Add pre-task baseline verifier check to warn on org contamination - #8
Open
laurahanu wants to merge 1 commit into
Open
Add pre-task baseline verifier check to warn on org contamination#8laurahanu wants to merge 1 commit into
laurahanu wants to merge 1 commit into
Conversation
|
Thanks for the contribution! Before we can merge this, we need @laurahanu to sign the Salesforce Inc. Contributor License Agreement. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Runs the SCUBA verifier against the starting org before each task begins and logs a warning if the baseline score is > 0. A clean org should score 0, so a non-zero baseline signals leftover artifacts from a previous run that could inflate the final score. This is a defensive layer to catch contamination before the agent starts.
utils.py: sharedrun_baseline_check()helper; skips QA templates (they need an agent answer) and never raises so a check failure can't break the runargs.py:--pretask_baseline_checkflag (default on;--no-to disable)main_bu.py: check runs beforeagent.run()lib_eval_single_task.py: check runs in both CUA workers after env resetTest plan
--no-pretask_baseline_checkdisables the check