Make local inference limits and workstation setup reproducible

libexec/hermes-stack-doctor

@@ -15,25 +15,25 @@ bad() { printf '✗ %s\n' "$*"; failures=$((failures + 1)); }
 source "$CONFIG_FILE"
 
 for command in git curl jq tar zstd systemctl hermes; do
-  command -v "$command" >/dev/null 2>&1 && ok "$command vorhanden" || bad "$command fehlt"
+  if command -v "$command" >/dev/null 2>&1; then ok "$command vorhanden"; else bad "$command fehlt"; fi
 done
 
 for script in "$HOME/.local/libexec"/hermes-stack-*; do
   [[ -f "$script" ]] || continue
-  bash -n "$script" && ok "Syntax: ${script##*/}" || bad "Syntaxfehler: ${script##*/}"
+  if bash -n "$script"; then ok "Syntax: ${script##*/}"; else bad "Syntaxfehler: ${script##*/}"; fi
 done
 
 if [[ -d "$HERMES_REPO/.git" ]]; then
   ok "Hermes-Git-Checkout vorhanden"
   dirty="$(git -C "$HERMES_REPO" status --porcelain --untracked-files=all |
     grep -vxF '?? .install_method' || true)"
-  [[ -z "$dirty" ]] && ok "Hermes-Checkout sauber" || bad "Hermes-Checkout enthält lokale Änderungen"
+  if [[ -z "$dirty" ]]; then ok "Hermes-Checkout sauber"; else bad "Hermes-Checkout enthält lokale Änderungen"; fi
 else
   bad "Hermes-Git-Checkout fehlt"
 fi
 
-systemctl --user is-active --quiet "$GATEWAY_SERVICE" && ok "Gateway aktiv" || bad "Gateway inaktiv"
-hermes gateway status >/dev/null 2>&1 && ok "Gateway gesund" || bad "Gateway-Status fehlgeschlagen"
+if systemctl --user is-active --quiet "$GATEWAY_SERVICE"; then ok "Gateway aktiv"; else bad "Gateway inaktiv"; fi
+if hermes gateway status >/dev/null 2>&1; then ok "Gateway gesund"; else bad "Gateway-Status fehlgeschlagen"; fi
 
 if curl --fail --silent --max-time 5 "$LLAMA_URL/health" |
    jq -e '.status == "ok"' >/dev/null 2>&1; then
@@ -51,7 +51,7 @@ set -u
 if [[ -n "${SIGNAL_HTTP_URL:-}" ]]; then
   status="$(curl --silent --output /dev/null --max-time 5 --write-out '%{http_code}' \
     "${SIGNAL_HTTP_URL%/}/api/v1/check" || true)"
-  [[ "$status" =~ ^2[0-9][0-9]$ ]] && ok "signal-cli HTTP erreichbar" || bad "signal-cli HTTP nicht erreichbar"
+  if [[ "$status" =~ ^2[0-9][0-9]$ ]]; then ok "signal-cli HTTP erreichbar"; else bad "signal-cli HTTP nicht erreichbar"; fi
 fi
 
 printf '\nFehler: %d\n' "$failures"

libexec/hermes-stack-llama-profile

@@ -24,7 +24,7 @@ flock -n 9 || {
   exit 1
 }
 
-# shellcheck disable=SC1090
+# shellcheck disable=SC1090,SC1091
 source "$config_dir/llama.env"
 [[ -n "${LLAMA_PROFILE:-}" ]] || {
   printf 'Profilbetrieb ist nicht konfiguriert.\n' >&2

libexec/hermes-stack-llama-report

@@ -3,7 +3,7 @@
 set -Euo pipefail
 config_dir="${XDG_CONFIG_HOME:-$HOME/.config}/hermes-stack-maintenance"
 if [[ -r "$config_dir/config.env" ]]; then
-  # shellcheck disable=SC1090
+  # shellcheck disable=SC1090,SC1091
   source "$config_dir/config.env"
 fi
 printf '\nGPU (Gesamtspeicher, belegt, frei in MiB):\n'

libexec/hermes-stack-llama-restart

@@ -8,7 +8,7 @@ if [[ "${1:-}" != --jobs-finished || $# -ne 1 ]]; then
 fi
 
 config_dir="${XDG_CONFIG_HOME:-$HOME/.config}/hermes-stack-maintenance"
-# shellcheck disable=SC1090
+# shellcheck disable=SC1090,SC1091
 source "$config_dir/config.env"
 
 exec 8>"${XDG_RUNTIME_DIR:-/tmp}/hermes-stack-hermes-update.lock"

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[@]}"
 )

libexec/hermes-stack-llama-watchdog

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+set -Eeuo pipefail
+umask 077
+config_dir="${XDG_CONFIG_HOME:-$HOME/.config}/hermes-stack-maintenance"
+set -a
+# shellcheck disable=SC1091
+source "$config_dir/config.env"
+set +a
+exec 9>"${XDG_RUNTIME_DIR:-/tmp}/hermes-stack-hermes-update.lock"
+flock -n 9 || exit 0
+exec python3 "$HOME/.local/lib/hermes-stack/llama_watchdog.py"

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"