# spark-executor-mcp — production runtime
#
# Bring up with:
#   docker compose up -d --build
#
# Prerequisites (one-time):
#   1. Put your YARN/Hadoop client configs in ./hadoop-conf/  (must contain
#      core-site.xml + yarn-site.xml + hdfs-site.xml matching the target
#      cluster). The Dockerfile's RUN mkdir -p already creates the dir, but
#      it will be empty until you populate it.
#   2. Set YARN_RESOURCE_MANAGER_URL in .env (or export it in your shell).
#      This is the fallback when a Connection was saved without yarn_rm_url.
#
# After it starts, the MCP endpoint is at:
#   http://localhost:8000/spark-executor-mcp   (initialize -> tools/list -> tools/call)

services:
  mcp-server:
    build:
      context: .
      dockerfile: Dockerfile
    image: mcp-server:latest
    container_name: mcp-tools

    restart: unless-stopped

    ports:
      - "8000:8000"

    environment:
      # Stream Python output to stdout/stderr line-by-line (live loguru output).
      PYTHONUNBUFFERED: "1"

      # Fallback YARN RM URL used by the REST client when a Connection's
      # yarn_rm_url is not set or a Job lacks a snapshot. Leave empty if
      # you always set yarn_rm_url per Connection via save_connection.
      YARN_RESOURCE_MANAGER_URL: ${YARN_RESOURCE_MANAGER_URL:-}

      # Gunicorn tuning (see gunicorn.conf.py for full list of knobs).
      # 2 workers is a good default for a small MCP service; raise for
      # high-concurrency deploys.
      GUNICORN_WORKERS: ${GUNICORN_WORKERS:-2}
      GUNICORN_TIMEOUT: ${GUNICORN_TIMEOUT:-120}
      GUNICORN_BIND: ${GUNICORN_BIND:-0.0.0.0:8000}

      # Optional: pass JVM options to spark-submit (e.g. for proxies, memory).
      # SPARK_SUBMIT_OPTS: "-Dhttps.proxyHost=..."

    volumes:
      # Persist Connections, PendingSubmissions, and loguru logs across
      # container restarts. Gitignored.
      - ./data:/app/data

      # Real Hadoop/YARN client configs read by spark-submit at submit time.
      # Read-only so the running container cannot mutate cluster config.
      - ./hadoop-conf:/etc/hadoop/conf:ro


    # No resource limits — spark-submit talks to YARN, which does the actual
    # heavy lifting. The MCP server itself is lightweight (FastAPI + httpx).
    # Uncomment to cap if needed:
    # deploy:
    #   resources:
    #     limits:
    #       cpus: "1.0"
    #       memory: 1G