Enable browser use for all browsers that support images

[chrarnoldus]

RooCodeInc/Roo-Code#5026 does this more thoroughly,
but limits browser use to Claude and Gemini for some reason.

From my testing it additionally also works with GPT-4.1, Mistral Medium 3 and Qwen 2.5 VL

[changeset-bot]

🦋 Changeset detected

Latest commit: 170e623

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
kilo-code	Minor

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[Copilot]

Pull Request Overview

This PR extends browser tool availability to all models that support image inputs by swapping out the supportsComputerUse check for supportsImages, and records the change in the project’s changelog.

• Replaces supportsComputerUse with supportsImages for browser gating in Task.ts
• Adds a changeset entry to document enabling browser tool for image-capable models

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
src/core/task/Task.ts	Use supportsImages flag to gate browser tool enablement instead of supportsComputerUse
.changeset/legal-wasps-shine.md	Document the change by enabling browser tool for all models that can read images

Comments suppressed due to low confidence (2)

src/core/task/Task.ts:1713

• Consider adding a unit or integration test to verify that browserToolEnabled is correctly gated by the supportsImages flag, ensuring no unintended models gain browser access.

				(this.api.getModel().info.supportsImages ?? false) && (browserToolEnabled ?? true),

.changeset/legal-wasps-shine.md:5

• [nitpick] For grammatical clarity, add a comma after "GPT":

Enable browser tool for Gemini, GPT, and all other models that can read images

Enable browser tool for Gemini, GPT and all other models that can read images