Bug: Handle error messages from the backend

[treo]

Sometimes OpenAI will respond with errors like the following

Status Code: 429

Payload:

{
  "error": {
    "message": "That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists. (Please include the request ID 1988ad485d5bb7448d7edc5a1367af39 in your message.)",
    "type": "server_error",
    "param": null,
    "code": null
  }
}

At the moment, it just looks like we are waiting for ever for a response.