- Check for 'not found' message (server response) in addition to '404'
- Only clear stored conversation ID on actual 404 errors
- Prevent unnecessary retries for deleted conversations
- Don't clear conversation on transient network errors
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When a stored conversation ID no longer exists (e.g., database was reset
or conversation was deleted), the UI would repeatedly try to fetch it,
causing endless 404 errors in the console.
This fix:
- Stops retrying on 404 errors (conversation doesn't exist)
- Automatically clears the stored conversation ID from localStorage
when a 404 is received, allowing the user to start fresh
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove assets/ollama.png (duplicate of ui/public/ollama.png)
- Remove .claude/settings.local.json from tracking
- Add .claude/settings.local.json to .gitignore
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
pkill on BSD systems accepts multiple pattern operands. Previous code
only validated args[-1], allowing disallowed processes to slip through
when combined with allowed ones (e.g., "pkill node sshd" would only
check "sshd").
Now validates every non-flag argument to ensure no disallowed process
can be targeted. Added tests for multiple pattern scenarios.
Addresses CodeRabbit feedback on PR #101.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changed from warning-only to proper error handling:
- if server doesn't respond after restart, exit with error
- prevents false negatives when server fails to start
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Address CodeRabbit security feedback - restrict pkill_processes entries
to alphanumeric names with dots, underscores, and hyphens only.
This prevents potential exploitation through regex metacharacters like
'.*' being registered as process names.
Changes:
- Added VALID_PROCESS_NAME_PATTERN regex constant
- Updated both org and project config validation to:
- Normalize (trim whitespace) process names
- Reject names with regex metacharacters
- Reject names with spaces
- Added 3 new tests for regex validation
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Address CodeRabbit feedback - use consistent conditional pattern:
`(max_priority.priority + 1) if max_priority else 1`
This matches the pattern used in create_feature and create_features_bulk.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Users can now access the WebUI remotely (e.g., via VS Code tunnels,
remote servers) by specifying a host address:
python start_ui.py --host 0.0.0.0
python start_ui.py --host 0.0.0.0 --port 8888
Changes:
- Added --host and --port CLI arguments to start_ui.py
- Security warning displayed when remote access is enabled
- AUTOCODER_ALLOW_REMOTE env var passed to server
- server/main.py conditionally disables localhost middleware
- CORS updated to allow all origins when remote access is enabled
- Browser auto-open disabled for remote hosts
Security considerations documented in warning:
- File system access to project directories
- API can start/stop agents and modify files
- Recommend firewall or VPN for protection
Fixes: leonvanzyl/autocoder#81
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When running multiple projects simultaneously, UI would show mixed data
because the manager registry used only project_name as key. Projects with
the same name but different paths shared the same manager instance.
Changed manager registries to use composite key (project_name, resolved_path):
- server/services/process_manager.py: AgentProcessManager registry
- server/services/dev_server_manager.py: DevServerProcessManager registry
This ensures that:
- /old/my-app and /new/my-app get separate managers
- Multiple browser tabs viewing different projects stay isolated
- Project renames don't cause callback contamination
Fixes: leonvanzyl/autocoder#71
Also fixes: leonvanzyl/autocoder#62 (progress bar sync)
Also fixes: leonvanzyl/autocoder#61 (features missing in kanban)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
When all features pass, the orchestrator continued spawning testing
agents for 10+ minutes, wasting tokens on unnecessary regression
tests. Added a check for get_all_complete() to prevent this.
Fixes: leonvanzyl/autocoder#66
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The REST API skip endpoint was using max_priority + 1000, while the
MCP server used max_priority + 1. This caused priority inflation where
values could reach 10,000+ after multiple skips.
Changed to use + 1 for consistency with mcp_server/feature_mcp.py:345.
Fixes: leonvanzyl/autocoder#65
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Escape parentheses in grep patterns: new Map\(\) and new Set\(\)
- Add --include="*.js" to all grep commands for complete coverage
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix math error in category totals (155→165, 255→265)
- Fix example JSON to include [0,1,2,3,4] dependencies for all features
- Add more robust server shutdown (SIGTERM then SIGKILL)
- Add health check after server restart
- Align grep patterns between templates (add .js, testData, TODO/STUB/MOCK)
- Add package.json check for mock backend libraries
- Reference STEP 5.6 instead of duplicating grep commands
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add focus-visible styles for keyboard navigation accessibility and
improve PLAYWRIGHT_HEADLESS environment variable validation to warn
users about invalid values instead of silently defaulting.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
Several API endpoints return 500 Internal Server Error because datetime
objects are not serializable by Pydantic. The error occurs when:
- GET /agent/{project}/status
- GET /devserver/{project}/status
- GET /schedules/{project}/next
Root cause:
Pydantic models expect strings for Optional datetime fields, but the code
was passing raw datetime objects.
Solution:
Convert datetime objects to ISO 8601 strings using .isoformat() before
returning in Pydantic response models.
Changes:
- server/routers/agent.py: Fix started_at serialization
- server/routers/devserver.py: Fix started_at serialization
- server/routers/schedules.py: Fix next_start/next_end serialization
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
The coding agent can implement in-memory storage (e.g., `dev-store.ts` with
`globalThis`) instead of a real database. These implementations pass all tests
because data persists during runtime, but data is lost on server restart.
This is a root cause for #68 - agent "passes" features that don't actually work.
Solution:
1. Add 5 mandatory Infrastructure Features (indices 0-4) that run first:
- Feature 0: Database connection established
- Feature 1: Database schema applied correctly
- Feature 2: Data persists across server restart (CRITICAL)
- Feature 3: No mock data patterns in codebase
- Feature 4: Backend API queries real database
2. Add STEP 5.7: Server Restart Persistence Test to coding prompt:
- Create test data, stop server, restart, verify data still exists
3. Extend grep patterns for mock detection in STEP 5.6:
- globalThis., devStore, dev-store, mockData, fakeData
- TODO.*real, STUB, MOCK, new Map() as data stores
Changes:
- .claude/templates/initializer_prompt.template.md - Infrastructure features
- .claude/templates/coding_prompt.template.md - STEP 5.6/5.7 enhancements
- .claude/commands/create-spec.md - Phase 3b database question
Backwards Compatible:
- Works with YOLO mode (uses bash/grep, not browser automation)
- Stateless apps can skip database features via create-spec question
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
UI Changes:
- Replace neobrutalism with clean Twitter/Supabase-style design
- Remove all shadows, use thin borders (1px)
- Single accent color (Twitter blue) for all status indicators
- Rounded corners (1.3rem base)
- Fix dark mode contrast and visibility
- Make KanbanColumn themeable via CSS classes
Backend Changes:
- Default Playwright browser changed to Firefox (lower CPU)
- Default Playwright mode changed to headless (saves resources)
- Add PLAYWRIGHT_BROWSER env var support
Documentation:
- Add CUSTOM_UPDATES.md with all customizations documented
- Update .env.example with new Playwright options
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Create custom-theme.css for theme overrides that won't conflict
with upstream updates. The file loads after globals.css, so its
CSS variables take precedence.
This approach ensures:
- Zero merge conflicts on git pull (new file, not in upstream)
- Theme persists across upstream updates
- Easy to modify without touching upstream code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added _kill_process_tree call in _read_output finally block to ensure
child processes (Claude CLI) are cleaned up when agents complete or fail.
This prevents accumulation of zombie processes that was causing 78+
Python processes when max concurrency was set to 5.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Resolved conflicts by combining:
- stdin=DEVNULL and CREATE_NO_WINDOW (blocking fix)
- PYTHONUNBUFFERED env var (output buffering fix)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add stdin=subprocess.DEVNULL to prevent blocking on stdin reads
- Add CREATE_NO_WINDOW flag on Windows to prevent console pop-ups
- Remove trailing pause from start_ui.bat
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove the testing_in_progress claim/release mechanism from the testing
agent architecture. Multiple testing agents can now test the same feature
concurrently, simplifying the system and eliminating potential stale lock
issues.
