修复任务卡死与安能启动失败

- runtime.py: launch_anneng 拉起前清除 NODE_OPTIONS，避免 Electron 因 --use-system-ca 启动即退出(rc=9)
- server.py: POST /tasks 在 worker 未就绪时返回 409 拦截误操作；worker 就绪后调用 fail_stale_tasks 实现重启自愈
- state_store.py: 新增 fail_stale_tasks()，将遗留 pending/running 任务标记为 failed

runtime.py

@@ -107,9 +107,14 @@ def _wait_cdp_up(port, timeout=60.0):
 
 def launch_anneng(app_path):
     """以调试模式启动安能 Electron 应用（自动选取空闲端口），返回子进程对象。"""
+    # 【环境兼容】WorkBuddy 等 shell 会注入 NODE_OPTIONS（含 --use-system-ca），
+    # Electron 内置 Node 拒绝该 flag 导致安能启动即退出（rc=9）。
+    # 拉起前从子进程环境里摘掉 NODE_OPTIONS。
+    anneng_env = os.environ.copy()
+    anneng_env.pop("NODE_OPTIONS", None)
     port = _find_free_port()
     print(f">> 以调试模式启动【安能】应用（端口 {port}）：{app_path}")
-    proc = subprocess.Popen([app_path, f"--remote-debugging-port={port}"])
+    proc = subprocess.Popen([app_path, f"--remote-debugging-port={port}"], env=anneng_env)
     site_anneng.set_cdp_port(port)
     if not _wait_cdp_up(port):
         raise RuntimeError(

server.py

@@ -61,6 +61,10 @@ def _worker_loop():
         ctx = launch_and_prepare()
         worker_state["ctx"] = ctx
         worker_state["ready"] = True
+        # 【P1-2 重启自愈】worker 就绪后清理上轮遗留的 pending/running 僵尸任务
+        cleaned = state_store.fail_stale_tasks()
+        if cleaned:
+            print(f">> [worker] 自愈：清理 {cleaned} 条遗留任务（pending/running → failed）")
         print(">> [worker] 各站就绪，开始接收任务 ...")
     except Exception as e:
         worker_state["error"] = str(e)
@@ -155,6 +159,9 @@ class TaskRequest(BaseModel):
 @app.post("/tasks")
 def create_task(req: TaskRequest):
     """提交任务 {site, kind} → 入队，返回 task_id。"""
+    # 【P0】后端未就绪时直接拒绝，避免任务在 worker 启动前入队卡死
+    if not worker_state["ready"]:
+        raise HTTPException(status_code=409, detail="后端尚未就绪，请等待各站点登录完成后再操作")
     if (req.site, req.kind) not in TASK_HANDLERS:
         raise HTTPException(status_code=400, detail=f"无效任务: {req.site}/{req.kind}")
     task_id = state_store.create_task(req.site, req.kind)

state_store.py

@@ -426,3 +426,16 @@ def list_tasks(limit=20):
         }
         for r in rows
     ]
+
+
+def fail_stale_tasks(reason: str = "服务重启，上轮未完成任务，请手动重跑") -> int:
+    """worker 启动时调用：把遗留的 pending/running 任务标记为 failed，实现重启自愈。
+    返回被清理的任务数量。"""
+    with sqlite3.connect(STATE_DB_PATH) as conn:
+        cur = conn.execute(
+            "UPDATE task_history SET status=?, finished_at=?, error=? "
+            "WHERE status IN (?, ?)",
+            (TASK_FAILED, _now(), reason, TASK_PENDING, TASK_RUNNING),
+        )
+        conn.commit()
+        return cur.rowcount