chore: baseline — ORM migration + systemd deploy + MCP server + daily check

- ORM migration: models/ops 重构
- deploy: 标准化 systemd timer/service 部署体系
- MCP server: 5 个只读工具(任务/状态/数据集)
- daily check: 数据一致性巡检
- watch: task_watch 后台监控
- kline_daily: 麦蕊优先,时间门禁15:00
- 删除: task_industry_sector, task_sector_features

app/tasks/task_tick_trade.py

@@ -12,12 +12,15 @@
      trade_date 可能比 wall-clock 早一天；重跑靠 PK + ON CONFLICT 幂等
   4) 单只股票日均 5w-10w tick，CHUNK=2000 upsert 防 driver 撑爆
   5) 数据是"当天 only"，无 start/end 窗口；不存增量概念
+  6) 2026-07-13 加固: 加上外层 FETCH_HARD_TIMEOUT,避免 mairui 挂起时
+     as_completed 无 timeout 导致整个 task 永久卡住(systemd 2h 超时杀)。
+     改用手动 pool 管理 + shutdown(wait=False),与 kline_daily 对齐。
 """
 from __future__ import annotations
 
 import os
 import time
-from concurrent.futures import ThreadPoolExecutor, as_completed
+from concurrent.futures import ThreadPoolExecutor, as_completed, TimeoutError as FuturesTimeoutError
 from datetime import datetime
 from typing import Any
 
@@ -36,6 +39,10 @@ MAIRUI_TICK_TRADE_PUBLISH_HOUR = 21
 MAIRUI_TICK_TRADE_PUBLISH_MIN = 0
 # 21:00 之后再跑（留 5 分钟缓冲，等 mairui 完整入库）
 TICK_TRADE_RUN_GATE = (MAIRUI_TICK_TRADE_PUBLISH_HOUR, MAIRUI_TICK_TRADE_PUBLISH_MIN + 5)
+# 外层超时: mairui _fetch 有 20s timeout,但 as_completed 无 timeout 的话
+# 若所有 worker 同时被 mairui 挂起(罕见),task 会永久卡住等 systemd 2h 杀。
+# 120s 内无任何 future 完成 → 判全部失败退出。
+FETCH_HARD_TIMEOUT = 120.0
 
 
 def _passes_publish_gate(now: Optional[datetime] = None, *, force: bool = False) -> tuple[bool, str]:
@@ -108,15 +115,18 @@ class SyncTickTrade(SyncTask):
         )
 
         # ── 执行 ──
+        # 不用 `with ThreadPoolExecutor` — 与外层 as_completed timeout 配合,
+        # 超时后 `with` 的 shutdown(wait=True) 会阻塞等卡死线程 → 进程挂死(同 kline_daily 教训)。
         t0 = time.time()
         ok_cnt = fail_cnt = 0
         rows_total = 0
-        with ThreadPoolExecutor(max_workers=max_workers) as pool:
-            futures = {pool.submit(self._sync_one, mr, c6): c6 for c6 in stock_codes}
-            for i, future in enumerate(as_completed(futures), 1):
+        pool = ThreadPoolExecutor(max_workers=max_workers)
+        futures = {pool.submit(self._sync_one, mr, c6): c6 for c6 in stock_codes}
+        try:
+            for i, future in enumerate(as_completed(futures, timeout=FETCH_HARD_TIMEOUT), 1):
                 c6 = futures[future]
                 try:
-                    res = future.result()
+                    res = future.result(timeout=0.1)
                     if res["status"] == "ok":
                         ok_cnt += 1
                         rows_total += res["rows"]
@@ -124,6 +134,9 @@ class SyncTickTrade(SyncTask):
                         fail_cnt += 1
                         if res.get("error"):
                             logger.warning(f"[tick_trade {c6}] {res['error']}")
+                except FuturesTimeoutError:
+                    fail_cnt += 1
+                    logger.warning(f"[tick_trade {c6}] 内部 race timeout, 记 fail")
                 except Exception as e:
                     fail_cnt += 1
                     logger.warning(f"[tick_trade {c6}] {e}")
@@ -132,6 +145,25 @@ class SyncTickTrade(SyncTask):
                         message=f"tick_trade 进度 {i}/{total} OK:{ok_cnt} FAIL:{fail_cnt} 行:{rows_total}",
                         current=i, total=total, current_step=c6,
                     )
+        except FuturesTimeoutError:
+            stuck = [(f, c6) for f, c6 in futures.items() if not f.done()]
+            logger.error(
+                "[tick_trade] 所有 fetcher 卡死 (>%ss), %d 只股票未完成, 标 fail 后退出",
+                FETCH_HARD_TIMEOUT, len(stuck),
+            )
+            fail_cnt += len(stuck)
+            for f, c6 in stuck:
+                try:
+                    if hasattr(f, "cancel"):
+                        f.cancel()
+                except Exception as e:
+                    logger.warning(f"[tick_trade] cancel future for {c6} 失败: {e}")
+            try:
+                pool.shutdown(wait=False)
+            except Exception as e:
+                logger.warning(f"[tick_trade] pool.shutdown(wait=False) 失败: {e}")
+        else:
+            pool.shutdown(wait=True)
         elapsed = round(time.time() - t0, 1)
         msg = f"逐笔 {ok_cnt}成 {fail_cnt}败 共{rows_total}行, {elapsed}s"
         return {