Add MissionExecutionLoop mock to @fusion/engine vi.mock block in
serve.test.ts. The mock provides start, stop, processTaskOutcome,
and recoverActiveMissions methods to match the actual class interface.
Also adds the scrutiny synthesis report for milestone execution-loop
which identifies 3 blocking issues in FEAT-004:
- parseValidationResult stub always returns pass
- notifyValidationComplete passes featureId instead of taskId
- recoverActiveMissions doesn't perform state transitions
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
The merger's test/build verification, executor's worktreeInitCommand,
setupScript, and script-mode workflow steps all used execSync, which
blocks Node's event loop until the child process exits. A hanging
pnpm test could freeze the entire engine (no logs, heartbeats, or
other task progress) for the full 5-minute timeout.
Switch these call sites to promisify(exec) with awaited calls so the
engine keeps running while user-configured commands execute. Short
internal git plumbing (rev-parse, branch -d, worktree remove) still
uses execSync since those commands are bounded and measured in ms.
Document the rule in AGENTS.md under a new "Engine process rules"
section so future agents don't reintroduce blocking behavior.
Tests: update child_process mocks in merger.test, executor.test, and
restart.integration.test to route the new async exec through the
existing execSync mock and expose promisify.custom so destructuring
{ stdout, stderr } matches real child_process.exec semantics.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add recordValidatorFailures() method to store assertion failures with generated IDs
- Add createGeneratedFixFeature() to create fix features with lineage tracking
- Add getFeatureLoopSnapshot() to return complete loop state with retryBudgetRemaining
- Add getValidatorRunsByFeature() returning runs ordered by startedAt DESC
- Add getFailuresForRun() returning failures ordered by createdAt ASC
- Add transitionLoopState() with validation for all valid loop state transitions
- Implement retry budget enforcement: blocks implementing when budget exhausted
- Add rowToFailure() and rowToLineage() converters
- Add generateFailureId() and generateLineageId() ID generators
- Add DEFAULT_IMPLEMENTATION_RETRY_BUDGET constant (3 attempts)
- Update MissionFeatureLoopSnapshot interface to include retryBudgetRemaining
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
This commit adds the schema migration and types for the mission execution loop validation system:
- Adds loop state tracking columns to mission_features table (loopState, implementationAttemptCount, validatorAttemptCount, lastValidatorRunId, lastValidatorStatus, generatedFromFeatureId, generatedFromRunId)
- Creates mission_validator_runs table for tracking validation runs
- Creates mission_validator_failures table for assertion failure records
- Creates mission_fix_feature_lineage table for tracking fix feature relationships
- Adds workflowStepRetries column to tasks table for retry tracking
- Adds FEATURE_LOOP_STATES and VALIDATOR_RUN_STATUSES enums
- Updates TaskStore to support workflowStepRetries field
- Updates TaskExecutor to handle workflow step failures with retry logic
Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
- Add projectId parameter to refineText API and TaskForm for proper scoping
- Update mission routes to require projectId and add regression tests
- Add mission interview fallback to mission-level context when target not found
- Add AI refine route scoping tests for project isolation
- Update component tests to expect projectId argument
- Update prompt-keys test counts for new system prompts
- Add FileMemoryBackend with atomic writes, persistence, and conflict resolution
- Add ReadOnlyMemoryBackend for read-only/external memory management
- Add memoryBackendType setting to select backend type (file or readonly)
- Add GET /api/memory/backend endpoint to query current backend status and capabilities
- Update AGENTS.md, README.md, and docs with architecture and settings guidance
- Add memory-backend.test.ts with comprehensive tests for all backends
- Add routes.test.ts coverage for /api/memory/backend endpoint
- Fix settings parity test to include new memoryBackendType key
- Detect when merge prompt exceeds context limit and gets truncated
- Retry merge with compacted prompt when truncation is detected
- Create fresh session after context limit recovery
- Add comprehensive tests for truncation detection and recovery flow
- Update merge prompt generation to include truncation signal
- Add step-based dependency to useTaskDiffStats hook to trigger refetch when task steps change
- Implement 5-second polling interval for live diff statistics updates
- Add comprehensive test coverage for polling behavior and step-change detection
- Update TaskCard to pass step information to useTaskDiffStats
- Add TaskCard unit tests for diff statistics display
- Fix More sheet content padding on iOS devices with notched screens
- Add CSS regression tests for safe-area-inset-* rules in mobile nav bar
- Ensure consistent padding for content area across different device safe areas
- Import resolvePrompt and PromptOverrideMap from @fusion/core
- Add promptOverrides parameter to all agent creation paths:
- createMissionInterviewSession
- submitMissionInterviewResponse
- retryMissionInterviewSession
- initializeAgent
- createMissionInterviewAgent
- ensureMissionInterviewAgent
- Use resolvePrompt('planning-system', promptOverrides) for effective prompt
- Fall back to MISSION_INTERVIEW_SYSTEM_PROMPT when override absent
- Update module docs to reflect prompt override behavior
Broaden the auto-heal pattern to cover build-verification failures and
add a 30m idle cooldown so tasks that exhausted mergeRetries without
matching the narrow heal pattern get another sweep-driven attempt
instead of being stranded until a human clears the counter.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Deterministic verification failures were embedding the raw stderr/stdout
(up to 50MB per VERIFICATION_COMMAND_MAX_BUFFER) in a second log entry,
flooding logs/stdout and crashing the app. The runVerificationCommand
helper already wrote a truncated summary, so verifyDeterministicBuild
now just references it.
