feat(m5): ADR-074 M5 — Docker 188 / Redis Streams / PostgreSQL 磁碟告警

新增 awoooi_infrastructure_detailed 告警群組：
- DockerContainerUnhealthyDetailed: 188 容器無活動 > 2min
- RedisStreamBacklogHigh: Stream 積壓 > 500 筆
- PostgreSQLDiskGrowthRate: 磁碟 1h 增長 > 500MB

2026-04-12 ogt (ADR-074 M5)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

k8s/monitoring/flywheel-alerts.yaml

@@ -117,6 +117,64 @@ spec:
             description: "上次備份測試距今 {{ $value | humanizeDuration }}，週排程 CronJob 可能失效。"
             runbook: "檢查 velero namespace 中的 backup-restore-test CronJob 狀態"
 
+    - name: awoooi_infrastructure_detailed
+      interval: 60s
+      rules:
+
+        # P1: Docker 188 容器不健康（docker inspect health=unhealthy）
+        # node-exporter + cAdvisor 暴露 container_last_seen / container_tasks_state
+        - alert: DockerContainerUnhealthyDetailed
+          expr: |
+            count by (name, instance) (
+              container_tasks_state{state="running", instance=~"192.168.0.188.*"}
+            ) == 0
+            or
+            container_last_seen{instance=~"192.168.0.188.*", name!=""} < (time() - 120)
+          for: 5m
+          labels:
+            severity: warning
+            alert_category: infrastructure
+            notification_type: TYPE-3
+          annotations:
+            summary: "188 主機容器 {{ $labels.name }} 異常"
+            description: "容器 {{ $labels.name }} 在 {{ $labels.instance }} 已超過 2 分鐘無活動或不在 running 狀態。"
+            runbook: "SSH 到 192.168.0.188：docker inspect {{ $labels.name }} 確認健康狀態"
+
+        # P1: Redis Streams 積壓過高（alert stream 或 incident stream）
+        - alert: RedisStreamBacklogHigh
+          expr: awoooi_redis_stream_len > 500
+          for: 10m
+          labels:
+            severity: warning
+            alert_category: infrastructure
+            notification_type: TYPE-3
+          annotations:
+            summary: "Redis Stream {{ $labels.stream }} 積壓 {{ $value }} 筆"
+            description: "Redis Stream 積壓超過 500 筆，飛輪消費者可能阻塞。"
+            runbook: "檢查 consumer group lag：XINFO GROUPS <stream-key>"
+
+        # P1: PostgreSQL 磁碟增長率過快（1小時增長超過 500MB）
+        - alert: PostgreSQLDiskGrowthRate
+          expr: |
+            (
+              node_filesystem_size_bytes{instance="192.168.0.188:9100", mountpoint="/"}
+              - node_filesystem_avail_bytes{instance="192.168.0.188:9100", mountpoint="/"}
+            )
+            - (
+              node_filesystem_size_bytes{instance="192.168.0.188:9100", mountpoint="/"}
+              - node_filesystem_avail_bytes{instance="192.168.0.188:9100", mountpoint="/"}
+            ) offset 1h
+            > 524288000
+          for: 5m
+          labels:
+            severity: warning
+            alert_category: infrastructure
+            notification_type: TYPE-3
+          annotations:
+            summary: "188 主機磁碟 1 小時增長超過 500MB"
+            description: "磁碟在過去 1 小時增長 {{ $value | humanize1024 }}B，可能是 PostgreSQL WAL 或日誌暴增。"
+            runbook: "SSH 188：df -h / && du -sh /var/lib/postgresql/*/pg_wal"
+
     - name: awoooi_host_connectivity
       interval: 60s
       rules: