Description of problem:

When using a LLM that is getting rate limited, a user wouldnt know about it when using the LS plugin UI. It is a silent error and nothing gets reported back.

If we check the LCS log, you wouldn't know its a rate limit error but if you check the llama stack logs you can check the LLM was getting rate limited

Prerequisites (if any, like setup, operators/versions):

Steps to Reproduce

1. <steps>

Actual results:

Expected results:

Reproducibility (Always/Intermittent/Only Once):

Acceptance criteria:

Definition of Done:

Build Details:

Additional info (Such as Logs, Screenshots, etc):