Make local inference limits and workstation setup reproducible

libexec/hermes-stack-llama-run

@@ -27,7 +27,7 @@ while (($#)); do
 done
 
 if [[ -n "${LLAMA_PROFILE:-}" && -r "$config_dir/llama-profile.env" ]]; then
-  # shellcheck disable=SC1090
+  # shellcheck disable=SC1090,SC1091
   source "$config_dir/llama-profile.env"
 fi
 [[ -z "$profile_override" ]] || LLAMA_PROFILE="$profile_override"
@@ -70,6 +70,9 @@ if [[ -n "${LLAMA_MMPROJ:-}" ]]; then
 fi
 [[ -z "${LLAMA_ALIAS:-}" ]] || model_args+=(--alias "$LLAMA_ALIAS")
 
+# Server defaults are not a wall-clock limit; the independent slot watchdog is.
+[[ "${LLAMA_MAX_OUTPUT_TOKENS:-2048}" =~ ^[1-9][0-9]*$ ]] || exit 2
+
 profile_args=()
 if [[ -n "${LLAMA_PROFILE:-}" ]]; then
   reasoning_budget=512
@@ -107,6 +110,7 @@ args=(
   "${model_args[@]}"
   --host "${LLAMA_HOST:-127.0.0.1}"
   --port "${LLAMA_PORT:-8080}"
+  --n-predict "${LLAMA_MAX_OUTPUT_TOKENS:-2048}"
   "${profile_args[@]}"
   "${LLAMA_ARGS[@]}"
 )