docker-compose.yml

version: '3.8'

volumes:
  grafana_data: {}
  lancedb_data: {}
  kuzu_data: {}
  vcf_data: {}

networks:
  vcf_network:
    driver: bridge

services:
  # =============================================================================
  # VCF Analysis Agent - Main Application
  # =============================================================================
  vcf-agent:
    build:
      context: .
      dockerfile: Dockerfile
      target: runtime
      args:
        - BCFTOOLS_VERSION=1.19
        - HTSLIB_VERSION=1.19
    container_name: vcf_analysis_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      - "8000:8000"  # Main application port
    volumes:
      - vcf_data:/app/data
      - lancedb_data:/app/lancedb
      - kuzu_data:/app/kuzu_db
      - ./sample_data:/app/sample_data:ro  # Read-only sample data
      - ./config:/app/config:ro  # Read-only configuration
    environment:
      - PYTHONUNBUFFERED=1
      - LANCEDB_PATH=/app/lancedb
      - KUZU_PATH=/app/kuzu_db
      - PROMETHEUS_GATEWAY=http://prometheus:9090
      - JAEGER_ENDPOINT=http://jaeger:14268/api/traces
      - LOG_LEVEL=INFO
    depends_on:
      - prometheus
      - jaeger
    healthcheck:
      test: ["CMD", "python", "-c", "import vcf_agent; print('healthy')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # =============================================================================
  # VCF Analysis Agent - Development Version
  # =============================================================================
  vcf-agent-dev:
    build:
      context: .
      dockerfile: Dockerfile
      target: development
    container_name: vcf_analysis_agent_dev
    restart: "no"
    networks:
      - vcf_network
    ports:
      - "8001:8000"  # Development port
      - "8888:8888"  # Jupyter notebook
    volumes:
      - .:/app/src:rw  # Mount source code for development
      - vcf_data:/app/data
      - lancedb_data:/app/lancedb
      - kuzu_data:/app/kuzu_db
    environment:
      - PYTHONUNBUFFERED=1
      - DEVELOPMENT=true
      - LANCEDB_PATH=/app/lancedb
      - KUZU_PATH=/app/kuzu_db
    profiles:
      - development
    command: ["bash"]

  # =============================================================================
  # Observability Stack
  # =============================================================================
  jaeger:
    image: jaegertracing/all-in-one:1.52
    container_name: jaeger_vcf_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      # OTLP gRPC receiver
      - "4317:4317"
      # OTLP HTTP receiver
      - "4318:4318"
      # Jaeger UI
      - "16686:16686"
      # Prometheus metrics from Jaeger itself
      - "16687:16687"
    environment:
      - COLLECTOR_OTLP_ENABLED=true
      - LOG_LEVEL=info
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:16686/"]
      interval: 30s
      timeout: 10s
      retries: 3

  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: prometheus_vcf_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./config/prometheus:/etc/prometheus/config:ro
    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'
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  grafana:
    image: grafana/grafana-oss:10.2.2
    container_name: grafana_vcf_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./config/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./config/grafana/dashboards:/var/lib/grafana/dashboards:ro
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
      - GF_INSTALL_PLUGINS=grafana-piechart-panel
    depends_on:
      - prometheus
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3

  # =============================================================================
  # Optional: Ollama for Local LLM Support
  # =============================================================================
  ollama:
    image: ollama/ollama:latest
    container_name: ollama_vcf_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      - "11434:11434"
    volumes:
      - ./ollama_data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
    profiles:
      - ollama
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434/api/tags"]
      interval: 30s
      timeout: 10s
      retries: 3

  # =============================================================================
  # Optional: MinIO for S3-compatible Storage
  # =============================================================================
  minio:
    image: minio/minio:RELEASE.2023-12-02T10-51-33Z
    container_name: minio_vcf_agent
    restart: unless-stopped
    networks:
      - vcf_network
    ports:
      - "9000:9000"
      - "9001:9001"
    volumes:
      - ./minio_data:/data
    environment:
      - MINIO_ROOT_USER=minioadmin
      - MINIO_ROOT_PASSWORD=minioadmin123
    command: server /data --console-address ":9001"
    profiles:
      - storage
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
      interval: 30s
      timeout: 10s
      retries: 3