fix(anthropic): convert multimodal base64 inputs to attachments#212
Open
Abhijeet Prasad (AbhiPrasad) wants to merge 1 commit intomainfrom
Open
fix(anthropic): convert multimodal base64 inputs to attachments#212Abhijeet Prasad (AbhiPrasad) wants to merge 1 commit intomainfrom
Abhijeet Prasad (AbhiPrasad) wants to merge 1 commit intomainfrom
Conversation
Process Anthropic image and document input blocks before tracing so spans store Braintrust Attachments instead of raw base64 payloads. This keeps multimodal input logs consistent with other provider integrations and avoids bloating spans with binary data. Add a focused regression test for input normalization plus VCR-backed image and PDF tests that exercise the real Anthropic API. Closes #208
Abhijeet Prasad (AbhiPrasad)
requested a review
from ViaDézo1er / cedric (viadezo1er)
|
Drop into this review session: No serious bugs or issues found 🎉 |
Luca Forstner (lforst)
approved these changes
Apr 8, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Process Anthropic image and document input blocks before tracing so spans store Braintrust Attachments instead of raw base64 payloads. This keeps multimodal input logs consistent with other provider integrations and avoids bloating spans with binary data.
Add a focused regression test for input normalization plus VCR-backed image and PDF tests that exercise the real Anthropic API.
Closes #208