Lee-W commented on code in PR #74695:
URL: https://github.com/apache/airflow/pull/74695#discussion_r4374366988
##########
providers/common/ai/src/airflow/providers/common/ai/operators/agent.py:
##########
@@ -1106,21 +1114,13 @@ def _complete_run(self, context: Context, result: Any,
*, attempt_usage: RunUsag
# So the approved answer is the last answer the agent returned,
and there is no need to parse
# it back from that text.
output = self._output_under_review
- if isinstance(output, BaseModel) and (
- self._serialize_model_output or type(output) not in
iter_pydantic_models(self.output_type)
- ):
- # A downstream task can load a model from XCom only if the
worker registered the model's
- # class. The worker registers the classes that
iter_pydantic_models finds in output_type.
- # iter_pydantic_models finds no class in a list of output
types, an output marker, an output
- # function, a TypeAliasType or a NewType, so the operator
pushes the model as a dict. When
- # iter_pydantic_models could not be imported,
_serialize_model_output is always True, so the
- # condition above never reaches the iter_pydantic_models call.
- output = output.model_dump()
+ output = dump_output_for_xcom(
Review Comment:
After the rebase, it goes through `_convert_output_for_xcom`, which dumps an
unregistered model with `model_dump(mode="json")`. I removed the comment in
`output_type.py` that claimed 1.0.0 pushed Python mode everywhere.
##########
providers/common/ai/src/airflow/providers/common/ai/utils/output_type.py:
##########
@@ -38,6 +46,70 @@
_CONVERSION_ERRORS = (ValidationError, ValueError, TypeError, AttributeError,
KeyError, IndexError)
+def is_model_dump_required(output: Any, output_type: Any, *, serialize_output:
bool) -> bool:
+ """
+ Tell whether an output holding ``BaseModel`` instances must be pushed to
XCom dumped.
+
+ The instances are looked up in the output itself, including the elements
of a list, tuple, set or
+ frozenset and the values of a dict. A downstream task can load a model
from XCom only if the worker
+ registered the model's class, and the worker registers the classes
``iter_pydantic_models`` finds in
+ ``output_type``. It finds none in a list of output types, an output
marker, an output function, a
+ ``TypeAliasType`` or a ``NewType``, so an instance of a class it did not
find is dumped.
+ Without ``iter_pydantic_models`` there is no evidence either way, so the
caller's ``serialize_output`` decides.
+ """
+ if not (found := [model for model, _ in _iter_models_in_output(output)]):
+ return False
+ if serialize_output:
+ return True
+ if iter_pydantic_models is None:
+ return False
+ registered = set(iter_pydantic_models(output_type))
+ return any(type(model) not in registered for model in found)
+
+
+def dump_output_for_xcom(output: Any, output_type: Any, *, serialize_output:
bool) -> Any:
+ """
+ Return the output as it is pushed to XCom: dumped when
``is_model_dump_required``, else unchanged.
+
+ With ``serialize_output`` the dump holds Python values, as the
``model_dump()`` of 1.0.0 does, so a
+ ``date`` or ``Decimal`` field keeps its type; an output with a set,
frozenset or dict key holding a model
+ is dumped to JSON values instead. A model the worker registers no class
for, without ``serialize_output``,
+ is dumped to JSON values as well, field names rather than aliases, so a
``HttpUrl``, ``Path`` or ``Enum``
+ field is a string that XCom accepts.
+ """
+ if not is_model_dump_required(output, output_type,
serialize_output=serialize_output):
+ return output
+ # Python mode is what 1.0.0 pushed, a minor release must not change it. A
model dumped to a dict cannot
+ # be a set member, so python mode raises on a set holding models.
+ if serialize_output and not any(in_set for _, in_set in
_iter_models_in_output(output)):
+ if isinstance(output, BaseModel):
+ return output.model_dump()
+ return TypeAdapter(Any).dump_python(output, mode="python")
+ return to_jsonable_python(output, by_alias=False)
+
+
+def _iter_models_in_output(output: Any) -> Iterator[tuple[BaseModel, bool]]:
+ """
+ Yield the ``BaseModel`` instances in an output, each with whether it must
be hashable.
+
+ Looks inside list, tuple, set, frozenset and dict. A set member or a dict
key is hashable, so it is
+ flagged, and so is whatever is nested in one. Dataclass and NamedTuple
contents and model fields
Review Comment:
Fixed. The docstring now says a `NamedTuple` is walked as a tuple. Only
dataclass contents and model fields are skipped, and a test covers the
`NamedTuple` case.
--
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]
