docker-compose.extras.yml

# Optional services for advanced local-dev workflows. Pair with
# `docker-compose.yml` via `pnpm run docker:full`.
#
# Same `name:` so `docker compose` treats both files as one project — bring
# them up together and they share the `app_network` and `triggerdotdev-docker`
# volume namespace. Tear down with `pnpm run docker:full:stop`.
#
# Includes:
#   - electric-shard-1:   second Electric instance for multi-shard testing
#   - ch-ui:              ClickHouse browser UI
#   - toxiproxy:          chaos / flake testing
#   - nginx-h2:           HTTP/2 reverse proxy
#   - otel-collector + prometheus + grafana: observability stack
name: triggerdotdev-docker

volumes:
  redis-cluster-data:
  prometheus-data:
  grafana-data:

networks:
  app_network:
    external: false

services:
  electric-shard-1:
    container_name: ${CONTAINER_PREFIX:-}electric-shard-1
    image: electricsql/electric:1.2.4@sha256:20da3d0b0e74926c5623392db67fd56698b9e374c4aeb6cb5cadeb8fea171c36
    restart: always
    environment:
      DATABASE_URL: postgresql://postgres:postgres@database:5432/postgres?sslmode=disable
      ELECTRIC_INSECURE: true
      ELECTRIC_REPLICATION_STREAM_ID: "triggershard1"
    networks:
      - app_network
    ports:
      - "${ELECTRIC_SHARD_1_HOST_PORT:-3061}:3000"
    depends_on:
      - database

  ch-ui:
    image: ghcr.io/caioricciuti/ch-ui:latest@sha256:288abf7103d6e0f45527ee835ee79bd1e0bfb82d55dc514fb3cf43816306b538
    restart: always
    ports:
      - "${CH_UI_HOST_PORT:-5521}:5521"
    environment:
      VITE_CLICKHOUSE_URL: "http://localhost:${CLICKHOUSE_HTTP_HOST_PORT:-8123}"
      VITE_CLICKHOUSE_USER: "default"
      VITE_CLICKHOUSE_PASS: "password"
    networks:
      - app_network

  toxiproxy:
    container_name: ${CONTAINER_PREFIX:-}toxiproxy
    image: ghcr.io/shopify/toxiproxy:latest@sha256:9378ed52a28bc50edc1350f936f518f31fa95f0d15917d6eb40b8e376d1a214e
    restart: always
    volumes:
      - ./config/toxiproxy.json:/config/toxiproxy.json
    ports:
      - "${TOXIPROXY_PROXY_HOST_PORT:-30303}:30303" # Proxied webapp port
      - "${TOXIPROXY_API_HOST_PORT:-8474}:8474" # Toxiproxy API port
    networks:
      - app_network
    command: ["-host", "0.0.0.0", "-config", "/config/toxiproxy.json"]

  nginx-h2:
    image: nginx:1.27@sha256:6784fb0834aa7dbbe12e3d7471e69c290df3e6ba810dc38b34ae33d3c1c05f7d
    container_name: ${CONTAINER_PREFIX:-}nginx-h2
    restart: unless-stopped
    ports:
      - "${NGINX_H2_HOST_PORT:-8443}:8443"
    volumes:
      - ./config/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./config/certs:/etc/nginx/certs:ro
    networks:
      - app_network

  # Observability stack for local development
  otel-collector:
    container_name: ${CONTAINER_PREFIX:-}otel-collector
    image: otel/opentelemetry-collector-contrib:0.96.0@sha256:7ef2a2ff46b9e432321fdd63df104bfeedaf7b4e276950f42c634d0f23521fc4
    restart: always
    command: ["--config", "/etc/otel-collector-config.yaml"]
    volumes:
      - ./config/otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
    ports:
      - "${OTEL_GRPC_HOST_PORT:-4317}:4317" # OTLP gRPC receiver
      - "${OTEL_HTTP_HOST_PORT:-4318}:4318" # OTLP HTTP receiver
      - "${OTEL_PROMETHEUS_HOST_PORT:-8889}:8889" # Prometheus exporter
    networks:
      - app_network

  prometheus:
    container_name: ${CONTAINER_PREFIX:-}prometheus
    image: prom/prometheus:v2.54.1@sha256:f6639335d34a77d9d9db382b92eeb7fc00934be8eae81dbc03b31cfe90411a94
    restart: always
    volumes:
      - ./config/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./config/alerts:/etc/prometheus/alerts:ro
      - prometheus-data:/prometheus
    ports:
      - "${PROMETHEUS_HOST_PORT:-9090}:9090"
    networks:
      - app_network
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--web.enable-lifecycle"

  grafana:
    container_name: ${CONTAINER_PREFIX:-}grafana
    image: grafana/grafana:11.3.0@sha256:a0f881232a6fb71a0554a47d0fe2203b6888fe77f4cefb7ea62bed7eb54e13c3
    restart: always
    volumes:
      - grafana-data:/var/lib/grafana
      - ./config/grafana/provisioning:/etc/grafana/provisioning:ro
    ports:
      - "${GRAFANA_HOST_PORT:-4001}:3000"
    environment:
      GF_SECURITY_ADMIN_USER: admin
      GF_SECURITY_ADMIN_PASSWORD: admin
      GF_USERS_ALLOW_SIGN_UP: false
    networks:
      - app_network
    depends_on:
      - prometheus

  # Six-node Redis cluster (3 masters, 3 replicas) for validating the execution-snapshot store.
  # The store's single-slot guarantee only means anything against a cluster-mode endpoint, and the
  # recovery worker's per-master fan-out is unreachable on a single node.
  #
  #   RUN_ENGINE_SNAPSHOT_STORE_REDIS_HOST=127.0.0.1
  #   RUN_ENGINE_SNAPSHOT_STORE_REDIS_PORT=7001
  #   RUN_ENGINE_SNAPSHOT_STORE_REDIS_CLUSTER_MODE_ENABLED=1
  #
  # ioredis discovers the other five nodes from that one seed.
  redis-cluster:
    container_name: ${CONTAINER_PREFIX:-}redis-cluster
    image: redis:7.2@sha256:74566c6910d13ae61e7ce73ebd3127438a1fe805b309b097c323142719ec8a5b
    restart: always
    volumes:
      - ./config/redis-cluster-init.sh:/init.sh:ro
      - redis-cluster-data:/data
    command: sh /init.sh
    ports:
      - "${REDIS_CLUSTER_PORT_1:-7001}:7001"
      - "${REDIS_CLUSTER_PORT_2:-7002}:7002"
      - "${REDIS_CLUSTER_PORT_3:-7003}:7003"
      - "${REDIS_CLUSTER_PORT_4:-7004}:7004"
      - "${REDIS_CLUSTER_PORT_5:-7005}:7005"
      - "${REDIS_CLUSTER_PORT_6:-7006}:7006"
      - "17001:17001"
      - "17002:17002"
      - "17003:17003"
      - "17004:17004"
      - "17005:17005"
      - "17006:17006"
    healthcheck:
      test: ["CMD-SHELL", "redis-cli -p 7001 cluster info | grep -q cluster_state:ok"]
      interval: 5s
      timeout: 3s
      retries: 20