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

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

@@ -0,0 +1,11 @@
+[Unit]
+Description=Check local model request limits every 15 seconds
+
+[Timer]
+OnBootSec=1min
+OnUnitActiveSec=15s
+AccuracySec=1s
+Unit=hermes-stack-llama-watchdog.service
+
+[Install]
+WantedBy=timers.target

systemd/user/llama-qwen.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=Local llama.cpp Qwen model server
+Description=Hermes local main model (routine/large)
 After=network-online.target graphical-session.target
 StartLimitIntervalSec=300
 StartLimitBurst=3