recipes/docker-images/glm53-kindling/.submodules/spark-agent/agent/spark-agent.yaml

# The agent runs on every node, including ones with no model on them.
#
#   docker compose -f spark-agent.yaml up -d
#
# It holds what the model container gave up. Keep the two asymmetric: this one
# is privileged and serves no model, that one serves a model and is not.
services:
  spark-agent:
    image: ${IMAGE:-spark-agent:v6}
    container_name: spark-agent
    restart: unless-stopped

    # mentatd's control port is on 127.0.0.1, and mentat-serve dials the
    # agent's MCP port on the host's own addresses. Both want the host's
    # network.
    network_mode: host

    # Container processes appear in the host's PID namespace, which is what
    # lets py-spy here reach an engine running in another container. This is
    # the whole reason the model container can drop CAP_SYS_PTRACE.
    pid: host
    # SYS_PTRACE and nothing else. Sharing the host PID namespace does not
    # widen the capability set on its own, so dropping the default 14 first
    # takes this from 15 capabilities to 1. Read /proc/self/status to check:
    # under pid: host, /proc/1 is the host's init rather than this process.
    cap_drop:
      - ALL
    cap_add:
      - SYS_PTRACE

    # Read-only throughout: the agent observes and never changes the host.
    # /proc needs no mount, because pid: host already makes the container's
    # own /proc the host's. No Docker socket either: it is root-equivalent,
    # and this endpoint answers a model. The host snapshot timer writes
    # docker-ps.log for the container inventory instead.
    volumes:
      - /sys:/sys:ro
      - ${LOG_DIR:?set LOG_DIR in .env to the host log directory}:/logs:ro

    environment:
      - AGENT_LOG_DIR=/logs
      # nvidia-smi and the driver libraries arrive through the container
      # runtime rather than the image, so the image stays small and the
      # versions cannot drift from the host's.
      - NVIDIA_VISIBLE_DEVICES=all
      # The router the page reads models from. Its address is also let in
      # to the MCP port, because it forwards every merged tool call.
      - MENTAT_ROUTER_URL=${MENTAT_ROUTER_URL:?set MENTAT_ROUTER_URL in .env}
      # Address prefixes allowed to reach the page and MCP: the node subnets.
      - ALLOWED_SOURCES=${ALLOWED_SOURCES:?set ALLOWED_SOURCES in .env}

    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]