kaxil opened a new pull request, #73904: URL: https://github.com/apache/airflow/pull/73904
With `enable_hitl_review=True`, `AgentOperator` ran the approved text through `json.loads` unless `output_type` was a Pydantic model. So with the default `output_type=str`, an approved answer of `42` came back as an int, and one that looked like a JSON object came back as a dict. `@task.llm` returns the same text unchanged. It now uses the same conversion as `LLMOperator`'s approval path: a `str` output passes through unchanged, any other `output_type` is validated from the JSON, and an edit the type rejects falls back to the reviewer's text. The new test fails on the old code for the two `str` cases. --- * Read the **[Pull Request Guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#pull-request-guidelines)** for more information. Note: commit author/co-author name and email in commits become permanently public when merged. * For fundamental code changes, an Airflow Improvement Proposal ([AIP](https://cwiki.apache.org/confluence/display/AIRFLOW/Airflow+Improvement+Proposals)) is needed. * When adding dependency, check compliance with the [ASF 3rd Party License Policy](https://www.apache.org/legal/resolved.html#category-x). * For significant user-facing changes create newsfragment: `{pr_number}.significant.rst`, in [airflow-core/newsfragments](https://github.com/apache/airflow/tree/main/airflow-core/newsfragments). You can add this file in a follow-up commit after the PR is created so you know the PR number. -- 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]
