fix(models): skip non-chat models when resolving chat defaults (#6907)

routes/model_routes.py

@@ -659,7 +659,7 @@ _NON_CHAT_CONTAINS = (
     "gliner", "riva", "-parse", "-embedqa", "-nemoretriever",
     "topic-control", "calibration",
     "ai-synthetic-video", "cosmos-reason2",
-    "bge", "llama-guard",
+    "bge", "llama-guard", "-embed", "rerank",
 )
 _NON_CHAT_EXACT_PREFIXES = (
     "gpt-audio",  # gpt-audio, gpt-audio-mini etc. (not gpt-4o-audio-preview which is chat)
@@ -2846,11 +2846,12 @@ def setup_model_routes(model_discovery):
                 return {"endpoint_id": "", "endpoint_url": "", "model": ""}
             base = _normalize_base(ep.base_url)
             chat_url = build_chat_url(base)
+            if model and not _is_chat_model(model):
+                model = ""
             if not model and (getattr(ep, "cached_models", None) or getattr(ep, "pinned_models", None)):
                 try:
                     visible = _visible_models(ep.cached_models, getattr(ep, "hidden_models", None), getattr(ep, "pinned_models", None))
-                    if visible:
-                        model = visible[0]
+                    model = next((mid for mid in visible if _is_chat_model(mid)), "")
                 except Exception:
                     pass
             return {"endpoint_id": ep.id, "endpoint_url": chat_url, "model": model}