version: '3.8'

# RuVector Full Stack Deployment
# Orchestrates all RuVector components with proper dependencies and health checks

services:
  # PostgreSQL Database with RuVector Extension
  postgres:
    image: ruvnet/ruvector:latest
    container_name: ruvector-postgres
    hostname: ruvector-postgres
    environment:
      POSTGRES_USER: ruvector
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-ruvector_pass}
      POSTGRES_DB: ruvector
      PGDATA: /var/lib/postgresql/data/pgdata
    ports:
      - "${POSTGRES_PORT:-5432}:5432"
    volumes:
      - pg-data:/var/lib/postgresql/data
      - ./init.sql:/docker-entrypoint-initdb.d/init.sql:ro
    networks:
      - ruvector-net
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ruvector -d ruvector"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 512M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # Core Vector Database Engine (Internal Only)
  ruvector-core:
    image: ruvnet/ruvector-core:latest
    container_name: ruvector-core
    hostname: ruvector-core
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      VECTOR_DIMENSION: ${VECTOR_DIMENSION:-1536}
    depends_on:
      postgres:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - core-data:/var/lib/ruvector
    healthcheck:
      test: ["CMD-SHELL", "test -f /var/lib/ruvector/health || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 20s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '1.5'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 256M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # REST API Server
  server:
    image: ruvnet/ruvector-server:latest
    container_name: ruvector-server
    hostname: ruvector-server
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      SERVER_HOST: ${SERVER_HOST:-0.0.0.0}
      SERVER_PORT: ${SERVER_PORT:-8080}
      RUST_LOG: ${RUST_LOG:-info}
      CORE_SERVICE_URL: http://ruvector-core:8081
      GNN_SERVICE_URL: http://ruvector-gnn:8082
      GRAPH_SERVICE_URL: http://ruvector-graph:7687
      ATTENTION_SERVICE_URL: http://ruvector-attention:8083
      CLUSTER_SERVICE_URL: http://ruvector-cluster:8084
      SONA_SERVICE_URL: http://ruvector-sona:8085
    ports:
      - "${SERVER_PORT:-8080}:8080"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - server-logs:/var/log/ruvector
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8080/health || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 3
      start_period: 30s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 1.5G
        reservations:
          cpus: '0.5'
          memory: 512M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "5"

  # CLI and MCP Server
  cli:
    image: ruvnet/ruvector-cli:latest
    container_name: ruvector-cli
    hostname: ruvector-cli
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      SERVER_URL: http://server:8080
      MCP_PORT: ${MCP_PORT:-3000}
    ports:
      - "${MCP_PORT:-3000}:3000"
    depends_on:
      postgres:
        condition: service_healthy
      server:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - cli-data:/root/.ruvector
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:3000/health || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 20s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 128M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # Graph Neural Network Engine
  ruvector-gnn:
    image: ruvnet/ruvector-gnn:latest
    container_name: ruvector-gnn
    hostname: ruvector-gnn
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      GNN_PORT: ${GNN_PORT:-8082}
      MODEL_PATH: /var/lib/ruvector/models
      CUDA_VISIBLE_DEVICES: ${CUDA_VISIBLE_DEVICES:-}
    ports:
      - "${GNN_PORT:-8082}:8082"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - gnn-models:/var/lib/ruvector/models
      - gnn-cache:/var/lib/ruvector/cache
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8082/health || exit 1"]
      interval: 15s
      timeout: 10s
      retries: 3
      start_period: 45s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 1G
    logging:
      driver: "json-file"
      options:
        max-size: "20m"
        max-file: "5"

  # Graph Database
  ruvector-graph:
    image: ruvnet/ruvector-graph:latest
    container_name: ruvector-graph
    hostname: ruvector-graph
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      BOLT_PORT: ${BOLT_PORT:-7687}
      HTTP_PORT: ${HTTP_PORT:-7474}
      NEO4J_AUTH: ${NEO4J_AUTH:-none}
    ports:
      - "${BOLT_PORT:-7687}:7687"
      - "${HTTP_PORT:-7474}:7474"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - graph-data:/var/lib/ruvector/graph
      - graph-logs:/var/log/ruvector/graph
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:7474/db/data/ || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 40s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 512M
    logging:
      driver: "json-file"
      options:
        max-size: "15m"
        max-file: "5"

  # Attention Mechanism Engine
  ruvector-attention:
    image: ruvnet/ruvector-attention:latest
    container_name: ruvector-attention
    hostname: ruvector-attention
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      ATTENTION_PORT: ${ATTENTION_PORT:-8083}
      ATTENTION_HEADS: ${ATTENTION_HEADS:-8}
      ATTENTION_LAYERS: ${ATTENTION_LAYERS:-6}
    ports:
      - "${ATTENTION_PORT:-8083}:8083"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
      ruvector-gnn:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - attention-cache:/var/lib/ruvector/attention
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8083/health || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 35s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '3.0'
          memory: 3G
        reservations:
          cpus: '1.0'
          memory: 1G
    logging:
      driver: "json-file"
      options:
        max-size: "15m"
        max-file: "5"

  # Cluster Coordinator
  ruvector-cluster:
    image: ruvnet/ruvector-cluster:latest
    container_name: ruvector-cluster
    hostname: ruvector-cluster
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      CLUSTER_PORT: ${CLUSTER_PORT:-8084}
      CLUSTER_MODE: ${CLUSTER_MODE:-standalone}
      CLUSTER_NODE_ID: ${CLUSTER_NODE_ID:-node-1}
      RAFT_PORT: ${RAFT_PORT:-9000}
    ports:
      - "${CLUSTER_PORT:-8084}:8084"
      - "${RAFT_PORT:-9000}:9000"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - cluster-data:/var/lib/ruvector/cluster
      - cluster-logs:/var/log/ruvector/cluster
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8084/health || exit 1"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 30s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 1.5G
        reservations:
          cpus: '0.5'
          memory: 512M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "5"

  # SONA Self-Learning Module
  ruvector-sona:
    image: ruvnet/ruvector-sona:latest
    container_name: ruvector-sona
    hostname: ruvector-sona
    environment:
      DATABASE_URL: postgresql://ruvector:${POSTGRES_PASSWORD:-ruvector_pass}@postgres:5432/ruvector
      RUST_LOG: ${RUST_LOG:-info}
      SONA_PORT: ${SONA_PORT:-8085}
      LEARNING_RATE: ${LEARNING_RATE:-0.001}
      TRAINING_ENABLED: ${TRAINING_ENABLED:-true}
      GNN_SERVICE_URL: http://ruvector-gnn:8082
      ATTENTION_SERVICE_URL: http://ruvector-attention:8083
    ports:
      - "${SONA_PORT:-8085}:8085"
    depends_on:
      postgres:
        condition: service_healthy
      ruvector-core:
        condition: service_healthy
      ruvector-gnn:
        condition: service_healthy
      ruvector-attention:
        condition: service_healthy
    networks:
      - ruvector-net
    volumes:
      - sona-models:/var/lib/ruvector/sona/models
      - sona-checkpoints:/var/lib/ruvector/sona/checkpoints
      - sona-logs:/var/log/ruvector/sona
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:8085/health || exit 1"]
      interval: 20s
      timeout: 10s
      retries: 3
      start_period: 60s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 4G
        reservations:
          cpus: '1.0'
          memory: 1G
    logging:
      driver: "json-file"
      options:
        max-size: "20m"
        max-file: "5"

# Named Volumes for Data Persistence
volumes:
  pg-data:
    driver: local
    name: ruvector-pg-data
  core-data:
    driver: local
    name: ruvector-core-data
  server-logs:
    driver: local
    name: ruvector-server-logs
  cli-data:
    driver: local
    name: ruvector-cli-data
  gnn-models:
    driver: local
    name: ruvector-gnn-models
  gnn-cache:
    driver: local
    name: ruvector-gnn-cache
  graph-data:
    driver: local
    name: ruvector-graph-data
  graph-logs:
    driver: local
    name: ruvector-graph-logs
  attention-cache:
    driver: local
    name: ruvector-attention-cache
  cluster-data:
    driver: local
    name: ruvector-cluster-data
  cluster-logs:
    driver: local
    name: ruvector-cluster-logs
  sona-models:
    driver: local
    name: ruvector-sona-models
  sona-checkpoints:
    driver: local
    name: ruvector-sona-checkpoints
  sona-logs:
    driver: local
    name: ruvector-sona-logs

# Isolated Network
networks:
  ruvector-net:
    driver: bridge
    name: ruvector-network
    ipam:
      config:
        - subnet: 172.25.0.0/16