proffesor-for-testing__agentic-qe/config/docker-compose.otel.yml

version: '3.8'

# OTEL Observability Stack for Agentic QE Fleet
# Issue #71: Complete OTEL Stack Docker Compose Configuration
#
# This compose file sets up a complete observability stack:
# - OTEL Collector: Receives telemetry via OTLP (gRPC:4317, HTTP:4318)
# - Prometheus: Scrapes metrics from OTEL Collector (port 9090)
# - Jaeger: Distributed tracing backend (UI on port 16686)
# - Grafana: Visualization and dashboards (port 3001)
#
# Usage:
#   docker-compose -f config/docker-compose.otel.yml up -d
#   docker-compose -f docker-compose.yml -f config/docker-compose.otel.yml up -d

services:
  # OpenTelemetry Collector
  otel-collector:
    image: otel/opentelemetry-collector-contrib:latest
    container_name: agentic-qe-otel-collector
    command: ["--config=/etc/otel-collector-config.yaml"]
    volumes:
      - ./otel-collector-config.yaml.example:/etc/otel-collector-config.yaml:ro
      - otel-data:/var/log/otel
    ports:
      # OTLP gRPC receiver
      - "4317:4317"
      # OTLP HTTP receiver
      - "4318:4318"
      # Prometheus exporter
      - "8889:8889"
      # Collector metrics (self-monitoring)
      - "8888:8888"
      # Health check endpoint
      - "13133:13133"
      # pprof profiling (development only)
      - "1777:1777"
      # zpages debug interface (development only)
      - "55679:55679"
    environment:
      - DEPLOYMENT_ENVIRONMENT=${DEPLOYMENT_ENVIRONMENT:-development}
    networks:
      - agentic-qe-otel
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:13133/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  # Prometheus - Metrics storage and querying
  prometheus:
    image: prom/prometheus:latest
    container_name: agentic-qe-prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=15d'
      - '--storage.tsdb.retention.size=10GB'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    volumes:
      - ./prometheus.yml.example:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
      # Optionally mount alerting rules
      # - ./prometheus-rules:/etc/prometheus/rules:ro
    ports:
      - "9090:9090"
    networks:
      - agentic-qe-otel
    restart: unless-stopped
    depends_on:
      otel-collector:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  # Jaeger - Distributed tracing backend
  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: agentic-qe-jaeger
    environment:
      # Collector settings
      - COLLECTOR_OTLP_ENABLED=true
      - COLLECTOR_ZIPKIN_HOST_PORT=:9411
      # Storage settings (in-memory for development)
      - SPAN_STORAGE_TYPE=badger
      - BADGER_EPHEMERAL=false
      - BADGER_DIRECTORY_VALUE=/badger/data
      - BADGER_DIRECTORY_KEY=/badger/key
      # Query settings
      - QUERY_BASE_PATH=/
      # Metrics backend
      - METRICS_BACKEND=prometheus
      - METRICS_HTTP_ROUTE=/metrics
    volumes:
      - jaeger-data:/badger
    ports:
      # Jaeger UI
      - "16686:16686"
      # OTLP gRPC receiver
      - "4327:4317"
      # OTLP HTTP receiver
      - "4328:4318"
      # Zipkin compatible endpoint
      - "9411:9411"
      # Admin port (health check, metrics)
      - "14269:14269"
      # Jaeger Thrift compact
      - "6831:6831/udp"
      # Jaeger Thrift binary
      - "6832:6832/udp"
      # Jaeger gRPC
      - "14250:14250"
    networks:
      - agentic-qe-otel
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:14269/"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  # Grafana - Visualization and dashboards
  grafana:
    image: grafana/grafana:latest
    container_name: agentic-qe-grafana
    environment:
      # Admin credentials (change in production!)
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      # Server settings
      - GF_SERVER_ROOT_URL=http://localhost:3001
      - GF_SERVER_SERVE_FROM_SUB_PATH=false
      # Enable anonymous access (development only)
      - GF_AUTH_ANONYMOUS_ENABLED=false
      # Provisioning
      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
      # Plugins
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource
    volumes:
      # Datasource provisioning
      - ./grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      # Dashboard provisioning
      - ./grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
      # Dashboard JSON files
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      # Persistent storage
      - grafana-data:/var/lib/grafana
    ports:
      - "3001:3000"
    networks:
      - agentic-qe-otel
    restart: unless-stopped
    depends_on:
      prometheus:
        condition: service_healthy
      jaeger:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

volumes:
  otel-data:
    driver: local
  prometheus-data:
    driver: local
  jaeger-data:
    driver: local
  grafana-data:
    driver: local

networks:
  agentic-qe-otel:
    driver: bridge
    name: agentic-qe-otel