Major refactoring of the parallel orchestrator to run regression testing
agents independently from coding agents. This improves system reliability
and provides better control over testing behavior.
Key changes:
Database & MCP Layer:
- Add testing_in_progress and last_tested_at columns to Feature model
- Add feature_claim_for_testing() for atomic test claim with retry
- Add feature_release_testing() to release claims after testing
- Refactor claim functions to iterative loops (no recursion)
- Add OperationalError retry handling for transient DB errors
- Reduce MAX_CLAIM_RETRIES from 10 to 5
Orchestrator:
- Decouple testing agent lifecycle from coding agents
- Add _maintain_testing_agents() for continuous testing maintenance
- Fix TOCTOU race in _spawn_testing_agent() - hold lock during spawn
- Add _cleanup_stale_testing_locks() with 30-min timeout
- Fix log ordering - start_session() before stale flag cleanup
- Add stale testing_in_progress cleanup on startup
Dead Code Removal:
- Remove count_testing_in_concurrency from entire stack (12+ files)
- Remove ineffective with_for_update() from features router
API & UI:
- Pass testing_agent_ratio via CLI to orchestrator
- Update testing prompt template to use new claim/release tools
- Rename UI label to "Regression Agents" with clearer description
- Add process_utils.py for cross-platform process tree management
Testing agents now:
- Run continuously as long as passing features exist
- Can re-test features multiple times to catch regressions
- Are controlled by fixed count (0-3) via testing_agent_ratio setting
- Have atomic claiming to prevent concurrent testing of same feature
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Introduce a new testing agent architecture that runs regression tests
independently from coding agents, improving quality assurance in
parallel mode.
Key changes:
Testing Agent System:
- Add testing_prompt.template.md for dedicated testing agent role
- Add feature_mark_failing MCP tool for regression detection
- Add --agent-type flag to select initializer/coding/testing mode
- Remove regression testing from coding prompt (now handled by testing agents)
Parallel Orchestrator Enhancements:
- Add testing agent spawning with configurable ratio (--testing-agent-ratio)
- Add comprehensive debug logging system (DebugLog class)
- Improve database session management to prevent stale reads
- Add engine.dispose() calls to refresh connections after subprocess commits
- Fix f-string linting issues (remove unnecessary f-prefixes)
UI Improvements:
- Add testing agent mascot (Chip) to AgentAvatar
- Enhance AgentCard to display testing agent status
- Add testing agent ratio slider in SettingsModal
- Update WebSocket handling for testing agent updates
- Improve ActivityFeed to show testing agent activity
API & Server Updates:
- Add testing_agent_ratio to settings schema and endpoints
- Update process manager to support testing agent type
- Enhance WebSocket messages for agent_update events
Template Changes:
- Delete coding_prompt_yolo.template.md (consolidated into main prompt)
- Update initializer_prompt.template.md with improved structure
- Streamline coding_prompt.template.md workflow
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove unused imports and organize import statements to pass ruff
linting checks:
- mcp_server/feature_mcp.py: Remove unused imports (are_dependencies_satisfied,
get_blocking_dependencies) and alphabetize import block
- parallel_orchestrator.py: Remove unused imports (time, Awaitable) and
add blank lines between import groups per PEP 8
- server/routers/features.py: Alphabetize imports in dependency resolver
These changes were identified by running `ruff check .` and auto-fixed
with `--fix` flag.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Critical fixes:
- Lock file TOCTOU race condition: Use atomic O_CREAT|O_EXCL for lock creation
- PID reuse vulnerability on Windows: Store PID:CREATE_TIME in lock file to
detect when a different process has reused the same PID
- WAL mode on network drives: Detect network paths (UNC, mapped drives, NFS,
CIFS) and fall back to DELETE journal mode to prevent corruption
High priority fixes:
- JSON migration now preserves dependencies field during legacy migration
- Process tree termination on Windows: Use psutil to kill child processes
recursively to prevent orphaned browser instances
- Retry backoff jitter: Add random 30% jitter to prevent synchronized retries
under high contention with 5 concurrent agents
Files changed:
- server/services/process_manager.py: Atomic lock creation, PID+create_time
- api/database.py: Network filesystem detection for WAL mode fallback
- api/migration.py: Add dependencies field to JSON migration
- parallel_orchestrator.py: _kill_process_tree helper function
- mcp_server/feature_mcp.py: Add jitter to exponential backoff
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changes:
- Add per-agent log viewer with copy-to-clipboard functionality
- New AgentLogEntry type for structured log entries
- Logs stored per-agent in WebSocket state (up to 500 entries)
- Log modal rendered via React Portal to avoid overflow issues
- Click log icon on agent card to view full activity history
- Fix agents getting stuck in "failed" state
- Wrap client context manager in try/except (agent.py)
- Remove failed agents from UI on error state (useWebSocket.ts)
- Handle permanently failed features in get_all_complete()
- Add friendlier agent state labels
- "Hit an issue" → "Trying plan B..."
- "Retrying..." → "Being persistent..."
- Softer colors (yellow/orange instead of red)
- Add scheduling scores for smarter feature ordering
- compute_scheduling_scores() in dependency_resolver.py
- Features that unblock others get higher priority
- Update CLAUDE.md with parallel mode documentation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Major feature implementation for parallel agent execution with dependency-aware
scheduling and an engaging multi-agent UI experience.
Backend Changes:
- Add parallel_orchestrator.py for concurrent feature processing
- Add api/dependency_resolver.py with cycle detection (Kahn's algorithm + DFS)
- Add atomic feature_claim_next() with retry limit and exponential backoff
- Fix circular dependency check arguments in 4 locations
- Add AgentTracker class for parsing agent output and emitting updates
- Add browser isolation with --isolated flag for Playwright MCP
- Extend WebSocket protocol with agent_update messages and log attribution
- Add WSAgentUpdateMessage schema with agent states and mascot names
- Fix WSProgressMessage to include in_progress field
New UI Components:
- AgentMissionControl: Dashboard showing active agents with collapsible activity
- AgentCard: Individual agent status with avatar and thought bubble
- AgentAvatar: SVG mascots (Spark, Fizz, Octo, Hoot, Buzz) with animations
- ActivityFeed: Recent activity stream with stable keys (no flickering)
- CelebrationOverlay: Confetti animation with click/Escape dismiss
- DependencyGraph: Interactive node graph visualization with dagre layout
- DependencyBadge: Visual indicator for feature dependencies
- ViewToggle: Switch between Kanban and Graph views
- KeyboardShortcutsHelp: Help overlay accessible via ? key
UI/UX Improvements:
- Celebration queue system to handle rapid success messages
- Accessibility attributes on AgentAvatar (role, aria-label, aria-live)
- Collapsible Recent Activity section with persisted preference
- Agent count display in header
- Keyboard shortcut G to toggle Kanban/Graph view
- Real-time thought bubbles and state animations
Bug Fixes:
- Fix circular dependency validation (swapped source/target arguments)
- Add MAX_CLAIM_RETRIES=10 to prevent stack overflow under contention
- Fix THOUGHT_PATTERNS to match actual [Tool: name] format
- Fix ActivityFeed key prop to prevent re-renders on new items
- Add featureId/agentIndex to log messages for proper attribution
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem: Features with NULL values in passes/in_progress fields caused
Pydantic validation errors in the API.
Solution - defense in depth:
1. Database model: Add nullable=False to passes and in_progress columns
2. Migration: Auto-fix existing NULL values to False on database connect
3. API layer: Handle NULL gracefully in feature_to_response (treat as False)
4. MCP server: Explicitly set in_progress=False when creating features
This ensures:
- New databases cannot have NULL boolean fields
- Existing databases are auto-migrated on connect
- Even if NULL values exist, they're handled gracefully at runtime
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit addresses issues found during review of PRs #12 and #28:
## PR #12 (Auth Error Handling) Fixes
- Create shared auth.py module with centralized AUTH_ERROR_PATTERNS,
is_auth_error(), and print_auth_error_help() functions
- Fix start.bat to use directory check instead of outdated
.credentials.json file check (matching start.sh behavior)
- Update process_manager.py to import from shared auth module
- Update start.py to import from shared auth module
- Update documentation comments in autonomous_agent_demo.py and
client.py to remove references to deprecated .credentials.json
## PR #28 (Feature Management) Improvements
- Add _priority_lock threading lock to feature_mcp.py to prevent
race conditions when multiple features are created simultaneously
- Apply lock to feature_create, feature_create_bulk, and feature_skip
- Add checkAndSendTimeoutRef cleanup in useAssistantChat.ts to
prevent memory leaks on component unmount
- Clear currentAssistantMessageRef on response_done
## Code Quality
- All Python files pass ruff linting
- All security tests pass (91/91)
- UI passes ESLint and TypeScript compilation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Match the same validation constraints used in FeatureCreateItem:
- category: min_length=1, max_length=100
- name: min_length=1, max_length=255
- description: min_length=1
- steps: min_length=1
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Allow users to interact with the project assistant to create features
through natural conversation. The assistant can now:
- Create single features via `feature_create` tool
- Create multiple features via `feature_create_bulk`
- Skip features to deprioritize them via `feature_skip`
Changes:
- Add `feature_create` MCP tool for single-feature creation
- Update assistant allowed tools to include feature management
- Update system prompt to explain new capabilities
- Enhance UI tool call display with friendly messages
Security: File system access remains read-only. The assistant cannot
modify source code or mark features as passing (requires actual
implementation by the coding agent).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implements feature locking to prevent multiple agent sessions from working
on the same feature simultaneously. This is essential for parallel agent
execution.
Database changes:
- Add `in_progress` boolean column to Feature model
- Add migration function to handle existing databases
MCP Server tools:
- Add `feature_mark_in_progress` - lock feature when starting work
- Add `feature_clear_in_progress` - unlock feature when abandoning
- Update `feature_get_next` to skip in-progress features
- Update `feature_get_stats` to include in_progress count
- Update `feature_mark_passing` and `feature_skip` to clear in_progress
Backend updates:
- Update progress.py to track and display in_progress count
- Update features router to properly categorize in-progress features
- Update WebSocket to broadcast in_progress in progress updates
- Add in_progress to FeatureResponse schema
Frontend updates:
- Add in_progress to TypeScript types (Feature, ProjectStats, WSProgressMessage)
- Update useWebSocket hook to track in_progress state
Prompt template:
- Add instructions for agents to mark features in-progress immediately
- Document new MCP tools in allowed tools section
Also fixes spec_chat_session.py to use absolute project path instead of
relative path for consistency with CLI behavior.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
