fix(litellm): fix gen_ai.request.messages to be as expected
#5255
+1,573
−1
Conversation
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
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
![sentry[bot]](https://avatars.githubusercontent.com/in/12637?s=60&v=4){kind=small}
…inal messages and handle data URLs correctly
Base automatically changed from
constantinius/fix/redact-message-parts-type-blob
to
master
January 13, 2026 09:56
Contributor
Semver Impact of This PR🟢 Patch (bug fixes) 📋 Changelog PreviewThis is how your changes will appear in the changelog. New Features ✨
Bug Fixes 🐛Litellm
Other
Documentation 📚
Internal Changes 🔧Release
Other
🤖 This preview updates automatically when you update the PR. |
sentry_sdk/integrations/litellm.py
Outdated
Comment on lines
90
to
95
| return { | ||
| "type": "blob", | ||
| "modality": "image", | ||
| "mime_type": mime_type, | ||
| "content": content, | ||
| } |
Contributor
There was a problem hiding this comment.
litellm accepts input which follows OpenAI format, is there an opportunity to deduplicate with the openai-python input handling here?
…AI messages Add transform_content_part() and transform_message_content() functions to standardize content part handling across all AI integrations. These functions transform various SDK-specific formats (OpenAI, Anthropic, Google, LangChain) into a unified format: - blob: base64-encoded binary data - uri: URL references (including file URIs) - file: file ID references Also adds get_modality_from_mime_type() helper to infer content modality (image/audio/video/document) from MIME types.
Replace local _convert_message_parts implementation with the shared transform_message_content function, removing ~50 lines of duplicated code.
Add dedicated transform functions for each AI SDK: - transform_openai_content_part() for OpenAI/LiteLLM image_url format - transform_anthropic_content_part() for Anthropic image/document format - transform_google_content_part() for Google GenAI inline_data/file_data - transform_generic_content_part() for LangChain-style generic format Refactor transform_content_part() to be a heuristic dispatcher that detects the format and delegates to the appropriate specific function. This allows integrations to use the specific function directly for better performance and clarity, while maintaining backward compatibility through the dispatcher for frameworks that can receive any format. Added 38 new unit tests for the SDK-specific functions.
LiteLLM uses OpenAI's message format, so use the OpenAI-specific transform_openai_content_part function directly for better performance. Also update test to reflect correct behavior: data URIs without base64 encoding are still inline data and should be treated as blobs, not URIs.
alexander-alderman-webb
approved these changes
Jan 16, 2026
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.
Issues
Closes https://linear.app/getsentry/issue/TET-1635/redact-images-litellm