Make local inference limits and workstation setup reproducible

libexec/hermes-stack-model

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+# Explicit model selection. Stops current gateway requests; keeps both model files.
+set -Eeuo pipefail
+umask 077
+config_dir="${XDG_CONFIG_HOME:-$HOME/.config}/hermes-stack-maintenance"
+usage() {
+  printf 'Aufruf: %s [status|routine|large] (Modellwechsel beendet laufende Anfragen)\n' "$0"
+}
+case "${1:-}" in
+  ''|status)
+    # shellcheck disable=SC1091
+    source "$config_dir/llama.env"
+    printf 'Aktives Modell: %s\nKonfiguration: %s/llama.env\n' "$LLAMA_MODEL" "$config_dir"
+    exit 0 ;;
+  -h|--help) usage; exit 0 ;;
+  routine|large) selected="$1" ;;
+  *) usage >&2; exit 2 ;;
+esac
+[[ $# -eq 1 ]] || exit 2
+exec 9>"${XDG_RUNTIME_DIR:-/tmp}/hermes-stack-hermes-update.lock"
+flock -n 9 || { printf 'Maintenance läuft.\n' >&2; exit 1; }
+runner="$(dirname -- "$(readlink -f -- "${BASH_SOURCE[0]}")")/hermes-stack-llama-run"
+candidate="$config_dir/llama-$selected.env"
+HERMES_LLAMA_CONFIG="$candidate" "$runner" --check
+backup="$(mktemp "$config_dir/llama.env.before-model-switch.XXXXXX")"
+cp -p -- "$config_dir/llama.env" "$backup"
+systemctl --user stop hermes-gateway.service
+rollback() {
+  local rc=$?
+  trap - EXIT
+  if ((rc != 0)); then
+    install -m 0600 "$backup" "$config_dir/llama.env" || true
+    systemctl --user restart llama-qwen.service || true
+    systemctl --user start hermes-gateway.service || true
+    printf 'Modellwechsel fehlgeschlagen; vorherige Konfiguration zurückkopiert. Dienststatus prüfen.\n' >&2
+  fi
+  exit "$rc"
+}
+trap rollback EXIT
+install -m 0600 "$candidate" "$config_dir/llama.env"
+ready=0
+if systemctl --user restart llama-qwen.service; then
+  for ((i=0; i<90; i++)); do
+    if curl -fsS --max-time 2 http://127.0.0.1:8080/health | jq -e '.status == "ok"' >/dev/null 2>&1; then
+      ready=1; break
+    fi
+    sleep 2
+  done
+fi
+if ((ready == 0)); then
+  exit 1
+fi
+systemctl --user start hermes-gateway.service
+trap - EXIT
+printf 'Modellprofil %s aktiv. Vorherige Konfiguration: %s\n' "$selected" "$backup"