docker-compose.yml

# ==============================================================================
# Enterprise Production Multi-Container Orchestration Specification
# Privacy-Preserving Cross-Bank Fraud Detection Consortium (CFI)
# Usage:
#   Quick Start: docker compose up -d --build
#   With Observability: docker compose --profile monitoring up -d --build
# ==============================================================================

services:
  # ── 1. Enterprise Security Gateway & Reverse Proxy ──────────────────────────
  gateway:
    image: nginx:1.27-alpine
    container_name: cfi-gateway
    restart: unless-stopped
    ports:
      - "${CFI_PORT_HTTP:-80}:80"
      - "${CFI_PORT_HTTPS:-443}:443"
    volumes:
      - ./docker/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
    depends_on:
      backend:
        condition: service_healthy
      frontend:
        condition: service_healthy
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1/gateway-health"]
      interval: 10s
      timeout: 3s
      retries: 3

  # ── 2. Frontend Web Container (React 19 SPA) ────────────────────────────────
  frontend:
    build:
      context: .
      dockerfile: docker/Dockerfile.frontend
    image: cfi-intelligence/frontend:latest
    container_name: cfi-frontend
    restart: unless-stopped
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1/health"]
      interval: 10s
      timeout: 3s
      retries: 3

  # ── 3. Database Migration Service (One-Shot Schema Preparation) ───────────────
  migrations:
    build:
      context: .
      dockerfile: docker/Dockerfile.backend
    image: cfi-intelligence/backend:latest
    container_name: cfi-migrations
    restart: "no"
    working_dir: /app/backend
    environment:
      - APP_ENV=${APP_ENV:-production}
      - DATABASE_TYPE=postgres
      - POSTGRES_HOST=postgres
      - POSTGRES_PORT=5432
      - POSTGRES_USER=${POSTGRES_USER}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
      - POSTGRES_DB=${POSTGRES_DB}
      - DATABASE_URL=postgresql+asyncpg://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
      - ALEMBIC_DATABASE_URL=postgresql+asyncpg://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
    command: ["alembic", "upgrade", "head"]
    depends_on:
      postgres:
        condition: service_healthy
    networks:
      - cfi-network

  # ── 4. Backend API & Federated ML Engine ────────────────────────────────────
  backend:
    build:
      context: .
      dockerfile: docker/Dockerfile.backend
    image: cfi-intelligence/backend:latest
    container_name: cfi-api-server
    restart: unless-stopped
    command: ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000", "--workers", "2"]
    ports:
      - "${CFI_PORT_GRPC:-50051}:50051"
    environment:
      - APP_ENV=${APP_ENV:-production}
      - LOG_LEVEL=${LOG_LEVEL:-INFO}
      - DATABASE_TYPE=postgres
      - POSTGRES_HOST=postgres
      - POSTGRES_PORT=5432
      - POSTGRES_USER=${POSTGRES_USER}
      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD}
      - POSTGRES_DB=${POSTGRES_DB}
      - DATABASE_URL=postgresql+asyncpg://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
      - TRAINING_JOB_DB_URL=postgresql://${POSTGRES_USER}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB}
      - REDIS_HOST=redis
      - REDIS_PORT=6379
      - REDIS_PASSWORD=${REDIS_PASSWORD}
      - REDIS_URL=redis://:${REDIS_PASSWORD}@redis:6379/0
      - SECRET_KEY=${SECRET_KEY}
      - OIDC_JWT_SIGNING_SECRET=${OIDC_JWT_SIGNING_SECRET}
      - PAYLOAD_SIGNING_SECRET=${PAYLOAD_SIGNING_SECRET}
      - TRAINING_COORDINATOR_TOKEN=${TRAINING_COORDINATOR_TOKEN}
      - TRAINING_WORKER_TOKEN=${TRAINING_WORKER_TOKEN}
      - IDENTITY_STORE_SECRET=${IDENTITY_STORE_SECRET}
      - CFI_IDENTITY_STORE_SECRET=${IDENTITY_STORE_SECRET}
      - CFI_CONSORTIUM_STORE_SECRET=${CFI_CONSORTIUM_STORE_SECRET}
      - CONSORTIUM_HMAC_SALT=${CONSORTIUM_HMAC_SALT}
      - CFI_REGULATORY_ENVELOPE_SECRET=${CFI_REGULATORY_ENVELOPE_SECRET}
      - CFI_CRON_SECRET=${CFI_CRON_SECRET}
      - CFI_STORAGE_DIR=/app/storage
      - TELEMETRY_ENABLED=true
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://otel-collector:4317
      - KAFKA_BOOTSTRAP_SERVERS=${KAFKA_BOOTSTRAP_SERVERS:-kafka:9092}
      - KAFKA_GROUP_ID=${KAFKA_GROUP_ID:-cfi-fraud-detection-group}
      - KAFKA_TRANSACTION_TOPIC=${KAFKA_TRANSACTION_TOPIC:-org.cfi.finint.transactions.v1}
      - KAFKA_ALERT_TOPIC=${KAFKA_ALERT_TOPIC:-org.cfi.finint.alerts.v1}
      - KAFKA_DLQ_TOPIC=${KAFKA_DLQ_TOPIC:-org.cfi.finint.dlq.v1}
      - KAFKA_ENABLED=${KAFKA_ENABLED:-false}
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
      migrations:
        condition: service_completed_successfully
    volumes:
      - storage-data:/app/storage
      - ./backend/storage/datasets:/app/storage/datasets:ro
      - ./backend/storage/datasets:/app/backend/storage/datasets:ro
      - logs-data:/app/logs
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://127.0.0.1:8000/health"]
      interval: 10s
      timeout: 3s
      start_period: 20s
      retries: 3

  # ── 5. PostgreSQL 16 Enterprise Database ────────────────────────────────────
  postgres:
    image: postgres:16-alpine
    container_name: cfi-postgres
    restart: unless-stopped
    environment:
      POSTGRES_USER: ${POSTGRES_USER}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_DB: ${POSTGRES_DB}
    ports:
      - "${CFI_PORT_PG:-5432}:5432"
    volumes:
      - postgres-data:/var/lib/postgresql/data
      - ./docker/postgres/01-init.sql:/docker-entrypoint-initdb.d/01-init.sql:ro
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-cfi_admin} -d ${POSTGRES_DB:-cfi_fraud_db}"]
      interval: 5s
      timeout: 3s
      retries: 5

  # ── 6. Redis 7.2 Cache & Message Broker ─────────────────────────────────────
  redis:
    image: redis:7.2-alpine
    container_name: cfi-redis
    restart: unless-stopped
    command: >
      redis-server
      --requirepass ${REDIS_PASSWORD}
      --appendonly yes
      --maxmemory 512mb
      --maxmemory-policy volatile-lru
    ports:
      - "${CFI_PORT_REDIS:-6379}:6379"
    volumes:
      - redis-data:/data
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD", "redis-cli", "--no-auth-warning", "-a", "${REDIS_PASSWORD}", "ping"]
      interval: 5s
      timeout: 3s
      retries: 3

  # ── 6. (Optional) OpenTelemetry Collector ───────────────────────────────────
  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.95.0
    container_name: cfi-otel-collector
    profiles: ["monitoring"]
    restart: unless-stopped
    command: ["--config=/etc/otelcol/config.yaml"]
    volumes:
      - ./docker/otel/otel-collector-config.yaml:/etc/otelcol/config.yaml
    ports:
      - "4317:4317"
      - "4318:4318"
      - "8889:8889"
    networks:
      - cfi-network

  # ── 7. (Optional) Prometheus Metrics Engine ─────────────────────────────────
  prometheus:
    image: prom/prometheus:v2.50.1
    container_name: cfi-prometheus
    profiles: ["monitoring"]
    restart: unless-stopped
    volumes:
      - ./docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
      - prometheus-data:/prometheus
    ports:
      - "9090:9090"
    networks:
      - cfi-network

