Lee-W opened a new pull request, #74450:
URL: https://github.com/apache/airflow/pull/74450
## Why
- `LLMBranchOperator` builds its output type from its downstream task IDs,
but it silently dropped any `output_type` the caller passed
(`kwargs.pop("output_type", None)`). A user who sets it gets no signal that it
has no effect.
- The HITL review loop in `run_hitl_review` swallowed `xcom_pull` errors
with a warning and kept polling. Since `hitl_timeout` can be `None`, persistent
failures (for example an unreachable API server) made the task spin forever.
- `LLMOperator.output_type` was annotated as `type`, which is narrower than
what pydantic-ai accepts.
## What
- `LLMBranchOperator`: passing `output_type` now raises `TypeError` instead
of being silently dropped. **This is a behaviour change**: callers who passed
it before (and had it rror.
- HITL review (`mixins/hitl_review.py`): added
`_MAX_CONSECUTIVE_XCOM_PULL_FAILURES = 10` and a `consecutive_pull_failures`
counter in the `run_hitl_review` loop. Each `xcom_pit. On the 10th consecutive
failure the originalexception is re-raised unchanged. Otherwise it logs a
warning and continues. A successful pull resets the counter to 0.
- When `hitl_timeout` is set, persistent XCom faial error on the 10th
failure instead of waiting forthe deadline and raising `HITLTimeoutError`.
- `LLMOperator`: `output_type: type = str`
becomes ny] = str`, with `OutputSpec` imported from`pydantic_ai.output` under
`TYPE_CHECKING`. This accepts union and list forms, ma- Tests:
- `test_hitl_review.py`: added `test_xcom_pull_failures_raise_after_limit`
and `test_xcom_pull_failure_counter_resets_on_success`.
- `test_llm_branch.py`: `test_output_type_ignored` becomes
`test_output_type_rejected`.
<!-- SPDX-License-Identifier: Apache-2.0
https://www.apache.org/licenses/LICENSE-2.0 -->
<!--
Thank you for contributing!
Please provide above a brief description of the changes made in this pull
request.
Write a good git commit message following this guide:
https://chris.beams.io/posts/git-commit/
Please make sure that your code changes are covered with tests.
And in case of new features or big changes remember to adjust the
documentation.
For user-facing UI changes, please attach before/after screenshots (or a
short
screen recording) so reviewers can assess the visual impact.
Feel free to ping (in general) for the review if you do not see reaction for
a few days
(72 Hours is the minimum reaction time you can expect from volunteers) - we
sometimes miss notifications.
In case of an existing issue, reference it using one of the following:
* closes: #ISSUE
* related: #ISSUE
-->
---
##### Was generative AI tooling used to co-author this PR?
<!--
If generative AI tooling has been used in the process of authoring this PR,
please
change below checkbox to `[X]` followed by the name of the tool, uncomment
the "Generated-by".
-->
- [x] Yes (please specify the tool below)
Generated-by: [Claude] following [the
guidelines](https://github.com/apache/airflow/blob/main/contributing-docs/05_pull_requests.rst#gen-ai-assisted-contributions)
---
* 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]
