Repository navigation
Rename Webwright to CUAWright and add OSWorld desktop workflows - #77
Merged
Merged
Conversation
Preserve separate browser and desktop contracts, add pinned OSWorld setup and verification, support custom and official desktop runs, and redact transport identity from public artifacts. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: 3dd553c9-070f-4969-ad26-3dffb49d4178
Set the desktop --reasoning default to xhigh and document the effort used for each reported OSWorld-V2 score (GPT-5.6 Sol max, GPT-5.5 xhigh). Move browser workflow details into docs/browser.md. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Link the CUAWright arXiv paper and add its BibTeX entry. Replace the Performance section with the six-benchmark results and OSWorld-V2 cost plot. Show the CUAWright demo first and fold the Webwright demo. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Renames Webwright to CUAWright and adds an OSWorld-V2 desktop runtime alongside the browser runtime.
cuawright.webwright. Existingwebwrightcommands and Python imports still work through compatibility aliases.cuawright.desktop): a persistent Actor in a pinned OSWorld Ubuntu VM. Tasks finish only through an explicitsubmit.pycommand. Includes official task setup, evaluation, and provenance (manifest.json,trace.jsonl,result.json).cuawright desktop runfor custom tasks andcuawright desktop reproduce osworldfor scored reproduction.cuawright setup osworld/cuawright verify osworlddownload and check the pinned release.cuawright.coreholds the Responses API helpers that both runtimes use.extensions/skill-factory.--reasoningflag defaults toxhigh.REPRODUCE.mdlists the effort for each reported score: GPT-5.6 Solmax= 67.9, GPT-5.5xhigh= 63.2 (OSWorld-V2 partial score).REPRODUCE.mdfor desktop anddocs/browser.mdfor browser workflows. The README is reorganized.All existing commits on
mainare kept, including the trajectory comparison tool and figures from #24.Testing
release/osworld/tests: 90 passed, 1 skipped.pytest -q, both wheel builds, andtests/packaging/check_wheels.pystill need to run in CI.🤖 Generated with Claude Code