fix(openai): emit response.failed for /v1/responses after stream started

When /v1/responses streaming hits the user/account concurrency wait, the
wait loop sends SSE ping comments to keep the connection alive, which
flushes HTTP 200 + headers. If the wait then times out (or any other
post-flush error fires), handleStreamingAwareError previously emitted a
generic `event: error` frame. Codex CLI requires the stream to end with
a Responses terminal event (response.completed/failed/incomplete/cancelled),
so it reports "stream closed before response.completed" and the user-facing
rate-limit intent is lost.

This change detects inbound = /v1/responses in both handleStreamingAwareError
implementations and emits a protocol-compliant response.failed event whose
field set mirrors apicompat.makeResponsesCompletedEvent
(id/object/model/status/output/error). The synthetic id reuses
ctxkey.RequestID so client errors can be grepped against server logs.
sequence_number is intentionally omitted to preserve monotonicity on streams
that already emitted real events.

Other inbound endpoints (/v1/chat/completions, /v1/messages) keep their
legacy formats untouched.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Jamie WongandClaude Opus 4.7 committed 2026-05-24 10:58:29 +08:00
1 parent 63b0631a58
commit 5e5c2062bf
4 files changed
+330

No files matched your search

@@ -1691,6 +1691,15 @@ func (h *OpenAIGatewayHandler) mapUpstreamError(statusCode int) (int, string, st
// handleStreamingAwareError handles errors that may occur after streaming has started
func (h *OpenAIGatewayHandler) handleStreamingAwareError(c *gin.Context, status int, errType, message string, streamStarted bool) {
if streamStarted {
// /v1/responses 的严格 SDK(Codex CLI)要求终止事件必须属于
// response.completed/failed/incomplete/cancelled 集合。
// 通用 `event: error` 帧不被识别为终止事件,会导致
// "stream closed before response.completed"。
if GetInboundEndpoint(c) == EndpointResponses {
if writeResponsesFailedSSE(c, errType, message) {
return
}
}
// Stream already started, send error as SSE event then close
flusher, ok := c.Writer.(http.Flusher)
if ok {