- Add BlockedStateSnapshot typing/export and AgentStore persistence APIs for last blocked heartbeat state
- Deduplicate blocked-task heartbeat comments using blockedBy + context hash, and clear blocked snapshots when tasks are no longer blocked
- Thread triggeringCommentIds/triggeringCommentType through heartbeat execution, wake context, scheduler assignment triggers, and runtime wiring
- Trigger immediate heartbeat runs from task/steering comment routes for assigned immediate-response agents, with validation for comment wake fields on /api/agents/:id/runs
- Expand core, engine, and dashboard tests to cover blocked dedup logic, comment-triggered wakes, validation, and skip scenarios
- Add InboxTask typing and TaskStore.selectNextTaskForAgent() with priority ordering, dependency checks, paused filtering, and FIFO selection
- Wire heartbeat execution to auto-select and assign inbox work when no task is set, with optional checkout attempts and graceful conflict fallback
- Add POST /api/agents/:id/inbox to expose next-task selection details (task, priority, reason) and return task:null when no work is available
- Expand core, engine, and dashboard tests to cover selection priorities, heartbeat precedence/metadata, checkout-conflict handling, and route behavior with type-safe mocks
- Add checkout lease types and conflict error exports, plus DB schema v20 migration for checkedOutBy/checkedOutAt
- Persist checkout lease fields in TaskStore and add AgentStore checkout/release/force-release/get-holder operations
- Add dashboard checkout API routes for acquire/release/force-release/status with explicit 409 conflict and 403 holder enforcement
- Enforce checkout ownership in heartbeat execution with graceful checkout_conflict exits when another agent holds the lease
- Expand core and dashboard test coverage for schema, store behavior, API routes, and leasing workflows, and document leasing behavior in AGENTS.md
- Add heartbeat stopRun support in the engine and wire it into the dashboard server lifecycle
- Add an agent run stop API route and client helper with route-level test coverage
- Add stop controls in AgentDetailView and AgentRunHistory with updated UI tests
- Add a changeset for @gsxdsm/fusion documenting the new stop run feature
- Replace dashboard calls to local getCurrentGitHubRepo helpers with getCurrentRepo from @fusion/core
- Update engine scheduler PR-monitor startup paths to use shared core repo resolution
- Remove duplicated remote parsing implementations from dashboard and engine packages
- Mark gap analysis finding 6.3 as resolved after centralizing parsing logic
- Update executor, triage, and merger prompt strings to identify the product as "fn"
- Align branch/worktree documentation examples with fusion/fn-* naming conventions
- Rename dashboard websocket attachment guard from __kbWebSocketsAttached to __fnWebSocketsAttached
- Refresh engine tests, dashboard utility comments, and TUI header text to remove stale kb wording
- 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
- Wire AgentLogger into heartbeat runs, including tool/text callbacks and stdout excerpts on run records
- Persist heartbeat context taskId snapshots earlier and ensure logger flushes on success and failure paths
- Pass TaskStore into StepSessionExecutor and flush per-attempt agent logs in finally cleanup
- Expand heartbeat and step-session tests to verify log persistence and flush behavior, and add a patch changeset for @gsxdsm/fusion
- Add task_document_write and task_document_read factories with schemas, revision-aware responses, and error handling in agent-tools
- Wire document tools into executor and triage sessions and update prompts to persist and reuse planning artifacts across runs
- Export document tool factories and parameter schemas from engine public entrypoints while keeping executor re-export compatibility
- Add comprehensive tests covering write/read success paths, empty/not-found cases, and store failure handling
- Gate heartbeat runs in executeHeartbeat when agents are over budget and skip timer runs above threshold
- Pause agents with pauseReason "budget-exhausted" when run usage pushes them over budget
- Budget-gate assignment and timer triggers in HeartbeatTriggerScheduler and include budgetStatus in assignment wake context
- Expand agent-heartbeat test coverage for budget exhaustion, threshold behavior, pause transitions, and trigger gating
- 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
- Move single-session and step-session executor failure paths to in-review after marking tasks failed
- Route exhausted transient recovery retries to in-review instead of leaving tasks outside review flow
- Move stuck-kill budget exhaustion failures in self-healing to in-review and update failure log wording
- Add regression tests in executor and self-healing suites to verify in-review transitions on these failure states
- 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 generation tracking plus dedicated SIGKILL and restart timer fields in ChildProcessRuntime
- Guard delayed kill/restart callbacks so stale generations and stopping runtimes are ignored
- Clear pending lifecycle timers during stop and before rescheduling to prevent stacked callbacks
- Expand child-process runtime tests to cover timer cancellation, generation safety, and spawn generation increments
- Add mission observability types and core exports for mission health snapshots and event records
- Extend SQLite schema and MissionStore with mission_events persistence plus health and staleness query helpers
- Emit mission start and autopilot lifecycle events from MissionAutopilot for richer runtime telemetry
- Add dashboard mission observability routes and end-to-end coverage for mission events and health APIs
- Expand unit tests across core and engine and include a changeset for mission observability updates
- Extend agent instruction resolution to append a Performance Feedback section with average score, trend, category breakdown, and recent comments when ratings exist
- Add rating-aware instruction resolution with graceful fallback when no store is configured, agent IDs are missing, or rating lookup fails
- Wire executor custom instruction loading to fetch agent rating summaries and include them in resolved instructions
- Expand agent-instructions tests to cover feedback formatting, trend indicators, comment limits, and fallback/error paths
- Extend project settings with reflection enablement, interval, and post-task trigger defaults
- Implement AgentReflectionService to gather agent/task history, generate structured AI reflections, and persist reflection metrics
- Add reflect_on_performance tool factory with optional focus area input and human-readable reflection output
