Skip to content

feat: Add computer use#402

Merged
Henry-811 merged 7 commits intodev/v0.1.9from
computer_tool_use
Nov 7, 2025
Merged

feat: Add computer use#402
Henry-811 merged 7 commits intodev/v0.1.9from
computer_tool_use

Conversation

@franklinnwren
Copy link
Copy Markdown
Collaborator

@franklinnwren franklinnwren commented Nov 2, 2025

Description

Enable computer use feature of massgen. Currently, we only support gemini computer use, claude computer use, and simple browsing, refer to MassGen/massgen/backend/docs/COMPUTER_USE_TOOLS_GUIDE.md for details

Closes MAS-23

Type of change

  • Bug fix (fix:) - Non-breaking change which fixes an issue
  • New feature (feat:) - Non-breaking change which adds functionality
  • Breaking change (breaking:) - Fix or feature that would cause existing functionality to not work as expected
  • Documentation (docs:) - Documentation updates
  • Code refactoring (refactor:) - Code changes that neither fix a bug nor add a feature
  • Tests (test:) - Adding missing tests or correcting existing tests
  • Chore (chore:) - Maintenance tasks, dependency updates, etc.
  • Performance improvement (perf:) - Code changes that improve performance
  • Code style (style:) - Changes that do not affect the meaning of the code (formatting, missing semi-colons, etc.)
  • CI/CD (ci:) - Changes to CI/CD configuration files and scripts

Checklist

  • I have run pre-commit on my changed files and all checks pass
  • My code follows the style guidelines of this project
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing unit tests pass locally with my changes

How to Test

Unit tests in MassGen/massgen/tests/test_computer_use.py

Test CLI Command

massgen --config @gemini_computer_use_example.yaml
image image

Gemini computer use successfully find the number

massgen --config @simple_browser_automation_example.yaml

(Using GPT as default)
Screenshot 2025-11-06 at 8 00 58 PM
Screenshot 2025-11-06 at 8 01 17 PM

GPT successfully find the number

massgen --config @claude_computer_use_example.yaml
Screenshot 2025-11-06 at 7 47 28 PM Screenshot 2025-11-06 at 8 04 11 PM

Claude computer user failed to find the number, but successfully opened the page and analyzed its failure.

Additional context

TODO: Support OpenAI computer use from Azure

@franklinnwren franklinnwren marked this pull request as draft November 2, 2025 00:37
@franklinnwren franklinnwren marked this pull request as ready for review November 7, 2025 04:50
@Henry-811 Henry-811 changed the base branch from main to dev/v0.1.10 November 7, 2025 15:43
@Henry-811 Henry-811 deleted the branch dev/v0.1.9 November 7, 2025 16:23
@Henry-811 Henry-811 closed this Nov 7, 2025
@Henry-811 Henry-811 reopened this Nov 7, 2025
@Henry-811 Henry-811 changed the base branch from dev/v0.1.10 to dev/v0.1.9 November 7, 2025 16:29
@Henry-811 Henry-811 merged commit c60cad7 into dev/v0.1.9 Nov 7, 2025
47 checks passed
@qidanrui qidanrui deleted the computer_tool_use branch November 14, 2025 08:48
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants