docker-compose.yml

# =============================================================================
# TelemetryFlow Platform - Docker Compose Configuration
# =============================================================================
#
# PROFILES:
#   core        - Infrastructure services (Postgres, ClickHouse, Redis, NATS)
#                 plus backend and frontend
#   monitoring  - OpenTelemetry Collector, TFO-Agent
#   tools       - Portainer management UI
#   all         - Everything: core + monitoring + tools
#   all-in      - Core with OTEL-instrumented backend/frontend variants
#
# USAGE EXAMPLES:
#   # Start core platform only (dev default):
#   docker compose --profile core up -d
#
#   # Start with monitoring stack:
#   docker compose --profile core --profile monitoring up -d
#
#   # Start everything:
#   docker compose --profile all up -d
#
#   # Start all-in-one with built-in OTEL instrumentation:
#   docker compose --profile all-in --profile monitoring --profile tools up -d
#
# QUICK START:
#   1. Copy .env.example to .env:
#      cp .env.example .env
#   2. Generate secrets:
#      sed -i '' 's/^JWT_SECRET=$/JWT_SECRET='$(openssl rand -hex 32)'/' .env
#      sed -i '' 's/^SESSION_SECRET=$/SESSION_SECRET='$(openssl rand -hex 32)'/' .env
#   3. Start the platform:
#      docker compose --profile core up -d
#   4. Access:
#      Frontend  -> http://localhost:${FRONTEND_PORT:-8080}
#      Backend   -> http://localhost:${BACKEND_PORT:-3000}
#      Portainer -> http://localhost:${PORTAINER_PORT:-9000} (tools profile)
#
# =============================================================================

networks:
  telemetryflow_platform_net:
    driver: bridge
    ipam:
      config:
        - subnet: 172.151.0.0/16

volumes:
  postgres_data:
    driver: local
  clickhouse_data:
    driver: local
  redis_data:
    driver: local
  nats_data:
    driver: local
  portainer_data:
    driver: local
  backend_logs:
    driver: local

services:

  # ===========================================================================
  # INFRASTRUCTURE SERVICES (profiles: core, all)
  # ===========================================================================

  postgres:
    image: postgres:${POSTGRES_VERSION:-16-alpine}
    profiles: ["core", "all"]
    container_name: ${POSTGRES_CONTAINER_NAME:-telemetryflow-postgres}
    restart: unless-stopped
    environment:
      POSTGRES_DB: ${POSTGRES_DB:-telemetryflow}
      POSTGRES_USER: ${POSTGRES_USER:-telemetryflow}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-}
      PGDATA: /var/lib/postgresql/data/pgdata
    ports:
      - "${POSTGRES_PORT:-5432}:5432"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/postgres/data:/var/lib/postgresql/data
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${POSTGRES_IP:-172.151.151.20}
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-telemetryflow} -d ${POSTGRES_DB:-telemetryflow}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s

  clickhouse:
    image: clickhouse/clickhouse-server:${CLICKHOUSE_VERSION:-latest}
    profiles: ["core", "all"]
    container_name: ${CLICKHOUSE_CONTAINER_NAME:-telemetryflow-clickhouse}
    restart: unless-stopped
    environment:
      CLICKHOUSE_DB: ${CLICKHOUSE_DB:-telemetryflow}
      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-default}
      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-}
      CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT: 1
    ports:
      - "${CLICKHOUSE_HTTP_PORT:-8123}:8123"
      - "${CLICKHOUSE_TCP_PORT:-9000}:9000"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/clickhouse/data:/var/lib/clickhouse
      - ${VOLUMES_BASE_PATH:-./volumes}/clickhouse/logs:/var/log/clickhouse-server
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${CLICKHOUSE_IP:-172.151.151.40}
    healthcheck:
      test: ["CMD-SHELL", "wget --spider --tries 1 http://localhost:8123/ping || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    ulimits:
      nofile:
        soft: 262144
        hard: 262144

  redis:
    image: redis:${REDIS_VERSION:-7-alpine}
    profiles: ["core", "all"]
    container_name: ${REDIS_CONTAINER_NAME:-telemetryflow-redis}
    restart: unless-stopped
    command: >
      redis-server
      --requirepass ${REDIS_PASSWORD:-}
      --maxmemory ${REDIS_MAXMEMORY:-256mb}
      --maxmemory-policy allkeys-lru
      --appendonly yes
    ports:
      - "${REDIS_PORT:-6379}:6379"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/redis/data:/data
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${REDIS_IP:-172.151.151.50}
    healthcheck:
      test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD:-}", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s

  nats:
    image: nats:${NATS_VERSION:-2-alpine}
    profiles: ["core", "all"]
    container_name: ${NATS_CONTAINER_NAME:-telemetryflow-nats}
    restart: unless-stopped
    command: >
      -js
      --store_dir /data
      --cluster_name ${NATS_CLUSTER_NAME:-telemetryflow-cluster}
      --max_mem_store ${NATS_MAX_MEM_STORE:-256MB}
      --max_file_store ${NATS_MAX_FILE_STORE:-1GB}
    ports:
      - "${NATS_CLIENT_PORT:-4222}:4222"
      - "${NATS_MANAGEMENT_PORT:-8222}:8222"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/nats/data:/data
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${NATS_IP:-172.151.151.55}
    healthcheck:
      test: ["CMD-SHELL", "wget --spider --tries 1 http://localhost:8222/healthz || exit 1"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 15s

  # ===========================================================================
  # APPLICATION SERVICES (profiles: core, all-in)
  # ===========================================================================

  backend:
    image: ${BACKEND_IMAGE:-telemetryflow/telemetryflow-platform}:${BACKEND_VERSION:-latest}
    profiles: ["core"]
    container_name: ${BACKEND_CONTAINER_NAME:-telemetryflow-backend}
    restart: unless-stopped
    env_file:
      - .env
    environment:
      NODE_ENV: ${NODE_ENV:-development}
      PORT: 3000
      POSTGRES_HOST: ${POSTGRES_IP:-172.151.151.20}
      POSTGRES_PORT: 5432
      POSTGRES_DB: ${POSTGRES_DB:-telemetryflow}
      POSTGRES_USER: ${POSTGRES_USER:-telemetryflow}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-}
      CLICKHOUSE_HOST: ${CLICKHOUSE_IP:-172.151.151.40}
      CLICKHOUSE_PORT: 9000
      CLICKHOUSE_DB: ${CLICKHOUSE_DB:-telemetryflow}
      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-default}
      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-}
      REDIS_HOST: ${REDIS_IP:-172.151.151.50}
      REDIS_PORT: 6379
      REDIS_PASSWORD: ${REDIS_PASSWORD:-}
      NATS_URL: nats://${NATS_IP:-172.151.151.55}:4222
      JWT_SECRET: ${JWT_SECRET:-}
      SESSION_SECRET: ${SESSION_SECRET:-}
      LLM_ENCRYPTION_KEY: ${LLM_ENCRYPTION_KEY:-}
      API_KEY: ${API_KEY:-}
      CORS_ORIGIN: ${CORS_ORIGIN:-http://localhost:${FRONTEND_PORT:-8080}}
    ports:
      - "${BACKEND_PORT:-3000}:3000"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/backend/logs:/app/logs
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${BACKEND_IP:-172.151.151.10}
    depends_on:
      postgres:
        condition: service_healthy
      clickhouse:
        condition: service_healthy
      redis:
        condition: service_healthy
      nats:
        condition: service_healthy

  backend-with-monitoring:
    image: ${BACKEND_IMAGE:-telemetryflow/telemetryflow-platform}:${BACKEND_VERSION:-latest}
    profiles: ["all-in"]
    container_name: ${BACKEND_CONTAINER_NAME:-telemetryflow-backend}-monitored
    restart: unless-stopped
    env_file:
      - .env
    environment:
      NODE_ENV: ${NODE_ENV:-development}
      PORT: 3000
      OTEL_ENABLED: "true"
      OTEL_SERVICE_NAME: ${OTEL_SERVICE_NAME:-telemetryflow-backend}
      OTEL_EXPORTER_OTLP_ENDPOINT: http://${TFO_COLLECTOR_IP:-172.151.151.30}:4317
      OTEL_EXPORTER_OTLP_PROTOCOL: ${OTEL_EXPORTER_OTLP_PROTOCOL:-grpc}
      POSTGRES_HOST: ${POSTGRES_IP:-172.151.151.20}
      POSTGRES_PORT: 5432
      POSTGRES_DB: ${POSTGRES_DB:-telemetryflow}
      POSTGRES_USER: ${POSTGRES_USER:-telemetryflow}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-}
      CLICKHOUSE_HOST: ${CLICKHOUSE_IP:-172.151.151.40}
      CLICKHOUSE_PORT: 9000
      CLICKHOUSE_DB: ${CLICKHOUSE_DB:-telemetryflow}
      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-default}
      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-}
      REDIS_HOST: ${REDIS_IP:-172.151.151.50}
      REDIS_PORT: 6379
      REDIS_PASSWORD: ${REDIS_PASSWORD:-}
      NATS_URL: nats://${NATS_IP:-172.151.151.55}:4222
      JWT_SECRET: ${JWT_SECRET:-}
      SESSION_SECRET: ${SESSION_SECRET:-}
      LLM_ENCRYPTION_KEY: ${LLM_ENCRYPTION_KEY:-}
      API_KEY: ${API_KEY:-}
      CORS_ORIGIN: ${CORS_ORIGIN:-http://localhost:${FRONTEND_PORT:-8080}}
    ports:
      - "${BACKEND_PORT:-3000}:3000"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/backend/logs:/app/logs
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${BACKEND_IP:-172.151.151.10}
    depends_on:
      postgres:
        condition: service_healthy
      clickhouse:
        condition: service_healthy
      redis:
        condition: service_healthy
      nats:
        condition: service_healthy
      tfo-collector:
        condition: service_started

  frontend:
    image: ${FRONTEND_IMAGE:-telemetryflow/telemetryflow-viz}:${FRONTEND_VERSION:-latest}
    profiles: ["core"]
    container_name: ${FRONTEND_CONTAINER_NAME:-telemetryflow-frontend}
    restart: unless-stopped
    environment:
      VITE_APP_TITLE: ${VITE_APP_TITLE:-TelemetryFlow}
      VITE_API_BASE_URL: ${VITE_API_BASE_URL:-http://localhost:${BACKEND_PORT:-3000}}
      VITE_API_KEY: ${VITE_API_KEY:-}
      VITE_MOCK_DATA_ENABLED: ${VITE_MOCK_DATA_ENABLED:-false}
      VITE_REFRESH_INTERVAL_MS: ${VITE_REFRESH_INTERVAL_MS:-30000}
    ports:
      - "${FRONTEND_PORT:-8080}:80"
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${FRONTEND_IP:-172.151.151.15}
    depends_on:
      backend:
        condition: service_started

  frontend-with-monitoring:
    image: ${FRONTEND_IMAGE:-telemetryflow/telemetryflow-viz}:${FRONTEND_VERSION:-latest}
    profiles: ["all-in"]
    container_name: ${FRONTEND_CONTAINER_NAME:-telemetryflow-frontend}-monitored
    restart: unless-stopped
    environment:
      VITE_APP_TITLE: ${VITE_APP_TITLE:-TelemetryFlow}
      VITE_API_BASE_URL: ${VITE_API_BASE_URL:-http://localhost:${BACKEND_PORT:-3000}}
      VITE_API_KEY: ${VITE_API_KEY:-}
      VITE_MOCK_DATA_ENABLED: ${VITE_MOCK_DATA_ENABLED:-false}
      VITE_REFRESH_INTERVAL_MS: ${VITE_REFRESH_INTERVAL_MS:-30000}
      VITE_OTEL_ENABLED: "true"
      VITE_OTEL_SERVICE_NAME: ${VITE_OTEL_SERVICE_NAME:-telemetryflow-frontend}
      VITE_OTEL_COLLECTOR_URL: http://${TFO_COLLECTOR_IP:-172.151.151.30}:4318/v1/traces
    ports:
      - "${FRONTEND_PORT:-8080}:80"
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${FRONTEND_IP:-172.151.151.15}
    depends_on:
      backend-with-monitoring:
        condition: service_started

  # ===========================================================================
  # MONITORING SERVICES (profiles: monitoring, all)
  # ===========================================================================

  tfo-collector:
    image: telemetryflow/telemetryflow-collector:${TFO_COLLECTOR_VERSION:-1.2.1}
    profiles: ["monitoring", "all", "all-in"]
    container_name: ${TFO_COLLECTOR_CONTAINER_NAME:-telemetryflow-collector}
    restart: unless-stopped
    environment:
      COLLECTOR_CONFIG: ${COLLECTOR_CONFIG:-/etc/otelcol/config.yaml}
      CLICKHOUSE_HOST: ${CLICKHOUSE_IP:-172.151.151.40}
      CLICKHOUSE_PORT: 9000
      CLICKHOUSE_DB: ${CLICKHOUSE_DB:-telemetryflow}
      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-default}
      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-}
    ports:
      - "${OTEL_GRPC_PORT:-4317}:4317"
      - "${OTEL_HTTP_PORT:-4318}:4318"
      - "${OTEL_METRICS_PORT:-8889}:8889"
      - "${OTEL_HEALTH_PORT:-13133}:13133"
    volumes:
      - ${VOLUMES_BASE_PATH:-./volumes}/collector/config:/etc/otelcol
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${TFO_COLLECTOR_IP:-172.151.151.30}

  tfo-agent:
    image: telemetryflow/telemetryflow-agent:${TFO_AGENT_VERSION:-1.2.0}
    profiles: ["monitoring", "all"]
    container_name: ${TFO_AGENT_CONTAINER_NAME:-telemetryflow-agent}
    restart: unless-stopped
    environment:
      TFO_AGENT_VERSION: ${TFO_AGENT_VERSION:-1.2.0}
      TFO_COLLECTOR_URL: http://${TFO_COLLECTOR_IP:-172.151.151.30}:4317
      TFO_AGENT_SCRAPE_INTERVAL: ${TFO_AGENT_SCRAPE_INTERVAL:-15s}
      TFO_AGENT_LOG_LEVEL: ${TFO_AGENT_LOG_LEVEL:-info}
      HOST_PROC: /host/proc
      HOST_SYS: /host/sys
    ports:
      - "${TFO_AGENT_PORT:-2025}:2025"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /var/log:/var/log:ro
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${TFO_AGENT_IP:-172.151.151.35}

  # ===========================================================================
  # TOOLS (profiles: tools, all)
  # ===========================================================================

  portainer:
    image: portainer/portainer-ce:${PORTAINER_VERSION:-latest}
    profiles: ["tools", "all"]
    container_name: ${PORTAINER_CONTAINER_NAME:-telemetryflow-portainer}
    restart: unless-stopped
    command: --no-auth
    ports:
      - "${PORTAINER_PORT:-9000}:9000"
      - "${PORTAINER_TUNNEL_PORT:-9443}:9443"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - ${VOLUMES_BASE_PATH:-./volumes}/portainer/data:/data
    networks:
      telemetryflow_platform_net:
        ipv4_address: ${PORTAINER_IP:-172.151.151.5}