler and hybrid executor listener wiring
- Add regression tests for executor and dashboard listener guards and include a patch changeset for @gsxdsm/fusion
- Update CLI command strings, help text, and project-resolution messaging to reference fn
- Sync core backup/store messaging and dashboard API/planning/subtask prompt examples with fn usage
- Refresh dashboard UI copy in settings, project detection, and PR guidance for consistent command naming
- Adjust CLI/dashboard tests and add a @gsxdsm/fusion changeset for the naming alignment patch
- Replace legacy companies.sh parser/types with the new agent companies parser and exported core types.
- Update CLI agent import wiring and tests to consume the new import source handling.
- Update dashboard agent import modal, API client, and import route tests to support archive-based sources.
- Add release-note changesets and lockfile updates for the @gsxdsm/fusion patch release.
- Add mission self-healing project settings for stale activation thresholds, task retry budgets, and mission health-check intervals
- Extend MissionAutopilot with failed-task retry handling, blocked feature escalation, stale activating mission recovery, and periodic feature/task consistency reconciliation
- Wire autopilot failure and recovery flows through Scheduler and InProcessRuntime, including startup recovery for watched missions after crashes
- Add blocked feature status support in core mission types and CLI mission status labels
- Expand mission-autopilot coverage for retry flows, stale/startup recovery, health checks, and regression scenarios, and include a patch changeset for @gsxdsm/fusion
- Add optional agentId parameter to kb_task_create and persist it as assignedAgentId
- Extend kb_task_create output/details to include assignee information when present
- Add kb_task_update support for setting or clearing assignedAgentId via agentId (including null)
- Expand extension tests for create/update/clear assignment flows and add a patch changeset for @gsxdsm/fusion
- Only require dist/bin.js in setup so tests do not depend on dashboard client artifacts being prebuilt
- Gate dashboard client asset assertion behind a presence check to avoid flaky environment-specific failures
- Add tsup.config.ts assertions to verify dashboard/dist/client is copied into cli dist/client during build
- Add resilient client asset staging in packages/cli/build.ts with automatic dist/client/index.html stub generation when dashboard assets are missing
- Update packages/cli/tsup.config.ts onSuccess hook to clear stale client output and emit the same minimal stub fallback in clean checkout builds
- Make bundle-output test build-aware by running pnpm build in beforeAll when bundle artifacts are absent, then assert client assets are present
- Preserve build output visibility by reporting whether real or stub client assets were staged
- Add a new serve command implementation that runs the dashboard server in headless mode and exposes a health endpoint
- Register the serve command in CLI routing and extend bin command coverage for dispatch behavior
- Add comprehensive serve command tests for startup flow, options handling, and health-check responses
- Fix mission event ordering in MissionStore to keep health snapshots deterministic under concurrent updates
- Include a changeset for @gsxdsm/fusion documenting the new fn serve capability
- 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 root .dockerignore to reduce build context and exclude local runtime state
- Add a multi-stage Dockerfile that builds the workspace, runs as non-root, and includes health checks
- Document Docker build/run usage, env vars, persistence, and quick-start commands in README and docs/docker.md
- Add Docker configuration tests in packages/cli/src/docker.test.ts to validate required image and docs expectations
- Add new `fn desktop` CLI command with argument handling and comprehensive command/bin tests
- Implement desktop build and hot-reload dev scripts and wire package scripts/dependencies for Electron workflows
- Add electron-builder configuration and desktop main-process/integration test coverage to stabilize packaging behavior
- Document desktop development and usage in README files and include a changeset for the published CLI package
- 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 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
- Fix pause-abort handler using updateTask({status: undefined}) which was a
no-op, leaving tasks stuck in 'specifying' forever after a pause interrupts
a session post-APPROVE. Changed to status: null to actually clear the field.
- Apply same fix to transient-error retry and general error catch paths.
- Wire StuckTaskDetector into TriageProcessor: trackTask/untrackTask/recordActivity
on session lifecycle, markStuckAborted to prevent stuck kills from being
reported as errors, and clear status to null on stuck-kill for next-poll retry.
