From a548169b991b73c69bdc190076d39edd793c8b7e Mon Sep 17 00:00:00 2001
From: Akram Ben Aissi <akram.benaissi@gmail.com>
Date: Fri, 10 Oct 2025 15:23:13 +0100
Subject: [PATCH] fix: allow skipping model availability check for vLLM (#3739)

# What does this PR do?
<!-- Provide a short summary of what this PR does and why. Link to
relevant issues if applicable. -->
Allows model check to fail gracefully instead of crashing on startup.


<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->

## Test Plan
<!-- Describe the tests you ran to verify your changes with result
summaries. *Provide clear instructions so the plan can be easily
re-executed.* -->

set VLLM_URL to your VLLM server

```
(base) akram@Mac llama-stack % LAMA_STACK_LOGGING="all=debug" VLLM_ENABLE_MODEL_DISCOVERY=false  MILVUS_DB_PATH=./milvus.db INFERENCE_MODEL=vllm uv run --with llama-stack llama stack build --distro starter  --image-type venv --run
```



```

INFO     2025-10-08 20:11:24,637 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues
INFO     2025-10-08 20:11:24,866 llama_stack.providers.utils.responses.responses_store:96 openai_responses: Write queue disabled for SQLite to avoid concurrency issues
ERROR    2025-10-08 20:11:26,160 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: <a
         href="https://oauth.akram.a1ey.p3.openshiftapps.com:443/oauth/authorize?approval_prompt=force&amp;client_id=system%3Aserviceaccount%3Arhoai-30-genai%3Adefault&amp;redirect_uri=ht
         tps%3A%2F%2Fvllm-rhoai-30-genai.apps.rosa.akram.a1ey.p3.openshiftapps.com%2Foauth%2Fcallback&amp;response_type=code&amp;scope=user%3Ainfo+user%3Acheck-access&amp;state=9fba207425
         5851c718aca717a5887d76%3A%2Fmodels">Found</a>.

[...]
INFO     2025-10-08 20:11:26,295 uvicorn.error:84 uncategorized: Started server process [83144]
INFO     2025-10-08 20:11:26,296 uvicorn.error:48 uncategorized: Waiting for application startup.
INFO     2025-10-08 20:11:26,297 llama_stack.core.server.server:170 core::server: Starting up
INFO     2025-10-08 20:11:26,297 llama_stack.core.stack:399 core: starting registry refresh task
INFO     2025-10-08 20:11:26,311 uvicorn.error:62 uncategorized: Application startup complete.
INFO     2025-10-08 20:11:26,312 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit)
ERROR    2025-10-08 20:11:26,791 llama_stack.providers.utils.inference.openai_mixin:439 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: <a
         href="https://oauth.akram.a1ey.p3.openshiftapps.com:443/oauth/authorize?approval_prompt=force&amp;client_id=system%3Aserviceaccount%3Arhoai-30-genai%3Adefault&amp;redirect_uri=ht
         tps%3A%2F%2Fvllm-rhoai-30-genai.apps.rosa.akram.a1ey.p3.openshiftapps.com%2Foauth%2Fcallback&amp;response_type=code&amp;scope=user%3Ainfo+user%3Acheck-access&amp;state=8ef0cba3e1
         71a4f8b04cb445cfb91a4c%3A%2Fmodels">Found</a>.

```
---
 .../providers/remote/inference/vllm/vllm.py        | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/llama_stack/providers/remote/inference/vllm/vllm.py b/llama_stack/providers/remote/inference/vllm/vllm.py
index 310eaf7b6..5974ca176 100644
--- a/llama_stack/providers/remote/inference/vllm/vllm.py
+++ b/llama_stack/providers/remote/inference/vllm/vllm.py
@@ -77,6 +77,20 @@ class VLLMInferenceAdapter(OpenAIMixin):
     def get_extra_client_params(self):
         return {"http_client": httpx.AsyncClient(verify=self.config.tls_verify)}
 
+    async def check_model_availability(self, model: str) -> bool:
+        """
+        Skip the check when running without authentication.
+        """
+        if not self.config.api_token:
+            model_ids = []
+            async for m in self.client.models.list():
+                if m.id == model:  # Found exact match
+                    return True
+                model_ids.append(m.id)
+            raise ValueError(f"Model '{model}' not found. Available models: {model_ids}")
+        log.warning(f"Not checking model availability for {model} as API token may trigger OAuth workflow")
+        return True
+
     async def openai_chat_completion(
         self,
         model: str,