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/forward.py

@@ -19,10 +19,13 @@ from fastapi.responses import JSONResponse
 
 from gateway.pool import (
     NoWorkerAvailable,
+    acquire_global_slot,
     acquire_worker,
     mark_worker_unhealthy,
+    release_global_slot,
     release_worker,
 )
+from gateway.reqlog import extract_form_params
 
 logger = logging.getLogger("gateway.forward")
 
@@ -143,17 +146,56 @@ async def proxy_request(request: Request, path: str) -> JSONResponse:
     """
     from gateway.config import get_config
     cfg = get_config()
+
+    # --- 1. 读取客户端请求体（原始字节，不做解析） ---
+    body = await request.body()
+
+    # --- 入参日志解析（非致命，绝不影响转发） ---
+    try:
+        request.state.log_request_params = extract_form_params(
+            request.headers.get("content-type", ""),
+            body,
+            cfg["static_dir"],
+            cfg["public_base_url"],
+        )
+    except Exception as ex:  # noqa: BLE001
+        request.state.log_request_params = {"_parse_error": str(ex)}
+
+    # --- 全局串行槽（GPU 请求在此排队；超时拒绝） ---
+    if not await acquire_global_slot(cfg):
+        request.state.worker_url = ""
+        return JSONResponse(
+            status_code=503,
+            content={
+                "code": 1007,
+                "message": "排队超时，请稍后重试",
+                "request_id": f"gw-{uuid.uuid4().hex[:8]}",
+                "data": None,
+            },
+        )
+
+    try:
+        return await _dispatch_with_retries(request, path, cfg, body)
+    finally:
+        release_global_slot()
+
+
+async def _dispatch_with_retries(
+    request: Request, path: str, cfg: dict, body: bytes
+) -> JSONResponse:
+    """在已持有全局串行槽的前提下：选 worker → 转发 → 重试 → 改写 base64 → 返回。
+
+    故障转移：worker 失败 → mark_worker_unhealthy → release_worker → 循环再 acquire
+    （此时主 worker 已下线，自动选备机）。全程在同一个全局槽持有期内，故
+    「平时只打主 worker，坏了才用备机」。
+    """
     dispatch_cfg = cfg["dispatch"]
     token = cfg["shared_password"]
     request_timeout = dispatch_cfg["request_timeout_seconds"]
     max_retries = dispatch_cfg.get("max_retries", 1)
-    retry_on_failure = dispatch_cfg.get("retry_on_failure", True)
     public_base_url = cfg["public_base_url"]
     static_dir = cfg["static_dir"]
 
-    # --- 1. 读取客户端请求体（原始字节，不做解析） ---
-    body = await request.body()
-
     # --- 2. 获取 worker（最多重试 max_retries+1 次） ---
     attempts = max_retries + 1
     last_error_response = None