- Wire reflection tool into TaskExecutor only when reflection is enabled and the task has an assigned agent
- Add comprehensive reflection service/tool tests and stabilize agent-store org tree expectation ordering
- Extend ntfy event types and default ntfyEvents to include awaiting-approval
- Send high-priority "Plan needs approval" notifications for awaiting-approval task updates with deep-link support
- Add Notifications settings checkbox handling for awaiting-approval event selection in Settings modal
- Expand notifier and settings modal tests for awaiting-approval defaults, toggles, filtering, and deduplication
- Update AGENTS.md ntfy documentation and sample config to include the new event
- Show resolved default executor, validator, and planning models in the task Model tab
- Pass merged settings into the Model tab from TaskDetailModal so default badges reflect effective runtime resolution
- Hot-swap active single-session executor models when task overrides change, including fallback to project defaults when overrides are cleared
- Add dashboard and executor tests for default model display, hot-swap behavior, fallback logic, and failure logging
- Document hot-swap behavior and limitations in AGENTS.md and add a patch changeset for @gsxdsm/fusion
- 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 RemoteNodeClient and RemoteNodeRuntime with comprehensive lifecycle, status, and metrics test coverage
- Route projects by node assignment in ProjectManager and integrate remote runtime handling in HybridExecutor
- Introduce NodeHealthMonitor and wire diagnostic logging/export updates for remote node health tracking
- Harden remote runtime shutdown checks and type-safety paths surfaced during review feedback
- 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 MessageResponseMode and messageResponseMode runtime config to core agent heartbeat types and exports
- Extend MessageStore with an onMessageToAgent hook plus runtime hook updates for agent-directed messages
- Wire HeartbeatMonitor to wake agents on incoming messages when messageResponseMode is immediate and state is eligible
- Update AgentDetailView with a Message Response Mode setting, validation, and runtimeConfig persistence
- Expand core and engine tests to cover hook behavior, wake-on-message triggering, and start/stop hook lifecycle
- 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
- Fix child agent session mock to use never-resolving prompt so spawned child count stays accurate during limit checks
- Remove flaky spawnedAgents assertion in terminateChildAgent test (cleanup is done by terminateAllChildren)
- Add missing prompt mock to runSpawnedChild dispose test session
- Extract per-task thinkingLevel from task detail, falling back to global defaultThinkingLevel
- Apply override in initial execution, retry session, and spawned agent paths
- Add 3 tests: per-task override, global fallback, explicit 'off' overrides global
- 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
- 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
- Track tasks created during heartbeat runs and clean them up on subsequent heartbeats
- Add heartbeatRunId to correlate tasks created within the same run
- Implement stale heartbeat run cleanup in checkMissedHeartbeats
- Add comprehensive test suite (276 lines) covering run tracking, cleanup, and edge cases
- Extend HeartbeatMonitor with task creation metadata and run lifecycle management
- Extract shared agent tools (bash, read, write, edit) from executor into agent-tools.ts for reuse
- Implement heartbeat execution in HeartbeatMonitor with configurable interval and task_done support
- Wire heartbeat execution into InProcessRuntime lifecycle (start/stop)
- Add comprehensive test suite covering execution, timeouts, concurrency, and error handling
- Add heartbeat-related log constants to logger
- 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
- 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
- Add project-memory module in @fusion/core with read/write/resolve helpers and upsert-on-store hook
- Bootstrap project memory during task creation (store) with structured task context
- Inject resolved project memory into executor and triage agent system prompts
- Add comprehensive tests for project-memory module, store integration, and agent prompt changes
- Document project memory architecture and usage in README
- Define StepSessionExecutor interfaces and utility types (FN-1039)
- Implement StepSessionExecutor class with parallel wave execution, conflict detection, and retry logic (FN-1039)
- Add comprehensive test suite for StepSessionExecutor (1225 lines) (FN-1039)
- Wire step-session execution branch into TaskExecutor with pause, stuck-kill, and global pause handlers
- Track active step executors per task for lifecycle management and cleanup
- Export StepSessionExecutor and types from engine package index
- Add executor integration tests for step session lifecycle (388 lines)
- Add MergeDetails type import and mergeDetails field to TaskStore.updateTask signature
- Store merge details (commitSha, filesChanged, insertions, deletions, mergeCommitMessage, resolution info) after successful squash merge
- Capture best-effort commitSha even when branch is not found (mergeConfirmed: false)
- Add comprehensive tests for store updateTask with mergeDetails and merger detail collection
- Update triage agent to proactively suggest splitting large tasks into subtasks during specification
- Tighten reviewer guidance to flag undersplit tasks that should be broken down further
- Add comprehensive tests for proactive subtask creation in triage (192 lines)
- Add reviewer tests for undersplit task detection (12 lines)
- Update README with documentation on proactive subtask splitting behavior
- 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 tokenCap to ProjectSettings with tokenCapEnabled flag, default 500K tokens
- Create TokenCapDetector class with usage tracking and cap enforcement
- Wire TokenCapDetector into executor agentWork() to auto-fail tasks exceeding cap
- Add token cap input fields to Settings Modal dashboard UI
- Add comprehensive unit tests for TokenCapDetector (174 lines)
When a configured primary/fallback model isn't found in the registry,
check if the provider has any known models and construct a model
on-the-fly using that provider as a template (mirroring the pi CLI's
buildFallbackModel logic). This lets any valid provider model ID work
(e.g. any OpenRouter model string) without requiring it to be in the
built-in or custom model list. Only throw if the provider itself is
completely unknown.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
