fix(models): query v1 models for llama-server endpoints (#3380)

* fix(models): query v1 models for llama-server endpoints * test(models): accept owner kwargs in llama-server regression
2026-06-30 00:22:10 -04:00 · 2026-06-08 19:09:02 -04:00
parent f7ae85590b
commit e7c1d75884
5 changed files with 66 additions and 4 deletions
@@ -857,7 +857,7 @@ def _ping_endpoint(base_url: str, api_key: str = None, timeout: float = 1.5) ->
            and 400 <= result["status_code"] < 500
            and result["status_code"] not in (401, 403)
        ):
-            models_url = base.rstrip("/") + "/models"
+            models_url = build_models_url(base)
            try:
                r2 = httpx.get(models_url, headers=headers, timeout=timeout, verify=llm_verify())
                result2 = _result_from_response(r2)