fix(OpenAI): don't bail out early on text/plain - only if JSON parsing errors occurred.#736
Merged
iBotPeaches merged 2 commits intomainfrom Jan 18, 2026
Merged
fix(OpenAI): don't bail out early on text/plain - only if JSON parsing errors occurred.#736iBotPeaches merged 2 commits intomainfrom
iBotPeaches merged 2 commits intomainfrom
Conversation
iBotPeaches
force-pushed
the
issue-735
branch
from
1f8302f to
1356bdf
Compare
iBotPeaches
changed the title
Radiergummi
approved these changes
Jan 18, 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What:
Description:
We have a problem that we get JSON back with
Content-Type: text/plainwhich destroys our SDK. This is because for some multi-modal endpoints like transcription - we get back non-JSON intentionally. So we rely on Content-Type to skip JSON decoding and move along.So errors or logic that is valid JSON with a wrong Content-Type cause bad things. I'd argue this is a bug with upstream providers, but we need to make a change.
Now during JSON parsing if we have an Exception (i.e not json) - we first check the Content-Type. If its not JSON - we bail out with no exception.
Related:
fixes: #735
closes: #723