This is an automated email from the ASF dual-hosted git repository.
Lee-W pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push:
new 350761ce775 Mark decision_policy experimental on the decision models
page and finish the ClassifierRetryPolicy stability row (#74713)
350761ce775 is described below
commit 350761ce775626f06ce2ae866fc0a7f78ffde692
Author: Wei Lee <[email protected]>
AuthorDate: Wed Oct 14 19:05:13 2026 +0900
Mark decision_policy experimental on the decision models page and finish
the ClassifierRetryPolicy stability row (#74713)
---
providers/common/ai/docs/decision_models.rst | 6 ++++--
providers/common/ai/docs/stability.rst | 5 ++++-
2 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/providers/common/ai/docs/decision_models.rst
b/providers/common/ai/docs/decision_models.rst
index 8320806ffb5..a84c895ab90 100644
--- a/providers/common/ai/docs/decision_models.rst
+++ b/providers/common/ai/docs/decision_models.rst
@@ -169,8 +169,8 @@ Where it fits in this provider
``llm_conn_id`` (or ``model_id``) at one is the only change, as long as
there are two
or more downstream tasks -- a one-option pick is refused. Describe each
branch in
``branches`` and set a
- ``decision_policy`` so an unsure pick goes to a person instead of
branching; see
- :doc:`operators/llm_branch`.
+ ``decision_policy`` (experimental, see :ref:`howto/stability`) so an
unsure pick goes
+ to a person instead of branching; see :doc:`operators/llm_branch`.
* - :class:`~airflow.providers.common.ai.operators.llm.LLMOperator` /
:class:`~airflow.providers.common.ai.operators.agent.AgentOperator`
with a typed
``output_type``
@@ -214,6 +214,8 @@ and
:class:`~airflow.providers.common.ai.operators.llm.LLMOperator` take a
``decision_policy`` whose ``min_confidence`` sends an unsure answer to a
person, or fails
the task, before anything downstream runs on it, and record the confidence, the
probabilities and the bar in the ``decision`` XCom (see
:doc:`operators/llm_branch`).
+``decision_policy`` and the per-option ``BranchOption.min_confidence`` are
experimental;
+see :ref:`howto/stability`.
:doc:`ClassifierRetryPolicy <retry_policies>` takes the same
``min_confidence`` and hands an
unsure answer to ``fallback_policy``, then its deterministic fallback rules.
In the branch operator and the retry policy, a
per-option bar lets the choice whose wrong pick costs most demand more
certainty than the rest.
diff --git a/providers/common/ai/docs/stability.rst
b/providers/common/ai/docs/stability.rst
index 70ce591b8cb..7877e20b709 100644
--- a/providers/common/ai/docs/stability.rst
+++ b/providers/common/ai/docs/stability.rst
@@ -182,7 +182,10 @@ Pydantic AI toolsets, but the Pydantic AI class they
inherit from can change.
names and their retry or fail split stay the same. When the model call
fails, or
``min_confidence`` is set and the answer is under it or carries no
confidence, the
policy uses the RETRY or FAIL of ``fallback_policy``, then
``fallback_rules``, then
- the task's own retry settings. Secrets are masked in the exception text
as for
+ the task's own retry settings. ``ErrorCategory.min_confidence``
overrides the
+ policy's ``min_confidence`` for that one category. ``min_confidence``
only has an
+ effect when the model reports a confidence, and that comes from the
``typesafe``
+ extra, which is still experimental. Secrets are masked in the exception
text as for
``LLMRetryPolicy``.
* - Output review: ``require_approval``, ``enable_hitl_review`` and the
review plugin
- With ``require_approval=True``, the task defers after generating output
and returns
