rakuten-api/app/gateway/main.py

"""下单任务网关入口：FastAPI 应用创建与生命周期管理

部署在服务器侧，与抓取服务（:31107）、交易服务（:31108）并列。本地 worker 通过
出站长轮询从这里领任务；上游业务系统通过 POST /api/orders 提交下单意图。

为什么必须独立部署单元（不能塞进抓取服务）：抓取无状态可多开，任务队列有状态，
多实例会抢同一批任务，同一账号的写操作必须串行（详见 docs/order-gateway.md §2）。
"""
from __future__ import annotations

import asyncio
import logging
from contextlib import asynccontextmanager

from fastapi import FastAPI

from app.gateway.api.routes.health import router as health_router
from app.gateway.api.routes.orders import router as orders_router
from app.gateway.container import GatewayContainer
from app.gateway.db import GatewayDB
from app.gateway.task_queue import TaskQueue
from app.shared.api import register_exception_handlers
from app.shared.config import get_settings
from app.shared.logging_setup import configure_logging

logger = logging.getLogger(__name__)

SWEEP_INTERVAL_SECONDS = 60


def build_container() -> GatewayContainer:
    """构建网关容器：DB + 任务队列"""
    settings = get_settings()
    db = GatewayDB(settings.gateway_db_path_resolved)
    task_queue = TaskQueue(
        db,
        lease_ttl_seconds=settings.lease_ttl_seconds,
        worker_offline_alert_seconds=settings.worker_offline_alert_seconds,
    )
    return GatewayContainer(settings=settings, db=db, task_queue=task_queue)


async def _sweep_loop(container: GatewayContainer) -> None:
    """常驻后台任务：每 60 秒扫一次过期租约，把 leased/running 推到 stale

    lease 请求本身也会顺带扫一次，但 worker 退场后没人来 lease，必须靠这个
    兜底——否则过期的任务永远停在 active 状态，健康检查看不到，stale 任务也
    取不出来 reclaim。
    """
    while True:
        try:
            await asyncio.sleep(SWEEP_INTERVAL_SECONDS)
            swept = await container.task_queue.sweep()
            if swept:
                logger.info("sweep 把 %s 个过期任务置为 stale", swept)
        except asyncio.CancelledError:
            raise
        except Exception:  # noqa: BLE001
            # 后台任务不能因为偶发错误退出，否则过期任务再也无人清理
            logger.exception("sweep 后台任务出错，将继续重试")


@asynccontextmanager
async def lifespan(app: FastAPI):
    """应用生命周期：启动 DB、起 sweep 后台任务、关闭时反序释放"""
    container = build_container()
    app.state.container = container

    configure_logging(container.settings)
    logger.info(
        "网关启动：%s:%s", container.settings.gateway_host, container.settings.gateway_port
    )
    logger.info("当前环境：%s", container.settings.app_env)
    logger.info("DB 路径：%s", container.settings.gateway_db_path_resolved)

    await container.db.start()
    # 启动时先扫一次：上次进程退出时可能留有 leased/running 的过期任务
    startup_swept = await container.task_queue.sweep()
    if startup_swept:
        logger.warning("启动时把 %s 个遗留过期任务置为 stale", startup_swept)

    container.sweep_task = asyncio.create_task(
        _sweep_loop(container), name="gateway-sweep"
    )

    try:
        yield
    finally:
        if container.sweep_task is not None:
            container.sweep_task.cancel()
            try:
                await container.sweep_task
            except asyncio.CancelledError:
                pass
            container.sweep_task = None
        await container.db.close()


def create_app() -> FastAPI:
    """创建 FastAPI 应用实例，注册路由和异常处理器"""
    app = FastAPI(title="Rakuten Order Gateway", lifespan=lifespan)
    app.include_router(health_router)
    app.include_router(orders_router)
    register_exception_handlers(app)
    return app


app = create_app()


if __name__ == "__main__":
    import uvicorn

    settings = get_settings()
    configure_logging(settings)
    uvicorn.run(
        "app.gateway.main:app",
        host=settings.gateway_host,
        port=settings.gateway_port,
        log_config=None,
        timeout_keep_alive=120,
        # 单进程：SQLite 单连接 + 全局并发度 1，多进程会抢同一个 DB
        workers=1,
    )