DEMO: intentional skill regression for eval pipeline validation (DO NOT MERGE)#61
Draft
saurabhrb wants to merge 1 commit into
Draft
DEMO: intentional skill regression for eval pipeline validation (DO NOT MERGE)#61saurabhrb wants to merge 1 commit into
saurabhrb wants to merge 1 commit into
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Purpose
Demo branch for validating the eval pipeline catches skill regressions. DO NOT MERGE.
Recreated from a fresh branch off
main(replaces closed PR #58) now that the pipeline default branch ismain.What's regressed
dv-data/SKILL.mdreplacesCreateMultiplebulk-create guidance with a per-record loop antipattern:forloopCreateMultiplereferences removedHow it's used
The ADO pipeline
DVSkillsPlugin-Evals-PR(32010) runs against this branch. Thedata_003_skill_contracttest asks the agent to report what the skill teaches, andNOT_CONTAINS:assertions catch the regressed content.Expected result: 2/3 FAIL (data_003 catches the regression; data_001 and data_002 may still pass due to model prior knowledge).