# Docker Compose workload harness for Phase 10 telemetry validation.
#
# Runs a 5-node validator cluster with full OTel telemetry stack:
#   - 5 rippled validator nodes (consensus network)
#   - OTel Collector (traces + StatsD metrics)
#   - Jaeger (trace search UI)
#   - Tempo (production trace backend)
#   - Prometheus (metrics)
#   - Loki (log aggregation for log-trace correlation)
#   - Grafana (dashboards + trace/log exploration)
#
# Usage:
#   # Start the harness (requires pre-built xrpld image or mount binary):
#   docker compose -f docker/telemetry/docker-compose.workload.yaml up -d
#
#   # Or use the orchestrator:
#   docker/telemetry/workload/run-full-validation.sh
#
# Prerequisites:
#   - xrpld binary built with -DXRPL_ENABLE_TELEMETRY=ON
#   - Validator keys generated via generate-validator-keys.sh
#   - Node configs generated by run-full-validation.sh

version: "3.8"

services:
  # ---------------------------------------------------------------------------
  # Telemetry Backend Stack
  # ---------------------------------------------------------------------------

  otel-collector:
    image: otel/opentelemetry-collector-contrib:latest
    command: ["--config=/etc/otel-collector-config.yaml"]
    ports:
      - "4317:4317" # OTLP gRPC
      - "4318:4318" # OTLP HTTP
      - "8125:8125/udp" # StatsD UDP (beast::insight metrics)
      - "8889:8889" # Prometheus metrics endpoint
      - "13133:13133" # Health check
    volumes:
      - ../otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
    depends_on:
      - jaeger
      - tempo
    networks:
      - workload-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:13133/"]
      interval: 5s
      timeout: 3s
      retries: 10

  jaeger:
    image: jaegertracing/all-in-one:latest
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    ports:
      - "16686:16686" # Jaeger UI
      - "14250:14250" # gRPC
    networks:
      - workload-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:16686/"]
      interval: 5s
      timeout: 3s
      retries: 10

  tempo:
    image: grafana/tempo:2.7.2
    command: ["-config.file=/etc/tempo.yaml"]
    ports:
      - "3200:3200" # Tempo HTTP API
    volumes:
      - ../tempo.yaml:/etc/tempo.yaml:ro
      - tempo-data:/var/tempo
    networks:
      - workload-net

  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ../prometheus.yml:/etc/prometheus/prometheus.yml:ro
    depends_on:
      otel-collector:
        condition: service_healthy
    networks:
      - workload-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9090/-/healthy"]
      interval: 5s
      timeout: 3s
      retries: 10

  loki:
    image: grafana/loki:2.9.4
    ports:
      - "3100:3100" # Loki HTTP API
    command: ["-config.file=/etc/loki/local-config.yaml"]
    networks:
      - workload-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3100/ready"]
      interval: 5s
      timeout: 3s
      retries: 10

  grafana:
    image: grafana/grafana:latest
    environment:
      - GF_AUTH_ANONYMOUS_ENABLED=true
      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
    ports:
      - "3000:3000"
    volumes:
      - ../grafana/provisioning:/etc/grafana/provisioning:ro
      - ../grafana/dashboards:/var/lib/grafana/dashboards:ro
    depends_on:
      - jaeger
      - tempo
      - prometheus
      - loki
    networks:
      - workload-net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
      interval: 5s
      timeout: 3s
      retries: 10

volumes:
  tempo-data:

networks:
  workload-net:
    driver: bridge