Trial GPU-resident Qwen3.5-9B with verified 4B rollback

libexec/hermes-stack-model

@@ -4,7 +4,7 @@ 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"
+  printf 'Aufruf: %s [status|routine|fallback|large] (Modellwechsel beendet laufende Anfragen)\n' "$0"
 }
 case "${1:-}" in
   ''|status)
@@ -13,7 +13,7 @@ case "${1:-}" in
     printf 'Aktives Modell: %s\nKonfiguration: %s/llama.env\n' "$LLAMA_MODEL" "$config_dir"
     exit 0 ;;
   -h|--help) usage; exit 0 ;;
-  routine|large) selected="$1" ;;
+  routine|fallback|large) selected="$1" ;;
   *) usage >&2; exit 2 ;;
 esac
 [[ $# -eq 1 ]] || exit 2
@@ -24,12 +24,20 @@ candidate="$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" "$backup"
-systemctl --user stop hermes-gateway.service
+hermes_config="${HERMES_HOME:-$HOME/.hermes}/config.yaml"
+hermes_backup=""
+if [[ -f "$hermes_config" ]]; then
+  hermes_backup="$(mktemp "$config_dir/hermes.yaml.before-model-switch.XXXXXX")"
+  cp -p -- "$hermes_config" "$hermes_backup"
+fi
 rollback() {
   local rc=$?
   trap - EXIT
   if ((rc != 0)); then
     install -m 0600 "$backup" "$config_dir/llama.env" || true
+    if [[ -n "$hermes_backup" ]]; then
+      install -m 0600 "$hermes_backup" "$hermes_config" || true
+    fi
     systemctl --user restart llama-qwen.service || true
     systemctl --user start hermes-gateway.service || true
     printf 'Modellwechsel fehlgeschlagen; vorherige Konfiguration zurückkopiert. Dienststatus prüfen.\n' >&2
@@ -37,11 +45,38 @@ rollback() {
   exit "$rc"
 }
 trap rollback EXIT
+systemctl --user stop hermes-gateway.service
 install -m 0600 "$candidate" "$config_dir/llama.env"
+# Keep Hermes' actual context and compression trigger paired with the model.
+# Legacy profiles without metadata use the original 64K window.
+LLAMA_CONTEXT_TOKENS=65536
+# shellcheck disable=SC1090
+source "$candidate"
+if [[ -n "$hermes_backup" ]]; then
+  python3 - "$hermes_config" "$LLAMA_CONTEXT_TOKENS" <<'PY'
+import os
+from pathlib import Path
+import sys
+import tempfile
+import yaml
+path = Path(sys.argv[1])
+context = int(sys.argv[2])
+if context < 64000:
+    raise ValueError("Hermes requires at least 64000 context tokens")
+config = yaml.safe_load(path.read_text())
+config.setdefault("model", {})["context_length"] = context
+config.setdefault("compression", {})["threshold_tokens"] = min(24000, context * 3 // 8)
+with tempfile.NamedTemporaryFile(mode="w", dir=path.parent, delete=False) as out:
+    yaml.safe_dump(config, out, allow_unicode=True, sort_keys=False, width=1000)
+    temporary = Path(out.name)
+os.chmod(temporary, 0o600)
+temporary.replace(path)
+PY
+fi
 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
+    if curl -fsS --max-time 2 http://127.0.0.1:8080/health 2>/dev/null | jq -e '.status == "ok"' >/dev/null 2>&1; then
       ready=1; break
     fi
     sleep 2