Is this a regression?

Yes

Description

When using o3-mini as a model, got the error 'Could not automatically map o3-mini to a tokeniser. Please use tiktoken.get_encoding to explicitly get the tokeniser you expect.'

Suggest defaulting to gpt-4o tokenizer in case of failure.

Please provide a link to a minimal reproduction of the bug

No response

Please provide the exception or error you saw

Anything else?

No response