docker-compose.yml

services:
  # -----------------------------
  # Prometheus - Metrics
  # -----------------------------
  prometheus:
    image: prom/prometheus:v3.2.1
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/alert.rules.yml:/etc/prometheus/alert.rules.yml:ro
      - prometheus-data:/prometheus
    command:
      - --config.file=/etc/prometheus/prometheus.yml
      - --web.enable-lifecycle
      - --web.enable-remote-write-receiver
    depends_on:
      alertmanager:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 2g
        reservations:
          memory: 256m
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "wget --spider -q http://prometheus:9090/-/ready || exit 1",
        ]
      interval: 10s
      timeout: 5s
      retries: 5

  # -----------------------------
  # Alertmanager - Alerts
  # -----------------------------
  alertmanager:
    image: prom/alertmanager:v0.28.1
    container_name: alertmanager
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager-data:/alertmanager
    command: ["--config.file=/etc/alertmanager/alertmanager.yml"]
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 256m
        reservations:
          memory: 64m
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "wget --spider -q http://alertmanager:9093/-/ready || exit 1",
        ]
      interval: 10s
      timeout: 5s
      retries: 5

  # -----------------------------
  # Grafana - Dashboards / Visualization
  # -----------------------------
  grafana:
    image: grafana/grafana:11.5.2
    container_name: grafana
    ports:
      - "3030:3000"
    environment:
      GF_SECURITY_ADMIN_USER: ${GF_SECURITY_ADMIN_USER:-admin}
      GF_SECURITY_ADMIN_PASSWORD: ${GF_SECURITY_ADMIN_PASSWORD:?GF_SECURITY_ADMIN_PASSWORD must be set in .env}
      GF_LOG_LEVEL: info
    depends_on:
      - prometheus
    volumes:
      - grafana-storage:/var/lib/grafana
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 512m
        reservations:
          memory: 128m
    healthcheck:
      test:
        [
          "CMD-SHELL",
          "wget --spider -q http://grafana:3000/api/health || exit 1",
        ]
      interval: 10s
      timeout: 5s
      retries: 5

  # -----------------------------
  # Loki - Logs aggregation
  # -----------------------------
  loki:
    image: grafana/loki:2.8.2
    container_name: loki
    ports:
      - "3100:3100"
    user: "10001:10001"
    command:
      - -config.file=/etc/loki/loki-config.yaml
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/loki-config.yaml:ro
      - loki-index:/loki/index
      - loki-cache:/loki/cache
      - loki-chunks:/loki/chunks
      - loki-wal:/loki/wal
      - loki-compactor:/loki/compactor
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 1g
        reservations:
          memory: 128m
    healthcheck:
      test: ["CMD-SHELL", "wget --spider -q http://loki:3100/ready || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5

  # -----------------------------
  # Promtail - Log collection
  # -----------------------------
  promtail:
    image: grafana/promtail:2.8.2
    container_name: promtail
    volumes:
      - ./promtail/promtail-config.yaml:/etc/promtail/config.yaml:ro
      - /var/log:/var/log:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - promtail-positions:/var/lib/promtail
    command:
      - -config.file=/etc/promtail/config.yaml
    depends_on:
      loki:
        condition: service_healthy
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 256m
        reservations:
          memory: 64m

  # -----------------------------
  # Tempo - Traces aggregation
  # -----------------------------
  tempo:
    image: grafana/tempo:2.5.0
    container_name: tempo
    ports:
      - "3200:3200" # HTTP API/Query
      - "4320:4320" # Internal gRPC (server port)
      - "4318:4318" # OTLP gRPC receiver (for receiving traces)
      - "4319:4319" # OTLP HTTP receiver
    user: "10001:10001"
    volumes:
      - ./tempo/tempo-config.yaml:/etc/tempo/tempo-config.yaml:ro
      - tempo-data:/tempo-data
    command:
      - -config.file=/etc/tempo/tempo-config.yaml
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 1g
        reservations:
          memory: 128m
    healthcheck:
      test: ["CMD-SHELL", "wget --spider -q http://tempo:3200/ready || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5

  # -----------------------------
  # IRC relay - Alert notifications
  # -----------------------------
  irc-relay:
    build:
      context: ./irc-deamon
      dockerfile: Dockerfile.irc
    container_name: irc-relay
    ports:
      - "8010:8010"
    environment:
      IRC_NICKSERV_PASS: ${IRC_NICKSERV_PASS:-}
    volumes:
      - ./irc-deamon/config.yml:/etc/alertmanager-irc-relay/config.yml:ro
    restart: unless-stopped
    depends_on:
      - alertmanager
    deploy:
      resources:
        limits:
          memory: 64m
        reservations:
          memory: 16m

  # -----------------------------
  # Ollama - Local LLM inference (optional, profile: llm)
  # -----------------------------
  ollama:
    image: ollama/ollama:0.6.5
    container_name: ollama
    profiles: [llm]
    ports:
      - "11434:11434"
    volumes:
      - ollama-data:/root/.ollama
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 8g
        reservations:
          memory: 1g
    healthcheck:
      test: ["CMD-SHELL", "curl -sf http://localhost:11434/api/tags || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 5

  # -----------------------------
  # IRC Bot - LLM alert analysis (optional, profile: llm)
  # -----------------------------
  irc-bot:
    build:
      context: ./irc-bot
    container_name: irc-bot
    profiles: [llm]
    environment:
      IRC_HOST: "irc.wetfish.net"
      IRC_PORT: "6697"
      IRC_USE_TLS: "true"
      IRC_NICK: "fishvision"
      IRC_NICKSERV_PASS: ${IRC_NICKSERV_PASS:-}
      IRC_CHANNEL: "#alerts"
      ALERT_BOT_NICK: "alertbot"
      OLLAMA_URL: "http://ollama:11434"
      OLLAMA_MODEL: "qwen2.5:3b"
      GRAFANA_URL: "http://grafana:3000"
    restart: unless-stopped
    depends_on:
      - irc-relay
      - prometheus
      - loki
      - tempo
    deploy:
      resources:
        limits:
          memory: 256m
        reservations:
          memory: 64m

volumes:
  prometheus-data:
  alertmanager-data:
  grafana-storage:
  tempo-data:
  loki-index:
  loki-cache:
  loki-chunks:
  loki-wal:
  loki-compactor:
  promtail-positions:
  ollama-data: