engines: detect Riva/NIM model from /metadata, show placeholder on empty fetch

- stt.list_models(): fall back to /metadata (NVIDIA Riva/NIM) when /models
  returns nothing — extracts shortName and strips the version tag suffix
- Settings: show "type model name manually" placeholder when fetch returns
  empty and no model is currently set

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

linux/blitztext/gtksettings.py

@@ -1445,6 +1445,8 @@ notebook.bt-nb tab:checked label {
             def apply():
                 cur = _combo_text(combo)
                 _fill_combo(combo, models, cur)
+                if not models and not cur:
+                    combo.entry.set_placeholder_text("type model name manually")
                 return False
             GLib.idle_add(apply)
         threading.Thread(target=work, daemon=True).start()

linux/blitztext/stt.py

@@ -62,29 +62,46 @@ def status(engine: STTEngine, timeout: float = 2.0) -> bool:
 
 
 def list_models(base_url: str, api_key_env: str = "", timeout: float = 5.0) -> list[str]:
-    """Fetch model ids from an OpenAI-compatible (or Ollama-style) /models endpoint."""
+    """Fetch model ids from an OpenAI-compatible, Ollama-style, or Riva/NIM /models endpoint."""
     import os
 
     if not base_url:
         return []
-    url = base_url.rstrip("/") + "/models"
+    base = base_url.rstrip("/")
-    headers = {}
+    headers: dict[str, str] = {}
     key = os.environ.get(api_key_env) if api_key_env else None
     if key:
         headers["Authorization"] = f"Bearer {key}"
+
+    def _get(url: str) -> dict | None:
         try:
             req = urllib.request.Request(url, headers=headers)
             with urllib.request.urlopen(req, timeout=timeout) as resp:
-            data = json.loads(resp.read().decode("utf-8"))
+                return json.loads(resp.read().decode("utf-8"))
         except (urllib.error.URLError, json.JSONDecodeError, OSError):
-        return []
+            return None
 
-    items = data.get("data") if isinstance(data, dict) else None
+    # 1. Standard OpenAI /models
+    data = _get(base + "/models")
+    if isinstance(data, dict):
+        items = data.get("data")
         if isinstance(items, list):  # OpenAI shape: {"data":[{"id":...}]}
             return [m["id"] for m in items if isinstance(m, dict) and m.get("id")]
-    items = data.get("models") if isinstance(data, dict) else None
+        items = data.get("models")
         if isinstance(items, list):  # Ollama shape: {"models":[{"name"/"model":...}]}
-        return [m.get("name") or m.get("model") for m in items if (m.get("name") or m.get("model"))]
+            return [m.get("name") or m.get("model") for m in items
+                    if (m.get("name") or m.get("model"))]
+
+    # 2. NVIDIA Riva / NIM — exposes model info at /metadata
+    data = _get(base + "/metadata")
+    if isinstance(data, dict):
+        for info in data.get("modelInfo") or []:
+            name = info.get("shortName") or info.get("modelUrl") or ""
+            if name:
+                # Strip the long tag suffix: keep everything before the first ':'
+                short = name.split(":")[0]
+                return [short]
+
     return []