Changes:
- parallel_orchestrator.py:
- Remove claim_feature_for_testing() and release_testing_claim() methods
- Remove _cleanup_stale_testing_locks() periodic cleanup
- Replace with simple _get_random_passing_feature() selection
- Remove startup stale lock cleanup code
- Remove STALE_TESTING_LOCK_MINUTES constant
- Remove unused imports (timedelta, text)
- api/database.py:
- Remove testing_in_progress and last_tested_at columns from Feature model
- Update to_dict() to exclude these fields
- Convert _migrate_add_testing_columns() to no-op for backwards compat
- mcp_server/feature_mcp.py:
- Remove feature_release_testing tool entirely
- Remove unused datetime import
- prompts.py:
- Update testing prompt to remove feature_release_testing instruction
- Testing agents now just verify and exit (no cleanup needed)
- server/websocket.py:
- Update AgentTracker to use composite keys (feature_id, agent_type)
- Prevents ghost agent creation from ambiguous [Feature #X] messages
- Proper separation of coding vs testing agent tracking
Benefits:
- Eliminates artificial bottleneck from claim coordination
- No stale locks to clean up after crashes
- Simpler crash recovery (no testing state to restore)
- Reduced database writes (no claim/release transactions)
- Matches intended design: random, concurrent regression testing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Previously, agents that completed their work would remain visible in the
Mission Control UI until a manual page refresh. This occurred because
the AgentTracker._handle_agent_complete method silently dropped completion
messages when an agent wasn't tracked (e.g., due to missed start messages
from WebSocket connection issues).
Backend changes:
- Modified _handle_agent_complete in server/websocket.py to always emit
completion messages, even for untracked agents
- Synthetic completions use agentIndex=-1 and agentName='Unknown' as
sentinel values to indicate untracked agents
Frontend changes:
- Updated useWebSocket.ts to handle synthetic completions by removing
agents by featureId when agentIndex is -1
- Added 30-minute stale agent cleanup as defense-in-depth for users who
leave the UI open for extended periods
- Updated TypeScript types to allow 'Unknown' as valid agent name
Component updates:
- AgentAvatar.tsx: Added UNKNOWN_COLORS and UnknownSVG fallback for
rendering unknown agents with a neutral gray question mark icon
- CelebrationOverlay.tsx, DependencyGraph.tsx: Updated interfaces to
accept 'Unknown' agent names
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add real-time visibility into the parallel orchestrator's decisions
and state in the Mission Control UI. The orchestrator now has its
own avatar ("Maestro") and displays capacity/queue information.
Backend changes (server/websocket.py):
- Add OrchestratorTracker class that parses orchestrator stdout
- Define regex patterns for key orchestrator events (spawn, complete, capacity)
- Track coding/testing agent counts, ready queue, blocked features
- Emit orchestrator_update WebSocket messages
- Reset tracker state when agent stops or crashes
Frontend changes:
- Add OrchestratorState, OrchestratorStatus, OrchestratorEvent types
- Add WSOrchestratorUpdateMessage to WSMessage union
- Handle orchestrator_update in useWebSocket hook
- Create OrchestratorAvatar component (Maestro - robot conductor)
- Create OrchestratorStatusCard with capacity badges and event ticker
- Update AgentMissionControl to show orchestrator above agent cards
- Add conducting/baton-tap CSS animations for Maestro
The orchestrator status card shows:
- Maestro avatar with state-based animations
- Current orchestrator state and message
- Coding agents, testing agents, ready queue badges
- Blocked features count (when > 0)
- Collapsible recent events list
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add cross-platform temporary_home() context manager to handle
environment variable differences between Unix and Windows systems.
Changes:
- Add temporary_home() context manager that handles both HOME (Unix)
and USERPROFILE/HOMEDRIVE/HOMEPATH (Windows) environment variables
- Update test_org_config_loading() to use temporary_home()
- Update test_hierarchy_resolution() to use temporary_home()
- Update test_org_blocklist_enforcement() to use temporary_home()
- Add missing imports: os, contextmanager
Why: The unit tests for org config loading were failing on Windows
because they only set the HOME environment variable, but Windows
uses USERPROFILE instead. The integration tests already had this
fix via a similar context manager.
Result: All 148 unit tests now pass on both Windows and Unix systems.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Move mimetypes import to the top of the import block to satisfy
ruff's import sorting rules (I001). The Windows mimetype fix from
PR #82 placed the import after other imports, which violated the
project's linting standards.
Changes:
- Move `import mimetypes` to alphabetically correct position
- Update comment to clarify timing requirement
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Changes:
- Add temporary_home() context manager for safe HOME manipulation
- Handle both Unix (HOME) and Windows (USERPROFILE, HOMEDRIVE, HOMEPATH)
- Update test_org_blocklist_enforcement to use context manager
- Update test_org_allowlist_inheritance to use context manager
Benefits:
- Environment variables always restored, even on exceptions
- Prevents test pollution across test runs
- Cross-platform compatibility (Windows + Unix)
All 9 integration tests passing.
Changes:
- Support path patterns without ./ prefix (e.g., 'scripts/test.sh')
- Reject non-string or empty command names in org config
- Add 8 new test cases (5 for path patterns, 3 for validation)
Details:
- matches_pattern() now treats any pattern with '/' as a path pattern
- load_org_config() validates that cmd['name'] is a non-empty string
- All 148 unit tests + 9 integration tests passing
Security hardening: Prevents invalid command names from reaching
pattern matching logic, reducing attack surface.
Replace agent-initiated feature selection with orchestrator pre-selection
for both coding and testing agents. This ensures Mission Control displays
correct feature numbers for testing agents (previously showed "Feature #0").
Key changes:
MCP Server (mcp_server/feature_mcp.py):
- Add feature_get_by_id tool for agents to fetch assigned feature details
- Remove obsolete tools: feature_get_next, feature_claim_next,
feature_claim_for_testing, feature_get_for_regression
- Remove helper functions and unused imports (text, OperationalError, func)
Orchestrator (parallel_orchestrator.py):
- Change running_testing_agents from list to dict[int, Popen]
- Add claim_feature_for_testing() with random selection
- Add release_testing_claim() method
- Pass --testing-feature-id to spawned testing agents
- Use unified [Feature #X] output format for both agent types
Agent Entry Points:
- autonomous_agent_demo.py: Add --testing-feature-id CLI argument
- agent.py: Pass testing_feature_id to get_testing_prompt()
Prompt Templates:
- coding_prompt.template.md: Update to use feature_get_by_id
- testing_prompt.template.md: Update workflow for pre-assigned features
- prompts.py: Update pre-claimed headers for both agent types
WebSocket (server/websocket.py):
- Simplify tracking with unified [Feature #X] pattern
- Remove testing-specific parsing code
Assistant (server/services/assistant_chat_session.py):
- Update help text with current available tools
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
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>
Changes:
- Increase command limit from 50 to 100 per project
- Add examples/OPTIMIZE_CONFIG.md with optimization strategies
- Update all documentation references (50 → 100)
- Update tests for new limit
Rationale:
- 50 was too restrictive for projects with many tools (Flutter, etc.)
- Users were unknowingly exceeding limit by listing subcommands
- 100 provides headroom while maintaining security
- New guide teaches wildcard optimization (flutter* vs listing each subcommand)
UI feedback idea: Show command count and optimization suggestions
(tracked for Phase 3 or future enhancement)
Add validation to reject bare wildcards for security:
- matches_pattern(): return False if pattern == '*'
- validate_project_command(): reject name == '*' with clear error
- Added 4 new tests for bare wildcard rejection
This prevents a config with from matching every command,
which would be a major security risk.
Tests: 140 unit tests passing (added 4 bare wildcard tests)
Changes:
- Revert incorrect import from claude_code_sdk to claude_agent_sdk in agent.py
(PR #50 introduced an undocumented change to a deprecated package)
- Clear activeAgents and recentActivity in useWebSocket when agent stops
to prevent stale UI state
The claude_code_sdk package is deprecated (last updated Sep 2025) while
claude_agent_sdk is the active, maintained package. The import change in
PR #50 was undocumented and would have caused ImportError since only
claude-agent-sdk is specified in requirements.txt.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Performance improvements:
- Fix N+1 query in get_conversations() using COUNT subquery instead of
len(c.messages) which triggered lazy loading for each conversation
- Add SQLAlchemy engine caching to avoid creating new database connections
on every request
- Add React.memo to ChatMessage component to prevent unnecessary re-renders
during message streaming
- Move BOLD_REGEX to module scope to avoid recreating on each render
Code quality improvements:
- Remove 10+ console.log debug statements from AssistantChat.tsx and
AssistantPanel.tsx that were left from development
- Add user feedback for delete errors in ConversationHistory - dialog now
stays open and shows error message instead of silently failing
- Update ConfirmDialog to accept ReactNode for message prop to support
rich error content
These changes address issues identified in the code review of PR #74
(conversation history feature).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
