Repository navigation
improvement(browser): accept observe on every page action - #9085
Merged
Merged
Conversation
Models carry observe: {} over from click and type to set_checked,
select_option, click_at, insert_text and drag, and the driver refused those
calls outright, costing a round each time (26 refusals across 650 benchmark
episodes). The observation runs after the action exactly as it does for the
other actions.
|
The latest updates on your projects. Learn more about Vercel for GitHub. |
Contributor
 [Medium impact] This PR appears safe to merge. SummaryAdds post-action observations to
Reviews (1) · Last reviewed commit: "improvement(browser): accept observe on ..." · Reviewed by Greptile |
This branch was previously deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Models pass
observe: {}to every page action because click and type accept it. The desktop driver refused the call outright forbrowser_click_at,browser_insert_text,browser_select_option,browser_set_checkedandbrowser_drag, which cost a round each time: 26 refusals in 650 benchmark episodes. These actions now run the post-action observation like the others.Paired A/B on the browser suites (WebGames, REAL, capbench; same seeds): refusals 11 → 0, and rounds on episodes both arms passed fell 4–8%. Pass rates were within noise (all p ≥ 0.5).
Test plan