Routeur de Code Claude

Commandes et workflows complets du Routeur de Code Claude pour acheminer les requêtes de Code Claude vers différents modèles d’IA, permettant le développement multi-modèles et l’optimisation des coûts.

Aperçu

Le Routeur de Code Claude est un outil open-source qui agit comme un proxy local pour les requêtes de Code Claude, vous permettant d’intercepter, modifier et acheminer des requêtes vers différents modèles d’IA, notamment GPT-4, Gemini, des modèles locaux et d’autres API compatibles OpenAI. Cela permet aux développeurs d’utiliser l’interface puissante de Code Claude tout en exploitant différents modèles pour des tâches spécifiques, l’optimisation des coûts ou l’accès à des crédits API gratuits.

⚠️ Avis d’utilisation : Le Routeur de Code Claude modifie les requêtes API et nécessite une configuration appropriée des clés et points d’accès API. Assurez-vous toujours de manipuler les identifiants de manière sécurisée et de respecter les conditions de service des API.

Installation

Configuration Rapide

# Install via npm
npm install -g claude-code-router

# Install via pip
pip install claude-code-router

# Clone from GitHub
git clone https://github.com/musistudio/claude-code-router.git
cd claude-code-router
npm install

Installation Docker

# Pull Docker image
docker pull claudecode/router:latest

# Run with Docker
docker run -p 8080:8080 -e OPENAI_API_KEY=your-key claudecode/router

# Docker Compose
version: '3.8'
services:
  claude-router:
    image: claudecode/router:latest
    ports:
      - "8080:8080"
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}

Compilation à partir des Sources

# Clone repository
git clone https://github.com/musistudio/claude-code-router.git
cd claude-code-router

# Install dependencies
npm install

# Build project
npm run build

# Start router
npm start

Configuration

Configuration de Base

{
  "router": {
    "port": 8080,
    "host": "localhost",
    "logLevel": "info",
    "enableCors": true
  },
  "models": {
    "claude-3-sonnet": {
      "provider": "anthropic",
      "apiKey": "${ANTHROPIC_API_KEY}",
      "endpoint": "https://api.anthropic.com/v1/messages"
    },
    "gpt-4": {
      "provider": "openai",
      "apiKey": "${OPENAI_API_KEY}",
      "endpoint": "https://api.openai.com/v1/chat/completions"
    },
    "gemini-pro": {
      "provider": "google",
      "apiKey": "${GOOGLE_API_KEY}",
      "endpoint": "https://generativelanguage.googleapis.com/v1/models"
    }
  },
  "routing": {
    "defaultModel": "claude-3-sonnet",
    "fallbackModel": "gpt-4",
    "loadBalancing": false,
    "costOptimization": true
  }
}

Règles de Routage Avancées

{
  "routingRules": [
    {
      "name": "code_generation",
      "condition": {
        "messageContains": ["write code", "implement", "create function"],
        "fileTypes": [".py", ".js", ".ts", ".java"]
      },
      "targetModel": "gpt-4",
      "priority": 1
    },
    {
      "name": "documentation",
      "condition": {
        "messageContains": ["document", "explain", "comment"],
        "taskType": "documentation"
      },
      "targetModel": "claude-3-sonnet",
      "priority": 2
    },
    {
      "name": "cost_optimization",
      "condition": {
        "tokenCount": { "max": 1000 },
        "complexity": "low"
      },
      "targetModel": "gpt-3.5-turbo",
      "priority": 3
    }
  ]
}

Commandes Principales

Gestion du Routeur

Commande	Description
router start	Démarrer le Claude Code Router
router stop	Arrêter le service router
router restart	Redémarrer le routeur
router status	Vérifier le statut du router
router config	Afficher la configuration actuelle
router logs	Afficher les journaux du routeur
router health	Point de contrôle de santé

Gestion des Modèles

Commande	Description
router models list	Lister les modèles disponibles
router models add	Ajouter une nouvelle configuration de modèle
router models remove	Supprimer la configuration du modèle
router models test	Tester la connectivité du modèle
router models switch	Changer de modèle par défaut
router models status	Vérifier le statut du modèle

Intégration de Code Claude

Configurer Code Claude

# Set Claude Code to use router
export ANTHROPIC_API_BASE=http://localhost:8080/v1
export ANTHROPIC_API_KEY=router-proxy-key

# Alternative configuration
claude-code config set api.base_url http://localhost:8080/v1
claude-code config set api.key router-proxy-key

# Verify configuration
claude-code config show

Configuration du Proxy du Routeur

# Start router with specific configuration
claude-code-router --config config.json --port 8080

# Start with environment variables
ROUTER_PORT=8080 ROUTER_CONFIG=config.json claude-code-router

# Start with custom models
claude-code-router --models gpt-4,claude-3-sonnet,gemini-pro

Fournisseurs de Modèles

Intégration OpenAI

{
  "openai": {
    "apiKey": "${OPENAI_API_KEY}",
    "baseUrl": "https://api.openai.com/v1",
    "models": {
      "gpt-4": {
        "maxTokens": 8192,
        "temperature": 0.7,
        "costPerToken": 0.00003
      },
      "gpt-3.5-turbo": {
        "maxTokens": 4096,
        "temperature": 0.7,
        "costPerToken": 0.000002
      }
    }
  }
}

Intégration de Google Gemini

{
  "google": {
    "apiKey": "${GOOGLE_API_KEY}",
    "baseUrl": "https://generativelanguage.googleapis.com/v1",
    "models": {
      "gemini-pro": {
        "maxTokens": 32768,
        "temperature": 0.7,
        "costPerToken": 0.000001
      },
      "gemini-pro-vision": {
        "maxTokens": 16384,
        "temperature": 0.7,
        "supportsImages": true
      }
    }
  }
}

Intégration de Modèles Locaux

{
  "local": {
    "baseUrl": "http://localhost:11434/v1",
    "models": {
      "llama2": {
        "endpoint": "/api/generate",
        "maxTokens": 4096,
        "temperature": 0.7,
        "costPerToken": 0
      },
      "codellama": {
        "endpoint": "/api/generate",
        "maxTokens": 8192,
        "temperature": 0.3,
        "specialization": "code"
      }
    }
  }
}

Intégration d’OpenRouter

{
  "openrouter": {
    "apiKey": "${OPENROUTER_API_KEY}",
    "baseUrl": "https://openrouter.ai/api/v1",
    "models": {
      "anthropic/claude-3-sonnet": {
        "maxTokens": 200000,
        "costPerToken": 0.000015
      },
      "openai/gpt-4": {
        "maxTokens": 8192,
        "costPerToken": 0.00003
      },
      "google/gemini-pro": {
        "maxTokens": 32768,
        "costPerToken": 0.000001
      }
    }
  }
}

Stratégies de Routage

Équilibrage de Charge

{
  "loadBalancing": {
    "enabled": true,
    "strategy": "round_robin",
    "models": ["gpt-4", "claude-3-sonnet", "gemini-pro"],
    "weights": {
      "gpt-4": 0.4,
      "claude-3-sonnet": 0.4,
      "gemini-pro": 0.2
    },
    "healthCheck": {
      "enabled": true,
      "interval": 60,
      "timeout": 10
    }
  }
}

Optimisation des Coûts

{
  "costOptimization": {
    "enabled": true,
    "budget": {
      "daily": 10.00,
      "monthly": 300.00,
      "currency": "USD"
    },
    "rules": [
      {
        "condition": "tokenCount < 500",
        "model": "gpt-3.5-turbo"
      },
      {
        "condition": "tokenCount >= 500 && tokenCount < 2000",
        "model": "claude-3-haiku"
      },
      {
        "condition": "tokenCount >= 2000",
        "model": "claude-3-sonnet"
      }
    ]
  }
}

Routage Intelligent

{
  "intelligentRouting": {
    "enabled": true,
    "rules": [
      {
        "name": "code_tasks",
        "patterns": ["implement", "write code", "debug", "refactor"],
        "model": "gpt-4",
        "confidence": 0.8
      },
      {
        "name": "analysis_tasks",
        "patterns": ["analyze", "explain", "review", "understand"],
        "model": "claude-3-sonnet",
        "confidence": 0.9
      },
      {
        "name": "creative_tasks",
        "patterns": ["create", "design", "brainstorm", "generate"],
        "model": "gemini-pro",
        "confidence": 0.7
      }
    ]
  }
}

Surveillance et Analytique

Suivi d’Utilisation

# View usage statistics
curl http://localhost:8080/api/stats

# Model usage breakdown
curl http://localhost:8080/api/stats/models

# Cost analysis
curl http://localhost:8080/api/stats/costs

# Performance metrics
curl http://localhost:8080/api/stats/performance

Configuration de la Journalisation

{
  "logging": {
    "level": "info",
    "format": "json",
    "outputs": ["console", "file"],
    "file": {
      "path": "./logs/router.log",
      "maxSize": "100MB",
      "maxFiles": 10,
      "compress": true
    },
    "metrics": {
      "enabled": true,
      "interval": 60,
      "endpoint": "/metrics"
    }
  }
}

Surveillance de la Santé

The translation preserves the markdown formatting, keeps technical terms in English, and maintains the overall structure and punctuation of the original text.```bash

