docker-compose.dev.yml

# docker-compose.dev.yml — Development stack with ALL components enabled.
# Usage:  docker compose -f docker-compose.dev.yml up --build
#
# Includes: API, Web (Nginx), Notification Worker, Export Worker, Automation Worker,
#           PostgreSQL, Redis, Mosquitto, Grafana, Tempo + Jaeger (tracing).
# All tracing and telemetry features are enabled by default.
#
# ⚠️  TimescaleDB-HA migration (ADR-007):
#   This compose file was migrated to timescale/timescaledb-ha:pg17.
#   If upgrading from a postgres:17-alpine deployment, you MUST wipe the volume:
#       docker compose -f docker-compose.dev.yml down
#       docker volume rm teslasync_dev_postgres_data
#       docker compose -f docker-compose.dev.yml up -d
#   Existing data is replaced; staging losses accepted per ADR-009.

services:
  teslasync-api:
    build:
      context: .
      dockerfile: Dockerfile
      args:
        VERSION: dev
    container_name: teslasync-api-dev
    restart: unless-stopped
    ports:
      - "8080:8080"
    environment:
      - TESLASYNC_PORT=8080
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_USER=teslasync
      - DATABASE_PASS=teslasync
      - DATABASE_NAME=teslasync
      - DATABASE_SSLMODE=disable
      - DATABASE_MAX_CONNS=12
      - DATABASE_MIN_CONNS=2
      - DATABASE_HEALTH_CHECK_PERIOD=30s
      - MQTT_HOST=mosquitto
      - MQTT_PORT=1883
      - REDIS_HOST=redis
      - REDIS_PORT=6379
      - TESLA_CLIENT_ID=${TESLA_CLIENT_ID:-dev-client-id}
      - TESLA_CLIENT_SECRET=${TESLA_CLIENT_SECRET:-dev-client-secret}
      - TESLA_REDIRECT_URI=http://localhost:8080/api/v1/auth/callback
      - TESLA_API_BASE_URL=${TESLA_API_BASE_URL:-https://fleet-api.prd.na.vn.cloud.tesla.com}
      - WORKER_POLL_INTERVAL=30s
      - TESLASYNC_LOG_LEVEL=error
      - FLEET_TELEMETRY_ENABLED=${FLEET_TELEMETRY_ENABLED:-false}
      - FLEET_TELEMETRY_HOST=${FLEET_TELEMETRY_HOST:-}
      - FLEET_TELEMETRY_PORT=4443
      - FLEET_TELEMETRY_TOPIC_BASE=telemetry
      - FLEET_TELEMETRY_BATCH_MS=100
      - FLEET_TELEMETRY_BATCH_MAX_MESSAGES=256
      - FLEET_TELEMETRY_PERSISTENCE_CONCURRENCY=2
      - FLEET_TELEMETRY_PERSISTENCE_QUEUE_CAPACITY=64
      - FLEET_TELEMETRY_PERSISTENCE_TIMEOUT=30s
      - FLEET_TELEMETRY_STALE_TIMEOUT=15m
      - FLEET_TELEMETRY_FALLBACK_POLL_INTERVAL=5m
      - FLEET_TELEMETRY_SNAPSHOT_WRITE_INTERVAL=10s
      - FLEET_TELEMETRY_CLEANUP_INTERVAL=2m
      - FLEET_TELEMETRY_STALE_SESSION_TIMEOUT=5m
      # Tracing enabled by default in dev
      - OTEL_ENABLED=true
      - OTEL_ENDPOINT=otel-collector:4317
      - OTEL_SERVICE_NAME=teslasync-api
      - OTEL_INSECURE=true
      - GOOGLE_MAPS_API_KEY=${GOOGLE_MAPS_API_KEY:-}
      - AZURE_MAPS_API_KEY=${AZURE_MAPS_API_KEY:-}
    depends_on:
      postgres:
        condition: service_healthy
      mosquitto:
        condition: service_started
      redis:
        condition: service_healthy
      otel-collector:
        condition: service_started
    healthcheck:
      test: ["CMD", "/usr/local/bin/teslasync", "healthcheck"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s

  web:
    build:
      context: .
      dockerfile: Dockerfile.web
    container_name: teslasync-web-dev
    restart: unless-stopped
    ports:
      - "3000:80"
    depends_on:
      teslasync-api:
        condition: service_healthy

  notification-worker:
    build:
      context: .
      dockerfile: Dockerfile.notification
      args:
        VERSION: dev
    container_name: teslasync-notification-worker-dev
    restart: unless-stopped
    environment:
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_USER=teslasync
      - DATABASE_PASS=teslasync
      - DATABASE_NAME=teslasync
      - DATABASE_SSLMODE=disable
      - DATABASE_MAX_CONNS=2
      - DATABASE_MIN_CONNS=1
      - DATABASE_HEALTH_CHECK_PERIOD=30s
      - MQTT_HOST=mosquitto
      - MQTT_PORT=1883
      - TESLASYNC_LOG_LEVEL=error
      - HEALTH_PORT=8081
      - OTEL_ENABLED=true
      - OTEL_ENDPOINT=otel-collector:4317
      - OTEL_SERVICE_NAME=teslasync-notification-worker
      - OTEL_INSECURE=true
    depends_on:
      postgres:
        condition: service_healthy
      mosquitto:
        condition: service_started
      otel-collector:
        condition: service_started
    healthcheck:
      test: ["CMD", "/usr/local/bin/notification-worker", "healthcheck"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s

  export-worker:
    build:
      context: .
      dockerfile: Dockerfile.export-worker
      args:
        VERSION: dev
    container_name: teslasync-export-worker-dev
    restart: unless-stopped
    environment:
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_USER=teslasync
      - DATABASE_PASS=teslasync
      - DATABASE_NAME=teslasync
      - DATABASE_SSLMODE=disable
      - DATABASE_MAX_CONNS=2
      - DATABASE_MIN_CONNS=1
      - DATABASE_HEALTH_CHECK_PERIOD=30s
      - MQTT_HOST=mosquitto
      - MQTT_PORT=1883
      - TESLASYNC_LOG_LEVEL=error
      - HEALTH_PORT=8082
      - OTEL_ENABLED=true
      - OTEL_ENDPOINT=otel-collector:4317
      - OTEL_SERVICE_NAME=teslasync-export-worker
      - OTEL_INSECURE=true
    depends_on:
      postgres:
        condition: service_healthy
      mosquitto:
        condition: service_started
      otel-collector:
        condition: service_started
    healthcheck:
      test: ["CMD", "/usr/local/bin/export-worker", "healthcheck"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s

  automation-worker:
    build:
      context: .
      dockerfile: Dockerfile.automation
      args:
        VERSION: dev
    container_name: teslasync-automation-worker-dev
    restart: unless-stopped
    environment:
      - DATABASE_HOST=postgres
      - DATABASE_PORT=5432
      - DATABASE_USER=teslasync
      - DATABASE_PASS=teslasync
      - DATABASE_NAME=teslasync
      - DATABASE_SSLMODE=disable
      - DATABASE_MAX_CONNS=2
      - DATABASE_MIN_CONNS=1
      - DATABASE_HEALTH_CHECK_PERIOD=30s
      - MQTT_HOST=mosquitto
      - MQTT_PORT=1883
      - TESLA_CLIENT_ID=${TESLA_CLIENT_ID:-dev-client-id}
      - TESLA_CLIENT_SECRET=${TESLA_CLIENT_SECRET:-dev-client-secret}
      - TESLA_API_BASE_URL=${TESLA_API_BASE_URL:-https://fleet-api.prd.na.vn.cloud.tesla.com}
      - TESLASYNC_LOG_LEVEL=error
      - HEALTH_PORT=8083
      - OTEL_ENABLED=true
      - OTEL_ENDPOINT=otel-collector:4317
      - OTEL_SERVICE_NAME=teslasync-automation-worker
      - OTEL_INSECURE=true
    depends_on:
      postgres:
        condition: service_healthy
      mosquitto:
        condition: service_started
      otel-collector:
        condition: service_started
    healthcheck:
      test: ["CMD", "/usr/local/bin/automation-worker", "healthcheck"]
      interval: 15s
      timeout: 5s
      retries: 3
      start_period: 10s

  # ── Infrastructure ────────────────────────────────────────

  postgres:
    # ⚠️  TimescaleDB-HA migration (ADR-007):
    #   Migrated from postgres:17-alpine to timescale/timescaledb-ha:pg17.
    #   If upgrading an existing deployment, you MUST wipe the volume:
    #       docker compose -f docker-compose.dev.yml down
    #       docker volume rm teslasync_dev_postgres_data
    #       docker compose -f docker-compose.dev.yml up -d
    #   Existing data is replaced; staging losses accepted per ADR-009.
    image: timescale/timescaledb-ha:pg17
    container_name: teslasync-postgres-dev
    restart: unless-stopped
    command: ["postgres", "-c", "max_connections=50", "-c", "shared_buffers=128MB", "-c", "effective_cache_size=512MB", "-c", "maintenance_work_mem=64MB", "-c", "shared_preload_libraries=timescaledb,pg_stat_statements,pg_textsearch", "-c", "pg_stat_statements.track=all"]
    ports:
      - "5432:5432"
    environment:
      - POSTGRES_USER=teslasync
      - POSTGRES_PASSWORD=teslasync
      - POSTGRES_DB=teslasync
      - PGDATA=/home/postgres/pgdata/data
    volumes:
      - dev_postgres_data:/home/postgres/pgdata
      - ./scripts/init-timescaledb.sql:/docker-entrypoint-initdb.d/00-init-timescaledb.sql:ro
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U teslasync"]
      interval: 5s
      timeout: 3s
      retries: 5

  redis:
    image: redis:7-alpine
    container_name: teslasync-redis-dev
    restart: unless-stopped
    ports:
      - "6379:6379"
    volumes:
      - dev_redis_data:/data
    command: redis-server --appendonly yes --maxmemory 128mb --maxmemory-policy noeviction
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5

  mosquitto:
    image: eclipse-mosquitto:2
    container_name: teslasync-mosquitto-dev
    restart: unless-stopped
    ports:
      - "1883:1883"
      - "9001:9001"
    volumes:
      - dev_mosquitto_data:/mosquitto/data
      - ./mosquitto.conf:/mosquitto/config/mosquitto.conf
    healthcheck:
      test: ["CMD", "mosquitto_sub", "-t", "$$SYS/#", "-C", "1", "-i", "healthcheck", "-W", "3"]
      interval: 15s
      timeout: 5s
      retries: 3

  grafana:
    image: grafana/grafana:10.4.0
    container_name: teslasync-grafana-dev
    restart: unless-stopped
    ports:
      - "3001:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=admin
      - GF_SECURITY_ADMIN_PASSWORD=teslasync
      - GF_INSTALL_PLUGINS=grafana-clock-panel
      - POSTGRES_HOST=postgres
      - POSTGRES_PORT=5432
      - POSTGRES_USER=teslasync
      - POSTGRES_PASSWORD=teslasync
      - POSTGRES_DB=teslasync
      - PROMETHEUS_URL=http://prometheus:9090
    volumes:
      - dev_grafana_data:/var/lib/grafana
      - ./grafana/custom.ini:/etc/grafana/grafana.ini:ro
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards
    depends_on:
      postgres:
        condition: service_healthy
      prometheus:
        condition: service_started

  prometheus:
    image: prom/prometheus:v2.51.0
    container_name: teslasync-prometheus-dev
    restart: unless-stopped
    ports:
      - "9099:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./helm/teslasync/files/prometheus/recording-rules.yaml:/etc/prometheus/rules/recording-rules.yaml:ro
      - ./helm/teslasync/files/prometheus/alerting-rules.yaml:/etc/prometheus/rules/alerting-rules.yaml:ro
      - dev_prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=15d'
      - '--web.enable-remote-write-receiver'
      - '--enable-feature=exemplar-storage'

  # ── Observability ─────────────────────────────────────────

  jaeger:
    image: jaegertracing/all-in-one:1.57
    container_name: teslasync-jaeger-dev
    restart: unless-stopped
    ports:
      - "16686:16686"   # Jaeger UI
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    deploy:
      resources:
        limits:
          memory: 256M

  tempo:
    image: grafana/tempo:2.7.0
    container_name: teslasync-tempo-dev
    restart: unless-stopped
    command:
      - "-config.file=/etc/tempo/config.yaml"
    ports:
      - "3200:3200"
    volumes:
      - ./observability/tempo/config.yaml:/etc/tempo/config.yaml:ro
      - dev_tempo_data:/var/tempo
    depends_on:
      prometheus:
        condition: service_started

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.103.1
    container_name: teslasync-otel-collector-dev
    restart: unless-stopped
    command:
      - "--config=/etc/otelcol/config.yaml"
    volumes:
      - ./observability/otel-collector/config.yaml:/etc/otelcol/config.yaml:ro
    ports:
      - "4317:4317"
      - "4318:4318"
      - "9464:9464"
    depends_on:
      jaeger:
        condition: service_started
      tempo:
        condition: service_started
    deploy:
      resources:
        limits:
          memory: 256M

volumes:
  dev_postgres_data:
  dev_redis_data:
  dev_mosquitto_data:
  dev_grafana_data:
  dev_prometheus_data:
  dev_tempo_data: