fix(gateway): detach upstream context unconditionally for image generation

Image generation requests (forwardOpenAIImagesOAuth and
forwardOpenAIImagesAPIKey) were calling detachStreamUpstreamContext with
parsed.Stream, which for non-streaming requests (Stream=false) simply
returned the original client context unchanged. When the client
disconnected before the upstream completed (30-80s for image gen), the
context cancellation propagated to the upstream HTTP request, causing a
502 error despite the upstream having already started processing.

Switch to detachUpstreamContext (unconditional detach) so the upstream
image generation request is always bound to a background context and
completes regardless of client lifecycle.

Fixes Wei-Shaw#2310

Author: wucm667

backend/internal/service/openai_images.go

@@ -639,7 +639,7 @@ func (s *OpenAIGatewayService) forwardOpenAIImagesAPIKey(
 		setOpsUpstreamRequestBody(c, forwardBody)
 	}
 
-	upstreamCtx, releaseUpstreamCtx := detachStreamUpstreamContext(ctx, parsed.Stream)
+	upstreamCtx, releaseUpstreamCtx := detachUpstreamContext(ctx)
 	defer releaseUpstreamCtx()
 
 	token, _, err := s.GetAccessToken(upstreamCtx, account)

backend/internal/service/openai_images_responses.go

@@ -948,7 +948,7 @@ func (s *OpenAIGatewayService) forwardOpenAIImagesOAuth(
 		)
 	}
 
-	upstreamCtx, releaseUpstreamCtx := detachStreamUpstreamContext(ctx, parsed.Stream)
+	upstreamCtx, releaseUpstreamCtx := detachUpstreamContext(ctx)
 	defer releaseUpstreamCtx()
 
 	token, _, err := s.GetAccessToken(upstreamCtx, account)