# Quadlet unit: frank-medium proxy (rootless, boot-persistent).
#
# Install path on dankserver: ~/.config/containers/systemd/frank-medium-proxy.container
# Unit name: frank-medium-proxy.service (container name: frank-medium-proxy)
#
# WHAT IT IS. A round-robin reverse proxy in front of the two single-GPU
# frank-medium replicas (:7771 on R9700 #1, :7772 on R9700 #2). It preserves
# the fleet contract: one endpoint on host port 7770 answering as the served
# model name frank-medium, OpenAI /v1, streaming included.
#
# WHY IT EXISTS. TP=2 — one vLLM process spanning both cards — is impossible
# on this host (see frank-medium-a.container and the runbook: RCCL's kernels
# need PCIe atomics, and the second card's chipset path advertises
# AtomicOpsCap: Routing-). Two replicas are how both cards get used.
#
# ROUTING. vLLM's OpenAI API is stateless per request, so round-robin is
# sound; there is no session affinity to preserve. /health answers 200 while
# at least one replica is up and names the ones that are down. The proxy runs
# on host networking so it can bind 7770 and reach the replicas on loopback.
#
# The script is a few dozen lines of aiohttp, mounted read-only out of
# /home/dank/serverAppConfigs (deploy.sh pulls that checkout before dispatch).
# It reuses the same image as the replicas: aiohttp is already there and no
# extra image has to be pulled on this host.
[Unit]
Description=frank-medium proxy — round-robin in front of the two single-GPU replicas
After=network-online.target
Wants=frank-medium-a.service frank-medium-b.service
After=frank-medium-a.service frank-medium-b.service

[Container]
ContainerName=frank-medium-proxy
Image=localhost/radiance-vllm:0.9.3
PodmanArgs=--network=host
Environment=PORT=7770
Environment=UPSTREAMS=http://127.0.0.1:7771,http://127.0.0.1:7772
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/proxy/roundrobin-proxy.py:/usr/local/bin/roundrobin-proxy.py:ro
Volume=/home/dank/serverAppConfigs/dankserver/frank-medium/frank-medium-healthcheck.py:/usr/local/bin/frank-medium-healthcheck.py:ro
PodmanArgs=--entrypoint /usr/local/bin/roundrobin-proxy.py
HealthCmd=python3 /usr/local/bin/frank-medium-healthcheck.py
HealthInterval=60s
HealthTimeout=30s
HealthRetries=3
HealthStartPeriod=60s
Pull=never

[Service]
Restart=on-failure
RestartSec=10

[Install]
WantedBy=default.target