Open
Conversation
jhgilbert
reviewed
Feb 19, 2026
Co-authored-by: Jen Gilbert <jen.gilbert@datadoghq.com>
…on into heston/llm-page-hint
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do? What is the motivation?
We publish
.mdversions of most pages on the docs site to help LLMs read our documentation, but agents seem to have trouble finding these pages when a user asks an Agent to fetch and read a page.This PR adds two methods to help the agent find the correct version of the page (if one exists).
If a
.mdversion of the page exists:.mdversion.metaentry to the page with the same link. This is a kind of fallback because some agents may automatically skip divs that are set todisplay:none. We haven't really landed on an industry standard for how agents search pages, so we have to cover a variety of bases.How it works
pages-json-cache.htmluses partialCached to download pages.json from the docs site and store the data in a cached Hugo dict.page-agent-hint.htmlchecks if a key exists in the cached dict and returns the.mdURL if one exists. This also uses partialCached to prevent multiple calls for the same page.Note:
bodyelement to get it to work