docker-compose.examples.yml

# Observability Stack Example Services
# Docker Compose configuration for example instrumented agents
# 
# ⚠️  This is NOT a standalone Docker Compose file!
# This file is included by docker-compose.yml via the 'include:' directive.
# It depends on networks and services defined in the main docker-compose.yml.
#
# To use: Set INCLUDE_COMPOSE_FILES=docker-compose.examples.yml in .env
# Then run: docker compose up -d
#

x-default-logging: &logging
  driver: "json-file"
  options:
    max-size: "5m"
    max-file: "2"
    tag: "{{.Name}}"

services:
  # Weather Agent API Server - Example instrumented agent
  example-weather-agent:
    build:
      context: ./examples/plain-agents/weather-agent
      dockerfile: Dockerfile
    container_name: weather-agent
    ports:
      # FastAPI server endpoint
      - "${WEATHER_AGENT_PORT}:8000"
    environment:
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC}
      - MCP_SERVER_URL=http://mcp-server:8003
      - FAULT_PANEL_URL=http://fault-panel:8085
      - AWS_REGION=${AWS_REGION:-us-west-2}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID:-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY:-}
      - AWS_SESSION_TOKEN=${AWS_SESSION_TOKEN:-}
      - BEDROCK_MODEL_ID=${BEDROCK_MODEL_ID:-global.anthropic.claude-haiku-4-5-20251001-v1:0}
    depends_on:
      - otel-collector
      - example-mcp-server
      - example-fault-panel
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: ${WEATHER_AGENT_MEMORY_LIMIT}
    logging: *logging

  # Travel Agent Control Panel - UI for toggling fault injection scenarios
  example-fault-panel:
    build:
      context: ./docker-compose/fault-panel
      dockerfile: Dockerfile
    container_name: fault-panel
    ports:
      - "${FAULT_PANEL_PORT:-8085}:8085"
    volumes:
      - fault-panel-data:/data
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 64M
    logging: *logging

  # Canary Service - Periodically invokes travel-planner for testing
  example-canary:
    build:
      context: ./docker-compose/canary
      dockerfile: Dockerfile
    container_name: canary
    environment:
      - TRAVEL_PLANNER_URL=http://travel-planner:8000
      - WEATHER_AGENT_URL=http://weather-agent:8000
      - EVENTS_AGENT_URL=http://events-agent:8002
      - FAULT_PANEL_URL=http://fault-panel:8085
      - CANARY_INTERVAL=${CANARY_INTERVAL}
    depends_on:
      - example-travel-planner
      - example-weather-agent
      - example-events-agent
      - example-fault-panel
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: ${CANARY_MEMORY_LIMIT}
    logging: *logging

  # Multi-Agent Planner: Travel Planner (Orchestrator)
  example-travel-planner:
    build:
      context: ./examples/plain-agents/multi-agent-planner/orchestrator
      dockerfile: Dockerfile
    container_name: travel-planner
    ports:
      - "8003:8000"
    environment:
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC}
      - WEATHER_AGENT_URL=http://weather-agent:8000
      - EVENTS_AGENT_URL=http://events-agent:8002
      - MCP_SERVER_URL=http://mcp-server:8003
      - FAULT_PANEL_URL=http://fault-panel:8085
      - AWS_REGION=${AWS_REGION:-us-west-2}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID:-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY:-}
      - AWS_SESSION_TOKEN=${AWS_SESSION_TOKEN:-}
      - BEDROCK_MODEL_ID=${BEDROCK_MODEL_ID:-global.anthropic.claude-haiku-4-5-20251001-v1:0}
    depends_on:
      - otel-collector
      - example-weather-agent
      - example-events-agent
      - example-mcp-server
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 128M
    logging: *logging

  # Multi-Agent Planner: MCP Server (Mock MCP tool server)
  example-mcp-server:
    build:
      context: ./examples/plain-agents/multi-agent-planner/mcp-server
      dockerfile: Dockerfile
    container_name: mcp-server
    ports:
      - "8004:8003"
    environment:
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC}
    depends_on:
      - otel-collector
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 128M
    logging: *logging

  # Multi-Agent Planner: Events Agent
  example-events-agent:
    build:
      context: ./examples/plain-agents/multi-agent-planner/events-agent
      dockerfile: Dockerfile
    container_name: events-agent
    ports:
      - "8002:8002"
    environment:
      - OTEL_EXPORTER_OTLP_ENDPOINT=http://${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC}
      - MCP_SERVER_URL=http://mcp-server:8003
      - FAULT_PANEL_URL=http://fault-panel:8085
      - AWS_REGION=${AWS_REGION:-us-west-2}
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID:-}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY:-}
      - AWS_SESSION_TOKEN=${AWS_SESSION_TOKEN:-}
      - BEDROCK_MODEL_ID=${BEDROCK_MODEL_ID:-global.anthropic.claude-haiku-4-5-20251001-v1:0}
    depends_on:
      - otel-collector
      - example-mcp-server
      - example-fault-panel
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: 128M
    logging: *logging

  # Agent Eval Canary: periodically scores un-evaluated agent traces
  example-agent-eval-canary:
    build:
      context: ./docker-compose/agent-eval-canary
      dockerfile: Dockerfile
    container_name: agent-eval-canary
    environment:
      - OPENSEARCH_HOST=https://${OPENSEARCH_HOST}:${OPENSEARCH_PORT}
      - OPENSEARCH_USER=${OPENSEARCH_USER}
      - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
      - OTEL_EXPORTER_OTLP_ENDPOINT=${OTEL_COLLECTOR_HOST}:${OTEL_COLLECTOR_PORT_GRPC}
      - EVAL_CANARY_INTERVAL=${EVAL_CANARY_INTERVAL}
      - EVAL_CANARY_LOOKBACK_MINUTES=${EVAL_CANARY_LOOKBACK_MINUTES}
    depends_on:
      - opensearch
      - otel-collector
    networks:
      - observability-stack-network
    restart: unless-stopped
    deploy:
      resources:
        limits:
          memory: ${CANARY_MEMORY_LIMIT}
    logging: *logging

volumes:
  fault-panel-data: