feat(observability): add Grafana with provisioned datasources and dashboards

Add obs-grafana service (grafana/grafana-oss:11.6.1) to docker-compose.observability.yml.
Datasources (Prometheus, Loki, Tempo) are auto-provisioned via
infra/observability/grafana/provisioning/datasources/datasources.yml with
cross-datasource linking (Loki traceId → Tempo, Tempo → Loki, service map via Prometheus).
Three dashboards are pre-loaded: Node Exporter Full (1860), Spring Boot Observability (17175),
Loki Logs (13639) — datasource template variables replaced with provisioned UIDs.
GRAFANA_ADMIN_PASSWORD added to .env.example.

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

.env.example

@@ -35,6 +35,9 @@ PORT_GRAFANA=3001
 PORT_GLITCHTIP=3002
 PORT_PROMETHEUS=9090
 
+# Grafana admin password — change this before exposing Grafana beyond localhost
+GRAFANA_ADMIN_PASSWORD=changeme
+
 # GlitchTip domain — production: use https://grafana.raddatz.cloud (must match Caddy vhost)
 GLITCHTIP_DOMAIN=http://localhost:3002
 

docker-compose.observability.yml

@@ -136,8 +136,26 @@ services:
       - obs-net      # Grafana reaches tempo:3200 over this network
 
   # --- Dashboards: Grafana ---
-  #   grafana: (see future issue)
+
-  #
+  obs-grafana:
+    image: grafana/grafana-oss:11.6.1
+    container_name: obs-grafana
+    restart: unless-stopped
+    ports:
+      - "127.0.0.1:${PORT_GRAFANA:-3001}:3000"
+    environment:
+      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-changeme}
+      GF_USERS_ALLOW_SIGN_UP: "false"
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./infra/observability/grafana/provisioning:/etc/grafana/provisioning:ro
+    depends_on:
+      - prometheus
+      - loki
+      - tempo
+    networks:
+      - obs-net
+
   # --- Error Tracking: GlitchTip ---
   #   glitchtip: (see future issue)
 

infra/observability/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,10 @@
+apiVersion: 1
+
+providers:
+  - name: default
+    type: file
+    disableDeletion: true
+    updateIntervalSeconds: 30
+    options:
+      path: /etc/grafana/provisioning/dashboards
+      foldersFromFilesStructure: false

