[Important] Add max_prompt_tokens and max_completion_tokens for Runs API

[neilord]

Confirm this is a feature request for the Node library and not the underlying OpenAI API.

• This is a feature request for the Node library

Describe the feature or improvement you're requesting

Hi, I belive that max_prompt_tokens and max_completion_tokens are essential features for using the whole Assistants API. Without being able to specify the max tokens, the thread is just getting longer, and running the AI model getting very expensive. Please add the max_prompt_tokens and max_completion_tokens parameters to the openai.beta.threads.runs.create. Thanks!

Additional context

No response

[rattrayalex]

I believe @pstern-sl is working on this.

[pstern-sl]

This is available starting in version 4.34 - released today #767

[neilord]

Awesome! Thanks a lot for implementing this! :)