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>
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>
This commit fixes several issues identified in the agent scheduling
feature from PR #75:
Frontend Fixes:
- Add day boundary handling in timeUtils.ts for timezone conversions
- Add utcToLocalWithDayShift/localToUTCWithDayShift functions
- Add shiftDaysForward/shiftDaysBackward helpers for bitfield adjustment
- Update ScheduleModal to correctly adjust days_of_week when crossing
day boundaries during UTC conversion (fixes schedules running on
wrong days for users in extreme timezones like UTC+9)
Backend Fixes:
- Add MAX_SCHEDULES_PER_PROJECT (50) limit to prevent resource exhaustion
- Wire up crash recovery callback in scheduler_service._start_agent()
- Convert schedules.py endpoints to use context manager for DB sessions
- Fix race condition in override creation with atomic delete-then-create
- Replace deprecated datetime.utcnow with datetime.now(timezone.utc)
- Add DB-level CHECK constraints for Schedule model fields
Files Modified:
- api/database.py: Add _utc_now helper, CheckConstraint imports, constraints
- progress.py: Replace deprecated datetime.utcnow
- server/routers/schedules.py: Add context manager, schedule limits
- server/services/assistant_database.py: Replace deprecated datetime.utcnow
- server/services/scheduler_service.py: Wire crash recovery, fix race condition
- ui/src/components/ScheduleModal.tsx: Use day shift functions
- ui/src/lib/timeUtils.ts: Add day boundary handling functions
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Security fixes to restore defense-in-depth after merging PR #78:
**client.py:**
- Revert permission mode from "bypassPermissions" to "acceptEdits"
- Remove redundant web_tools_auto_approve_hook from PreToolUse hooks
- Remove unused import of web_tools_auto_approve_hook
**security.py:**
- Remove web_tools_auto_approve_hook function (was redundant and
returned {} for ALL tools, not just WebFetch/WebSearch)
**server/services/spec_chat_session.py:**
- Restore allowed_tools restriction: [Read, Write, Edit, Glob,
WebFetch, WebSearch]
- Revert permission mode from "bypassPermissions" to "acceptEdits"
- Keeps setting_sources=["project", "user"] for global skills access
**ui/src/components/AgentAvatar.tsx:**
- Remove unused getMascotName export to fix React Fast Refresh warning
- File now only exports AgentAvatar component as expected
The bypassPermissions mode combined with unrestricted tool access in
spec_chat_session.py created a security gap where Bash commands could
execute without validation (sandbox disabled, no bash_security_hook).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
UI Changes:
- Add "Create Spec with AI" button in empty kanban when project has no spec
- Button opens SpecCreationChat to guide users through spec creation
- Shows in Pending column when has_spec=false and no features exist
Windows Fixes:
- Fix asyncio subprocess NotImplementedError on Windows
- Set WindowsProactorEventLoopPolicy in server/__init__.py
- Remove --reload from uvicorn (incompatible with Windows subprocess)
- Add process cleanup on startup in start_ui.bat
Spec Chat Improvements:
- Enable full tool access (remove allowed_tools restriction)
- Add "user" to setting_sources for global skills access
- Use bypassPermissions mode for auto-approval
- Add WebFetch/WebSearch auto-approve hook
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add comprehensive scheduling system that allows agents to automatically
start and stop during configured time windows, helping users manage
Claude API token limits by running agents during off-hours.
Backend Changes:
- Add Schedule and ScheduleOverride database models for persistent storage
- Implement APScheduler-based SchedulerService with UTC timezone support
- Add schedule CRUD API endpoints (/api/projects/{name}/schedules)
- Add manual override tracking to prevent unwanted auto-start/stop
- Integrate scheduler lifecycle with FastAPI startup/shutdown
- Fix timezone bug: explicitly set timezone=timezone.utc on CronTrigger
to ensure correct UTC scheduling (critical fix)
Frontend Changes:
- Add ScheduleModal component for creating and managing schedules
- Add clock button and schedule status display to AgentControl
- Add timezone utilities for converting between UTC and local time
- Add React Query hooks for schedule data fetching
- Fix 204 No Content handling in fetchJSON for delete operations
- Invalidate nextRun cache when manually stopping agent during window
- Add TypeScript type annotations to Terminal component callbacks
Features:
- Multiple overlapping schedules per project supported
- Auto-start at scheduled time via APScheduler cron jobs
- Auto-stop after configured duration
- Manual start/stop creates persistent overrides in database
- Crash recovery with exponential backoff (max 3 retries)
- Server restart preserves schedules and active overrides
- Times displayed in user's local timezone, stored as UTC
- Immediate start if schedule created during active window
Dependencies:
- Add APScheduler for reliable cron-like scheduling
Co-Authored-By: Claude Sonnet 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>
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>
- Fix duplicate onConversationCreated callbacks by tracking activeConversationId
- Fix history loss when switching conversations with Map-based deduplication
- Disable input while conversation is loading to prevent message routing issues
- Gate WebSocket debug logs behind DEV flag (import.meta.env.DEV)
- Downgrade server logging from info to debug level for reduced noise
- Fix .gitignore prefixes for playwright paths (ui/playwright-report/, ui/test-results/)
- Remove debug console.log from ConversationHistory.tsx
- Add staleTime (30s) to single conversation query for better caching
- Increase history message cap from 20 to 35 for better context
- Replace fixed timeouts with condition-based waits in e2e tests
- Add ConversationHistory dropdown component with list of past conversations
- Add useConversations hook for fetching and managing conversations via React Query
- Implement conversation switching with proper state management
- Fix bug where reopening panel showed new greeting instead of resuming conversation
- Fix bug where selecting from history caused conversation ID to revert
- Add server-side history context loading for resumed conversations
- Add Playwright E2E tests for conversation history feature
- Add logging for debugging conversation flow
Key changes:
- AssistantPanel: manages conversation state with localStorage persistence
- AssistantChat: header with [+] New Chat and [History] buttons
- Server: skips greeting for resumed conversations, loads history context on first message
- Fixed race condition in onConversationCreated callback
Complete the defense-in-depth approach from PR #53 by adding explicit
in_progress=False to all remaining feature creation locations. This
ensures consistency with the MCP server pattern and prevents potential
NULL values in the in_progress field.
Changes:
- server/routers/features.py: Add in_progress=False to create_feature()
and create_features_bulk() endpoints
- server/services/expand_chat_session.py: Add in_progress=False to
_create_features_bulk() in the expand chat session
- api/migration.py: Add in_progress field handling in JSON migration,
reading from source data with False as default
This follows up on PR #53 which added nullable=False constraints and
fixed existing NULL values, but only updated the MCP server creation
paths. Now all 6 feature creation locations explicitly set both
passes=False and in_progress=False.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add the ability for users to edit features that are not yet completed,
allowing them to provide corrections or additional instructions when the
agent is stuck or implementing a feature incorrectly.
Backend changes:
- Add FeatureUpdate schema in server/schemas.py with optional fields
- Add PATCH /api/projects/{project_name}/features/{feature_id} endpoint
- Validate that completed features (passes=True) cannot be edited
Frontend changes:
- Add FeatureUpdate type in ui/src/lib/types.ts
- Add updateFeature() API function in ui/src/lib/api.ts
- Add useUpdateFeature() React Query mutation hook
- Create EditFeatureForm.tsx component with pre-filled form values
- Update FeatureModal.tsx with Edit button for non-completed features
The edit form allows modifying category, name, description, priority,
and test steps. Save button is disabled until changes are detected.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The model was hardcoded to "claude-opus-4-5-20251101" in chat session
services, ignoring the ANTHROPIC_DEFAULT_OPUS_MODEL environment variable.
This caused issues when using alternative API providers (e.g., GLM via z.ai)
that don't support Claude model names.
Fixes#51
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>
Changes:
- Write system prompts to CLAUDE.md file instead of passing inline
- Use setting_sources=["project"] to load prompts from file
- Affects spec_chat_session.py and assistant_chat_session.py
Why:
- Windows has ~8191 character command line limit
- System prompts (e.g., create-spec.md at ~19KB) exceeded this limit
- The SDK serializes system_prompt as a CLI argument
- Writing to file and using setting_sources bypasses the limit
This completes the fix for GitHub issue #33 (Windows "Command Line Too Long").
The previous commit removed **os.environ from MCP configs; this commit
addresses the larger system prompt issue.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add support for using alternative API endpoints (like Zhipu AI's GLM models)
without affecting the user's global Claude Code settings. Configuration is
done via AutoCoder's .env file.
Changes:
- Add API_ENV_VARS constant and pass through ClaudeAgentOptions.env parameter
in client.py and all server service files (spec, expand, assistant sessions)
- Add glm_mode to settings API response to indicate when GLM is configured
- Add purple "GLM" badge in UI header when GLM mode is active
- Update setup status to accept GLM credentials as valid authentication
- Update .env.example with GLM configuration documentation
- Update README.md with AutoCoder-scoped GLM setup instructions
Supported environment variables:
- ANTHROPIC_BASE_URL: Custom API endpoint (e.g., https://api.z.ai/api/anthropic)
- ANTHROPIC_AUTH_TOKEN: API authentication token
- API_TIMEOUT_MS: Request timeout in milliseconds
- ANTHROPIC_DEFAULT_SONNET_MODEL: Model override for Sonnet
- ANTHROPIC_DEFAULT_OPUS_MODEL: Model override for Opus
- ANTHROPIC_DEFAULT_HAIKU_MODEL: Model override for Haiku
This approach routes API requests through the alternative endpoint while
keeping all Claude Code features (MCP servers, hooks, permissions) intact.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add support for multiple terminal instances per project with tabbed
navigation in the debug panel. Each terminal maintains its own PTY
session and WebSocket connection.
Backend changes:
- Add terminal metadata storage (id, name, created_at) per project
- Update terminal_manager.py with create, list, rename, delete functions
- Extend WebSocket endpoint to /api/terminal/ws/{project}/{terminal_id}
- Add REST endpoints for terminal CRUD operations
- Implement deferred PTY start with initial resize message
Frontend changes:
- Create TerminalTabs component with neobrutalism styling
- Support double-click rename and right-click context menu
- Fix terminal switching issues with transform-based hiding
- Use isActiveRef to prevent stale closure bugs in connect()
- Add double requestAnimationFrame for reliable activation timing
- Implement proper dimension validation in fitTerminal()
Other updates:
- Add GLM model configuration documentation to README
- Simplify client.py by removing CLI_COMMAND support
- Update chat session services with consistent patterns
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add new features for interactive terminal sessions and dev server control:
Terminal Component:
- New Terminal.tsx component using xterm.js for full terminal emulation
- WebSocket-based PTY communication with bidirectional I/O
- Cross-platform support (Windows via winpty, Unix via built-in pty)
- Auto-reconnection with exponential backoff
- Fix duplicate WebSocket connection bug by checking CONNECTING state
- Add manual close flag to prevent auto-reconnect race conditions
- Add project tracking to avoid duplicate connects on initial activation
Dev Server Management:
- New DevServerControl.tsx for starting/stopping dev servers
- DevServerManager service for subprocess management
- WebSocket streaming of dev server output
- Project configuration service for reading package.json scripts
Backend Infrastructure:
- Terminal router with WebSocket endpoint for PTY I/O
- DevServer router for server lifecycle management
- Terminal session manager with callback-based output streaming
- Enhanced WebSocket schemas for terminal and dev server messages
UI Integration:
- New Terminal and Dev Server tabs in the main application
- Updated DebugLogViewer with improved UI and functionality
- Extended useWebSocket hook for terminal message handling
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove automatic subfolder creation when creating projects. Users now
select the exact folder they want to use, enabling support for existing
projects without requiring folder names to match project names.
Changes:
- NewProjectModal.tsx: Remove path concatenation that appended project
name to selected folder. Update instruction text to clarify users
select THE project folder, not a parent location.
- FolderBrowser.tsx: Add visual indicator "This folder will contain
all project files" to clarify selection behavior.
- projects.py: Add duplicate path validation to prevent multiple
projects from registering the same directory. Includes case-insensitive
path comparison on Windows for proper cross-platform support.
This allows users to:
- Use Auto Coder on existing projects by selecting their folder directly
- Have project names that differ from folder names (name is a registry label)
- Get clear feedback when a path is already registered under another name
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add support for alternative CLI commands via CLI_COMMAND environment
variable, allowing users to use CLIs other than 'claude' (e.g., 'glm').
