Enable 'grounding' for gemini via vertex AI too

[anguslees]

What specific problem does this solve?

#5959 enabled grounding features for gemini via the gemini API. We should make it possible to use these gemini features via vertex AI too.

Additional context (optional)

No response

Roo Code Task Links (Optional)

No response

Request checklist

• I've searched existing Issues and Discussions for duplicates
• This describes a specific problem with clear impact and context

Interested in implementing this?

• Yes, I'd like to help implement this feature

Implementation requirements

• I understand this needs approval before implementation begins

How should this be solved? (REQUIRED if contributing, optional otherwise)

From a quick look at the code, I think vertex AI provider inherits from gemini provider - so the necessary code is all there. I think we just have to add the UI options to allow this to be enabled.

How will we know it works? (Acceptance Criteria - REQUIRED if contributing, optional otherwise)

No response

Technical considerations (REQUIRED if contributing, optional otherwise)

No response

Trade-offs and risks (REQUIRED if contributing, optional otherwise)

No response

[roomote]

I'm here to help out the maintainers and am going to see if I can fix this issue! I'll work on enabling the grounding features for Vertex AI, since the backend code should already support it through inheritance from the Gemini provider. I'll focus on adding the necessary UI options to make these features accessible for Vertex AI users.

[roomote]

I've successfully implemented the grounding features for Vertex AI! 🎉

The implementation is complete and a pull request has been created: #6777

Summary of changes:

• Added URL context and Google Search grounding options to the Vertex AI provider settings
• Updated the Vertex.tsx UI component to include the same checkboxes as the Gemini provider
• Added comprehensive tests for the new functionality
• Reused existing localization strings from the Gemini provider

Since Vertex AI inherits from the Gemini provider, the backend functionality was already in place - we just needed to expose the UI options. All tests are passing and the CI checks are currently running on the PR.

This should now allow Vertex AI users to take advantage of the same grounding features that were previously only available for the Gemini provider.