kaxil opened a new pull request, #74307: URL: https://github.com/apache/airflow/pull/74307
The `usage_limits` docstrings on `AgentOperator` and `LLMOperator` say `None` (the default) "means no enforcement". That is wrong: pydantic-ai replaces `None` with `UsageLimits()` (`usage_limits = usage_limits or UsageLimits()` in `Agent.iter`), so its default `request_limit=50` still applies and a long tool loop fails with `UsageLimitExceeded` at 50 requests. That is the failure the run captured in #74297 hit with `usage_limits` unset. The docstrings now say `None` sets no token, cost, or tool-call limits but keeps the 50-request cap. The `LLMOperator` docstring also drops the sentence implying that moving from `None` to a `cost_limit`-only dict newly introduces the cap. Both already have it. The `LLM*` operators that inherit `usage_limits` from `LLMOperator` pick up the fix, and the how-to pages already describe the default correctly. Checked against `pydantic-ai-slim` 2.33.0 (the provider's floor) and 2.48.0: a `FunctionModel` that always calls a tool raises `UsageLimitExceeded: The next request would exceed the request_limit of 50` with `usage_limits=None`, and `UsageLimits(request_limit=None)` runs past 50 requests. --- * 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]
