nic-6443 opened a new pull request, #13922: URL: https://github.com/apache/apisix/pull/13922
Streaming responses without `usage` never populated `llm_response_text`, so `ai-aliyun-content-moderation` could silently skip its final-packet response check even after receiving the complete text. Finalize the accumulated text on protocol completion and clean EOF, independently of token accounting. Existing usage handling and interrupted-stream behavior stay the same. Add Consumer-level integration coverage for streams with and without usage, including clean EOF without a terminal event, and document that response moderation does not require usage statistics. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
