no indication in stack logs for why model listing is empty

[mattf]

System Info

main (d45137a)

Information

• The official example scripts
• My own modified scripts

🐛 Describe the bug

$ OPENAI_API_KEY=BOGUS uv run llama stack run --providers inference=remote::openai
...

$ curl http://localhost:8321/v1/models | jq
{
  "data": []
}

Error logs

there are no errors -

INFO     2025-11-02 07:09:05,167 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue        
         disabled for SQLite to avoid concurrency issues                                                                
INFO     2025-11-02 07:09:05,301 uvicorn.error:84 uncategorized: Started server process [590303]                        
INFO     2025-11-02 07:09:05,303 uvicorn.error:48 uncategorized: Waiting for application startup.                       
INFO     2025-11-02 07:09:05,309 llama_stack.core.server.server:172 core::server: Starting up Llama Stack server        
         (version: 0.3.0)                                                                                               
INFO     2025-11-02 07:09:05,311 llama_stack.core.stack:495 core: starting registry refresh task                        
INFO     2025-11-02 07:09:05,313 uvicorn.error:62 uncategorized: Application startup complete.                          
INFO     2025-11-02 07:09:05,315 uvicorn.error:216 uncategorized: Uvicorn running on http://0.0.0.0:8321 (Press CTRL+C  
         to quit)                                                                                                       
INFO     2025-11-02 07:09:15,050 uvicorn.access:473 uncategorized: 127.0.0.1:41874 - "GET /v1/models HTTP/1.1" 200

Expected behavior

errors in stack log