docker-compose.yml

networks:
  monitor-net:
    driver: bridge

volumes:
    prometheus_data: {}
    grafana_data: {}
    loki_data: {}
    tempo_data: {}

services:

  prometheus:
    image: prom/prometheus:v3.10.0
    container_name: prometheus
    volumes:
      - ./prometheus:/etc/prometheus
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'
    restart: unless-stopped
    expose:
      - 9090
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  alertmanager:
    image: prom/alertmanager:v0.31.1
    container_name: alertmanager
    volumes:
      - ./alertmanager:/etc/alertmanager
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
    restart: unless-stopped
    expose:
      - 9093
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  nodeexporter:
    image: prom/node-exporter:v1.10.2
    container_name: nodeexporter
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    restart: unless-stopped
    expose:
      - 9100
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.55.1
    container_name: cadvisor
    privileged: true
    devices:
      - /dev/kmsg:/dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      #- /cgroup:/cgroup:ro #doesn't work on MacOS only for Linux
    restart: unless-stopped
    expose:
      - 8080
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  grafana:
    image: grafana/grafana:12.4.0
    container_name: grafana
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources
    environment:
      - GF_SECURITY_ADMIN_USER=${ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    restart: unless-stopped
    expose:
      - 3000
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  loki:
    image: grafana/loki:2.9.8
    container_name: loki
    command: -config.file=/etc/loki/loki.yml
    volumes:
      - ./loki:/etc/loki:ro
      - loki_data:/loki
    restart: unless-stopped
    expose:
      - 3100
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  tempo:
    image: grafana/tempo:2.3.1
    container_name: tempo
    command: -config.file=/etc/tempo/tempo.yml
    volumes:
      - ./tempo:/etc/tempo:ro
      - tempo_data:/var/tempo
    restart: unless-stopped
    expose:
      - 3200
      - 4317
      - 4318
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.96.0
    container_name: otel-collector
    command: ["--config=/etc/otel-collector/config.yml"]
    volumes:
      - ./otel-collector:/etc/otel-collector:ro
    restart: unless-stopped
    ports:
      # OTLP endpoints for apps (host -> collector)
      - "4317:4317"   # OTLP gRPC
      - "4318:4318"   # OTLP HTTP
    expose:
      - 8889          # Prometheus scrape (OTLP metrics -> Prometheus exporter)
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  ollama-gateway:
    image: envoyproxy/envoy:v1.30.4
    container_name: ollama-gateway
    command: ["/usr/local/bin/envoy", "-c", "/etc/envoy/envoy.yml", "--log-level", "info"]
    volumes:
      - ./envoy:/etc/envoy:ro
    extra_hosts:
      # Linux Docker: maps to host gateway IP (Docker 20.10+)
      - "host.docker.internal:host-gateway"
    ports:
      # Local Ollama gateway for users/apps (host -> gateway)
      - "11435:11434"
    expose:
      # Envoy admin (/stats/prometheus)
      - 9901
    restart: unless-stopped
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  alloy:
    image: grafana/alloy:v1.3.0
    container_name: alloy
    command: ["run", "--server.http.listen-addr=0.0.0.0:12345", "/etc/alloy/config.alloy"]
    volumes:
      - ./alloy:/etc/alloy:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    restart: unless-stopped
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  pushgateway:
    image: prom/pushgateway:v1.11.2
    container_name: pushgateway
    restart: unless-stopped
    expose:
      - 9091
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"

  caddy:
    image: caddy:2.11.2
    container_name: caddy
    ports:
      - "3000:3000"
      - "8080:8080"
      - "9090:9090"
      - "9093:9093"
      - "9091:9091"
      - "3100:3100"
      - "3200:3200"
    volumes:
      - ./caddy:/etc/caddy
    environment:
      - ADMIN_USER=${ADMIN_USER:-admin}
      - ADMIN_PASSWORD=${ADMIN_PASSWORD:-admin}
      - ADMIN_PASSWORD_HASH=${ADMIN_PASSWORD_HASH:-$2a$14$1l.IozJx7xQRVmlkEQ32OeEEfP5mRxTpbDTCTcXRqn19gXD8YK1pO}
    restart: unless-stopped
    networks:
      - monitor-net
    labels:
      org.label-schema.group: "monitoring"