- agent-executor: move executeQuery into try block for proper heartbeat cleanup,
re-parse tasks when edited plan is approved
- auto-loop-coordinator: handle feature execution failures with proper logging
and failure tracking, support backward-compatible method signatures
- facade: delegate getActiveAutoLoopProjects/Worktrees to coordinator,
always create own AutoLoopCoordinator (not shared), pass projectPath
to approval methods and branchName to failure tracking
- global-service: document shared autoLoopCoordinator is for monitoring only
- execution-types: fix ExecuteFeatureFn type to match implementation
- feature-state-manager: use readJsonWithRecovery for loadFeature
- pipeline-orchestrator: add defensive null check and try/catch for
merge response parsing
- plan-approval-service: use project-scoped keys to prevent cross-project
collisions, maintain backward compatibility for featureId-only lookups
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The PipelineOrchestrator passes previousContent to preserve the agent
output history when running pipeline steps. This was being lost because
the facade's runAgentFn callback wasn't forwarding it to AgentExecutor.
Without this fix, pipeline steps would overwrite the agent-output.md
file instead of appending to it with a "Follow-up Session" separator.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The wrench emoji (🔧) was accidentally removed in commit 6ec9a257
during the service condensing refactor. This broke:
1. Log parser - uses startsWith('🔧') to detect tool calls, causing
them to be categorized as "info" instead of "tool_call"
2. Agent context parser - uses '🔧 Tool: TodoWrite' marker to find
tasks, causing task list to not appear on kanban cards
This fix restores the emoji to fix both issues.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The facade had stubs for runAgentFn that threw errors, causing feature
execution to fail with "runAgentFn not implemented in facade".
This fix wires both ExecutionService and PipelineOrchestrator runAgentFn
callbacks to properly call AgentExecutor.execute() with:
- Provider from ProviderFactory.getProviderForModel()
- Bare model from stripProviderPrefix()
- Proper AgentExecutorCallbacks for waitForApproval, saveFeatureSummary, etc.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Create agent-executor-types.ts with execution option/result/callback types
- Create pipeline-types.ts with context/status/result types
- Condense agent-executor.ts stream processing and add buildExecOpts helper
- Condense pipeline-orchestrator.ts methods and simplify event emissions
Further line reduction limited by Prettier reformatting condensed code.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Delete the 2705-line auto-mode-service.ts monolith
- Create AutoModeServiceCompat as compatibility layer for routes
- Create GlobalAutoModeService for cross-project operations
- Update all routes to use AutoModeServiceCompat type
- Add SharedServices interface for state sharing across facades
- Add getActiveProjects/getActiveWorktrees to AutoLoopCoordinator
- Delete obsolete monolith test files
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- features/routes/list.ts: Add facadeFactory parameter, use facade.detectOrphanedFeatures
- projects/routes/overview.ts: Add facadeFactory parameter, use facade.getRunningAgents/getStatusForProject
- features/index.ts: Pass facadeFactory to list handler
- projects/index.ts: Pass facadeFactory to overview handler
- auto-mode/index.ts: Accept facadeFactory parameter and wire to all route handlers
- All routes maintain backward compatibility with autoModeService fallback
- stop-feature.ts: Add facade parameter for feature stopping
- stop.ts: Add facadeFactory parameter for auto loop control
- verify-feature.ts: Add facadeFactory parameter for verification
- commit-feature.ts: Add facadeFactory parameter for committing
All routes maintain backward compatibility by accepting both
autoModeService (legacy) and facade/facadeFactory (new).
- status.ts: Add facadeFactory parameter for per-project status
- context-exists.ts: Add facadeFactory parameter for context checks
- running-agents/index.ts: Add facade parameter for getRunningAgents
All routes maintain backward compatibility by accepting both
autoModeService (legacy) and facade/facadeFactory (new).
- Export AutoModeServiceFacade class
- Export createAutoModeFacade convenience factory function
- Re-export all types from types.ts for route consumption
- Re-export types from extracted services (AutoModeConfig, RunningFeature, etc.)
All 1809 server tests pass.
- Replace executeFeature body with delegation to executionService.executeFeature()
- Replace stopFeature body with delegation to executionService.stopFeature()
- Remove ~312 duplicated lines from AutoModeService (3017 -> 2705)
- All 1809 server tests pass
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace startAutoLoopForProject body with delegation to autoLoopCoordinator
- Replace stopAutoLoopForProject body with delegation to autoLoopCoordinator
- Replace isAutoLoopRunningForProject body with delegation
- Replace getAutoLoopConfigForProject body with delegation
- Replace resumeFeature body with delegation to recoveryService
- Replace resumeInterruptedFeatures body with delegation
- Remove runAutoLoopForProject method (~95 lines) - now in AutoLoopCoordinator
- Remove failure tracking methods (~180 lines) - now in AutoLoopCoordinator
- Remove resolveMaxConcurrency (~40 lines) - now in AutoLoopCoordinator
- Update checkWorktreeCapacity to use coordinator
- Simplify legacy startAutoLoop to delegate
- Remove failure tracking from executeFeature (now handled by coordinator)
Line count reduced from 3604 to 3013 (~591 lines removed)
- Add imports for AutoLoopCoordinator, ExecutionService, RecoveryService
- Add private properties for the three coordination services
- Update constructor to accept optional parameters for dependency injection
- Create AutoLoopCoordinator with callbacks for loop lifecycle
- Create ExecutionService with callbacks for feature execution
- Create RecoveryService with callbacks for crash recovery
- Add 29 unit tests for crash recovery functionality
- Test execution state persistence (save/load/clear)
- Test context detection (agent-output.md exists check)
- Test feature resumption flow (pipeline vs non-pipeline)
- Test interrupted feature batch resumption
- Test idempotent behavior and error handling
- Add 45 unit tests for execution lifecycle coordination
- Test constructor, executeFeature, stopFeature, buildFeaturePrompt
- Test approved plan handling, error handling, worktree resolution
- Test auto-mode integration, planning mode, summary extraction
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Extract executeFeature, stopFeature, buildFeaturePrompt from AutoModeService
- Export callback types for test mocking and integration
- Implement persist-before-emit pattern for status updates
- Support approved plan continuation and context resumption
- Track failures and signal pause when threshold reached
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add AutoModeService integration tests for delegation verification
- Test executePipeline delegation with context fields
- Test detectPipelineStatus delegation for pipeline/non-pipeline status
- Test resumePipeline delegation with autoLoadClaudeMd and useWorktrees
- Add edge case tests for abort signals, missing context, deleted steps
- Add PipelineOrchestrator constructor parameter and property
- Initialize PipelineOrchestrator with all required dependencies and callbacks
- Delegate executePipelineSteps to pipelineOrchestrator.executePipeline()
- Delegate detectPipelineStatus to pipelineOrchestrator.detectPipelineStatus()
- Delegate resumePipelineFeature to pipelineOrchestrator.resumePipeline()
- Tests for executePipeline: step sequence, events, status updates
- Tests for buildPipelineStepPrompt: context inclusion, previous work
- Tests for detectPipelineStatus: pipeline status detection and parsing
- Tests for resumePipeline/resumeFromStep: excluded steps, slot management
- Tests for executeTestStep: 5-attempt fix loop, failure events
- Tests for attemptMerge: merge endpoint, conflict detection
- Tests for buildTestFailureSummary: output parsing
37 tests covering all core functionality
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add 11 new test cases for execute() behavior
- Test callback invocation (progress events, tool events)
- Test error handling (API errors, auth failures)
- Test result structure and response accumulation
- Test abort signal propagation
- Test branchName propagation in event payloads
Test file: 388 -> 935 lines (+547 lines)
- Add AgentExecutor import to auto-mode-service.ts
- Add agentExecutor as constructor parameter (optional, with default)
- Initialize AgentExecutor with TypedEventBus, FeatureStateManager,
PlanApprovalService, and SettingsService dependencies
This enables constructor injection for testing and prepares for
incremental delegation of runAgent() logic to AgentExecutor.
The AgentExecutor contains the full execution pipeline;
runAgent() delegation will be done incrementally to ensure
stability.
- Test constructor injection with all dependencies
- Test interface exports (AgentExecutionOptions, AgentExecutionResult)
- Test callback type signatures (WaitForApprovalFn, SaveFeatureSummaryFn, etc.)
- Test dependency injection patterns with custom implementations
- Verify execute method signature
Note: Full integration tests for streaming/marker detection require
complex mocking of @automaker/utils module which has hoisting issues.
Integration testing covered in E2E and auto-mode-service tests.
- Extract parseTasksFromSpec for parsing tasks from spec content
- Extract marker detection functions (task start/complete, phase complete)
- Extract detectSpecFallback for non-Claude model support
- Extract extractSummary with multi-format support and last-match behavior
- Add 65 unit tests covering all functions and edge cases
- Extract plan approval workflow from AutoModeService
- Timeout-wrapped Promise creation via waitForApproval()
- Resolution handling (approve/reject) with needsRecovery flag
- Cancellation support for stopped features
- Per-project configurable timeout (default 30 minutes)
- Event emission through TypedEventBus for plan_rejected
- Add WorktreeResolver and FeatureStateManager as constructor parameters
- Remove top-level getCurrentBranch function (now in WorktreeResolver)
- Delegate loadFeature, updateFeatureStatus to FeatureStateManager
- Delegate markFeatureInterrupted, resetStuckFeatures to FeatureStateManager
- Delegate updateFeaturePlanSpec, saveFeatureSummary, updateTaskStatus
- Replace findExistingWorktreeForBranch calls with worktreeResolver
- Update tests to mock featureStateManager instead of internal methods
- All 89 tests passing across 3 service files
- Create FeatureStateManager class for feature status updates
- Extract updateFeatureStatus, markFeatureInterrupted, resetStuckFeatures
- Extract updateFeaturePlanSpec, saveFeatureSummary, updateTaskStatus
- Persist BEFORE emit pattern for data integrity (Pitfall 2)
- Handle corrupted JSON with readJsonWithRecovery backup support
- Preserve pipeline_* statuses in markFeatureInterrupted
- Fix bug: version increment now checks old content before applying updates
- Add 33 unit tests covering all state management operations
- Add TypedEventBus as wrapper around EventEmitter
- Implement emitAutoModeEvent method for auto-mode event format
- Add emit, subscribe, getUnderlyingEmitter methods
- Create comprehensive test suite (20 tests)
- Verify exact event format for frontend compatibility
- AutoModeService now delegates to ConcurrencyManager for all running feature tracking
- Constructor accepts optional ConcurrencyManager for dependency injection
- Remove local RunningFeature interface (imported from ConcurrencyManager)
- Migrate all this.runningFeatures usages to concurrencyManager methods
- Update tests to use concurrencyManager.acquire() instead of direct Map access
- ConcurrencyManager accepts getCurrentBranch function for testability
BREAKING: AutoModeService no longer exposes runningFeatures Map directly.
Tests must use concurrencyManager.acquire() to add running features.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Lease-based reference counting for nested execution support
- acquire() creates entry with leaseCount: 1 or increments existing
- release() decrements leaseCount, deletes at 0 or with force:true
- Project and worktree-level running counts
- RunningFeature interface exported for type sharing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Test lease counting basics (acquire/release semantics)
- Test running count queries (project and worktree level)
- Test feature state queries (isRunning, getRunningFeature, getAllRunning)
- Test edge cases (multiple features, multiple worktrees)
- 36 test cases documenting expected behavior
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
