fix(ui): emit safe errors for failed SSE streams#226
Open
EfeDurmaz16 wants to merge 1 commit into
Open
Conversation
|
@EfeDurmaz16 is attempting to deploy a commit to the Vercel Labs Team on Vercel. A member of the Team first needs to authorize it. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
A FastAPI route can start streaming an agent response before the upstream provider fails. In that case,
to_sse()currently propagates the exception, so AI SDK UI receives a truncated response with no protocol error and no[DONE]marker.This change:
UIErrorEventfor ordinary stream failuresAn error occurred.by defaulton_errorcallback for logging or a deliberate client-facing message[DONE]to_stream(), cancellation, and generator shutdown behavior unchangedWhy
The existing
web_agentexample pipesto_sse()directly into FastAPIStreamingResponse. Once the response has started, an in-band AI SDK UI error chunk is the only structured way to report a provider failure touseChat.This follows the concrete AI SDK UI interoperability direction discussed in #224.
Verification
uv run --frozen pytest -q: 593 passedSuggested release label:
fix.