# Setup Guide

## Prerequisites

- Python 3.10+
- Node.js 16+ (for frontend)
- Redis (optional, for production)
- PostgreSQL (optional, for production)

## Local Development Setup

### Using Scripts (Recommended)

**Windows:**
```bash
cd backend
scripts\setup.bat
scripts\run.bat
```

**Linux/macOS:**
```bash
cd backend
chmod +x scripts/setup.sh scripts/run.sh
./scripts/setup.sh
./scripts/run.sh
```

### Manual Setup

#### Backend

1. **Create virtual environment:**
   ```bash
   python -m venv venv
   
   # Windows
   venv\Scripts\activate.bat
   
   # Linux/macOS
   source venv/bin/activate
   ```

2. **Install dependencies:**
   ```bash
   pip install -r requirements.txt
   pip install -r requirements-dev.txt
   ```

3. **Setup environment:**
   ```bash
   cp .env.example .env
   # Edit .env with your OpenAI API key and settings
   ```

4. **Run backend:**
   ```bash
   uvicorn backend.api.main:app --reload
   ```

   Backend will be available at: `http://localhost:8000`
   API Documentation: `http://localhost:8000/docs`

#### Frontend

1. **Install dependencies:**
   ```bash
   cd frontend
   npm install
   ```

2. **Start development server:**
   ```bash
   npm run dev
   ```

   Frontend will be available at: `http://localhost:3000`

## Using Docker

### Docker Compose (All Services)

```bash
docker-compose up --build
```

This starts:
- Backend: `http://localhost:8000`
- Redis: `localhost:6379`
- PostgreSQL: `localhost:5432`

### Single Container

```bash
docker build -t multi-agent .
docker run -p 8000:8000 -e OPENAI_API_KEY=your_key multi-agent
```

## Configuration

### Environment Variables

See `.env.example` for all available options:

- `OPENAI_API_KEY` - Required: Your OpenAI API key
- `DATABASE_URL` - Database connection string
- `REDIS_HOST/PORT` - Redis configuration
- `LOG_LEVEL` - Logging level (INFO, DEBUG, etc.)

### Database

#### SQLite (Development Default)
Automatically created as `multi_agent.db`

#### PostgreSQL (Production)
```bash
# Update DATABASE_URL in .env
DATABASE_URL=postgresql://user:password@localhost:5432/multi_agent
```

## Running Tests

```bash
# All tests
pytest

# With coverage
pytest --cov=backend tests/

# Specific test file
pytest tests/test_agents.py -v
```

## Troubleshooting

### Port Already in Use
```bash
# Find process using port 8000
lsof -i :8000

# Kill process (Linux/macOS)
kill -9 <PID>

# Or change port
uvicorn backend.api.main:app --port 8001
```

### OpenAI API Key Not Working
- Ensure key is set in `.env` file
- Check key is valid at https://platform.openai.com/account/api-keys
- Verify key has available credits

### Redis Connection Issues
- Ensure Redis is running: `redis-cli ping`
- Check REDIS_HOST and REDIS_PORT in `.env`
- For Docker: use service name `redis` instead of `localhost`

## Next Steps

- Check [API Documentation](./API.md)
- Review [Deployment Guide](./DEPLOYMENT.md)
- See [Architecture Overview](./ARCHITECTURE.md)