feat: integrate Uptime Kuma and Alertmanager into Docker setup

- Add Uptime Kuma service for status monitoring with health checks.
- Introduce Alertmanager service for alert management and notifications.
- Update docker-compose.yml to include new services and their configurations.
- Enhance Makefile with commands for managing Uptime Kuma and Alertmanager logs.
- Modify Ansible playbook to install necessary packages and configure SSL for new services.
- Update Nginx configuration to route traffic to Uptime Kuma and Alertmanager.
- Adjust Prometheus configuration to include alert rules and external URLs.

docker-compose.yml

@@ -12,10 +12,12 @@ services:
       - '--web.console.templates=/etc/prometheus/consoles'
       - '--storage.tsdb.retention.time=${PROMETHEUS_RETENTION_DAYS:-30}d'
       - '--web.enable-lifecycle'
+      - '--web.external-url=https://${SERVER_IP}/prometheus/'
     ports:
       - "9090:9090"
     volumes:
       - ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./infra/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
       - prometheus_data:/prometheus
     networks:
       - bots_network
@@ -35,9 +37,9 @@ services:
       - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
       - GF_USERS_ALLOW_SIGN_UP=false
       - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
-      - GF_SERVER_ROOT_URL=https://${SERVER_IP:-localhost}/grafana/
+      - GF_SERVER_ROOT_URL=https://${SERVER_IP}/grafana/
       - GF_SERVER_SERVE_FROM_SUB_PATH=true
-      - GF_SERVER_DOMAIN=${SERVER_IP:-localhost}
+      - GF_SERVER_DOMAIN=${SERVER_IP}
     ports:
       - "3000:3000"
     volumes:
@@ -53,6 +55,51 @@ services:
       timeout: 10s
       retries: 3
 
+  # Uptime Kuma Status Page
+  uptime-kuma:
+    image: louislam/uptime-kuma:latest
+    container_name: bots_uptime_kuma
+    restart: unless-stopped
+    volumes:
+      - uptime_kuma_data:/app/data
+    ports:
+      - "3001:3001"
+    environment:
+      - UPTIME_KUMA_PORT=3001
+    networks:
+      - bots_network
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3001"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+
+  # Alertmanager
+  alertmanager:
+    image: prom/alertmanager:latest
+    container_name: bots_alertmanager
+    restart: unless-stopped
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+      - '--web.external-url=https://${SERVER_IP}/alertmanager/'
+      - '--web.route-prefix=/'
+    ports:
+      - "9093:9093"
+    volumes:
+      - alertmanager_data:/alertmanager
+      - ./infra/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
+    networks:
+      - bots_network
+    depends_on:
+      - prometheus
+    healthcheck:
+      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+
   # Nginx Reverse Proxy
   nginx:
     image: nginx:alpine
@@ -61,16 +108,20 @@ services:
     ports:
       - "80:80"
       - "443:443"
+    environment:
+      - SERVER_IP=${SERVER_IP}
     volumes:
-      - ./infra/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
+      - ./infra/nginx/nginx.conf:/etc/nginx/templates/nginx.conf.template:ro
       - ./infra/nginx/conf.d:/etc/nginx/conf.d:ro
       - ./infra/nginx/ssl:/etc/nginx/ssl:ro
       - ./infra/nginx/.htpasswd:/etc/nginx/.htpasswd:ro
+      - /etc/letsencrypt:/etc/letsencrypt:ro
     networks:
       - bots_network
     depends_on:
       - grafana
       - prometheus
+      - uptime-kuma
     healthcheck:
       test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost/nginx-health"]
       interval: 30s
@@ -194,6 +245,10 @@ volumes:
     driver: local
   grafana_data:
     driver: local
+  uptime_kuma_data:
+    driver: local
+  alertmanager_data:
+    driver: local
 
 networks:
   bots_network: