fix(backend): use ai-sdk buffer instead of data url#1410
Merged
Conversation
After an ai-sdk update the old way led to problems with some models like gpt-5-nano.
There was a problem hiding this comment.
Pull request overview
This PR updates the files-vision tool to send image inputs to ai-sdk as binary buffers (with explicit MIME types) instead of embedding images as base64 data URLs, addressing compatibility issues introduced after an ai-sdk update (notably with models like gpt-5-nano).
Changes:
- Convert stored base64-encoded image blobs into
Bufferinstances (Buffer.from(..., 'base64')) for model input. - Update the
generateTextprompt image parts to passimageas binary data plusmimeTyperather than a data URL string.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
surt91
changed the title
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
After an ai-sdk update the old way led to problems with some models like gpt-5-nano.
See also: https://github.com/vercel/ai/releases/tag/ai%406.0.116