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)

fam-core/src/fam_core/dispatcher/dispatcher.py

@@ -9,8 +9,9 @@ Dispatcher - 30s 轮询 PENDING 任务，上传视频至 Edge 异步队列
 4. Dispatcher 标记任务为 PROCESSING（已派发，等待 Poller 拉取结果）
 5. Poller 线程定期从 Edge /api/edge/results 拉取结果，写库后标记 SUCCESS
 
-退避重试: min(60 * (retry_count + 1) * 2, 600) 秒
+退避重试: min(30 * (retry_count + 1), 300) 秒
 分块级重试: 每块最多重试 3 次
+看门狗: 线程崩溃后自动重启
 """
 import os
 import io
@@ -51,8 +52,8 @@ class Dispatcher:
         self._thread = None
 
     def _calculate_backoff(self, retry_count):
-        """退避策略: min(60 * (retry_count + 1) * 2, 600)"""
-        return min(60 * (retry_count + 1) * 2, 600)
+        """退避策略: min(30 * (retry_count + 1), 300)"""
+        return min(30 * (retry_count + 1), 300)
 
     def _should_retry(self, task):
         """检查任务是否可以重试"""
@@ -275,7 +276,7 @@ class Dispatcher:
         except Exception as e:
             logger.error(f"僵尸任务回收失败: {e}", exc_info=True)
 
-        tasks = db_layer.get_pending_tasks(limit=10)
+        tasks = db_layer.get_pending_tasks(limit=1)
         for task in tasks:
             if self._should_retry(task):
                 try:
@@ -301,6 +302,17 @@ class Dispatcher:
         self._thread = threading.Thread(target=self._run, daemon=True, name='dispatcher')
         self._thread.start()
 
+    def is_alive(self):
+        """线程是否存活"""
+        return self._thread is not None and self._thread.is_alive()
+
+    def check_and_restart(self):
+        """看门狗：线程崩溃后自动重启"""
+        if self._running and not self.is_alive():
+            logger.warning("Dispatcher 线程已死亡，正在重启...")
+            self._thread = threading.Thread(target=self._run, daemon=True, name='dispatcher')
+            self._thread.start()
+
     def stop(self):
         """停止下发线程"""
         self._running = False

fam-core/src/fam_core/poller/poller.py

@@ -121,6 +121,17 @@ class Poller:
         self._thread = threading.Thread(target=self._run, daemon=True, name='poller')
         self._thread.start()
 
+    def is_alive(self):
+        """线程是否存活"""
+        return self._thread is not None and self._thread.is_alive()
+
+    def check_and_restart(self):
+        """看门狗：线程崩溃后自动重启"""
+        if self._running and not self.is_alive():
+            logger.warning("Poller 线程已死亡，正在重启...")
+            self._thread = threading.Thread(target=self._run, daemon=True, name='poller')
+            self._thread.start()
+
     def stop(self):
         """停止拉取线程"""
         self._running = False

fam-core/src/fam_core/scheduler/scheduler.py

@@ -104,6 +104,17 @@ class TaskScheduler:
         self._thread = threading.Thread(target=self._run, daemon=True, name='task-scheduler')
         self._thread.start()
 
+    def is_alive(self):
+        """线程是否存活"""
+        return self._thread is not None and self._thread.is_alive()
+
+    def check_and_restart(self):
+        """看门狗：线程崩溃后自动重启"""
+        if self._running and not self.is_alive():
+            logger.warning("Scheduler 线程已死亡，正在重启...")
+            self._thread = threading.Thread(target=self._run, daemon=True, name='task-scheduler')
+            self._thread.start()
+
     def stop(self):
         """停止调度线程"""
         self._running = False