[Unit]
Description=halogen-flash-server container (Quat3rnion NATIVE v2 abliterated Qwen3.8-Flash-Next, MTP spec decode, 2 slots over ONE 401408-position pool at ctx 200704, vision ON), root systemd unit (dankclaw, frank-dragoon, Strix Halo iGPU)
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=dank
Group=dank
# The engine pins staging buffers; keep the memlock budget unbounded so an
# RLIMIT smaller than the pinned set cannot fail the load. Parity with the
# other LLM units on this fleet.
LimitMEMLOCK=infinity
Environment="FRANK_DRAGOON_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-dragoon.env"
ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-dragoon.sh
# systemd stop alone cannot stop the container child; stop it explicitly
# (frank-archon pattern). The engine drains on SIGTERM.
ExecStop=/usr/bin/podman stop -t 60 frank-dragoon-halogen
TimeoutStartSec=1200
TimeoutStopSec=120
# always, not on-failure: an engine that exits 0 after an internal fault
# would otherwise leave the endpoint down until someone notices.
Restart=always
RestartSec=10
# The engine pins ~62 GiB of v2 weights and keeps a multi-GiB working set
# on a box that also hosts frank-zealot, ComfyUI and the Caddy/observability
# stack; make it a late OOM candidate, not the first.
OOMScoreAdjust=-500

[Install]
WantedBy=multi-user.target