Skip to content

Conversation

@roomote
Copy link
Contributor

@roomote roomote bot commented Jul 23, 2025

This PR enables video upload support for Gemini 2.5 Pro and Flash models in Roo Code.

Changes

  • Added supportsVideo property to the ModelInfo schema
  • Marked Gemini 2.5 Flash and all Gemini 2.5 Pro model variants as supporting video
  • Updated ChatTextArea component to accept video files (mp4, mov, avi, webm) when the selected model supports video
  • Video files are handled through the existing image upload mechanism, as Gemini API accepts both images and videos through the same inlineData format

Implementation Details

  • The supportsVideo property is optional and defaults to false for backward compatibility
  • Video support is conditionally enabled based on the selected model
  • Supported video formats: MP4, MOV, AVI, WebM
  • No changes were needed to the Gemini format transformer as it already handles videos correctly

Fixes #6144


Important

Adds video upload support for Gemini 2.5 Pro and Flash models by introducing a supportsVideo property and updating UI components to handle video files.

  • Behavior:
    • Adds supportsVideo property to modelInfoSchema in model.ts, defaulting to false for backward compatibility.
    • Enables video upload for Gemini 2.5 Pro and Flash models in gemini.ts by setting supportsVideo to true.
    • Updates ChatTextArea in ChatTextArea.tsx to accept video files (mp4, mov, avi, webm) if the model supports video.
    • Video files are processed through the existing image upload mechanism.
  • UI Components:
    • Modifies ChatTextArea and ChatView to handle video file selection and upload.
    • Adds supportsVideo prop to ChatTextArea to conditionally allow video uploads.
  • Misc:
    • No changes to the Gemini format transformer as it already supports videos.

This description was created by Ellipsis for d5cbfea. You can customize this summary. It will automatically update as commits are pushed.

- Add supportsVideo property to ModelInfo schema
- Mark Gemini 2.5 Flash and Pro models as supporting video
- Update ChatTextArea to accept video files (mp4, mov, avi, webm) when model supports video
- Pass supportsVideo prop from ChatView to ChatTextArea component

Fixes #6144
@roomote roomote bot requested review from cte, jr and mrubens as code owners July 23, 2025 23:39
@dosubot dosubot bot added size:M This PR changes 30-99 lines, ignoring generated files. enhancement New feature or request labels Jul 23, 2025
@hannesrudolph hannesrudolph added the Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. label Jul 23, 2025
@daniel-lxs
Copy link
Member

Closing in favor of #6150, it seems to have a more complete implementation

@daniel-lxs daniel-lxs closed this Jul 24, 2025
@github-project-automation github-project-automation bot moved this from Triage to Done in Roo Code Roadmap Jul 24, 2025
@github-project-automation github-project-automation bot moved this from New to Done in Roo Code Roadmap Jul 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request Issue/PR - Triage New issue. Needs quick review to confirm validity and assign labels. size:M This PR changes 30-99 lines, ignoring generated files.

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

feat: Enable Video Uploads for Multimodal Analysis

4 participants