I get 500 status code while sending newly added

llmRequestNonPunctuatedDelaySeconds

parameter to

PATCH /assistant

. Potentially, the same is applies to

POST /assistant

. Here is the example of request body without

llmRequestNonPunctuatedDelaySeconds

which leads to getting 200 response:

{'url': 'there_was_model_url', 'model': 'there_was_model_name', 'provider': 'custom-llm'}, 'voice': {'provider': '11labs', 'voiceId': 'QrRJx7pPvPGFVMtAx4IR', 'model': 'eleven_turbo_v2', 'inputPreprocessingEnabled': True, 'inputReformattingEnabled': False, 'enableSsmlParsing': True}, 'language': 'en-US', 'name': 'vapi_caller', 'firstMessage': "Hello! This is Reaper's VAPI test agent from DEV environment!!", 'voicemailDetectionEnabled': False, 'silenceTimeoutSeconds': 600, 'llmRequestDelaySeconds': 0.05, 'transcriber': {'provider': 'deepgram', 'model': 'nova-2-phonecall', 'language': 'en', 'smartFormat': False}}

Here is the example of request body with

llmRequestNonPunctuatedDelaySeconds

which leads to getting 500 response:

{'model': {'url': 'there_was_model_url', 'model': 'there_was_model_name', 'provider': 'custom-llm'}, 'voice': {'provider': '11labs', 'voiceId': 'QrRJx7pPvPGFVMtAx4IR', 'model': 'eleven_turbo_v2', 'inputPreprocessingEnabled': True, 'inputReformattingEnabled': False, 'enableSsmlParsing': True}, 'language': 'en-US', 'name': 'vapi_caller', 'firstMessage': "Hello! This is Reaper's VAPI test agent from DEV environment!!", 'voicemailDetectionEnabled': False, 'silenceTimeoutSeconds': 600, 'llmRequestDelaySeconds': 0.05, 'llmRequestNonPunctuatedDelaySeconds': 0.25, 'transcriber': {'provider': 'deepgram', 'model': 'nova-2-phonecall', 'language': 'en', 'smartFormat': False}}

@Moody Reaper It seems like there might be an issue with the implementation or recognition of the

llmRequestNonPunctuatedDelaySeconds

parameter in the API. Since you're receiving a 500 status code, this indicates a server-side error, which could be due to various reasons such as a bug in the API, incorrect handling of the new parameter, or the parameter not being supported yet. To resolve this issue, please double-check the API documentation to ensure that the

llmRequestNonPunctuatedDelaySeconds

parameter is correctly implemented and supported. If the documentation confirms that it should work as expected, then the issue might be on the server side, and I would recommend reaching out to the API support team with the details of the error. If you need further assistance or if there's anything else I can help you with, please let me know!

Looks like a bug, we will get this fixed.

@Sahil, are there any updates regarding that?

It will require one to two more days.