feat(ops): 添加生产监控告警基线

- 新增 Prometheus/Grafana/Loki/Promtail 监控 profile\n- 覆盖 DB、磁盘、慢 API、慢 Prisma、任务失败和小宝摘要 stale 告警\n- 补充 postgres-exporter 自定义查询、Dashboard、部署文档和校验\n\nCo-Authored-By: GPT-5 Codex <codex@openai.com>

deploy/monitoring/grafana/dashboards/ftb-production-overview.json

@@ -0,0 +1,78 @@
+{
+  "uid": "ftb-production-overview",
+  "title": "FTB Production Overview",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "tags": ["ftb", "production", "v2.8"],
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "stat",
+      "title": "DB Availability",
+      "gridPos": { "x": 0, "y": 0, "w": 6, "h": 4 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "pg_up", "refId": "A" }
+      ]
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Slow API Logs",
+      "gridPos": { "x": 6, "y": 0, "w": 6, "h": 4 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "increase(ftb_slow_api_log_total[10m])", "refId": "A" }
+      ]
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Slow Prisma Logs",
+      "gridPos": { "x": 12, "y": 0, "w": 6, "h": 4 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "increase(ftb_slow_prisma_log_total[10m])", "refId": "A" }
+      ]
+    },
+    {
+      "id": 4,
+      "type": "stat",
+      "title": "Xiaobao Stale Summaries",
+      "gridPos": { "x": 18, "y": 0, "w": 6, "h": 4 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "ftb_xiaobao_stale_summary_count", "refId": "A" }
+      ]
+    },
+    {
+      "id": 5,
+      "type": "timeseries",
+      "title": "Job Failure Logs",
+      "gridPos": { "x": 0, "y": 4, "w": 8, "h": 5 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "increase(ftb_job_failure_log_total[10m])", "refId": "A" }
+      ]
+    },
+    {
+      "id": 6,
+      "type": "stat",
+      "title": "Root Disk Free %",
+      "gridPos": { "x": 8, "y": 4, "w": 8, "h": 5 },
+      "targets": [
+        { "datasource": { "type": "prometheus", "uid": "Prometheus" }, "expr": "100 * node_filesystem_avail_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"}", "refId": "A" }
+      ]
+    },
+    {
+      "id": 7,
+      "type": "logs",
+      "title": "Server Warning/Error Logs",
+      "gridPos": { "x": 16, "y": 4, "w": 8, "h": 5 },
+      "targets": [
+        { "datasource": { "type": "loki", "uid": "Loki" }, "expr": "{compose_service=\"server\"} |~ \"warn|error|失败|Slow\"", "refId": "A" }
+      ]
+    }
+  ]
+}
+

deploy/monitoring/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: FTB Production
+    orgId: 1
+    folder: FTB
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards
+

deploy/monitoring/grafana/provisioning/datasources/datasources.yml

@@ -0,0 +1,16 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false
+
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    editable: false
+