o1-mini unusable : use 'max_completion_tokens' instead

[TsiAizen]

Verify it's not a duplicate bug report

• I searched for similar bugs reported on GitHub and nobody has reported a similar issue. Search all issuees.
• I read Troubleshooting guide on Readme and there is not a guide on how to solve my problem.

Describe the Bug

OpenAI error 400: {
"error": {
"message": "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",
"type": "invalid_request_error",
"param": "max_tokens",
"code": "unsupported_parameter"
}
}

Please tell us if you have customized any of the extension settings or whether you are using the defaults.

model : o1-mini

Additional context

No response

[nrbrt]

I can confirm this bug. None of the o1-preview models work.

[dnnspaul]

Confirming for o1 as well:

[ryanwyler]

Using o1-mini and o1 require additional changes beyond only changing the max_completion_tokens.

o1 appears to use a different format streaming sections of the response back within nested calls back.

I found additional problems using AI Genie to work with the "o1" model. Simple queries worked, but extensive queries seemed to come back with responses that AI Genie was not able to parse so it would come back with blank results. I suspect there is a change with nested queries for sections that the client needs to individually query to get the data for each section.