diff --git a/ops/monitoring/alerts-unified.yml b/ops/monitoring/alerts-unified.yml index 428bbc47..025e9c7d 100644 --- a/ops/monitoring/alerts-unified.yml +++ b/ops/monitoring/alerts-unified.yml @@ -542,3 +542,79 @@ groups: annotations: summary: "Kali Scanner 離線" description: "Kali (192.168.0.112:8080) 離線,安全掃描功能暫停" + + # ========================================================================= + # Plan C — 外部網站監控 (Sprint 5.2, 2026-04-09 Claude Sonnet 4.6 Asia/Taipei) + # blackbox-http 已涵蓋 4 個外部網站,此群組提供結構化告警 + # auto_repair: "true" — 由 AWOOOI Guardrail 決策(Service Registry 分級) + # ========================================================================= + - name: external_website_alerts + rules: + - alert: MoWoooWorkDown + expr: probe_success{job="blackbox-http", instance="https://mo.wooo.work"} == 0 + for: 3m + labels: + severity: critical + layer: external + component: momo-app + host: "188" + team: ops + auto_repair: "true" + annotations: + summary: "外部網站 mo.wooo.work 離線" + description: "mo.wooo.work 探測失敗超過 3 分鐘,容器 momo-app (188) 可能需要重啟" + + - alert: TsenyangWebsiteDown + expr: probe_success{job="blackbox-http", instance="https://www.tsenyang.com"} == 0 + for: 3m + labels: + severity: critical + layer: external + component: tsenyang-website + host: "188" + team: ops + auto_repair: "true" + annotations: + summary: "外部網站 tsenyang.com 離線" + description: "tsenyang.com 探測失敗超過 3 分鐘,容器 tsenyang-website (188) 可能需要重啟" + + - alert: StockWoooWorkDown + expr: probe_success{job="blackbox-http", instance="http://stock.wooo.work"} == 0 + for: 3m + labels: + severity: critical + layer: external + component: stock-platform + host: "110" + team: ops + auto_repair: "true" + annotations: + summary: "外部網站 stock.wooo.work 離線" + description: "stock.wooo.work 探測失敗超過 3 分鐘,容器 stock-platform (110) 可能需要重啟" + + - alert: BitanWoooWorkDown + expr: probe_success{job="blackbox-http", instance="https://bitan.wooo.work"} == 0 + for: 3m + labels: + severity: critical + layer: external + component: bitan-app + host: "188" + team: ops + auto_repair: "true" + annotations: + summary: "外部網站 bitan.wooo.work 離線" + description: "bitan.wooo.work 探測失敗超過 3 分鐘,容器 bitan-app (188) 可能需要重啟" + + - alert: ExternalSiteSSLExpiringSoon + expr: probe_ssl_earliest_cert_expiry{job="blackbox-http"} - time() < 14 * 24 * 3600 + for: 1h + labels: + severity: warning + layer: external + component: ssl + team: ops + auto_repair: "false" + annotations: + summary: "SSL 憑證即將到期: {{ $labels.instance }}" + description: "{{ $labels.instance }} SSL 憑證將在 14 天內到期,請手動更新"