When the failure surfaces in the dashboard merge handler, kick the task
back to in-progress with a steering comment so the agent can fix the
failing test/build instead of parking it in in-review with a fatal
error.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add SplitMenu component for reusable dropdown menus in modal footers
- Update TaskDetailModal footer to use LeftMenu (Plan, Subtask, Models) and RightMenu (Save, Close)
- Add comprehensive tests for dropdown menu behavior in modal footers
- Update QuickEntryBox and NewTaskModal tests to match new menu patterns
- Add testing patterns for modal dropdown menus to project memory
- Update project memory instructions to encourage selective writes instead of unconditional appends
- Instruct agents to consolidate existing entries rather than add duplicates
- Add guidance to skip memory updates when no durable learnings were discovered
- Clarify what qualifies as durable learnings vs task-specific trivia
- Update user-facing memory documentation to reflect new selective behavior
- Add test coverage for selective memory write instructions
- Add showQuickChatFAB boolean setting to ProjectSettings type
- Add useAppSettings hook function for accessing the setting
- Wire QuickChatFAB visibility in App.tsx based on setting
- Hide QuickChatFAB in MobileNavBar when setting is false
- Add Settings UI toggle for the new setting
- Add CSS for hiding QuickChatFAB on mobile when disabled
- Add comprehensive tests for all affected components
- Fix QuickChatFAB onOpenChange test to use controlled mode
- Update settings reference documentation
Changed @testing-library/jest-dom import to @testing-library/jest-dom/vitest
in vitest.setup.ts to properly provide type definitions for jest-dom matchers
like toBeInTheDocument, toHaveClass, toBeDisabled, and toHaveAttribute in the
vitest environment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Tighten GitHubOperations.findPrForBranch and mergePr param types to
match the literal unions in FindPrParams/MergePrParams, fixing the
GitHubClient assignability error in dashboard.ts and serve.ts
- Cast MockStore as unknown as TaskStore at mesh-routes.test.ts call
site to satisfy TaskStore shape without implementing 117 methods
- Double-cast AgentGenerationSession via unknown in agent-generation.test.ts
to silence the unsafe conversion diagnostic
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Bundles staged work-in-progress modifications across multiple packages
(routes, store, agent-instructions, self-healing, QuickEntryBox, etc.)
plus the dashboard theme-data.css preload fix.
Note: an unstaged 621-line deletion in .fusion/memory.md was deliberately
NOT committed — it appears to be an accidental overwrite of architecture
notes and is left in the working tree for review.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The previous slim listing dropped log, comments, steps,
workflowStepResults, and steeringComments from the board task payload.
Of those, only `log` is actually heavy (~60 MB across 1200 tasks);
everything else combined is under 500 KB and is needed by the board UI:
- TaskCard step progress badge reads task.steps
- TaskCard comment count badge reads task.comments
- Workflow status indicators read task.workflowStepResults
Slim mode now drops *only* log. The other JSON columns stay in board
payloads, so progress bars and badges render again without forcing a
full per-task fetch.
Also fix the TaskDetailModal regression where the Activity tab and the
Step Progress section read task.log/task.steps from the slim board prop
instead of workingTask (the full row loaded via fetchTaskDetail). The
prop is the cached slim row from the board, so the activity tab was
empty until the user scrolled — now both tabs read workingTask.
Updated the slim listTasks regression test to assert the new contract:
log is dropped, but steps/comments/workflowStepResults/steeringComments
match the full row.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
