Skip to content

[Feature Request] BrowserToolkit enhancement roadmap #2886

@lightaime

Description

@lightaime

Required prerequisites

Motivation

  • Rename browser toolkits function names to include browser. For example, click -> browser_click
  • Add snapshot tags descriptions to tools' docstrings4 that related to snapshots
  • Add a mode to show only the snapshot in the current window instead of the whole page to reduce context
  • Add browser_console_exec to execute JavaScript code in the browser console.
  • Add browser_console_view to allow agent be able to view the info from the browser console for debugging
  • Add browser_mouse_control to allow agent be able to interact with browser with x,y coordinates
  • Add browser_press_key to allow agent be able to press keys and key combinations
  • Add browser_select_option to allow select option from a dropdown list

Solution

No response

Alternatives

No response

Additional context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions