Make local inference limits and workstation setup reproducible

config/config.env.example

@@ -7,6 +7,9 @@ HERMES_BRANCH="main"
 GATEWAY_SERVICE="hermes-gateway.service"
 LLAMA_SERVICE="llama-qwen.service"
 LLAMA_URL="http://127.0.0.1:8080"
+# Independent slot watchdog. Active requests only; updates hold the same lock.
+LLAMA_MAX_REQUEST_SECONDS=600
+LLAMA_MAX_OUTPUT_TOKENS=2048
 # 1: inaktiven Dienst wieder starten. HTTP-Timeouts allein starten nie neu.
 # Standard 0 verhindert unerwünschte Modellstarts während Wartung/Tuning.
 LLAMA_HEALTH_AUTORESTART=0