Files
deer-flow/backend/src/gateway/app.py
hetaoBackend 411d9d57c3 feat: add MCP API endpoint and enhance API documentation
Add new MCP configuration management endpoint and enhance API documentation
with detailed descriptions, examples, and OpenAPI support for better
developer experience.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-20 13:20:50 +08:00

115 lines
3.2 KiB
Python

import logging
from collections.abc import AsyncGenerator
from contextlib import asynccontextmanager
from fastapi import FastAPI
from src.gateway.config import get_gateway_config
from src.gateway.routers import artifacts, mcp, models
# Configure logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
)
logger = logging.getLogger(__name__)
@asynccontextmanager
async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
"""Application lifespan handler."""
config = get_gateway_config()
logger.info(f"Starting API Gateway on {config.host}:{config.port}")
# Initialize MCP tools at startup
try:
from src.mcp import initialize_mcp_tools
await initialize_mcp_tools()
except Exception as e:
logger.warning(f"Failed to initialize MCP tools: {e}")
yield
logger.info("Shutting down API Gateway")
def create_app() -> FastAPI:
"""Create and configure the FastAPI application.
Returns:
Configured FastAPI application instance.
"""
app = FastAPI(
title="DeerFlow API Gateway",
description="""
## DeerFlow API Gateway
API Gateway for DeerFlow - A LangGraph-based AI agent backend with sandbox execution capabilities.
### Features
- **Models Management**: Query and retrieve available AI models
- **MCP Configuration**: Manage Model Context Protocol (MCP) server configurations
- **Artifacts**: Access thread artifacts and generated files
- **Health Monitoring**: System health check endpoints
### Architecture
LangGraph requests are handled by nginx reverse proxy.
This gateway provides custom endpoints for models, MCP configuration, and artifacts.
""",
version="0.1.0",
lifespan=lifespan,
docs_url="/docs",
redoc_url="/redoc",
openapi_url="/openapi.json",
openapi_tags=[
{
"name": "models",
"description": "Operations for querying available AI models and their configurations",
},
{
"name": "mcp",
"description": "Manage Model Context Protocol (MCP) server configurations",
},
{
"name": "artifacts",
"description": "Access and download thread artifacts and generated files",
},
{
"name": "health",
"description": "Health check and system status endpoints",
},
],
)
# CORS is handled by nginx - no need for FastAPI middleware
# Include routers
# Models API is mounted at /api/models
app.include_router(models.router)
# MCP API is mounted at /api/mcp
app.include_router(mcp.router)
# Artifacts API is mounted at /api/threads/{thread_id}/artifacts
app.include_router(artifacts.router)
@app.get("/health", tags=["health"])
async def health_check() -> dict:
"""Health check endpoint.
Returns:
Service health status information.
"""
return {"status": "healthy", "service": "deer-flow-gateway"}
return app
# Create app instance for uvicorn
app = create_app()