The GitHub Actions job "Tests (AMD)" on airflow.git/main has failed.
Run started by GitHub user potiuk (triggered by potiuk).

Head commit for run:
6769feb82e1d8e8f71b29a81691cd00680ebe41a / Kaxil Naik <[email protected]>
Return common.ai SQLToolset errors to the agent so it self-corrects (#68117)

SQLToolset's query, get_schema, and list_tables tools raised on any
database error, failing the whole @task.agent task. The agent never saw
the error, so it could not correct its SQL and retry within the run.

call_tool now surfaces any tool failure to the agent as ModelRetry,
carrying the database's own message, without inspecting the error type or
text. pydantic-ai bounds the loop with the tool's max_retries, so a
fixable SQL error is corrected within the run while an unrecoverable one
(a bad connection, an auth failure) exhausts the budget and fails the
task for Airflow to retry.

The airflow_toolset_to_langchain_tools bridge feeds ModelRetry back to
the model as tool output; it now bounds that by the tool's max_retries
too, so a tool that keeps failing propagates instead of looping forever.

Removes the previous _is_retryable_query_error classifier and its
per-driver exception-tuple imports: matching exception class names and
error-message substrings is brittle and cannot cover every backend.

Report URL: https://github.com/apache/airflow/actions/runs/27103815388

With regards,
GitHub Actions via GitBox


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to