Health check endpoint

curl http://localhost:8080/health

Detailed health status

curl http://localhost:8080/health/detailed

Model availability

curl http://localhost:8080/health/models

Performance metrics

curl http://localhost:8080/metrics

```javascript
// Custom request transformer
const requestTransformer = {
  transform: (request, targetModel) => {
    // Modify request based on target model
    if (targetModel === 'gpt-4') {
      request.temperature = 0.3; // Lower temperature for code
    } else if (targetModel === 'claude-3-sonnet') {
      request.max_tokens = 4096; // Adjust token limit
    }
    return request;
  }
};

// Response transformer
const responseTransformer = {
  transform: (response, sourceModel) => {
    // Standardize response format
    return {
      content: response.content || response.message,
      model: sourceModel,
      usage: response.usage,
      timestamp: new Date().toISOString()
    };
  }
};
```### Système de Plugins
```javascript
// Router plugin interface
class RouterPlugin {
  constructor(config) {
    this.config = config;
  }
  
  onRequest(request, context) {
    // Pre-process request
    return request;
  }
  
  onResponse(response, context) {
    // Post-process response
    return response;
  }
  
  onError(error, context) {
    // Handle errors
    console.error('Router error:', error);
  }
}

// Load plugins
const plugins = [
  new CostTrackingPlugin(),
  new CachePlugin(),
  new RateLimitPlugin()
];
```### Système de Mise en Cache
```json
{
  "cache": {
    "enabled": true,
    "type": "redis",
    "connection": {
      "host": "localhost",
      "port": 6379,
      "password": "${REDIS_PASSWORD}"
    },
    "ttl": 3600,
    "keyPrefix": "claude-router:",
    "compression": true,
    "rules": [
      {
        "pattern": "explain*",
        "ttl": 7200
      },
      {
        "pattern": "generate*",
        "ttl": 1800
      }
    ]
  }
}
```## Sécurité et Authentification
```json
{
  "security": {
    "authentication": {
      "enabled": true,
      "type": "bearer",
      "keys": [
        {
          "key": "router-key-1",
          "permissions": ["read", "write"],
          "rateLimit": 1000
        },
        {
          "key": "router-key-2",
          "permissions": ["read"],
          "rateLimit": 100
        }
      ]
    },
    "encryption": {
      "enabled": true,
      "algorithm": "AES-256-GCM",
      "keyRotation": 86400
    }
  }
}
```### Gestion des Clés API
```json
{
  "rateLimit": {
    "enabled": true,
    "global": {
      "requests": 1000,
      "window": 3600
    },
    "perKey": {
      "requests": 100,
      "window": 3600
    },
    "perModel": {
      "gpt-4": {
        "requests": 50,
        "window": 3600
      },
      "claude-3-sonnet": {
        "requests": 100,
        "window": 3600
      }
    }
  }
}
```### Limitation de Débit
```bash
# Router not starting
- Check port availability
- Verify configuration file
- Check API key validity
- Review log files

# Model connection failures
- Test API endpoints
- Verify API keys
- Check network connectivity
- Review rate limits

# Performance issues
- Monitor memory usage
- Check cache configuration
- Review routing rules
- Optimize model selection
```## Dépannage
```bash
# Enable debug logging
DEBUG=claude-router:* npm start

# Verbose logging
claude-code-router --log-level debug

# Request tracing
curl -H "X-Debug: true" http://localhost:8080/v1/messages

# Performance profiling
curl http://localhost:8080/debug/profile
```### Problèmes Courants
```json
{
  "performance": {
    "connectionPool": {
      "maxConnections": 100,
      "timeout": 30000,
      "keepAlive": true
    },
    "compression": {
      "enabled": true,
      "level": 6,
      "threshold": 1024
    },
    "clustering": {
      "enabled": true,
      "workers": "auto"
    }
  }
}
```### Mode Débogage
```yaml
# Kubernetes deployment
apiVersion: apps/v1
kind: Deployment
metadata:
  name: claude-router
spec:
  replicas: 3
  selector:
    matchLabels:
      app: claude-router
  template:
    metadata:
      labels:
        app: claude-router
    spec:
      containers:
      - name: claude-router
        image: claudecode/router:latest
        ports:
        - containerPort: 8080
        env:
        - name: OPENAI_API_KEY
          valueFrom:
            secretKeyRef:
              name: api-keys
              key: openai
        - name: ANTHROPIC_API_KEY
          valueFrom:
            secretKeyRef:
              name: api-keys
              key: anthropic
```### Optimisation des Performances
```yaml
version: '3.8'
services:
  claude-router:
    image: claudecode/router:latest
    ports:
      - "8080:8080"
    environment:
      - NODE_ENV=production
      - ROUTER_CONFIG=/app/config/production.json
    volumes:
      - ./config:/app/config
      - ./logs:/app/logs
    restart: unless-stopped
    
  redis:
    image: redis:alpine
    ports:
      - "6379:6379"
    volumes:
      - redis_data:/data
    
volumes:
  redis_data:
```## Déploiement
https://github.com/musistudio/claude-code-router##

# Déploiement en Production
https://docs.claude-router.dev/##

# Docker Compose
https://discord.gg/claude-router#

# Ressources
https://youtube.com/claude-router- [Dépôt GitHub de Claude Code Router](https://openrouter.ai/docs)