Added request_id to the model response.

[peterHoburg]

I could not find an easy way to get the AWS Bedrock generated request_id in the response.

Is this something other people would want to use? If so I can update the docs, fix the tests, and update the other models to set request_id (if they support it).

[hyperlint-ai]

PR Change Summary

Added request_id to the model response to facilitate tracking of AWS Bedrock requests.

• Introduced request_id in the model response for better request tracking.
• Updated multiple documentation files to include the new request_id parameter.

Modified Files

• docs/agents.md
• docs/message-history.md
• docs/tools.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.

[DouweM]

@peterHoburg Is this equivalent to OpenAI's chat.id at https://platform.openai.com/docs/api-reference/chat/object? What do you think about calling it vendor_id and covering other providers as well?

[peterHoburg]

@peterHoburg Is this equivalent to OpenAI's chat.id at https://platform.openai.com/docs/api-reference/chat/object? What do you think about calling it vendor_id and covering other providers as well?

@DouweM Yes it is the same, and that sounds great! I will make the changes tonight and mark the PR as ready to review.

[DouweM]

@peterHoburg Thank you! Can you please implement this for OpenAI as well using the chat.id I mentioned above? Note that there are 2 model classes in models/openai.py.

[DouweM]

@peterHoburg Alternatively, in #1238 we're adding a new vendor_metadata dict that could also be a good place for this so we don't immediately have to try to support this for all models. If it works for you, we can wait for that to land and you can add the request_id there in a new PR.