fix(clients): avoid empty text parts when encoding OpenAI message content#37
Open
DeNeRATe-cool wants to merge 1 commit intoArtificialAnalysis:mainfrom
Open
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This change updates
content_to_openaiso that an empty string is passed through as""instead of being wrapped as[{"type": "text", "text": ""}]. Empty string segments inside list content are skipped, and if no parts remain, the result is"".Background
Assistant turns that only invoke tools often have
content="". Some OpenAI-compatible gateways appear to strip emptytextfields from content parts, which can leave invalid fragments containing onlytypeand trigger 400 errors. Representing “no visible content” as a plain empty string aligns better with common API usage for assistant messages that includetool_calls.Thank you for maintaining Stirrup — happy to adjust anything if you would prefer a different approach or additional coverage.