ai-video-fullstack/backend/app.py

"""FastAPI 入口。挂载路由,放行前端跨域,启动时同步接口定义。

启动:  uv run --with-requirements requirements.txt uvicorn app:app --reload --port 8000

路由分组(对齐 dograh 的 routes/ 结构):
  /health              健康检查
  /api/assistants      助手 CRUD
  /api/interface-definitions 接口定义
  /api/model-resources 模型资源 CRUD
  /ws/voice            WebRTC 输出(浏览器)
  /ws/stream           WS 输出(裸音频流)
  /api/webrtc/ice-servers  WebRTC STUN/TURN 配置
"""

import asyncio
import os

# NLTK 3.9+ blocks dependency imports when .venv lives under cwd (local dev layout).
# pipecat -> nltk -> regex hits this false positive; disable before any nltk import.
os.environ.setdefault("NLTK_DISABLE_IMPORT_SECURITY", "1")

from contextlib import asynccontextmanager

import settings
import uvicorn
from db.session import sync_default_tools, sync_interface_definitions
from loguru import logger
from services.openai_api import (
    PUBLIC_API_NAME,
    RequestIDMiddleware,
    openai_error_response,
)
from services.knowledge import recover_interrupted_documents
from services.openai_responses.state import recover_interrupted_responses
from services.post_call.worker import recover_interrupted_analyses, run_analysis_worker
from services.webhooks.worker import recover_interrupted_webhooks, run_webhook_worker
from services.test_runs.orchestrator import (
    recover_interrupted_test_runs,
    test_run_orchestrator,
)
from fastapi import FastAPI, Request
from fastapi.exception_handlers import (
    http_exception_handler,
    request_validation_exception_handler,
)
from fastapi.exceptions import RequestValidationError
from fastapi.middleware.cors import CORSMiddleware
from starlette.exceptions import HTTPException as StarletteHTTPException

from routes import (
    assistants,
    auth,
    conversations,
    health,
    input_assets,
    knowledge_bases,
    mcp_servers,
    model_registry,
    node_types,
    openai_models,
    openai_realtime,
    openai_responses,
    realtime_api_keys,
    site_settings,
    test_cases,
    test_assets,
    test_runs,
    tools,
    voice_webrtc,
    voice_ws,
)


@asynccontextmanager
async def lifespan(_app: FastAPI):
    await sync_interface_definitions()
    await sync_default_tools()
    await recover_interrupted_documents()
    await recover_interrupted_analyses()
    await recover_interrupted_webhooks()
    await recover_interrupted_test_runs()
    await recover_interrupted_responses()
    analysis_worker = asyncio.create_task(
        run_analysis_worker(), name="post-call-analysis-worker"
    )
    webhook_worker = asyncio.create_task(
        run_webhook_worker(), name="analysis-webhook-worker"
    )
    try:
        yield
    finally:
        analysis_worker.cancel()
        webhook_worker.cancel()
        await asyncio.gather(
            analysis_worker, webhook_worker, return_exceptions=True
        )
        await test_run_orchestrator.shutdown()
        await voice_webrtc.shutdown_active_sessions()


app = FastAPI(
    title="AI Video Assistant 平台 - 后端",
    description=f"Public protocol: {PUBLIC_API_NAME}.",
    version="1.0.0",
    lifespan=lifespan,
)

app.add_middleware(
    CORSMiddleware,
    allow_origins=settings.CORS_ORIGINS,
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
    expose_headers=["X-Request-ID", "X-Idempotent-Replayed", "Location"],
)
app.add_middleware(RequestIDMiddleware)


def _validation_param(error: dict) -> str | None:
    location = list(error.get("loc") or [])
    if location and location[0] in {"body", "query", "path", "header"}:
        location.pop(0)
    if not location or location == ["json"]:
        return None
    value = ""
    for part in location:
        if isinstance(part, int):
            value += f"[{part}]"
        else:
            value += ("." if value else "") + str(part)
    return value or None


@app.exception_handler(RequestValidationError)
async def validation_exception_handler(
    request: Request,
    exc: RequestValidationError,
):
    if not request.url.path.startswith("/v1/"):
        return await request_validation_exception_handler(request, exc)
    first = (exc.errors() or [{}])[0]
    return openai_error_response(
        str(first.get("msg") or "Request does not match the API schema"),
        code="invalid_request_error",
        param=_validation_param(first),
        status_code=422,
    )


@app.exception_handler(StarletteHTTPException)
async def public_http_exception_handler(
    request: Request,
    exc: StarletteHTTPException,
):
    if not request.url.path.startswith("/v1/"):
        return await http_exception_handler(request, exc)
    code = "not_found" if exc.status_code == 404 else "http_error"
    return openai_error_response(
        str(exc.detail),
        code=code,
        status_code=exc.status_code,
    )


@app.exception_handler(Exception)
async def public_unhandled_exception_handler(request: Request, exc: Exception):
    if not request.url.path.startswith("/v1/"):
        raise exc
    logger.exception(
        f"Unhandled public API error: {type(exc).__name__}"
    )
    return openai_error_response(
        "The server encountered an internal error",
        code="internal_error",
        status_code=500,
    )

app.include_router(health.router)
app.include_router(auth.router)
app.include_router(conversations.router)
app.include_router(input_assets.router)
app.include_router(assistants.router)
app.include_router(knowledge_bases.router)
app.include_router(mcp_servers.router)
app.include_router(model_registry.router)
app.include_router(node_types.router)
app.include_router(openai_models.router)
app.include_router(openai_realtime.router)
app.include_router(openai_responses.router)
app.include_router(realtime_api_keys.router)
app.include_router(site_settings.router)
app.include_router(test_cases.router)
app.include_router(test_assets.router)
app.include_router(test_runs.router)
app.include_router(tools.router)
app.include_router(voice_webrtc.router)
app.include_router(voice_ws.router)


if __name__ == "__main__":
    uvicorn.run("app:app", host=settings.HOST, port=settings.PORT, reload=True)