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Outdated suggestions cannot be applied.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.
Problem
The streaming methods (fetchStream and fetchAssistantStreamEvents) don't decode OpenAI error responses, only returning generic "status code X" messages instead of detailed error information.
Solution
Apply the same OpenAI error decoding logic from the working fetch method to both streaming methods.
Note
This PRs also modifies the
errorMessageto keep the original error message from API server, giving application full control over how to construct the final error message. Rationale: I think at library-level, we should not modify the error message from remote API server. This would make it very difficult at the app-level to offer good error reporting UX.