227 lines
8.6 KiB
Python
227 lines
8.6 KiB
Python
#!/usr/bin/env python3
|
||
"""
|
||
run_scheduler.py — momo-scheduler 容器入口點
|
||
|
||
排程任務清單（對齊 app.py init_scheduler + scheduler.py 全任務）：
|
||
每 30 分鐘：auto_import、whitepage_check
|
||
每 1 小時：momo、edm、festival
|
||
每 4 小時：competitor_price_feeder、icaim_analysis
|
||
每 6 小時：openclaw_meta_analysis、quality_rescore
|
||
每 12 小時：dedup_batch
|
||
每 1 天 ：db_backup（03:00）、cleanup_agent_context（03:30）、backup_monitor（04:00）、daily_report（09:00）
|
||
每 1 週 ：weekly_strategy（週一 06:00）
|
||
每 1 月 ：monthly_report（每月1日 07:00）
|
||
"""
|
||
import asyncio
|
||
import logging
|
||
import threading
|
||
import time
|
||
|
||
import schedule
|
||
|
||
# 匯入全部排程任務函式
|
||
from scheduler import (
|
||
run_momo_task,
|
||
run_edm_task,
|
||
run_festival_task,
|
||
run_promo_event_task,
|
||
run_auto_import_task,
|
||
run_whitepage_check,
|
||
run_competitor_price_feeder_task,
|
||
run_icaim_analysis_task,
|
||
run_weekly_strategy_task,
|
||
run_db_backup_task,
|
||
run_backup_monitor_task,
|
||
run_openclaw_meta_analysis_task,
|
||
run_dedup_batch_task,
|
||
run_quality_rescore_task,
|
||
run_daily_report_task,
|
||
run_monthly_report_task,
|
||
)
|
||
|
||
logging.basicConfig(
|
||
level=logging.INFO,
|
||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
||
)
|
||
logger = logging.getLogger(__name__)
|
||
|
||
|
||
def _register_schedules():
|
||
schedule.every(30).minutes.do(run_auto_import_task)
|
||
logger.info("📅 每 30 分鐘：auto_import")
|
||
|
||
schedule.every(30).minutes.do(run_whitepage_check)
|
||
logger.info("📅 每 30 分鐘：whitepage_check")
|
||
|
||
schedule.every(1).hours.do(run_momo_task)
|
||
logger.info("📅 每 1 小時：momo_task")
|
||
|
||
schedule.every(1).hours.do(run_edm_task)
|
||
logger.info("📅 每 1 小時：edm_task")
|
||
|
||
schedule.every(1).hours.do(run_festival_task)
|
||
logger.info("📅 每 1 小時：festival_task")
|
||
|
||
# 動態註冊促銷活動爬蟲（根據配置）
|
||
from services.crawler_config_loader import get_enabled_crawlers
|
||
enabled_crawlers = get_enabled_crawlers()
|
||
|
||
promo_event_configs = {
|
||
'mothers_day_2026': {'lpn': '', 'page_type': 'mothers_day', 'name': '母親節超值限時購'},
|
||
'valentine_520_2026': {'lpn': '', 'page_type': 'valentine_520', 'name': '520情人節限定購物'},
|
||
'labor_day_2026': {'lpn': '', 'page_type': 'labor_day', 'name': '勞動節購物優惠'}
|
||
}
|
||
|
||
for crawler_key, config in enabled_crawlers.items():
|
||
if crawler_key in promo_event_configs:
|
||
event_config = promo_event_configs[crawler_key]
|
||
lpn_code = config.get('lpn_code', '')
|
||
if lpn_code:
|
||
schedule_hours = config.get('schedule_hours', 4)
|
||
schedule.every(schedule_hours).hours.do(
|
||
lambda lpn=lpn_code, pt=event_config['page_type'], an=event_config['name']:
|
||
run_promo_event_task(lpn, pt, an)
|
||
)
|
||
logger.info(f"📅 每 {schedule_hours} 小時：{event_config['name']} ({event_config['page_type']})")
|
||
else:
|
||
logger.warning(f"⚠️ {event_config['name']} 未配置 LPN 代碼，跳過排程")
|
||
|
||
schedule.every(4).hours.do(run_competitor_price_feeder_task)
|
||
logger.info("📅 每 4 小時：competitor_price_feeder")
|
||
|
||
schedule.every(4).hours.do(run_icaim_analysis_task)
|
||
logger.info("📅 每 4 小時：icaim_analysis")
|
||
|
||
schedule.every(6).hours.do(run_openclaw_meta_analysis_task)
|
||
logger.info("📅 每 6 小時：openclaw_meta_analysis")
|
||
|
||
schedule.every(6).hours.do(run_quality_rescore_task)
|
||
logger.info("📅 每 6 小時：quality_rescore")
|
||
|
||
schedule.every(12).hours.do(run_dedup_batch_task)
|
||
logger.info("📅 每 12 小時：dedup_batch")
|
||
|
||
schedule.every().day.at("03:00").do(run_db_backup_task)
|
||
logger.info("📅 每日 03:00：db_backup")
|
||
|
||
schedule.every().day.at("03:30").do(run_cleanup_agent_context)
|
||
logger.info("📅 每日 03:30：cleanup_agent_context")
|
||
|
||
schedule.every().day.at("04:00").do(run_backup_monitor_task)
|
||
logger.info("📅 每日 04:00：backup_monitor")
|
||
|
||
schedule.every().monday.at("06:00").do(run_weekly_strategy_task)
|
||
logger.info("📅 每週一 06:00：weekly_strategy")
|
||
|
||
schedule.every().day.at("09:00").do(run_daily_report_task)
|
||
logger.info("📅 每日 09:00：daily_report")
|
||
|
||
# 每月1日 07:00 月報（schedule 不支援 every().month，用每日 07:00 + 日期判斷）
|
||
def _monthly_report_gate():
|
||
from datetime import datetime as _dt
|
||
if _dt.now().day == 1:
|
||
run_monthly_report_task()
|
||
|
||
schedule.every().day.at("07:00").do(_monthly_report_gate)
|
||
logger.info("📅 每月1日 07:00：monthly_report")
|
||
|
||
|
||
def run_cleanup_agent_context():
|
||
"""每日 03:30 — 清理 agent_context 表中已過期的 TTL 記錄（migration 018 定義）"""
|
||
from database.manager import get_session
|
||
from sqlalchemy import text
|
||
session = get_session()
|
||
try:
|
||
session.execute(text("SELECT cleanup_expired_agent_context()"))
|
||
session.commit()
|
||
logger.info("[Cleanup] agent_context TTL 清理完成")
|
||
except Exception as e:
|
||
logger.error(f"[Cleanup] agent_context 清理失敗: {e}")
|
||
try:
|
||
from services.event_router import notify_failure
|
||
notify_failure(
|
||
task_name="run_cleanup_agent_context",
|
||
error=e,
|
||
source="Scheduler.Cleanup",
|
||
event_type="agent_context_cleanup_failure",
|
||
priority="P2",
|
||
title="agent_context TTL 清理失敗",
|
||
dedup_ttl_sec=3600,
|
||
)
|
||
except Exception as _router_e:
|
||
logger.error(f"[Cleanup] event_router 失敗: {_router_e}")
|
||
finally:
|
||
session.close()
|
||
|
||
|
||
def _run_elephant_alpha_engine():
|
||
"""Daemon thread: ElephantAlpha 自主監控引擎（獨立 asyncio loop）"""
|
||
loop = None
|
||
try:
|
||
from services.elephant_alpha_autonomous_engine import autonomous_engine
|
||
loop = asyncio.new_event_loop()
|
||
asyncio.set_event_loop(loop)
|
||
logger.info("🐘 [ElephantAlpha] Autonomous engine thread started")
|
||
loop.run_until_complete(autonomous_engine.start_autonomous_monitoring())
|
||
except Exception as e:
|
||
logger.error(f"🐘 [ElephantAlpha] Engine crashed: {e}")
|
||
finally:
|
||
if loop is not None:
|
||
loop.close()
|
||
|
||
|
||
if __name__ == "__main__":
|
||
logger.info("🚀 momo-scheduler 啟動中...")
|
||
|
||
_register_schedules()
|
||
logger.info("✅ 全部排程任務已註冊")
|
||
|
||
_ea_thread = threading.Thread(
|
||
target=_run_elephant_alpha_engine,
|
||
daemon=True,
|
||
name="elephant-alpha-engine",
|
||
)
|
||
_ea_thread.start()
|
||
logger.info("🐘 [ElephantAlpha] Autonomous engine thread launched")
|
||
|
||
logger.info("⏰ 排程主迴圈啟動，等待任務觸發...")
|
||
_ea_watchdog_counter = 0 # 每 60 秒（60 次 sleep(1)）做一次存活檢查
|
||
while True:
|
||
try:
|
||
schedule.run_pending()
|
||
time.sleep(1)
|
||
|
||
# 每 60 秒檢查 ElephantAlpha 執行緒是否還活著
|
||
_ea_watchdog_counter += 1
|
||
if _ea_watchdog_counter >= 60:
|
||
_ea_watchdog_counter = 0
|
||
if not _ea_thread.is_alive():
|
||
logger.error("[ElephantAlpha] 監控執行緒已死亡，嘗試重啟")
|
||
try:
|
||
from services.event_router import dispatch_sync as _dispatch_sync
|
||
_dispatch_sync({
|
||
"source": "Scheduler.ElephantAlpha",
|
||
"event_type": "thread_crashed",
|
||
"severity": "alert",
|
||
"title": "ElephantAlpha 執行緒死亡",
|
||
"status": "自動重啟中",
|
||
"impact": "P2 - 自主監控引擎暫停",
|
||
"summary": "ElephantAlphaEngine daemon thread 意外終止，排程主迴圈已偵測並觸發重啟",
|
||
})
|
||
except Exception as _alert_err:
|
||
logger.error(f"[ElephantAlpha] 無法發送告警: {_alert_err}")
|
||
_ea_thread = threading.Thread(
|
||
target=_run_elephant_alpha_engine,
|
||
daemon=True,
|
||
name="ElephantAlphaEngine",
|
||
)
|
||
_ea_thread.start()
|
||
logger.info("[ElephantAlpha] 執行緒已重啟")
|
||
|
||
except KeyboardInterrupt:
|
||
logger.info("⛔ Scheduler stopped.")
|
||
break
|
||
except Exception as e:
|
||
logger.error(f"Scheduler error: {e}")
|
||
time.sleep(5)
|