Error Traps

[ArMaTeC]

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

[jleinenbach]

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.