fix: dispatcher 串行上传 + 看门狗自动重启 + 线程状态真实检测

- Dispatcher limit=10→1: 一次只传一个视频，传完再传下一个
- 退避缩短: min(30*(n+1),300)s → 失败后更快重试（原 min(60*(n+1)*2,600)s）
- /api/status: 用 thread.is_alive() 替代 _running 布尔标志
- 三组件(scheduler/dispatcher/poller)添加 is_alive()+check_and_restart()
- app.py 新增 watchdog 线程: 每 60s 检测线程死亡并自动重启

fam-core/src/fam_core/app.py

@@ -5,6 +5,8 @@ FAM-Core 主应用 - Flask 单进程
 """
 import os
 import sys
+import time
+import threading
 from flask import Flask, jsonify
 
 # 确保包路径
@@ -64,14 +66,31 @@ except Exception as e:
 
 @app.route('/api/status', methods=['GET'])
 def status():
-    """系统状态"""
+    """系统状态（检查线程实际存活）"""
     return jsonify({
-        "scheduler_running": _scheduler._running if _scheduler else False,
-        "dispatcher_running": _dispatcher._running if _dispatcher else False,
-        "poller_running": _poller._running if _poller else False,
+        "scheduler_running": _scheduler.is_alive() if _scheduler else False,
+        "dispatcher_running": _dispatcher.is_alive() if _dispatcher else False,
+        "poller_running": _poller.is_alive() if _poller else False,
     }), 200
 
 
+def _watchdog_run():
+    """看门狗：每 60s 检查线程存活，崩溃自动重启"""
+    logger.info("Watchdog 线程启动，检查间隔 60s")
+    while True:
+        time.sleep(60)
+        for comp, name in [(_scheduler, 'Scheduler'), (_dispatcher, 'Dispatcher'), (_poller, 'Poller')]:
+            if comp and hasattr(comp, 'check_and_restart'):
+                try:
+                    comp.check_and_restart()
+                except Exception as e:
+                    logger.error(f"Watchdog 重启 {name} 失败: {e}", exc_info=True)
+
+
+_watchdog_thread = threading.Thread(target=_watchdog_run, daemon=True, name='watchdog')
+_watchdog_thread.start()
+
+
 if __name__ == '__main__':
     cfg = load_config()
     port = cfg.get('server', {}).get('port', 8000)