docker-compose.yml

version: "3.9"

# ============================================================
# IncidentCommander – Full Stack Docker Compose
# ============================================================
# Usage:
#   docker compose up -d                  # start all services
#   docker compose up -d --build          # rebuild & start
#   docker compose --profile monitoring up -d   # include monitoring
#   docker compose --profile traffic up -d      # include locust
# ============================================================

x-logging: &default-logging
  driver: json-file
  options:
    max-size: "10m"
    max-file: "3"
    tag: "{{.Name}}"

services:
  # ──────────────────────────────────────────────
  # Data tier
  # ──────────────────────────────────────────────
  postgres:
    image: postgres:16-alpine
    environment:
      POSTGRES_DB: acmecorp
      POSTGRES_USER: postgres
      POSTGRES_PASSWORD: password
    ports:
      - "5432:5432"
    volumes:
      - pgdata:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 5s
      timeout: 3s
      retries: 5
    logging: *default-logging

  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    command: redis-server --maxmemory 256mb --maxmemory-policy allkeys-lru
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5
    logging: *default-logging

  zookeeper:
    image: confluentinc/cp-zookeeper:7.5.0
    environment:
      ZOOKEEPER_CLIENT_PORT: 2181
      ZOOKEEPER_TICK_TIME: 2000
    logging: *default-logging

  kafka:
    image: confluentinc/cp-kafka:7.5.0
    depends_on:
      - zookeeper
    ports:
      - "9092:9092"
    environment:
      KAFKA_BROKER_ID: 1
      KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_AUTO_CREATE_TOPICS_ENABLE: "true"
    healthcheck:
      test: ["CMD-SHELL", "kafka-topics --bootstrap-server localhost:9092 --list"]
      interval: 10s
      timeout: 5s
      retries: 5
    logging: *default-logging

  mailhog:
    image: mailhog/mailhog:latest
    ports:
      - "1025:1025"  # SMTP
      - "8025:8025"  # Web UI
    logging: *default-logging

  # ──────────────────────────────────────────────
  # Application services
  # ──────────────────────────────────────────────
  checkout-frontend:
    build:
      context: ./frontend
      dockerfile: Dockerfile
    ports:
      - "3000:3000"
    environment:
      NEXT_PUBLIC_API_BASE: http://localhost:4001
      PAYMENTS_API_URL: http://payments-api:4001
      INVENTORY_API_URL: http://inventory-service:4002
      NOTIFICATION_API_URL: http://notification-service:4003
    depends_on:
      payments-api:
        condition: service_healthy
    logging: *default-logging

  payments-api:
    build:
      context: ./backend/payments-api
    ports:
      - "4001:4001"
    environment:
      DATABASE_URL: postgresql+asyncpg://postgres:password@postgres:5432/acmecorp
      KAFKA_BOOTSTRAP_SERVERS: kafka:9092
      DB_POOL_SIZE: "10"
      SERVICE_VERSION: "2.3.0"
      PORT: "4001"
    depends_on:
      postgres:
        condition: service_healthy
      kafka:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:4001/health"]
      interval: 10s
      timeout: 3s
      retries: 5
    logging: *default-logging

  inventory-service:
    build:
      context: ./backend/inventory-service
    ports:
      - "4002:4002"
    environment:
      DATABASE_URL: postgres://postgres:password@postgres:5432/acmecorp?sslmode=disable
      REDIS_ADDR: redis:6379
      REDIS_POOL_SIZE: "10"
      KAFKA_BOOTSTRAP_SERVERS: kafka:9092
      PORT: "4002"
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:4002/health"]
      interval: 10s
      timeout: 3s
      retries: 5
    logging: *default-logging

  order-worker:
    build:
      context: ./backend/order-worker
    environment:
      CELERY_BROKER_URL: redis://redis:6379/1
      CELERY_RESULT_BACKEND: redis://redis:6379/2
      CELERY_CONCURRENCY: "4"
      PAYMENTS_API_URL: http://payments-api:4001
      INVENTORY_API_URL: http://inventory-service:4002
      NOTIFICATION_API_URL: http://notification-service:4003
    depends_on:
      redis:
        condition: service_healthy
      payments-api:
        condition: service_healthy
    logging: *default-logging

  notification-service:
    build:
      context: ./backend/notification-service
    ports:
      - "4003:4003"
    environment:
      SMTP_HOST: mailhog
      SMTP_PORT: "1025"
      PORT: "4003"
    depends_on:
      - mailhog
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:4003/health"]
      interval: 10s
      timeout: 3s
      retries: 5
    logging: *default-logging

  # ──────────────────────────────────────────────
  # RL Agent (OpenEnv server)
  # ──────────────────────────────────────────────
  rl-agent:
    build:
      context: ./rl-agent
    ports:
      - "8000:8000"
    environment:
      PROMETHEUS_URL: http://prometheus:9090
      LOKI_URL: http://loki:3100
      CHAOS_MESH_URL: ""
      MOCK_MODE: "true"
      ANTHROPIC_API_KEY: "${ANTHROPIC_API_KEY:-}"
      OPENAI_API_KEY: "${OPENAI_API_KEY:-}"
    depends_on:
      payments-api:
        condition: service_healthy
      inventory-service:
        condition: service_healthy
    logging: *default-logging

  # ──────────────────────────────────────────────
  # Monitoring (profile: monitoring)
  # ──────────────────────────────────────────────
  prometheus:
    image: prom/prometheus:v2.48.0
    profiles: ["monitoring", "full"]
    ports:
      - "9090:9090"
    volumes:
      - ./observability/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./observability/prometheus/rules:/etc/prometheus/rules:ro
      - promdata:/prometheus
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.retention.time=15d"
      - "--web.enable-lifecycle"
    logging: *default-logging

  loki:
    image: grafana/loki:2.9.3
    profiles: ["monitoring", "full"]
    ports:
      - "3100:3100"
    volumes:
      - ./observability/loki/loki-config.yml:/etc/loki/local-config.yaml:ro
      - lokidata:/loki
    command: -config.file=/etc/loki/local-config.yaml
    logging: *default-logging

  promtail:
    image: grafana/promtail:2.9.3
    profiles: ["monitoring", "full"]
    volumes:
      - ./observability/loki/promtail-config.yml:/etc/promtail/config.yml:ro
      - /var/log:/var/log:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    command: -config.file=/etc/promtail/config.yml
    depends_on:
      - loki
    logging: *default-logging

  grafana:
    image: grafana/grafana:10.2.2
    profiles: ["monitoring", "full"]
    ports:
      - "3001:3000"
    environment:
      GF_SECURITY_ADMIN_USER: admin
      GF_SECURITY_ADMIN_PASSWORD: admin
      GF_USERS_ALLOW_SIGN_UP: "false"
    volumes:
      - ./observability/grafana/provisioning/datasources.yml:/etc/grafana/provisioning/datasources/datasources.yml:ro
      - ./observability/grafana/provisioning/dashboards.yml:/etc/grafana/provisioning/dashboards/dashboards.yml:ro
      - ./observability/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - grafanadata:/var/lib/grafana
    depends_on:
      - prometheus
      - loki
    logging: *default-logging

  alertmanager:
    image: prom/alertmanager:v0.26.0
    profiles: ["monitoring", "full"]
    ports:
      - "9093:9093"
    volumes:
      - ./observability/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    logging: *default-logging

  jaeger:
    image: jaegertracing/all-in-one:1.52
    profiles: ["monitoring", "full"]
    ports:
      - "16686:16686"  # UI
      - "14268:14268"  # Collector HTTP
      - "6831:6831/udp" # Agent compact
    environment:
      COLLECTOR_ZIPKIN_HOST_PORT: ":9411"
    logging: *default-logging

  # ──────────────────────────────────────────────
  # Traffic generator (profile: traffic)
  # ──────────────────────────────────────────────
  locust:
    image: locustio/locust:2.20.0
    profiles: ["traffic", "full"]
    ports:
      - "8089:8089"
    volumes:
      - ./traffic/locustfile.py:/mnt/locust/locustfile.py:ro
    command: -f /mnt/locust/locustfile.py --host=http://checkout-frontend:3000
    depends_on:
      - checkout-frontend
    logging: *default-logging

volumes:
  pgdata:
  promdata:
  lokidata:
  grafanadata: