Replace the JSON-based project registry with SQLite using SQLAlchemy ORM for improved reliability, concurrency handling, and simpler code. Changes: - registry.py: Complete rewrite from JSON to SQLite storage - Remove manual file locking (RegistryLock class with msvcrt/fcntl) - Remove atomic write logic (temp file + rename pattern) - Remove backup/recovery logic for corrupted JSON - Add SQLAlchemy Project model with name, path, created_at columns - Add singleton database engine pattern (_get_engine) - Add session context manager (_get_session) for transactions - Simplify from 493 to 367 lines of code - CLAUDE.md: Update documentation to reflect new storage Storage location change: - Before: Platform-specific paths - Windows: %APPDATA%\autonomous-coder\projects.json - macOS: ~/Library/Application Support/autonomous-coder/projects.json - Linux: ~/.config/autonomous-coder/projects.json - After: Unified path for all platforms - ~/.autocoder/registry.db Benefits: - SQLite handles concurrency automatically (no manual locking needed) - Atomic transactions built-in (no temp file + rename dance) - Crash-safe by default (no backup/recovery code needed) - Consistent with existing features.db pattern in api/database.py - Data persists across app updates (stored in user home, not project) All public API functions maintain their existing signatures, so no changes are required in the 7 consumer files (start.py, autonomous_agent_demo.py, and 5 server routers). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
7.1 KiB
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an autonomous coding agent system with a React-based UI. It uses the Claude Agent SDK to build complete applications over multiple sessions using a two-agent pattern:
- Initializer Agent - First session reads an app spec and creates features in a SQLite database
- Coding Agent - Subsequent sessions implement features one by one, marking them as passing
Commands
Quick Start (Recommended)
# Windows - launches CLI menu
start.bat
# macOS/Linux
./start.sh
# Launch Web UI (serves pre-built React app)
start_ui.bat # Windows
./start_ui.sh # macOS/Linux
Python Backend (Manual)
# Create and activate virtual environment
python -m venv venv
venv\Scripts\activate # Windows
source venv/bin/activate # macOS/Linux
# Install dependencies
pip install -r requirements.txt
# Run the main CLI launcher
python start.py
# Run agent directly for a project (use absolute path or registered name)
python autonomous_agent_demo.py --project-dir C:/Projects/my-app
python autonomous_agent_demo.py --project-dir my-app # if registered
# YOLO mode: rapid prototyping without browser testing
python autonomous_agent_demo.py --project-dir my-app --yolo
YOLO Mode (Rapid Prototyping)
YOLO mode skips all testing for faster feature iteration:
# CLI
python autonomous_agent_demo.py --project-dir my-app --yolo
# UI: Toggle the lightning bolt button before starting the agent
What's different in YOLO mode:
- No regression testing (skips
feature_get_for_regression) - No Playwright MCP server (browser automation disabled)
- Features marked passing after lint/type-check succeeds
- Faster iteration for prototyping
What's the same:
- Lint and type-check still run to verify code compiles
- Feature MCP server for tracking progress
- All other development tools available
When to use: Early prototyping when you want to quickly scaffold features without verification overhead. Switch back to standard mode for production-quality development.
React UI (in ui/ directory)
cd ui
npm install
npm run dev # Development server (hot reload)
npm run build # Production build (required for start_ui.bat)
npm run lint # Run ESLint
Note: The start_ui.bat script serves the pre-built UI from ui/dist/. After making UI changes, run npm run build in the ui/ directory.
Architecture
Core Python Modules
start.py- CLI launcher with project creation/selection menuautonomous_agent_demo.py- Entry point for running the agentagent.py- Agent session loop using Claude Agent SDKclient.py- ClaudeSDKClient configuration with security hooks and MCP serverssecurity.py- Bash command allowlist validation (ALLOWED_COMMANDS whitelist)prompts.py- Prompt template loading with project-specific fallbackprogress.py- Progress tracking, database queries, webhook notificationsregistry.py- Project registry for mapping names to paths (cross-platform)
Project Registry
Projects can be stored in any directory. The registry maps project names to paths using SQLite:
- All platforms:
~/.autocoder/registry.db
The registry uses:
- SQLite database with SQLAlchemy ORM
- POSIX path format (forward slashes) for cross-platform compatibility
- SQLite's built-in transaction handling for concurrency safety
Server API (server/)
The FastAPI server provides REST endpoints for the UI:
server/routers/projects.py- Project CRUD with registry integrationserver/routers/features.py- Feature managementserver/routers/agent.py- Agent control (start/stop/pause/resume)server/routers/filesystem.py- Filesystem browser API with security controlsserver/routers/spec_creation.py- WebSocket for interactive spec creation
Feature Management
Features are stored in SQLite (features.db) via SQLAlchemy. The agent interacts with features through an MCP server:
mcp_server/feature_mcp.py- MCP server exposing feature management toolsapi/database.py- SQLAlchemy models (Feature table with priority, category, name, description, steps, passes)
MCP tools available to the agent:
feature_get_stats- Progress statisticsfeature_get_next- Get highest-priority pending featurefeature_get_for_regression- Random passing features for regression testingfeature_mark_passing- Mark feature completefeature_skip- Move feature to end of queuefeature_create_bulk- Initialize all features (used by initializer)
React UI (ui/)
- Tech stack: React 18, TypeScript, TanStack Query, Tailwind CSS v4, Radix UI
src/App.tsx- Main app with project selection, kanban board, agent controlssrc/hooks/useWebSocket.ts- Real-time updates via WebSocketsrc/hooks/useProjects.ts- React Query hooks for API callssrc/lib/api.ts- REST API clientsrc/lib/types.ts- TypeScript type definitionssrc/components/FolderBrowser.tsx- Server-side filesystem browser for project folder selectionsrc/components/NewProjectModal.tsx- Multi-step project creation wizard
Project Structure for Generated Apps
Projects can be stored in any directory (registered in ~/.autocoder/registry.db). Each project contains:
prompts/app_spec.txt- Application specification (XML format)prompts/initializer_prompt.md- First session promptprompts/coding_prompt.md- Continuation session promptfeatures.db- SQLite database with feature test cases.agent.lock- Lock file to prevent multiple agent instances
Security Model
Defense-in-depth approach configured in client.py:
- OS-level sandbox for bash commands
- Filesystem restricted to project directory only
- Bash commands validated against
ALLOWED_COMMANDSinsecurity.py
Claude Code Integration
.claude/commands/create-spec.md-/create-specslash command for interactive spec creation.claude/skills/frontend-design/SKILL.md- Skill for distinctive UI design.claude/templates/- Prompt templates copied to new projects
Key Patterns
Prompt Loading Fallback Chain
- Project-specific:
{project_dir}/prompts/{name}.md - Base template:
.claude/templates/{name}.template.md
Agent Session Flow
- Check if
features.dbhas features (determines initializer vs coding agent) - Create ClaudeSDKClient with security settings
- Send prompt and stream response
- Auto-continue with 3-second delay between sessions
Real-time UI Updates
The UI receives updates via WebSocket (/ws/projects/{project_name}):
progress- Test pass countsagent_status- Running/paused/stopped/crashedlog- Agent output lines (streamed from subprocess stdout)feature_update- Feature status changes
Design System
The UI uses a neobrutalism design with Tailwind CSS v4:
- CSS variables defined in
ui/src/styles/globals.cssvia@themedirective - Custom animations:
animate-slide-in,animate-pulse-neo,animate-shimmer - Color tokens:
--color-neo-pending(yellow),--color-neo-progress(cyan),--color-neo-done(green)