- Update dashboard.ts to pass stuckTaskDetector to TriageProcessor and call
triageRef.current?.markStuckAborted in the shared onStuck callback.
- Add 3 tests covering pause-abort status clearing and stuck detector wiring.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 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
- Fix step status not being tracked correctly in executor callbacks (done/skipped were not updated)
- Expose runStepsInNewSessions and maxParallelSteps settings in CLI settings command
- Add AGENTS.md documentation for runStepsInNewSessions and maxParallelSteps settings
- Add changeset for the published CLI package
- Add tests for CLI settings validation and executor step status tracking
- 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
- Define AiPromptExecutor type and update CronRunner constructor to accept injected executor
- Implement executeAiPromptStep with real agent session execution in worktrees
- Create createAiPromptStepExecutor factory and wire up in dashboard CLI
- Add comprehensive tests for AI prompt step execution (mock agent, errors, output capture)
- Fix mock typing for dashboard test build compatibility
- Instantiate MissionAutopilot with TaskStore and MissionStore before Scheduler creation
- Pass missionAutopilot and missionStore to Scheduler constructor options
- Break circular dependency via setScheduler() after Scheduler construction
- Start autopilot in engine startup sequence, stop on graceful shutdown
- Add comprehensive tests verifying MissionAutopilot wiring in both test files
- Add `fn agent stop <id>` and `fn agent start <id>` CLI commands for pausing/resuming agents
- Add `kb_agent_stop` and `kb_agent_start` tools to the pi extension for in-session agent control
- Validate state transitions using AGENT_VALID_TRANSITIONS before applying changes
- Export AgentStore from @fusion/core public API
- Add comprehensive tests for agent CLI commands (210 lines)
- Add changeset for @gsxdsm/fusion patch release
- Wire AgentStore into TaskExecutor initialization within dashboard.ts startup
- Add AgentStore mock to dashboard command tests for proper test coverage
- Update test mocks to reflect new AgentStore dependency injection
- 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
- Extend retry API to accept 'stuck-killed' as a retryable status alongside 'failed'
- Update CLI retry command to recognize stuck-killed tasks
- Update pi extension retry tool to handle stuck-killed tasks
- Show retry button in TaskDetailModal for stuck-killed task status
- Add changeset for patch release
- Set project status to 'active' after registration in runInit (kb init)
- Set project status to 'active' after registration in runProjectAdd (kb project add)
- Set project status to 'active' after interactive registration in resolveProjectDirectory
- Add updateProject mock to init.test.ts, project.test.ts, and project-resolver.test.ts
- Add ContextLimitDetector to detect agent loops via repeated tool call patterns
- Implement compact-and-resume strategy: summarize conversation and restart agent from current step
- Add loop recovery to StuckTaskDetector with configurable attempt tracking and retry limits
- Extend executor with automatic loop recovery on context limit detection
- Add loop recovery support to pi executor with same compact-and-resume pattern
- Add comprehensive tests for context-limit-detector, stuck-task-detector loop detection, executor, and pi recovery
- Add changeset for patch bump to @gsxdsm/fusion
- Update README with loop detection and recovery documentation
When the stuck task detector killed a task and immediately called
moveTask("todo"), the scheduler could re-dispatch the task before the
old execution's finally block cleared this.executing. The new execute()
call hit the guard and silently returned, stranding the task in
"in-progress" with no active session or worktree (seen on FN-810/FN-912).
Move the requeue responsibility from StuckTaskDetector.killAndRetry to
the executor's finally block, which runs after this.executing.delete().
The beforeRequeue budget check now runs before session.dispose() and its
result is passed via StuckTaskEvent.shouldRequeue → markStuckAborted().
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add explicit no-progress loop detection signals to executor agent sessions
- Enhance stuck-task detector with configurable strategies (timeout, no-progress, combined)
- Add comprehensive test coverage for stuck-task detector (371 lines of tests)
- Remove modelFilter test utilities (198 lines of dead test code)
- Simplify modelFilter.ts by removing unused filtering logic
- Clean up dashboard server startup and minor README fix
- 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
