Skip to content

Conversation

@jck411
Copy link
Owner

@jck411 jck411 commented Nov 14, 2025

Enable display of images from tool outputs in the chat frontend by rehydrating attachments in the backend and processing them in the frontend.

Previously, when a tool like gdrive_analyze_image was invoked, the LLM would analyze the image and provide a description, but the image itself was not visible in the chat interface. This PR ensures that the backend includes the full multimodal content with signed URLs in the tool event payload, and the frontend's chat store is updated to correctly parse and display these attachments, making the image visible to the user.


Open in Cursor Open in Web

Co-authored-by: jck411 <jck411@gmail.com>
@cursor
Copy link

cursor bot commented Nov 14, 2025

Cursor Agent can help with this pull request. Just @cursor in comments and I'll start working on changes in this branch.
Learn more about Cursor Agents

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants