feat: add recall skill for forward ML lineage blast radius - #139
Open
Ahmad-Zeid wants to merge 1 commit into
Open
feat: add recall skill for forward ML lineage blast radius#139Ahmad-Zeid wants to merge 1 commit into
Ahmad-Zeid wants to merge 1 commit into
Conversation
Teaches agents to bound a data defect window via ACK/MCP, cross the dataset→model→deployment hops via aspect reads (get_lineage returns 0 there today), and write a scoped recall back into DataHub. References datahub#19061 and the measured lineage gap. Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds
skills/datahub-recall/— a workflow skill for forward blast-radius on contaminated training data (source → batches → dataset → model → deployment).Why
DataHub's agent lineage tools stop at the dataset layer for ML hops (
get_lineagereturns 0 for dataset→model and model→deployment on GMS v1.6.0), even though aspects store the edges. Agents that trust an empty lineage result will miss production impact.Filed upstream: datahub-project/datahub#19061
This skill teaches:
get_lineage)Reference implementation from the Agent Hackathon: https://github.com/Ahmad-Zeid/recall
Test plan
Made with Cursor