This change affects all server services and the main CLI launcher.
Key changes:
- Configurable CLI command via CLI_COMMAND env var (defaults to 'claude')
- Configurable Playwright headless mode via PLAYWRIGHT_HEADLESS env var
- Pin claude-agent-sdk version to <0.2.0 for stability
- Use tail -500 for progress notes to avoid context overflow
- Add project delete functionality with confirmation dialog
- Replace single-line input with resizable textarea in spec chat
- Add coder agent configuration for code implementation tasks
- Ignore issues/ directory in git
Files modified:
- client.py: CLI command and Playwright headless configuration
- server/main.py, server/services/*: CLI command configuration
- start.py: CLI command configuration and error messages
- .env.example: Document new environment variables
- .gitignore: Ignore issues/ directory
- requirements.txt: Pin SDK version
- .claude/templates/*: Use tail -500 for progress notes
- ui/src/components/ProjectSelector.tsx: Add delete button
- ui/src/components/SpecCreationChat.tsx: Auto-resizing textarea
- ui/src/components/ConfirmDialog.tsx: New reusable dialog
- .claude/agents/coder.md: New coder agent configuration
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>
- Add language specifier to fenced code block in expand-project.md
- Remove detailed exception strings from WebSocket responses (security)
- Make WebSocket "start" message idempotent to avoid session reset
- Fix race condition in bulk feature creation with row-level lock
- Add validation for starting_priority (must be >= 1)
- Fix _query_claude to handle multiple feature blocks and deduplicate
- Add FileReader error handling in ExpandProjectChat
- Fix disconnect() to clear pending reconnect timeout
- Enable sandbox mode and validate CLI path in expand_chat_session
- Clean up temporary settings file on session close
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds the ability to add multiple features to an existing project through
a natural language conversation with Claude, similar to how initial spec
creation works.
Features:
- New "Expand" button in header (keyboard shortcut: E)
- Full-screen chat interface for describing new features
- Claude reads existing app_spec.txt for context
- Features created directly in database after user approval
- Bulk feature creation endpoint for batch operations
New files:
- .claude/commands/expand-project.md - Claude skill for expansion
- server/services/expand_chat_session.py - Chat session service
- server/routers/expand_project.py - WebSocket endpoint
- ui/src/components/ExpandProjectChat.tsx - Chat UI
- ui/src/components/ExpandProjectModal.tsx - Modal wrapper
- ui/src/hooks/useExpandChat.ts - WebSocket hook
Modified:
- Added POST /bulk endpoint to features router
- Added FeatureBulkCreate schemas
- Integrated Expand button and modal in App.tsx
Co-Authored-By: Claude <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>
Extend auth error detection to the web UI flow:
server/main.py:
- Fix setup_status() endpoint to check ~/.claude directory instead of
non-existent .credentials.json file
- Add explanatory comments about Claude CLI credential storage changes
server/services/process_manager.py:
- Add AUTH_ERROR_PATTERNS for detecting auth errors in agent output
- Add is_auth_error() helper function
- Add AUTH_ERROR_HELP message template
- Update _stream_output() to detect auth errors in real-time
- Buffer last 20 lines to catch auth errors on process exit
- Broadcast clear help message to WebSocket clients when auth fails
start_ui.sh:
- Add Claude CLI installation check with helpful guidance
- Add ~/.claude directory check with login reminder
- Non-blocking warnings that don't prevent UI from starting
This ensures users get clear, actionable feedback when authentication
fails, whether using the CLI or the web UI.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds a settings system for global configuration with YOLO mode toggle and
model selection. Simplifies the agent control UI by removing redundant
status indicator and pause functionality.
## Settings System
- New SettingsModal with YOLO mode toggle and model selection
- Settings persisted in SQLite (registry.db) - shared across all projects
- Models fetched from API endpoint (/api/settings/models)
- Single source of truth for models in registry.py - easy to add new models
- Optimistic UI updates with rollback on error
## Agent Control Simplification
- Removed StatusIndicator ("STOPPED"/"RUNNING" label) - redundant
- Removed Pause/Resume buttons - just Start/Stop toggle now
- Start button shows flame icon with fiery gradient when YOLO mode enabled
## Code Review Fixes
- Added focus trap to SettingsModal for accessibility
- Fixed YOLO button color contrast (WCAG AA compliance)
- Added model validation to AgentStartRequest schema
- Added model to AgentStatus response
- Added aria-labels to all icon-only buttons
- Added role="radiogroup" to model selection
- Added loading indicator during settings save
- Added SQLite timeout (30s) and retry logic with exponential backoff
- Added thread-safe database engine initialization
- Added orphaned lock file cleanup on server startup
## Files Changed
- registry.py: Model config, Settings CRUD, SQLite improvements
- server/routers/settings.py: New settings API
- server/schemas.py: Settings schemas with validation
- server/services/process_manager.py: Model param, orphan cleanup
- ui/src/components/SettingsModal.tsx: New modal component
- ui/src/components/AgentControl.tsx: Simplified to Start/Stop only
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add CI workflow with Python (ruff lint, security tests) and UI (ESLint, TypeScript, build) jobs
- Add ruff, mypy, pytest to requirements.txt
- Add pyproject.toml with ruff configuration
- Fix import sorting across Python files (ruff --fix)
- Fix test_security.py expectations to match actual security policy
- Remove invalid 'eof' command from ALLOWED_COMMANDS
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Implement a slide-in chat panel that allows users to ask questions about
their codebase using Claude Opus 4.5 with read-only access to project files.
Backend changes:
- Add SQLAlchemy models for conversation persistence (assistant_database.py)
- Create AssistantChatSession with read-only Claude SDK client
- Add WebSocket endpoint for real-time chat streaming
- Include read-only MCP tools: feature_get_stats, feature_get_next, etc.
Frontend changes:
- Add floating action button (bottom-right) to toggle panel
- Create slide-in panel component (400px width)
- Implement WebSocket hook with reconnection logic
- Add keyboard shortcut 'A' to toggle assistant
Key features:
- Read-only access: Only Read, Glob, Grep, WebFetch, WebSearch tools
- Persistent history: Conversations saved to SQLite per project
- Real-time streaming: Text chunks streamed as Claude generates response
- Tool visibility: Shows when assistant is using tools to explore code
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add multiple escape hatches to prevent users from getting stuck during
spec creation when the WebSocket completion signal fails.
Changes:
- Add "Exit to Project" button always visible in chat header
- Add /exit command detection to immediately exit to project
- Add backend GET /api/spec/status/{project} endpoint to poll status file
- Add getSpecStatus() API function in frontend
- Add status file polling (every 3s) in useSpecChat hook
- Update create-spec.md with status file write instructions
How it works:
1. Happy path: Claude writes .spec_status.json as final step, UI polls
and detects completion, shows "Continue to Project" button
2. Escape hatch: User can always click "Exit to Project" or type /exit
to instantly select the project and close modal, then manually start
the agent from the main UI
This ensures users always have a way forward even if the WebSocket
completion detection fails due to tool call tracking issues.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add the ability to attach images (JPEG, PNG) in the Spec Creation chat
interface for Claude to analyze during app specification creation.
Frontend changes:
- Add ImageAttachment interface to types.ts with id, filename, mimeType,
base64Data, previewUrl, and size fields
- Update ChatMessage interface with optional attachments field
- Update useSpecChat hook to accept and send attachments via WebSocket
- Add file input, drag-drop support, and preview thumbnails to
SpecCreationChat component with validation (5 MB max, JPEG/PNG only)
- Update ChatMessage component to render image attachments with
click-to-enlarge functionality
Backend changes:
- Add ImageAttachment Pydantic schema with base64 validation
- Update spec_creation.py WebSocket handler to parse and validate
image attachments from client messages
- Update spec_chat_session.py to format multimodal content blocks
for Claude API using async generator pattern
Features:
- Drag-and-drop or click paperclip button to attach images
- Preview thumbnails with remove button before sending
- File type validation (image/jpeg, image/png)
- File size validation (5 MB maximum)
- Images display in chat history
- Click images to view full size
- Cross-platform compatible (Windows, macOS, Linux)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
