[Unit]
Description=Hy3-preview NVFP4 2-node vLLM stack (marlin, worker-first)
After=network-online.target docker.service
Wants=network-online.target
Requires=docker.service

[Service]
Type=oneshot
RemainAfterExit=yes
User=jon
Group=jon
SupplementaryGroups=docker
Environment=HOME=/home/jon
WorkingDirectory=/home/jon/hy3-serve
# Wait (up to 10 min) for the worker box to be SSH-able before orchestrating
ExecStartPre=/bin/bash -c 'set -a; . /home/jon/hy3-serve/.env.hy3; set +a; for i in $(seq 1 60); do ssh -o ConnectTimeout=5 -o BatchMode=yes "$WORKER_HOST" true && exit 0; sleep 10; done; echo "worker $WORKER_HOST not reachable" >&2; exit 1'
ExecStart=/home/jon/hy3-serve/start-hy3.sh
ExecStop=/home/jon/hy3-serve/stop-hy3.sh
TimeoutStartSec=1800
TimeoutStopSec=300

[Install]
WantedBy=multi-user.target