Adds a SelfHealingManager scan that finds tasks parked in in-review with
a failed pre-merge workflow step and no active session, and sends them
back through the existing sendTaskBackForFix flow (PROMPT.md injection,
step reset, todo → in-progress). Bounded by a new maxPostReviewFixes
setting (default 1) and a per-task postReviewFixCount so a persistently-
failing verifier cannot ping-pong a task indefinitely.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add a reusable .btn-secondary style (including light-theme hover/focus states) for reflections tab actions
- Initialize ReflectionStore in reflection API routes before reading or writing reflections
- Create AgentStore and ReflectionStore during in-process runtime startup and wire AgentReflectionService into TaskExecutor
- Reuse the initialized AgentStore for HeartbeatMonitor and trigger scheduler setup with non-fatal guards
- Apply a default 30s heartbeat interval when scheduler config is missing or invalid
- Dynamically register and update heartbeat triggers from AgentStore create/update events
- Register all non-disabled agents at startup and guard listener cleanup when stopping runtime
- Treat non-periodic agents as healthy in dashboard health checks to avoid stale-time false alarms
- Expand engine and dashboard tests and add a patch changeset for @gsxdsm/fusion
Why: tests were leaking ~700 per-temp-dir collection registrations
into the user's global ~/.config/qmd/index.yml because searchWithQmd
and the agent-memory qmd path called execFile("qmd", ...) with the
real binary, bypassing shouldSkipBackgroundQmdRefresh() which only
guarded the schedule* wrappers.
Guard both direct-execFile paths under the same skip flag and fall
back to file-based agent memory search when skipping.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add Memory section controls for enabling auto-summarize with threshold and cron schedule inputs
- Wire ProjectEngine to sync auto-summarize automation on startup and when related settings change
- Reuse a single startup settings snapshot when syncing insight extraction and auto-summarize automations
- Add SettingsModal and ProjectEngine tests covering auto-summarize UI persistence and automation re-sync behavior
- Add agent memory support to instruction resolution and introduce/export buildAgentChatPrompt for identity-aware prompt assembly with optional project memory
- Wire ChatManager to AgentStore so chat sessions can enrich system prompts per agent and include recent conversation context in prompt payloads
- Update server chat wiring to provide an AgentStore for prompt enrichment and keep graceful fallback behavior when agent context is unavailable
- Enrich HeartbeatMonitor system prompts with resolved agent instructions/ratings while preserving base-prompt fallback paths
- Expand dashboard and engine tests to cover prompt enrichment, fallback behavior, conversation context assembly, and AgentStore route mocks
- Wire MessageStore into the in-process executor runtime and project engine
- Forward MessageStore events through dashboard SSE infrastructure for mailbox updates
- Close mailbox pipeline gaps across API routes, server wiring, and mailbox UI components
- Add regression coverage for messaging routes, SSE forwarding, and agent tool behavior
- Document the MessageStore SSE wiring pattern in .fusion/memory.md
- Add list_agents tool for discovering agents by role, state, or includeEphemeral filter
- Add delegate_task tool for assigning work to a specific agent by ID
- Add comprehensive test coverage for both delegation tools in agent-tools-delegation.test.ts
- Update executor.ts to wire up delegation tools when agentStore is configured
- Document both tools in AGENTS.md and docs/agents.md
- Expose getAgentStore from runtime and engine packages
- Add includeSystem filter to getOrgTree API endpoint
- Wire AgentStore into SSE endpoint for event forwarding
- Forward agent events through the SSE pipeline
- Exclude ephemeral agents from org tree API and UI
- Filter ephemeral agents in useAgents hook
- Update AgentsView test to expect includeSystem filter
- Document agent SSE event forwarding architecture
- Auto-delete spawned child agents when their parent task terminates (reportsTo cleanup)
- Auto-delete task-worker agents when their owned task completes
- Add includeSystem filter to AgentStore.list() and REST API
- Hide system agents by default on the agents page (show only user-facing agents)
- Wire includeSystem toggle through the API layer and AgentsView component
- Add changeset for @gsxdsm/fusion patch release
- Add comprehensive tests for agent cleanup and includeSystem filtering
- Add pauseProject() and resumeProject() methods to ProjectEngineManager
- Wire pause and resume routes to engineManager with proper error handling
- Update frontend useProjectActions hook to use dedicated pause/resume APIs
- Add comprehensive tests for pause/resume in ProjectEngineManager
- Add route tests for project pause/resume with engineManager mocks
- Fix mock stubs for getProject/updateProject/updateProjectHealth
- Add scope field to automations and routines for granular control
- Update automation-store and routine-store with scope-aware query methods
- Extend database schema with scope column for automations and routines
- Update cron-runner and routine-scheduler to respect scope boundaries
- Add project context injection to in-process runtime for scoped execution
- Include changeset for minor version bump
Add self-healing for stale in-review tasks left in merging status after the merge commit lands. Recovery uses taskStuckTimeoutMs, records merge details, moves confirmed merges to done, and clears stale merge status for retry when no landed commit is found.
- Detect context-window-limit errors from AI sessions and automatically compact
the session conversation history before retrying (one attempt per session)
- Centralize auto-compaction in promptWithFallback (pi.ts) so executor, merger,
and step-session-executor all benefit from the same mechanism
- Remove scattered context-limit error handling from executor.ts, merger.ts, and
step-session-executor.ts in favor of the centralized approach
- Add comprehensive tests for auto-compaction retry behavior in pi.test.ts
- Remove unused compactSessionContext import from step-session-executor.ts
- Add memory note documenting the centralized auto-compaction design
- Add sendTaskBackForFix() method that encapsulates the 'verification failed
— send back to in-progress' pattern
- Replace all 4 hard failure locations with sendTaskBackForFix() calls
- Update failure feedback template to mention 'sent back to in-progress'
- Update test assertions for workflow step failure cases
- Rename test that verifies passing workflow step behavior
- Add new test for verification failure send-back flow
- Add addTaskComment mock to store factories for testing
The task executor now sends tasks back to in-progress (instead of 'in-review'
with 'failed' status) when workflow step verification fails and retries are
exhausted. This allows the executor to attempt to fix the issues on the
next pass, mirroring the existing deterministic verification failure behavior
in project-engine.ts.
- Add MailboxView as a full-page navigation view replacing the modal-based approach
- Migrate MessageStore from filesystem to SQLite backend for message persistence
- Implement conversation grouping for inbox display with unread badge state
- Remove modal plumbing (useModalManager, AppModals exports) and simplify App.tsx
- Add evictStaleProcessing() to TriageProcessor for self-healing hung triage sessions
- Add comprehensive MailboxView tests and Header mailbox tests
- Update README documentation with MailboxView features
- Add CSS styles for MailboxView component
- Fix MobileNavBar tests for mailbox tab visibility
- Replace filesystem-based message storage with SQLite backend
- Add MessageStore class using better-sqlite3 with WAL mode
- Update message.ts CLI command to use new MessageStore API
- Update dashboard routes and engine runtime for SQLite integration
- Update all related tests for new storage implementation
- Add SignalListener type definition to child-process-worker.test.ts
- Update mockImplementation callbacks to use unknown type instead of any
- Add proper TypeScript types to createAgentWithTaskDone opts parameter
- Use optional chaining for safer customTools access
- Use () => void | undefined type for resolvePrompt variables
- restart.integration.test.ts: add eslint-disable for Function/any types in mocks
- child-process-worker.test.ts: add eslint-disable for Function[] in baseline arrays
- Restore build to passing by avoiding overly strict type changes
- All tests pass
- child-process-worker.test.ts: replace Function[] with SignalListener type
- remote-node-runtime.test.ts: add yield statement to idleStream generator
- All 57 test files pass with 0 errors
- executor.test.ts: remove unused imports (Column, StuckTaskDetector),
replace Function type with EventListener, add MockTaskStore interface
- restart.integration.test.ts: replace require() with ESM import,
replace Function types with proper function signatures
- All tests pass
