feat(ops): add database backup strategy and log aggregation stack

- Add pg-backup container with daily automated pg_dump (02:00 UTC) and 7-day retention
- Add backup/restore scripts with documented recovery procedure
- Add Loki + Promtail for centralized log aggregation from all Docker containers
- Add Loki as Grafana datasource with correlation ID derived fields
- Add Grafana logs dashboard with volume, error rate, HTTP request, and log viewer panels
- Configure Promtail to parse Pino structured JSON logs with level/context labels
- Enhance LoggerService with string-level formatter and service base field
- Configure 15-day log retention in Loki

Co-Authored-By: Paperclip <noreply@paperclip.ing>

monitoring/grafana/dashboards/logs.json

@@ -0,0 +1,137 @@
+{
+  "annotations": { "list": [] },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Log Volume by Level",
+      "type": "timeseries",
+      "gridPos": { "h": 6, "w": 24, "x": 0, "y": 0 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "sum by (level) (count_over_time({compose_service=~\"$service\"} | json [$__interval]))",
+          "legendFormat": "{{ level }}",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "drawStyle": "bars",
+            "stacking": { "mode": "normal" },
+            "fillOpacity": 80
+          },
+          "color": { "mode": "palette-classic" }
+        },
+        "overrides": [
+          { "matcher": { "id": "byName", "options": "error" }, "properties": [{ "id": "color", "value": { "fixedColor": "red", "mode": "fixed" } }] },
+          { "matcher": { "id": "byName", "options": "fatal" }, "properties": [{ "id": "color", "value": { "fixedColor": "dark-red", "mode": "fixed" } }] },
+          { "matcher": { "id": "byName", "options": "warn" }, "properties": [{ "id": "color", "value": { "fixedColor": "orange", "mode": "fixed" } }] },
+          { "matcher": { "id": "byName", "options": "info" }, "properties": [{ "id": "color", "value": { "fixedColor": "green", "mode": "fixed" } }] },
+          { "matcher": { "id": "byName", "options": "debug" }, "properties": [{ "id": "color", "value": { "fixedColor": "blue", "mode": "fixed" } }] }
+        ]
+      }
+    },
+    {
+      "title": "Error Rate",
+      "type": "stat",
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 6 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "sum(count_over_time({compose_service=~\"$service\"} | json | level = `error` or level = `fatal` [$__range]))",
+          "refId": "A"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 10 },
+              { "color": "red", "value": 50 }
+            ]
+          }
+        }
+      }
+    },
+    {
+      "title": "Errors by Service",
+      "type": "piechart",
+      "gridPos": { "h": 8, "w": 6, "x": 6, "y": 6 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "sum by (compose_service) (count_over_time({compose_service=~\".+\"} | json | level = `error` or level = `fatal` [$__range]))",
+          "legendFormat": "{{ compose_service }}",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "HTTP Request Logs (4xx/5xx)",
+      "type": "table",
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "{compose_service=~\"$service\", component=\"http\"} | json | statusCode >= 400 | line_format \"{{.method}} {{.url}} {{.statusCode}} {{.duration}}ms\"",
+          "refId": "A"
+        }
+      ]
+    },
+    {
+      "title": "All Logs",
+      "type": "logs",
+      "gridPos": { "h": 12, "w": 24, "x": 0, "y": 14 },
+      "datasource": { "type": "loki", "uid": "loki" },
+      "targets": [
+        {
+          "expr": "{compose_service=~\"$service\"} | json |= `$search`",
+          "refId": "A"
+        }
+      ],
+      "options": {
+        "showTime": true,
+        "showLabels": true,
+        "showCommonLabels": false,
+        "wrapLogMessage": true,
+        "prettifyLogMessage": true,
+        "enableLogDetails": true,
+        "sortOrder": "Descending"
+      }
+    }
+  ],
+  "refresh": "10s",
+  "schemaVersion": 39,
+  "tags": ["goodgo", "logs", "loki"],
+  "templating": {
+    "list": [
+      {
+        "name": "service",
+        "type": "query",
+        "datasource": { "type": "loki", "uid": "loki" },
+        "query": "label_values(compose_service)",
+        "includeAll": true,
+        "allValue": ".+",
+        "current": { "text": "All", "value": "$__all" },
+        "refresh": 2,
+        "multi": true
+      },
+      {
+        "name": "search",
+        "type": "textbox",
+        "current": { "text": "", "value": "" },
+        "label": "Search"
+      }
+    ]
+  },
+  "time": { "from": "now-1h", "to": "now" },
+  "title": "GoodGo - Logs",
+  "uid": "goodgo-logs"
+}

monitoring/grafana/provisioning/datasources/datasource.yml

@@ -7,3 +7,15 @@ datasources:
     url: http://prometheus:9090
     isDefault: true
     editable: true
+
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    editable: true
+    jsonData:
+      derivedFields:
+        - datasourceUid: prometheus
+          matcherRegex: 'correlationId":"([^"]+)'
+          name: correlationId
+          url: '$${__value.raw}'