Tests cover:
- parseValidationResult with JSON extraction from markdown code blocks and malformed responses
- handleValidationPass verifying feature marked 'passed' and autopilot notified
- handleValidationFail verifying fix feature generated and retry budget decremented
- handleValidationBlocked verifying feature marked 'blocked' without fix generation
- Retry budget enforcement preventing further implementations when exhausted
- recoverActiveMissions verifying actual processTaskOutcome calls for features in validating/needs_fix states
Added 23 new tests (1916 total, up from 1893).
- Implement actual AI response parsing in parseValidationResult() with JSON extraction
from markdown code blocks, repair for common JSON issues, and assertion result parsing
- Fix notifyValidationComplete to pass feature.taskId instead of featureId to
handleTaskCompletion() in in-process-runtime, dashboard, and serve
- Fix recoverActiveMissions() to actually transition validating features back to
implementing and call processTaskOutcome for features with completed tasks
- Add comprehensive unit tests for MissionExecutionLoop lifecycle, processTaskOutcome,
recoverActiveMissions, and error handling
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>
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>
- 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
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>
- 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
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>
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>
GET /api/tasks was returning ~69 MB of JSON per call (67.9 MB of agent
logs across 1199 tasks), causing the dashboard to hang for 2+ minutes.
- core: extend listTasks() with slim and includeArchived options
- dashboard: GET /api/tasks now uses slim mode and excludes archived
by default; ?includeArchived=1 opts in
- frontend: lazy-load archived tasks when the archived column is first
expanded via new useTasks.loadArchivedTasks()
- engine: self-healing maintenance now auto-archives done tasks older
than 48h (data stays in SQLite, column flips done -> archived)
- tests: slim mode + includeArchived coverage in store.test.ts;
routes.test.ts assertion updated for new args
Also bundles in-progress test-setup noise filters and pre-existing
QuickEntryBox/routes test work that was already modified locally.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add ESLint configuration (eslint.config.mjs) for TypeScript/JavaScript linting
- Update executor prompts to include lint instruction before code submission
- Add lint check to triage prompt validation workflow
- Update agent prompts to emphasize lint compliance as quality requirement
- Add lint tool to agent toolset with file-level rule disabling capability
- Include lint in CI workflow with non-blocking status
- Update tests to verify lint-inclusive prompt behavior
- Add documentation for lint integration in contributing.md
- Add changeset for @gsxdsm/fusion minor release
- Add verification runner that executes testCommand then buildCommand before merge completion
- Verification runs on all merge paths (AI resolve, auto-resolve, -X theirs)
- If verification fails, merge is aborted and task stays out of done
- Add comprehensive tests for merger verification logic
- Fix routine-store test variable reference bug (created.id vs routine.id)
- Add changeset for @gsxdsm/fusion patch release
- Add RoutineRunner class for routine execution via heartbeat system
- Add RoutineScheduler class for cron-based routine polling
- Add triggerManual and triggerWebhook methods for API and webhook triggers
- Wire RoutineScheduler into InProcessRuntime lifecycle
- Add routine trigger and webhook API endpoints
- Fix type mismatches between PROMPT and actual FN-1519 types
The RoutineRunner and RoutineScheduler were written against a different
interface than what RoutineStore actually implements, causing TypeError
crashes as soon as any routine became due. This adds the missing
agentId/catchUpLimit fields to the Routine type and DB schema, adds
startRoutineExecution/completeRoutineExecution/cancelRoutineExecution
methods to RoutineStore, and fixes all property name mismatches
(lastExecutedAt→lastRunAt, trigger.cron→trigger.cronExpression,
policy value alignment) in the runner, scheduler, and tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Add step-scoped tracking key support in StuckTaskDetector for step-session mode
- Update tracking keys to include step session IDs when runStepsInNewSessions is enabled
- Add tests for step-scoped tracking behavior in executor and stuck-task-detector
- Ensure stuck task detection works correctly with per-step retry recovery
- Add freshSession option to MergeOptions to start clean agent sessions instead of resuming
- Add compactSession option for compacting session history before retry attempts
- Implement RetryStrategy type with freshSession and compactSession variants
- Add retryWithStrategy() method that attempts merge, then retries with configured strategy on failure
- Add comprehensive tests for retry logic covering success, simple retry, and compact-and-retry paths
- Update memory documentation with merger retry strategy guidance
- Add ChatStore mock to all dashboard route tests that mock @fusion/core,
since server.ts now instantiates ChatStore(store.getFusionDir(), ...)
- Add getFusionDir to createMockStore in server.test.ts
- Gate AI session cleanup scheduling behind shouldScheduleAiSessionCleanup()
(returns false in test env) to prevent open handle warnings
- Fix desktop tests: DASHBOARD_URL is now exported as a function alias,
update assertions to call DASHBOARD_URL() instead of using as string
- Add node:os mocks to system-metrics.test.ts for deterministic results
- Replace hardcoded maxWorkers=16 with availableParallelism()-based
calculation in all vitest configs to prevent OOM on 2-core CI runners
- Add --workspace-concurrency=2 to pnpm test commands
- Fix TaskCard tests: update mission badge title assertions to full titles
- Remove unused /api/mesh/state route
- Fix plugin-auto-label: add isError field, async onTaskCreated, "tests" keyword
- Fix plugin-ci-status: add module-level logger, tighten test assertions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add return statement after successful context compaction and resume
- When compact-and-resume succeeds (promptWithFallback completes without error),
executor now returns early instead of falling through to failure path
- This allows the finally block to clean up without marking the task as failed
- Add logging for recovery success and failure paths
- Add regression tests for context limit error detection
- Pattern is conservative: requires both 'context window' and 'exceeds' present
- Add new regex pattern /context\s+window\s+exceeds/i to match provider JSON error
envelope variant: "context window exceeds limit (2013)"
- Add 4 new test cases for the variant pattern
- Pattern is conservative: requires both "context window" and "exceeds" present
- Add shared RunAuditService in packages/engine/src/run-audit.ts for tracking agent run state transitions
- Instrument HeartbeatMonitor to log run mutations (create, complete, error, skip) with timestamps and context
- Instrument TaskExecutor to log run mutations during task execution lifecycle
- Instrument Merger to log run mutations during merge workflow
- Add run-audit pattern documentation to project memory
- Fix: remove audit calls from non-run recovery methods to avoid false positives
- Add assigneeUserId field to Task type and SQLite schema for human assignment
- Add reviewHandoffPolicy setting to control automatic handoff behavior
- Implement handoff detection in executor: detect user assignment during review and auto-transition task
- Add dashboard API routes for user assignment, handoff queries, and completion
- Add frontend API functions: getHandoffTask, assignTaskToUser, completeHandoff
- Add comprehensive tests for store methods, API routes, and executor handoff logic
- Update memory documentation with review handoff pattern
When a stuck task's session is disposed but an in-flight bash subprocess
keeps running, the executor's Promise never resolves, so the requeue
finally block never fires and the task stays stranded in-progress
indefinitely (observed with FN-1269).
Add a 60s safety-net timer in markStuckAborted: if the task is still in
executing after the grace period, force-requeue it directly by clearing
the worktree, setting status=stuck-killed, moving to todo, and removing
it from the executing set so the scheduler can re-dispatch normally.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add explicit always-green test suite instructions to executor agent prompts
- Update executor to enforce test-suite validation before task completion
- Add tests for agent prompt generation and executor behavior
- Ensure test failures block merge-ready state rather than allowing broken builds
store.logEntry, assignTask, and checkoutTask now receive an extra
runContext argument. Updated test assertions in executor.test.ts,
agent-heartbeat.test.ts, and restart.integration.test.ts to match
the current call signatures using expect.objectContaining where
appropriate.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
In step-session mode each step is registered with StuckTaskDetector
under a compound key (e.g. "FN-1452-step-1") rather than the bare
task ID. When stuck detection fired, event.taskId was that compound
key, breaking three things simultaneously:
1. beforeRequeue("FN-1452-step-1") → store.getTask() threw (no such
task) → stuckKillCount never incremented on the real task.
2. markStuckAborted("FN-1452-step-1") → activeStepExecutors.get()
returned undefined (keyed by "FN-1452") → terminateAllSessions()
never called, other step sessions kept running.
3. stuckAborted.set("FN-1452-step-1") → executor checks
stuckAborted.has("FN-1452") → miss → stuckRequeue never set
→ task never moved to todo.
Fix: add a canonicalTaskId field to TrackedTask (defaults to the
tracking key for single-session mode where they are identical).
StepSessionExecutor now passes taskDetail.id as the third arg to
trackTask(). killAndRetry() uses entry.canonicalTaskId for all
external callbacks so they always resolve to the real task ID.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Unify slice activation and auto-triage semantics for mission progression
- Align engine progression with stale recovery logic for active missions
- Fix scheduler delegation check to use feature.missionId instead of deprecated field
- Add integration tests for stale mission recovery scenarios
- Fix mission API recovery gaps for active missions (activate on first non-done slice)
- Update README.md autopilot documentation section
- 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
