-
Notifications
You must be signed in to change notification settings - Fork 103
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error Traps #198
Comments
This is indeed quite annoying if ChatGPT guesses entity_ids etc. Then the function breaks and you get this. Then you need to close the chat and start over. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi all,
Is there any way to add a error trap for the LLM response
Here is 2 examples
Sometimes when I talk to the assistant I get this spam:
[D][voice_assistant:619]: Response: "Sorry, I had a problem talking to OpenAI: Error code: 400 - {'error': {'message': "An assistant message with 'tool_calls' must be followed by tool messages responding to each 'tool_call_id'. The following tool_call_ids did not have response messages: call_0Ju96bO4XKU8w1ylwRykk5nj", 'type': 'invalid_request_error', 'param': 'messages.[9].role', 'code': None}}"
but the most important and wanted one would be a way to retrigger the assistant when it asks
[D][voice_assistant:619]: Response: "Is there anything else I can help you with"
[D][voice_assistant:619]: Response: "Are you certain you wish to turn off all lights"
[D][voice_assistant:619]: Response: "Is this correct"
and so on
The text was updated successfully, but these errors were encountered: