Re: [PR] Support Pydantic structured outputs in OpenAIResponseOperator [airflow]

["YAshhh29 (via GitHub)" <gi...@apache.org>]

YAshhh29 commented on PR #69812:
URL: https://github.com/apache/airflow/pull/69812#issuecomment-5839306256

   Hi @kaxil, sorry this one went quiet for so long. I pushed fixes for your July 30 review the same day but never replied to the threads, which I should have. I've answered them now. I'm also trying to move and get more used to Linux, so I can run Breeze and the full checks locally before pushing.
   
   Main changed this operator quite a bit in the meantime (#72049, #72150, #72151), so instead of just fixing the conflicts I wired structured outputs into those changes:
   
   - `max_output_tokens` and `max_tool_calls` now work for structured requests too
   - `response_id` and `usage` are pushed to XCom for structured responses as well, before the output is checked, so even a rejected response shows what it cost (same order as `OpenAIAgentSessionOperator`)
   - `text_format` is keyword-only now
   - the XCom push moved into a small shared helper, in its own commit with no behaviour change
   
   I tested it on openai 2.37, 2.46 and 2.54, and checked that every safeguard has a test that fails if it's removed. Would you mind taking another look when you get a chance?
   
   cc @Lee-W, since this builds on your recent changes to the operator.
   


-- 
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: commits-unsubscribe@airflow.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org