  # ── 8. (Optional) Grafana Operations Dashboard ──────────────────────────────
  grafana:
    image: grafana/grafana-oss:10.3.3
    container_name: cfi-grafana
    profiles: ["monitoring"]
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - ./docker/grafana/provisioning:/etc/grafana/provisioning
      - grafana-data:/var/lib/grafana
    ports:
      - "${CFI_PORT_GRAFANA:-3001}:3000"
    depends_on:
      - prometheus
    networks:
      - cfi-network

  # ── 9. (Optional) HashiCorp Vault KMS / PKI / Transit Engine ────────────────
  vault:
    image: hashicorp/vault:1.16.2
    container_name: cfi-vault
    profiles: ["enterprise"]
    restart: unless-stopped
    ports:
      - "${CFI_PORT_VAULT:-8200}:8200"
    environment:
      VAULT_DEV_ROOT_TOKEN_ID: ${VAULT_TOKEN:-dev-token}
      VAULT_DEV_LISTEN_ADDRESS: "0.0.0.0:8200"
      VAULT_ADDR: "http://0.0.0.0:8200"
    cap_add:
      - IPC_LOCK
    volumes:
      - vault-data:/vault/file
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://127.0.0.1:8200/v1/sys/health || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 3

  # ── 10. (Optional) MinIO S3-Compatible Object Store ─────────────────────────
  minio:
    image: minio/minio:RELEASE.2024-03-05T04-48-44Z
    container_name: cfi-minio
    profiles: ["storage"]
    restart: unless-stopped
    command: server /data --console-address ":9001"
    environment:
      MINIO_ROOT_USER: ${MINIO_ROOT_USER:-cfi_minio_admin}
      MINIO_ROOT_PASSWORD: ${MINIO_ROOT_PASSWORD:-cfi_minio_secret_pass_2026}
    ports:
      - "${CFI_PORT_MINIO:-9000}:9000"
      - "${CFI_PORT_MINIO_CONSOLE:-9001}:9001"
    volumes:
      - minio-data:/data
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://127.0.0.1:9000/minio/health/live || exit 1"]
      interval: 10s
      timeout: 3s
      retries: 3

  # ── 11. (Optional) MLflow Experiment & Artifact Tracking ────────────────────
  mlflow:
    image: ghcr.io/mlflow/mlflow:v2.11.1
    container_name: cfi-mlflow
    profiles: ["ml"]
    restart: unless-stopped
    command: mlflow server --host 0.0.0.0 --port 5000 --backend-store-uri sqlite:////mlflow/mlflow.db --default-artifact-root /mlflow/artifacts
    ports:
      - "${CFI_PORT_MLFLOW:-5000}:5000"
    volumes:
      - mlflow-data:/mlflow
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://127.0.0.1:5000/health || exit 1"]
      interval: 10s
      timeout: 3s
      retries: 3

  # ── 12. Apache Kafka 3.7 Event Streaming Bus (KRaft Mode) ───────────────────
  kafka:
    image: apache/kafka:3.7.0
    container_name: cfi-kafka
    restart: unless-stopped
    ports:
      - "${CFI_PORT_KAFKA:-9092}:9092"
    environment:
      KAFKA_NODE_ID: 1
      KAFKA_PROCESS_ROLES: broker,controller
      KAFKA_LISTENERS: PLAINTEXT://:9092,CONTROLLER://:9093
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092
      KAFKA_CONTROLLER_LISTENER_NAMES: CONTROLLER
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: CONTROLLER:PLAINTEXT,PLAINTEXT:PLAINTEXT
      KAFKA_CONTROLLER_QUORUM_VOTERS: 1@kafka:9093
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
      KAFKA_NUM_PARTITIONS: 3
    volumes:
      - kafka-data:/var/lib/kafka/data
    networks:
      - cfi-network
    healthcheck:
      test: ["CMD-SHELL", "/opt/kafka/bin/kafka-topics.sh --bootstrap-server localhost:9092 --list || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5

networks:
  cfi-network:
    driver: bridge

volumes:
  postgres-data:
  redis-data:
  storage-data:
  logs-data:
  prometheus-data:
  grafana-data:
  minio-data:
  mlflow-data:
  kafka-data:
  vault-data: