Fix OpenAI messages empty stream handling#3808
Open
stgmt wants to merge 10 commits into
Open
Conversation
Contributor
|
All contributors have signed the CLA. ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
Clears obsolete OpenAI/Codex quota-origin model_rate_limits when fresh Codex usage snapshots show quota headroom, while preserving upstream model-not-found and image cooldowns.\n\nRefs #1
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fix the OpenAI
/v1/messagesAnthropic-compat streaming bridge so pre-output upstream failures are not surfaced to Claude-compatible clients as successful empty streams or generic 502s.This patch:
message_start.usage.input_tokenscontext_length_exceeded/ no-visible-output client failures to non-retryable Anthropic-compatible 4xx errors instead of masking them asUpstream service temporarily unavailableWhy
Claude-compatible clients can treat an Anthropic stream that only contains
message_start/message_stopas a completed assistant turn even when OpenAI Responses actually ended withresponse.failed,response.incomplete, or reasoning-only output. In large-context sessions this hides actionable upstream errors such ascontext_length_exceededbehind an empty reply or a generic 502.Tests
go test ./internal/pkg/apicompat -run TestStreamingMessageStartUsesPrefilledInputTokens -count=1go test ./internal/service -run 'TestOpenAIMessagesAnthropicStream(ContextLengthBeforeVisibleOutputReturnsClientError|BuffersStartUntilVisibleOutput)' -count=1go test ./internal/handler -run TestOpenAIHandleAnthropicFailoverExhaustedPreservesClientError -count=1Notes
I did not run the full unit/integration/lint matrix locally; the change is covered by targeted regression tests around the affected bridge path.