feat(gateway): 全局串行化(并发=1) + 记录入参/出参/耗时日志

并发模型从「每worker并发1 + 多worker并行」改为全局串行：同一时间
只处理1个请求，其余排队；多 worker 仅作热备（主 worker 坏了才用备机）。
接口4(face/features) 走豆包、不占 GPU，不纳入串行。

- pool: asyncio.Semaphore(max_global_concurrency=1) + acquire/release_global_slot
  （依赖单进程 uvicorn 部署，已在注释中标注）
- forward: proxy_request 最外层 acquire 全局槽、try/finally 全路径释放；
  入参 multipart 解析挂 request.state；原重试/故障转移逻辑抽到 _dispatch_with_retries
- reqlog(新): 标量入参保留；图片(file/base64)存盘转URL，绝不内嵌base64；
  出参递归摘要截断(landmarks/长串/大数组)
- logging_middleware: RequestLogEntry 加 request_params/response_data，
  jsonl 全量记录；_load_from_logfile 同步映射防重启丢字段；get_stats recent 暴露
- /gateway-health 暴露 global_max/global_busy/global_waiting
- config: dispatch 新增 max_global_concurrency / max_queue_wait_seconds
- tests: test_reqlog + test_gateway_serialization（9 用例）

顺带提交此前未提交的网关统计(daily stats 接口)与耗时看板(api_timing_dashboard.html)。

Co-Authored-By: Claude <noreply@anthropic.com>

gateway/pool.py

@@ -50,6 +50,14 @@ _pool_condition: Optional[asyncio.Condition] = None
 _health_task: Optional[asyncio.Task] = None
 _shutdown_event: Optional[asyncio.Event] = None
 
+# 全局串行槽：同一时间最多 max_global_concurrency 个请求进入 worker 派发，其余排队。
+# ⚠️ 依赖单进程 uvicorn 部署（hair-gateway.service 无 --workers）。
+#    若改多 worker / gunicorn，进程内信号量会失效，需换成跨进程锁（文件锁/Redis）。
+_global_sem: Optional[asyncio.Semaphore] = None
+_global_max: int = 1
+_global_busy: int = 0
+_global_waiting: int = 0
+
 
 # ---------------------------------------------------------------------------
 # 健康检查后台任务
@@ -162,6 +170,9 @@ async def init_pool(cfg: dict) -> None:
     _pool_condition = asyncio.Condition()
     _shutdown_event = asyncio.Event()
 
+    # 全局串行槽（独立于 worker busy 标志）
+    init_global_slot(cfg)
+
     # 立即做一轮健康检查以快速上线
     hc_cfg = cfg["health_check"]
     token = cfg["shared_password"]
@@ -206,6 +217,56 @@ async def shutdown_pool() -> None:
     logger.info("Worker 池已关闭")
 
 
+# ---------------------------------------------------------------------------
+# 全局串行槽
+# ---------------------------------------------------------------------------
+
+def init_global_slot(cfg: dict) -> None:
+    """初始化全局串行信号量。
+
+    max_global_concurrency=1 → 同一时间只有一个请求进入 worker 派发，其余在信号量上排队。
+    依赖单进程 uvicorn 部署；多进程需换跨进程锁。
+    """
+    global _global_sem, _global_max, _global_busy, _global_waiting
+    n = int(cfg.get("dispatch", {}).get("max_global_concurrency", 1))
+    if n < 1:
+        n = 1
+    _global_sem = asyncio.Semaphore(n)
+    _global_max = n
+    _global_busy = 0
+    _global_waiting = 0
+    logger.info("全局并发槽初始化: max=%d（单进程生效）", n)
+
+
+async def acquire_global_slot(cfg: dict) -> bool:
+    """获取一个全局处理槽。True=获得；False=排队超时。
+
+    超时由 dispatch.max_queue_wait_seconds 控制（需 < nginx proxy_read_timeout 600s）。
+    """
+    global _global_busy, _global_waiting
+    if _global_sem is None:
+        return True  # 未初始化，不限流
+    timeout = float(cfg.get("dispatch", {}).get("max_queue_wait_seconds", 590))
+    _global_waiting += 1
+    try:
+        await asyncio.wait_for(_global_sem.acquire(), timeout=timeout)
+        _global_busy += 1
+        return True
+    except asyncio.TimeoutError:
+        logger.warning("全局排队超时（%.1fs），拒绝请求 | waiting=%d", timeout, _global_waiting)
+        return False
+    finally:
+        _global_waiting -= 1
+
+
+def release_global_slot() -> None:
+    """释放全局处理槽。"""
+    global _global_busy
+    if _global_sem is not None:
+        _global_busy -= 1
+        _global_sem.release()
+
+
 # ---------------------------------------------------------------------------
 # 派发
 # ---------------------------------------------------------------------------
@@ -270,9 +331,14 @@ async def release_worker(w: WorkerState) -> None:
 
 def get_pool_status() -> dict:
     """返回当前池状态（供 /gateway-health 使用）。"""
+    global_info = {
+        "global_max": _global_max,
+        "global_busy": _global_busy,
+        "global_waiting": _global_waiting,
+    }
     if not _workers:
-        return {"total": 0, "healthy": 0, "busy": 0}
+        return {"total": 0, "healthy": 0, "busy": 0, **global_info}
     total = len(_workers)
     healthy = sum(1 for w in _workers.values() if w.online)
     busy = sum(1 for w in _workers.values() if w.busy)
-    return {"total": total, "healthy": healthy, "busy": busy}
+    return {"total": total, "healthy": healthy, "busy": busy, **global_info}