fix: merge monitoring into main docker-compose.yml

All services (app + Prometheus + Grafana + node-exporter + cAdvisor)
are now in a single docker-compose.yml. One `docker compose up -d`
starts everything. No more separate monitoring file needed.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.gitea/workflows/deploy.yml

@@ -66,10 +66,6 @@ jobs:
             echo "=== Deploy summary ==="
             docker compose ps
             echo "Health: $(curl -sf http://localhost:8001/health 2>/dev/null || echo 'FAILED')"
-
-            echo "=== Starting monitoring ==="
-            docker compose -f docker-compose.yml -f docker-compose.monitoring.yml up -d prometheus grafana node-exporter cadvisor || true
-            docker compose -f docker-compose.yml -f docker-compose.monitoring.yml ps || true
           ENDSSH
 
       - name: Wait for frontend

docker-compose.yml

@@ -180,6 +180,100 @@ services:
     profiles:
       - with-ollama
 
+  # ===========================================
+  # Prometheus - Metrics Collection
+  # ===========================================
+  prometheus:
+    image: prom/prometheus:v2.52.0
+    container_name: wordly-prometheus
+    restart: unless-stopped
+    volumes:
+      - ./docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./docker/prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=30d'
+      - '--storage.tsdb.retention.size=5GB'
+      - '--web.enable-lifecycle'
+    networks:
+      - wordly-network
+    healthcheck:
+      test: ["CMD", "wget", "-q", "--spider", "http://localhost:9090/-/healthy"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+
+  # ===========================================
+  # Grafana - Dashboards & Visualization
+  # ===========================================
+  grafana:
+    image: grafana/grafana:11.0.0
+    container_name: wordly-grafana
+    restart: unless-stopped
+    environment:
+      - GF_SECURITY_ADMIN_USER=${GRAFANA_USER:-admin}
+      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_PASSWORD:-WordlyGrafana2026!}
+      - GF_USERS_ALLOW_SIGN_UP=false
+      - GF_SERVER_ROOT_URL=https://monitoring.wordly.art
+      - GF_INSTALL_PLUGINS=grafana-clock-panel
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./docker/grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./docker/grafana/dashboards:/var/lib/grafana/dashboards:ro
+    ports:
+      - "3001:3000"
+    networks:
+      - wordly-network
+    depends_on:
+      prometheus:
+        condition: service_healthy
+    healthcheck:
+      test: ["CMD", "wget", "-q", "--spider", "http://localhost:3000/api/health"]
+      interval: 30s
+      timeout: 5s
+      retries: 3
+
+  # ===========================================
+  # Node Exporter - System Metrics
+  # ===========================================
+  node-exporter:
+    image: prom/node-exporter:v1.8.0
+    container_name: wordly-node-exporter
+    restart: unless-stopped
+    pid: host
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - '--path.rootfs=/rootfs'
+      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|etc|var/lib/docker)($$|/)'
+    networks:
+      - wordly-network
+
+  # ===========================================
+  # cAdvisor - Container Metrics
+  # ===========================================
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:v0.49.1
+    container_name: wordly-cadvisor
+    restart: unless-stopped
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:ro
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+      - /dev/disk:/dev/disk:ro
+    privileged: true
+    devices:
+      - /dev/kmsg
+    networks:
+      - wordly-network
+
 # ===========================================
 # Networks
 # ===========================================
@@ -204,3 +298,7 @@ volumes:
     driver: local
   ollama_data:
     driver: local
+  prometheus_data:
+    driver: local
+  grafana_data:
+    driver: local