feat: hint field filtering in get-dataset-items description#1032
Open
RobertCrupa wants to merge 2 commits into
Open
feat: hint field filtering in get-dataset-items description#1032RobertCrupa wants to merge 2 commits into
RobertCrupa wants to merge 2 commits into
Conversation
jirispilka
requested changes
Jun 26, 2026
jirispilka
left a comment
Collaborator
There was a problem hiding this comment.
First I would not tell the model do this or this. There should be one preferred way.
Second, I would not even nudge model to get-dataset-schema. The schema is typically very big and will blow out the context (the would be against the idea that you want to achieve here), see this PR: #986 w.r.t to dataset-schema
Address review: drop the get-dataset-schema pointer (schemas are large and blow out context) and the "this or that" phrasing — point only at get-dataset for field discovery. Tighten the nudge wording. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Q286TCpASDvaeUhPRnGgh6
Contributor
Author
|
@jirispilka Thank you for your comment. I think I went from being too aggressive to too passive here :) Hopefully this new nudge is better |
jirispilka
approved these changes
Jun 26, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Nudges the
get-dataset-itemstool description to passfieldswhen only specific columns are needed, to reduce response size.The hint is framed as optional ("when you only need specific columns") so the model does not under-fetch data the user actually asked for. It points only at
get-datasetfor discovering field names — a lightweight metadata call — notget-dataset-schema, which is often large and would blow out the context (the opposite of the goal here; see #986).Why
Takeaway from the workflow eval work: dataset responses are often large, and selecting only the needed columns meaningfully cuts response size when the full row isn't required.
Verification
pnpm run type-check— cleanpnpm run lint— cleanpnpm run test:unit— cleanpnpm run format— cleanpnpm run check:agents— clean