services:

  postgres:

    image: timescale/timescaledb-ha:pg16

    environment:

      POSTGRES_USER: ${POSTGRES_USER:-drophawk}

      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}

      POSTGRES_DB: ${POSTGRES_DB:-drophawk}

      POSTGRES_INITDB_ARGS: "--encoding=UTF8 --locale=C"

    volumes:

      - pg-data:/var/lib/postgresql/data

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-drophawk} -d ${POSTGRES_DB:-drophawk}"]

      interval: 5s

      timeout: 5s

      retries: 10

      start_period: 30s

    restart: on-failure

  redis:

    image: redis:7.4.3-alpine3.21

    command: >

      redis-server

      --requirepass ${REDIS_PASSWORD}

      --maxmemory 200mb

      --maxmemory-policy allkeys-lru

      --save 60 100

      --appendonly yes

    volumes:

      - redis-data:/data

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD}", "ping"]

      interval: 5s

      timeout: 3s

      retries: 10

      start_period: 10s

    restart: on-failure

  nats:

    image: nats:2.14.2-alpine3.22

    command: >

      -js

      -sd /data

      -m 8222

    volumes:

      - nats-data:/data

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:8222/healthz | grep -q ok"]

      interval: 5s

      timeout: 3s

      retries: 10

      start_period: 10s

    restart: on-failure

  ntfy:

    image: binwiederhier/ntfy:v2.14.0

    command: serve --config /etc/ntfy/server.yml

    volumes:

      - ntfy-data:/var/lib/ntfy

      - ./infra/ntfy.server.yml:/etc/ntfy/server.yml:ro

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:80/v1/health | grep -q '\"healthy\":true'"]

      interval: 10s

      timeout: 5s

      retries: 6

      start_period: 15s

    restart: on-failure

  backend:

    build:

      context: ./backend

      dockerfile: Dockerfile

    environment:

      DATABASE_URL: ${DATABASE_URL}

      REDIS_URL: ${REDIS_URL}

      NATS_URL: ${NATS_URL}

      NTFY_BASE_URL: ${NTFY_BASE_URL:-http://ntfy:80}

      NTFY_TOPIC: ${NTFY_TOPIC:-drophawk-drops}

      NTFY_TOKEN: ${NTFY_TOKEN}

      TICKETMASTER_API_KEYS: ${TICKETMASTER_API_KEYS}

      SEATGEEK_CLIENT_ID: ${SEATGEEK_CLIENT_ID:-}

      TICKETMASTER_AFFILIATE_ID: ${TICKETMASTER_AFFILIATE_ID:-}

      SEATGEEK_AFFILIATE_ID: ${SEATGEEK_AFFILIATE_ID:-}

      LOG_LEVEL: ${LOG_LEVEL:-info}

      OTEL_EXPORTER_OTLP_ENDPOINT: ${OTEL_EXPORTER_OTLP_ENDPOINT:-}

      PUBLIC_BASE_URL: ${PUBLIC_BASE_URL:-http://localhost}

      API_RATE_LIMIT_PER_MIN: ${API_RATE_LIMIT_PER_MIN:-100}

      SSE_MAX_CLIENTS: ${SSE_MAX_CLIENTS:-200}

      POLL_DEFAULT_INTERVAL_S: ${POLL_DEFAULT_INTERVAL_S:-300}

      POLL_TIGHT_INTERVAL_S: ${POLL_TIGHT_INTERVAL_S:-10}

      POLL_TIGHT_WINDOW_S: ${POLL_TIGHT_WINDOW_S:-900}

      WATCHLIST_MAX_RULES: ${WATCHLIST_MAX_RULES:-500}

    networks:

      - drophawk-net

    depends_on:

      postgres:

        condition: service_healthy

      redis:

        condition: service_healthy

      nats:

        condition: service_healthy

    restart: on-failure

  frontend:

    build:

      context: ./frontend

      dockerfile: Dockerfile

    environment:

      NEXT_PUBLIC_API_BASE_URL: ${NEXT_PUBLIC_API_BASE_URL:-/api}

      NEXT_PUBLIC_NTFY_PUBLIC_URL: ${NEXT_PUBLIC_NTFY_PUBLIC_URL:-/ntfy}

      NEXT_PUBLIC_NTFY_PUBLIC_TOPIC: ${NEXT_PUBLIC_NTFY_PUBLIC_TOPIC:-drophawk-drops}

      NEXT_PUBLIC_SENTRY_DSN: ${NEXT_PUBLIC_SENTRY_DSN:-}

    networks:

      - drophawk-net

    depends_on:

      backend:

        condition: service_started

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/ | grep -q DropHawk || wget -qO- http://localhost:3000/api/health 2>/dev/null; exit 0"]

      interval: 15s

      timeout: 10s

      retries: 6

      start_period: 60s

    restart: on-failure

  caddy:

    image: caddy:2.11.4-alpine

    ports:

      - "80:80"

      - "443:443"

    volumes:

      - ./infra/Caddyfile:/etc/caddy/Caddyfile:ro

      - caddy-data:/data

      - caddy-config:/config

    networks:

      - drophawk-net

    depends_on:

      frontend:

        condition: service_started

      backend:

        condition: service_started

      ntfy:

        condition: service_healthy

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:80/ 2>/dev/null | head -c 1 | wc -c | grep -q '[1-9]' || caddy validate --config /etc/caddy/Caddyfile"]

      interval: 15s

      timeout: 10s

      retries: 6

      start_period: 20s

    restart: on-failure

  prometheus:

    image: prom/prometheus:v3.4.1

    command:

      - "--config.file=/etc/prometheus/prometheus.yml"

      - "--storage.tsdb.path=/prometheus"

      - "--storage.tsdb.retention.time=30d"

      - "--web.enable-lifecycle"

    volumes:

      - ./infra/prometheus.yml:/etc/prometheus/prometheus.yml:ro

      - prometheus-data:/prometheus

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:9090/-/healthy | grep -q Healthy"]

      interval: 15s

      timeout: 5s

      retries: 6

      start_period: 20s

    restart: on-failure

  grafana:

    image: grafana/grafana-oss:13.0.2

    environment:

      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}

      GF_PATHS_PROVISIONING: /etc/grafana/provisioning

      GF_SERVER_ROOT_URL: "%(protocol)s://%(domain)s/grafana"

      GF_SERVER_SERVE_FROM_SUB_PATH: "true"

    volumes:

      - grafana-data:/var/lib/grafana

      - ./infra/grafana/datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml:ro

      - ./infra/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro

    networks:

      - drophawk-net

    depends_on:

      prometheus:

        condition: service_healthy

      loki:

        condition: service_healthy

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:3000/api/health | grep -q ok"]

      interval: 15s

      timeout: 5s

      retries: 6

      start_period: 30s

    restart: on-failure

  loki:

    image: grafana/loki:3.5.5

    command: -config.file=/etc/loki/loki-config.yml

    user: "0"

    volumes:

      - ./infra/loki/loki-config.yml:/etc/loki/loki-config.yml:ro

      - loki-data:/var/loki

    networks:

      - drophawk-net

    healthcheck:

      test: ["CMD-SHELL", "wget -qO- http://localhost:3100/ready | grep -q ready"]

      interval: 15s

      timeout: 5s

      retries: 6

      start_period: 30s

    restart: on-failure

volumes:

  pg-data:

  redis-data:

  nats-data:

  ntfy-data:

  caddy-data:

  caddy-config:

  prometheus-data:

  grafana-data:

  loki-data:

networks:

  drophawk-net:

    driver: bridge

    name: drophawk-net