diff --git a/deploy/profile-scripts/meta_watchdog.py b/deploy/profile-scripts/meta_watchdog.py index 2e0c24de..9aee6ae9 100644 --- a/deploy/profile-scripts/meta_watchdog.py +++ b/deploy/profile-scripts/meta_watchdog.py @@ -1,14 +1,15 @@ #!/usr/bin/env python3 """meta_watchdog.py — L4 自检系统的自检(看门狗的看门狗) -检查 L0-L3 各自检组件本身是否在正常运转: -- L0 agents_health_check: last_health_check.json 是否 <10min +检查 L1-L3 各自检组件本身是否在正常运转: - L1 functional_health_check: functional_health.json 是否 <20min(交易时段) - L2 system_hygiene_audit: hygiene_report.json 是否 <26h(每日) - L3 self_repair: repair_state.json 存在性 + cron 是否注册 - mofin_health 采集: mofin_health.json 是否 <20min(交易时段) - XMPP 桥: :5805 是否可发(self_repair 的报备通道) +(2026-08-13 删除 L0 agents_health_check 检查项:MoFin 无该组件,且 L1 functional_health_check 已覆盖健康检查功能,检查项是死代码) + 任何一层死了 → 推 XMPP 点名(这是最后的兜底,必须直达用户)。 频率:每小时(cron)。输出 gateway/logs/meta_watchdog.json。 """ @@ -18,9 +19,6 @@ from datetime import datetime OUT = '/home/hmo/MoFin/gateway/logs/meta_watchdog.json' LAYERS = [ - {"layer": "L0 agents_health_check", "file": "/home/hmo/MoFin/gateway/temp/last_health_check.json", - "max_age_min": 10, "when": "always", - "repair": "crontab */5 agents_health_check.py 停摆,检查系统 crontab"}, {"layer": "L1 functional_health", "file": "/home/hmo/MoFin/gateway/logs/functional_health.json", "max_age_min": 25, "when": "trading", "repair": "L1 cron 停摆,检查 hermes cron 引擎"},