Make local inference limits and workstation setup reproducible

systemd/user/hermes-stack-llama-watchdog.service

@@ -0,0 +1,9 @@
+[Unit]
+Description=Enforce local model request duration and output limits
+After=llama-qwen.service
+
+[Service]
+Type=oneshot
+ExecStart=%h/.local/libexec/hermes-stack-llama-watchdog
+TimeoutStartSec=45
+UMask=0077