Using o3-mini for PrReview fails due to tiktoken encoding

[patched-admin]

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

[endic-sam928281]

Hello, we tried to solve the issue.

This is what we did:

Modified the OpenAiLlmClient class to use the gpt-4o tokenizer as a fallback when the specified model's tokenizer is not found. This addresses the issue with unsupported models like o3-mini.

You can review changes in this commit: endic-sam928281@2ea93cf.

Caution

Disclaimer: The concept of solution was created by AI and you should never copy paste this code before you check the correctness of generated code. Solution might not be complete, you should use this code as an inspiration only.

---

Latta AI seeks to solve problems in open source projects as part of its mission to support developers around the world. Learn more about our mission at https://latta.ai/ourmission . If you no longer want Latta AI to attempt solving issues on your repository, you can block this account.