The following accounts have interacted with this PR and/or linked issues. I will continue to update these lists as activity occurs. You can also manually ask me to refresh this list by adding the props-bot label.

If you're merging code through a pull request on GitHub, copy and paste the following into the bottom of the merge commit message.

Co-authored-by: JasonTheAdams <jason_the_adams@git.wordpress.org>
Co-authored-by: felixarntz <flixos90@git.wordpress.org>
Co-authored-by: saarnilauri <laurisaarni@git.wordpress.org>

To understand the WordPress project's expectations around crediting contributors, please review the Contributor Attribution page in the Core Handbook.

@JasonTheAdams here is explanation for the parameters that I added in #194

I added $providerStopReason as reaching max tokens is not the only case when AI cuts of output. There is also the case for the when the Anthropic API return model_context_window_exceeded as a stop reason. I thought this param can help the developers to identify different cases.

The idea for $functionName was to highlight if the max tokens was the stop reason when the AI was doing a tool call and the output was cut out. I thought that this could help developers help to identify a tool call that makes AI output tokens over the limit.

The idea for $missingRequiredParameters is more detailed addition to $functionName. It would list all the required parameters for the tool call that was interupted due reaching the token limit. When Anthropic API is forming the parameters for the tool to be used and the token limit runs full the AI return the tool call but with only the parameters that is was able to fully generate. So, $missingRequiredParameters could help the developer to understand what part of the tool call is consuming the tokens and are missing.

Thanks for the context, @saarnilauri! Those do make sense, but feel a bit nice-to-have at the moment. Let's start simple and gather more feedback over time.