AI模型路由服务器

git clone https://github.com/yourusername/gpt5-mcp-agent.git
cd gpt5-mcp-agent

npm install

npm run build

# Provider Selection
API_PROVIDER=azure

# Azure OpenAI Configuration
AZURE_OPENAI_API_KEY=your_api_key_here
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/
AZURE_OPENAI_API_VERSION=2025-01-01-preview

# Azure Deployment Names (customize to match your deployments)
AZURE_OPENAI_DEPLOYMENT_GPT5=your-gpt5-deployment-name
AZURE_OPENAI_DEPLOYMENT_GPT5_CHAT=your-gpt5-chat-deployment-name

# Provider Selection
API_PROVIDER=openai

# OpenAI Configuration
OPENAI_API_KEY=your_openai_api_key_here
# Optional: Custom base URL (leave empty for default)
OPENAI_BASE_URL=
# Optional: Organization ID
OPENAI_ORG_ID=

# OpenAI Model Names
OPENAI_MODEL_GPT5=gpt-5
OPENAI_MODEL_GPT5_CHAT=gpt-5-chat

# Multiple Providers Enabled
PROVIDERS_ENABLED=azure,xai,google,groq,ollama

# xAI Grok Configuration
XAI_API_KEY=your_xai_api_key_here
XAI_ENABLE_LIVE_SEARCH=true
XAI_SEARCH_DEPTH=deep

# Google AI Configuration  
GOOGLE_AI_API_KEY=your_google_api_key_here
GOOGLE_PROJECT_ID=your_project_id
GOOGLE_LOCATION=us-central1

# Groq Configuration
GROQ_API_KEY=your_groq_api_key_here
GROQ_PRIORITY_TIER=paid

# Ollama Local Models
OLLAMA_HOST=http://localhost:11434
OLLAMA_AUTO_INSTALL=true
OLLAMA_DEFAULT_MODEL=llama3.2

# Model Selection
DEFAULT_CHAT_MODEL=gpt-5-chat          # For fast conversations
DEFAULT_REASONING_MODEL=gpt-5          # For complex analysis
ENABLE_MODEL_ROUTING=true              # Auto-select optimal model

# GPT-5-Chat Settings (Traditional Chat Model)
DEFAULT_TEMPERATURE=0.7                # Controls randomness (0.0-2.0)
DEFAULT_TOP_P=1.0                      # Nucleus sampling
DEFAULT_PRESENCE_PENALTY=0             # Encourages new topics (-2.0 to 2.0)
DEFAULT_FREQUENCY_PENALTY=0            # Reduces repetition (-2.0 to 2.0)

# GPT-5 Reasoning Model Settings
DEFAULT_REASONING_EFFORT=medium        # minimal, low, medium, high
DEFAULT_VERBOSITY=medium               # low, medium, high

# Performance Settings
MAX_COMPLETION_TOKENS=128000          # Max tokens for responses
ENABLE_STREAMING=true                 # Enable streaming for GPT-5-Chat
SESSION_TIMEOUT_MINUTES=60            # Session cleanup interval

{
  "tool": "gpt5_smart",
  "parameters": {
    "message": "Analyze the algorithmic complexity of this sorting algorithm",
    "autoRoute": true
  }
}
// Automatically routes to GPT-5 for complex analysis

{
  "tool": "gpt5_chat_fast",
  "parameters": {
    "message": "Write a creative story about AI",
    "temperature": 0.9,
    "topP": 0.95,
    "presencePenalty": 0.3
  }
}

{
  "tool": "gpt5_code",
  "parameters": {
    "code": "function quickSort(arr) { ... }",
    "task": "review",
    "language": "javascript",
    "reasoningEffort": "high"
  }
}

{
  "tool": "gpt5_design",
  "parameters": {
    "brief": "Design a scalable microservices architecture for e-commerce",
    "type": "architecture",
    "depth": "deep",
    "constraints": ["AWS cloud", "100k concurrent users", "Sub-second response"]
  }
}

{
  "tool": "gpt5_conversation",
  "parameters": {
    "message": "Let's discuss machine learning",
    "model": "gpt-5-chat",
    "temperature": 0.7
  }
}

{
  "tool": "ai_smart",
  "parameters": {
    "message": "Analyze this private code locally",
    "forceModel": "llama3.2",
    "preferredModel": "llama3.2"
  }
}
// Automatically uses local Ollama for complete privacy

{
  "tool": "ai_benchmark_models",
  "parameters": {
    "testPrompts": ["Explain quantum computing", "Write a Python function"],
    "models": [
      {"provider": "azure", "model": "gpt-5"},
      {"provider": "xai", "model": "grok-4"},
      {"provider": "ollama", "model": "llama3.2"}
    ]
  }
}

start.bat

npm start

npm run dev

{
  "mcpServers": {
    "gpt5-agent": {
      "command": "node",
      "args": ["C:\\path\\to\\gpt5-mcp-agent\\dist\\index.js"]
    }
  }
}

{
  "mcpServers": {
    "gpt5-agent": {
      "command": "node",
      "args": ["/path/to/gpt5-mcp-agent/dist/index.js"]
    }
  }
}

gpt5-agent/
├── src/
│   ├── index.ts           # Main server with all tools
│   ├── gpt5-client.ts     # Enhanced client with dual model support
│   ├── model-router.ts    # Intelligent model selection logic
│   └── types.ts           # TypeScript definitions
├── dist/                  # Compiled JavaScript
├── .env                   # Configuration
└── package.json

npm run build

# Test build
debug.bat

# Test server startup
test-server.bat