feat(monitoring): expose backend version in Prometheus

.github/workflows/deploy-production.yaml

@@ -107,13 +107,15 @@ jobs:
             cp ~/.env-production dashboard-production/.env &&
             cd dashboard-production &&
             git checkout ${GITHUB_SHA} &&
+            export DASHBOARD_VERSION=${DASHBOARD_VERSION} &&
             docker compose -f docker-compose-next.yml pull --policy=always &&
             docker compose -f docker-compose-next.yml up -d --remove-orphans
           "
         env:
           SSH_USER: ${{ secrets.STAGING_USER }}
           SSH_HOST: ${{ secrets.STAGING_HOST }}
           SSH_KEY: ${{ secrets.STAGING_KEY }}
+          DASHBOARD_VERSION: ${{ github.event.inputs.tag }}
 
       - name: Discord notification on success
         if: success()

backend/kernelCI/wsgi.py

@@ -10,7 +10,15 @@
 import os
 
 from django.core.wsgi import get_wsgi_application
+from prometheus_client import Gauge
 
 os.environ.setdefault("DJANGO_SETTINGS_MODULE", "kernelCI.settings")
 
 application = get_wsgi_application()
+
+Gauge(
+    "dashboard_build_info",
+    "Deployed backend version, always reported as 1",
+    ["version"],
+    multiprocess_mode="max",
+).labels(version=os.environ.get("DASHBOARD_VERSION") or "unknown").set(1)

docker-compose-next.yml

@@ -52,6 +52,8 @@ services:
             - --bind=0.0.0.0:8000
             - --timeout=250
         env_file: .env
+        environment:
+            - DASHBOARD_VERSION=${DASHBOARD_VERSION:-unknown}
         volumes:
             - backend-data:${BACKEND_VOLUME_DIR:-/volume_data}
         restart: always

docker-compose.dev.yml

@@ -16,6 +16,7 @@ services:
         env_file: [.env]
         environment:
             - PYTHONOPTIMIZE=0            # required for runserver/reload to work correctly
+            - DASHBOARD_VERSION=${DASHBOARD_VERSION:-local-dev}
         networks: [private, public]
         ports: ["8000:8000"]
         command:

docker-compose.yml

@@ -17,6 +17,8 @@ services:
             - backend-data:${BACKEND_VOLUME_DIR:-/volume_data}
         env_file:
             - .env
+        environment:
+            - DASHBOARD_VERSION=${DASHBOARD_VERSION:-local-dev}
         networks:
             - private
             - public

docs/monitoring.md

@@ -71,6 +71,7 @@ After importing the dashboard, you'll have:
   - Total Calls
   - Average Response Time
   - Total Time (cumulative time per endpoint)
+- **Deploys** - Annotation and Running Version panel from `dashboard_build_info` (`DASHBOARD_VERSION`)
 
 ### Aggregation Process Dashboard
 
@@ -93,6 +94,7 @@ The monitoring system supports multi-worker Gunicorn deployments using Prometheu
 ### Configuration
 
 #### Environment Variables
+- `DASHBOARD_VERSION`: Label on `dashboard_build_info` (default: `unknown`)
 - `PROMETHEUS_METRICS_ENABLED`: Set to `true` to enable Prometheus metrics (default: `false`)
 - `PROMETHEUS_METRICS_PORT`: Port for the metrics aggregator (default: `8001`)
 - `PROMETHEUS_MULTIPROC_DIR`: Directory for multiprocess metric files (default: `/tmp/prometheus_multiproc_dir`)

monitoring/dashboard.json

@@ -12,6 +12,23 @@
         "iconColor": "rgba(0, 211, 255, 1)",
         "name": "Annotations & Alerts",
         "type": "dashboard"
+      },
+      {
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "enable": true,
+        "iconColor": "purple",
+        "name": "Deploys",
+        "target": {
+          "expr": "dashboard_build_info unless dashboard_build_info offset 1m",
+          "instant": false,
+          "interval": "60s",
+          "legendFormat": "",
+          "refId": "Anno"
+        },
+        "titleFormat": "Deploy {{version}}"
       }
     ]
   },
@@ -22,6 +39,60 @@
   "links": [],
   "liveNow": false,
   "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "fixedColor": "text",
+            "mode": "fixed"
+          },
+          "mappings": [],
+          "noValue": "unknown"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 3,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "none",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "textMode": "name"
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "prometheus"
+          },
+          "editorMode": "code",
+          "expr": "dashboard_build_info",
+          "instant": true,
+          "legendFormat": "{{version}}",
+          "range": false,
+          "refId": "A"
+        }
+      ],
+      "title": "Running Version",
+      "type": "stat"
+    },
     {
       "datasource": {
         "type": "prometheus",
@@ -82,7 +153,7 @@
         "h": 8,
         "w": 12,
         "x": 0,
-        "y": 0
+        "y": 3
       },
       "id": 1,
       "options": {
@@ -173,7 +244,7 @@
         "h": 8,
         "w": 12,
         "x": 12,
-        "y": 0
+        "y": 3
       },
       "id": 2,
       "options": {
@@ -355,7 +426,7 @@
         "h": 8,
         "w": 24,
         "x": 0,
-        "y": 8
+        "y": 11
       },
       "id": 3,
       "options": {
@@ -443,11 +514,15 @@
                 "operation": "groupby"
               },
               "Total Calls": {
-                "aggregations": ["sum"],
+                "aggregations": [
+                  "sum"
+                ],
                 "operation": "aggregate"
               },
               "Total Time": {
-                "aggregations": ["sum"],
+                "aggregations": [
+                  "sum"
+                ],
                 "operation": "aggregate"
               }
             },
@@ -525,15 +600,27 @@
   "templating": {
     "list": [
       {
-        "current": { "selected": false, "text": "Time Range", "value": "range" },
+        "current": {
+          "selected": false,
+          "text": "Time Range",
+          "value": "range"
+        },
         "hide": 0,
         "includeAll": false,
         "multi": false,
         "label": "Summary Mode",
         "name": "summary_mode",
         "options": [
-          { "selected": false, "text": "All Time", "value": "all" },
-          { "selected": true, "text": "Time Range", "value": "range" }
+          {
+            "selected": false,
+            "text": "All Time",
+            "value": "all"
+          },
+          {
+            "selected": true,
+            "text": "Time Range",
+            "value": "range"
+          }
         ],
         "query": "all,range",
         "queryValue": "",