Skip to content

feat(browser): add in-app element picker for active split agents #2519

Description

@Drakaniia

Feature Summary

Add an in-app browser element picker that lets users select an element from the browser pane and insert its context into any active agent running in a split pane.

Problem or Use Case

When debugging or automating UI work, users often need to point an agent at a specific browser element. Manually copying selectors, text, attributes, or outer HTML is slow and error-prone.

Proposed Solution

  • Add a browser toolbar action to enter element selection mode.
  • Highlight hovered elements inside the in-app browser.
  • Capture useful element context:
    • URL
    • page title
    • tag
    • CSS selector
    • XPath
    • visible text
    • relevant attributes
    • bounding box
    • outer HTML
  • Insert the captured element context into the active running agent in a split pane.
  • Show feedback if no active agent is available.

Alternatives Considered

No response

Additional Context

This improves UI automation, debugging, QA, and frontend development workflows by making it easier to hand off precise browser context to coding agents.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions