uranusjr commented on code in PR #71737:
URL: https://github.com/apache/airflow/pull/71737#discussion_r4311936108
##########
airflow-core/src/airflow/models/dagrun.py:
##########
@@ -163,14 +164,51 @@ def validate_loop_decision(decision: str | None,
region_index: int, group: Seria
raise InvalidLoopDecision("Fixed-count loop decision does not match
its iteration limit")
+@dataclass(frozen=True, slots=True, eq=False)
+class FinishedTI:
+ """
+ Immutable view of a task instance in a terminal state.
+
+ Keeps the dag_run rescan lightweight and fast: scheduling only reads these
columns
+ off finished task instances, so a fully instrumented TaskInstance per row
is
+ unnecessary. ``task`` is attached from the serialized dag rather than the
row.
+
+ ``eq=False`` keeps the same identity-based equality and hashing a
TaskInstance has.
+
+ Anything needing a full TaskInstance must re-fetch it (see
``_ensure_type_task_instance``).
+ """
+
+ id: UUID
+ dag_id: str
+ run_id: str
+ task_id: str
+ region_id: UUID
+ region_index: int
+ dag_version_id: UUID | None
+ state: str | None
+ start_date: datetime | None
+ end_date: datetime | None
+ task: Operator | None = None
+
+ @property
+ def map_index(self) -> int:
+ """Mirror the ``TaskInstance.map_index`` synonym of
``region_index``."""
+ return self.region_index
+
+
+# Get the necessary columns from the FinishedTI fields so that the class stays
+# the single source of truth. For any needed change, add or remove a field
there.
+FINISHED_TI_COLUMNS = tuple(getattr(TI, f.name) for f in fields(FinishedTI) if
f.name != "task")
+
+
class TISchedulingDecision(NamedTuple):
"""Type of return for DagRun.task_instance_scheduling_decisions."""
- tis: list[TI]
+ tis: list[TI | FinishedTI]
Review Comment:
Instead of having this union everywhere, we should create a base protocol or
type to represent the shape instead.
--
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]
