History processor replaces message history

[AlexEnrique]

This PR closes #2095

Summary

• [BREAKING CHANGE]: history_processor's now replaces the message history with its result.
• Updates docs with warnings about new behavior and issues related to slicing the message history
• Added tests to test new behavior

Concerns

The new behavior also processes/replaces the current ModelRequest being sent to the LLM. This may lead to unexpected behaviors for users of the library, for example, the following history_processor must prepend the messages[-1:] in order to not remove the model request being sent.

def process_previous_answers(messages: list[ModelMessage]) -> list[ModelMessage]:
        # Keep the last message (last question) and add a new system prompt
        return messages[-1:] + [ModelRequest(parts=[SystemPromptPart(content='Processed answer')])]

Although this may be unexpected, changing it to keep the last model request as is may also be a surprise for users. This was in conflict with exiting tests and I though it would be better to keep in this way and let the library user handle this.

I've added a warning to the docs, but maybe I need to emphasize this more.

c.c: @Kludex

[hyperlint-ai]

PR Change Summary

Updated the message history processing behavior in the library, introducing breaking changes and enhanced documentation to address potential user concerns.

• Replaced message history with results from the history processor, introducing a breaking change.
• Updated documentation with warnings about new behavior and issues related to message history slicing.
• Added tests to validate the new message history processing behavior.

Modified Files

• docs/message-history.md

---

How can I customize these reviews?

Check out the Hyperlint AI Reviewer docs for more information on how to customize the review.

If you just want to ignore it on this PR, you can add the hyperlint-ignore label to the PR. Future changes won't trigger a Hyperlint review.

Note specifically for link checks, we only check the first 30 links in a file and we cache the results for several hours (for instance, if you just added a page, you might experience this). Our recommendation is to add hyperlint-ignore to the PR to ignore the link check for this PR.

[Wh1isper]

LGTM

[DouweM]

@AlexEnrique Thanks Alex! The code looks good to me but I'd like for @Kludex to have a look at the concern you mention in the description as he built the feature. He's out this week though, so expect a more careful review of the implications early next week!