feat(agent-office): 노드 헬스 1분 cron + 텔레그램 경보(다운/복구/dead-letter)

agent-office/app/scheduler.py

@@ -4,6 +4,7 @@ from apscheduler.schedulers.asyncio import AsyncIOScheduler
 
 from .agents import AGENT_REGISTRY
 from .db import delete_old_logs
+from . import node_monitor
 
 scheduler = AsyncIOScheduler(timezone="Asia/Seoul")
 
@@ -98,6 +99,9 @@ async def _poll_pipelines():
     if agent:
         await agent.poll_state_changes()
 
+async def _run_node_health_check():
+    await node_monitor.check_and_alert()
+
 def _cleanup_old_logs():
     n = delete_old_logs(days=90)
     if n:
@@ -142,5 +146,6 @@ def init_scheduler():
     scheduler.add_job(_run_youtube_research,     "cron", hour=9, minute=10, id="youtube_research")
     scheduler.add_job(_send_youtube_weekly_report, "cron", day_of_week="mon", hour=8, minute=0, id="youtube_weekly_report")
     scheduler.add_job(_poll_pipelines, "interval", seconds=30, id="pipeline_poll")
+    scheduler.add_job(_run_node_health_check, "interval", seconds=60, id="node_health_check", replace_existing=True)
     scheduler.add_job(_cleanup_old_logs, "cron", hour=3, minute=0, id="cleanup_old_logs", replace_existing=True)
     scheduler.start()