[BUG] Token limitations don't seem to get thrown from the client library

[adameska]

Library name and version

Azure.AI.OpenAI

Describe the bug

When trying to call a chat completion it seems like if there is an error nothing is ever thrown and it appears like the application just sits. I have a controller action that calls with a user request that catches a generic exception and the catch is never hit nor is anything ever returned. I was hitting the token limit (the only way i knew this was replicating the messages in the playground) and had no idea. Here is a very small snippet of the code illustrating the line causing it.

ChatClient chatClient = _azureOpenAIClient.GetChatClient("gpt-4o-mini");
chatClient.CompleteChat(conversationMessages, options); //this never returns, never throws, i have no idea if this is a slow request or it immediately crashed. conversationMessages is over the token limit.

Expected behavior

An meaningful exception should be thrown if an error occurred.

Actual behavior

Call never returns anything.

Reproduction Steps

ChatClient chatClient = _azureOpenAIClient.GetChatClient("gpt-4o-mini");
//some large request in conversation messages
chatClient.CompleteChat(conversationMessages, options); //this never returns, never throws, i have no idea if this is a slow request or it immediately crashed. conversationMessages is over the token limit.

Environment

Windows 11 .netcore 8 VS 17.11

[github-actions]

Thanks for the feedback! We are routing this to the appropriate team for follow-up. cc @jpalvarezl @ralph-msft @trrwilson.