wenjin272 commented on issue #912: URL: https://github.com/apache/flink-agents/issues/912#issuecomment-6076179261
Thanks @weiqingy. The timeline works for me. The proposed behavior also makes sense. We expect users to go through the setup layer and do not recommend calling `connection.chat(..., outputSchema)` directly, so there’s no need to retain the model allowlist check specifically for direct callers. The setup can own strategy selection, while connections apply the schema as requested and retain request-level validation. The docs can follow after code freeze. -- 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]
