Uh oh!
There was an error while loading. Please reload this page.
chore: add agent app-creation docs evaluation harness - #455
Draft
adidottxt wants to merge 3 commits into
Draft
Conversation
Contributor
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
- Delete the dead codeSnippets response shape and its test/fixture remnants - Extract shared CLI helpers (arg parsing via node:util, output writing, gates table, main-error handling) into cli.mjs - Deduplicate scoring constants and helpers; score each Claude run once - Derive gate denominators from query groups instead of hard-coding counts - Run Claude trials through a bounded worker pool (--concurrency, default 4) - Index corpus chunks by page path; hoist token aliases; overlap visibility fetches with corpus fetches
adidottxt
marked this pull request as draft
August 12, 2026 19:57
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 freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the evaluation harness for measuring agent-path prominence in the app-creation docs, split out of #454 so that PR carries only the docs change.
run.mjsfetches production and previewllms-full.txt, ranks each query's canonical page with a small fielded BM25 retriever, and gates on tokens-to-first-agent-path plus agent-only visibility checks.claude-outcomes.mjsruns three Claude trials per query, using the retrieval output as the only documentation context.node --test evals/agent-app-creation/*.test.mjs).The Context7 comparison from the original PR was dropped; the local harness is the only gate.
Linear: https://linear.app/porter/issue/RUN-4007/chore-make-the-agent-path-more-prominent-in-the-app-creation-docs