Repository navigation
Conversation
Contributor
|
Automated PR Cleanup Thank you for contributing to opencode. Due to the high volume of PRs from users and AI agents, we periodically close older PRs using automated criteria so maintainers can focus review time on the most active and community-supported contributions. This PR was closed because it matched the following cleanup criteria:
PRs created within the last month are not affected by this cleanup. If you believe this PR was closed incorrectly, or if you are still actively working on it, please leave a comment explaining why it should be reopened. A maintainer can review and reopen it if appropriate. Thanks again for taking the time to contribute. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Closes #30916
Type of change
What does this PR do?
Some OpenAI-compatible gateways serving the Responses API (
/v1/responses) emit a synthetic SSE frame at the start of the stream withid: "chatcmpl-dummy"andobject: "chat.completion.chunk"before the real Responses API events. This frame has empty content ("content":"") and noevent:prefix, so it is not a valid Responses API event.When the AI SDK receives this frame, it tries to validate it against the Responses API event schema union, which fails with a
TypeValidationErrorthat terminates the agent turn immediately. All subsequent real events are lost.The fix pipes the SSE response body through a
TransformStreamin the customfetchwrapper insideresolveSDK(). Each chunk is split into SSE frames; if adata:line parses as JSON and hasid === "chatcmpl-dummy", that frame is dropped. All other frames pass through unchanged.The filter is scoped to Responses API calls only (URL contains
/responsesand content-type istext/event-stream), so it does not affect Chat Completions streams or other providers.How did you verify your code works?
opencode run "say hi" --model openai/gpt-5.5no longer errors.chatcmpl-dummyframe) continues to work.tsgo --noEmitinpackages/opencode.Screenshots / recordings
N/A — not a UI change.
Checklist
Update: the filtering is now configurable through
opencode.jsonvia provider options, for exampleprovider.openai.options.filterSseFrame.By default, no SSE frames are filtered. The filter only runs when
filterSseFrameis explicitly configured, so existing users are unaffected.