fix: target explicit computer use app windows#25674
Open
helaskeutuja wants to merge 2 commits into
Open
Conversation
Collaborator
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
computer_use capture(app=...)targeting for macOS apps whose usable AX window is not returned bylist_windows(on_screen_only=True)Test Plan
scripts/run_tests.sh tests/tools/test_computer_use.pyReal behavior proof
computer_use capture(app="DaVinci Resolve")could fall back to iTerm2 because DaVinci Resolve's main AX window appeared only when listing all windows, not on-screen-only windows.cua-driver 0.1.9, Accessibility and Screen Recording granted.CUA_DRIVER_MCP_NO_RELAUNCH=1 hermes chat -q 'Käytä vain computer_use-työkalua. Tee capture mode=ax app="DaVinci Resolve"...' --toolsets computer_use -QApp/window: DaVinci Resolve, “Untitled Project”andElementtimäärä: 104.mode=somread-only capture also selected DaVinci Resolve and returned 104 interactable elements, but no screenshot dimensions.