airflow.providers.common.ai.fallback_exceptions

The error a failed fallback_conn_ids chain raises.

Kept apart from airflow.providers.common.ai.exceptions, which must stay importable without loading pydantic-ai: this class subclasses pydantic-ai’s FallbackExceptionGroup.

Exceptions

FallbackChainExhaustedError

Raised when every connection of a fallback_conn_ids chain failed.

Module Contents

exception airflow.providers.common.ai.fallback_exceptions.FallbackChainExhaustedError[source]

Bases: pydantic_ai.exceptions.FallbackExceptionGroup

Raised when every connection of a fallback_conn_ids chain failed.

Subclasses pydantic-ai’s FallbackExceptionGroup, so except clauses and RetryRule(exception=FallbackExceptionGroup) written for it keep matching. The operator raises it from the group the chain raised, which stays __cause__.

replayed_steps and recorded_steps are what the durable journal replayed and recorded in this attempt before the chain failed, summed over every step kind, so a retry policy can tell an attempt that advanced the run from one that failed where it started. They are None when no durable journal was active.

replayed_steps: int | None = None[source]
recorded_steps: int | None = None[source]
property member_errors: tuple[Exception, ...][source]

The error each connection raised, in chain order.

classmethod from_group(group, *, replayed_steps=None, recorded_steps=None)[source]

Build the error from the group the chain raised, keeping its attempts and members.

Was this entry helpful?