infra/observability/grafana/provisioning/dashboards/loki-logs.json

@@ -0,0 +1,284 @@
+{
+  "__inputs": [
+    {
+      "name": "DS_LOKI",
+      "label": "Loki",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "loki",
+      "pluginName": "Loki"
+    }
+  ],
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "7.1.0"
+    },
+    {
+      "type": "panel",
+      "id": "graph",
+      "name": "Graph",
+      "version": ""
+    },
+    {
+      "type": "panel",
+      "id": "logs",
+      "name": "Logs",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "loki",
+      "name": "Loki",
+      "version": "1.0.0"
+    }
+  ],
+  "annotations": {
+    "list": [
+      {
+        "$$hashKey": "object:75",
+        "builtIn": 1,
+        "datasource": "-- Grafana --",
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "description": "Log Viewer Dashboard for Loki",
+  "editable": false,
+  "gnetId": 13639,
+  "graphTooltip": 0,
+  "id": null,
+  "iteration": 1608932746420,
+  "links": [
+    {
+      "$$hashKey": "object:59",
+      "icon": "bolt",
+      "includeVars": true,
+      "keepTime": true,
+      "tags": [],
+      "targetBlank": true,
+      "title": "View In Explore",
+      "type": "link",
+      "url": "/explore?orgId=1&left=[\"now-1h\",\"now\",\"Loki\",{\"expr\":\"{job=\\\"$app\\\"}\"},{\"ui\":[true,true,true,\"none\"]}]"
+    },
+    {
+      "$$hashKey": "object:61",
+      "icon": "external link",
+      "tags": [],
+      "targetBlank": true,
+      "title": "Learn LogQL",
+      "type": "link",
+      "url": "https://grafana.com/docs/loki/latest/logql/"
+    }
+  ],
+  "panels": [
+    {
+      "aliasColors": {},
+      "bars": true,
+      "dashLength": 10,
+      "dashes": false,
+      "datasource": {"type": "loki", "uid": "loki"},
+      "fieldConfig": {
+        "defaults": {
+          "custom": {},
+          "links": []
+        },
+        "overrides": []
+      },
+      "fill": 1,
+      "fillGradient": 0,
+      "gridPos": {
+        "h": 3,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "hiddenSeries": false,
+      "id": 6,
+      "legend": {
+        "avg": false,
+        "current": false,
+        "max": false,
+        "min": false,
+        "show": false,
+        "total": false,
+        "values": false
+      },
+      "lines": false,
+      "linewidth": 1,
+      "nullPointMode": "null",
+      "percentage": false,
+      "pluginVersion": "7.1.0",
+      "pointradius": 2,
+      "points": false,
+      "renderer": "flot",
+      "seriesOverrides": [],
+      "spaceLength": 10,
+      "stack": false,
+      "steppedLine": false,
+      "targets": [
+        {
+          "expr": "sum(count_over_time({job=\"$app\"} |= \"$search\" [$__interval]))",
+          "legendFormat": "",
+          "refId": "A"
+        }
+      ],
+      "thresholds": [],
+      "timeFrom": null,
+      "timeRegions": [],
+      "timeShift": null,
+      "title": "",
+      "tooltip": {
+        "shared": true,
+        "sort": 0,
+        "value_type": "individual"
+      },
+      "type": "graph",
+      "xaxis": {
+        "buckets": null,
+        "mode": "time",
+        "name": null,
+        "show": true,
+        "values": []
+      },
+      "yaxes": [
+        {
+          "$$hashKey": "object:168",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        },
+        {
+          "$$hashKey": "object:169",
+          "format": "short",
+          "label": null,
+          "logBase": 1,
+          "max": null,
+          "min": null,
+          "show": false
+        }
+      ],
+      "yaxis": {
+        "align": false,
+        "alignLevel": null
+      }
+    },
+    {
+      "datasource": {"type": "loki", "uid": "loki"},
+      "fieldConfig": {
+        "defaults": {
+          "custom": {}
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 25,
+        "w": 24,
+        "x": 0,
+        "y": 3
+      },
+      "id": 2,
+      "maxDataPoints": "",
+      "options": {
+        "showLabels": false,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      },
+      "targets": [
+        {
+          "expr": "{job=\"$app\"} |= \"$search\" | logfmt",
+          "hide": false,
+          "legendFormat": "",
+          "refId": "A"
+        }
+      ],
+      "timeFrom": null,
+      "timeShift": null,
+      "title": "",
+      "transparent": true,
+      "type": "logs"
+    }
+  ],
+  "refresh": false,
+  "schemaVersion": 26,
+  "style": "dark",
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "allValue": null,
+        "current": {},
+        "datasource": {"type": "loki", "uid": "loki"},
+        "definition": "label_values(job)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "App",
+        "multi": false,
+        "name": "app",
+        "options": [],
+        "query": "label_values(job)",
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "tagValuesQuery": "",
+        "tags": [],
+        "tagsQuery": "",
+        "type": "query",
+        "useTags": false
+      },
+      {
+        "current": {
+          "selected": false,
+          "text": "",
+          "value": ""
+        },
+        "hide": 0,
+        "label": "String Match",
+        "name": "search",
+        "options": [
+          {
+            "selected": true,
+            "text": "",
+            "value": ""
+          }
+        ],
+        "query": "",
+        "skipUrlSync": false,
+        "type": "textbox"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {
+    "hidden": false,
+    "refresh_intervals": [
+      "10s",
+      "30s",
+      "1m",
+      "5m",
+      "15m",
+      "30m",
+      "1h",
+      "2h",
+      "1d"
+    ]
+  },
+  "timezone": "",
+  "title": "Logs / App",
+  "uid": "sadlil-loki-apps-dashboard",
+  "version": 13
+}

infra/observability/grafana/provisioning/datasources/datasources.yml

@@ -0,0 +1,38 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    url: http://obs-prometheus:9090
+    isDefault: true
+    editable: false
+
+  - name: Loki
+    type: loki
+    uid: loki
+    url: http://obs-loki:3100
+    editable: false
+    jsonData:
+      derivedFields:
+        - name: TraceID
+          matcherRegex: '"traceId":"(\w+)"'
+          url: "${__value.raw}"
+          datasourceUid: tempo
+
+  - name: Tempo
+    type: tempo
+    uid: tempo
+    url: http://obs-tempo:3200
+    editable: false
+    jsonData:
+      tracesToLogsV2:
+        datasourceUid: loki
+        spanStartTimeShift: "-1m"
+        spanEndTimeShift: "1m"
+        filterByTraceID: true
+        filterBySpanID: false
+      serviceMap:
+        datasourceUid: prometheus
+      nodeGraph:
+        enabled: true