Skip to content

fix: handle trial component status message longer than API supports #5276

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 24, 2025
Merged

fix: handle trial component status message longer than API supports #5276

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/sagemaker/experiments/run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,7 @@
TRIAL_NAME_TEMPLATE = "Default-Run-Group-{}"
MAX_RUN_TC_ARTIFACTS_LEN = 30
MAX_NAME_LEN_IN_BACKEND = 120
MAX_STATUS_MESSAGE_LEN = 1024
EXPERIMENT_NAME = "ExperimentName"
TRIAL_NAME = "TrialName"
RUN_NAME = "RunName"
Expand Down Expand Up @@ -759,7 +760,7 @@ def __exit__(self, exc_type, exc_value, exc_traceback):
if exc_value:
self._trial_component.status = _api_types.TrialComponentStatus(
primary_status=_TrialComponentStatusType.Failed.value,
message=str(exc_value),
message=(str(exc_value) or "")[:MAX_STATUS_MESSAGE_LEN],
)
else:
self._trial_component.status = _api_types.TrialComponentStatus(
Expand Down
16 changes: 16 additions & 0 deletions tests/unit/sagemaker/experiments/test_run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1078,6 +1078,22 @@ def test_exit_fail(sagemaker_session, run_obj):
assert isinstance(run_obj._trial_component.end_time, datetime.datetime)


def test_exit_fail_message_too_long(sagemaker_session, run_obj):
sagemaker_session.sagemaker_client.update_trial_component.return_value = {}
# create an error message that is longer than the max status message length of 1024
# 3 x 342 = 1026
too_long_error_message = "Foo" * 342
try:
with run_obj:
raise ValueError(too_long_error_message)
except ValueError:
pass

assert run_obj._trial_component.status.primary_status == _TrialComponentStatusType.Failed.value
assert run_obj._trial_component.status.message == too_long_error_message[:1024]
assert isinstance(run_obj._trial_component.end_time, datetime.datetime)


@pytest.mark.parametrize(
"metric_value",
[1.3, "nan", "inf", "-inf", None],
Expand Down