Skip to content

fix(interface): reject duplicate names within output_processors (#675) #697

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
nabinchha merged 1 commit into from
May 21, 2026
+30 −0
Merged

fix(interface): reject duplicate names within output_processors (#675) #697

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
9 changes: 9 additions & 0 deletions packages/data-designer/src/data_designer/interface/composite_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -558,6 +558,15 @@ def _validate_distinct_output_processors(
config_builder: DataDesignerConfigBuilder,
output_processors: list[ProcessorConfig],
) -> None:
seen: set[str] = set()
duplicate_within: set[str] = set()
for processor in output_processors:
if processor.name in seen:
duplicate_within.add(processor.name)
seen.add(processor.name)
if duplicate_within:
names = ", ".join(sorted(duplicate_within))
raise DataDesignerWorkflowError(f"Output processor names must be distinct within output_processors: {names}.")
stage_processor_names = {processor.name for processor in config_builder.get_processor_configs()}
duplicate_names = stage_processor_names.intersection(processor.name for processor in output_processors)
if duplicate_names:
Expand Down
21 changes: 21 additions & 0 deletions packages/data-designer/tests/interface/test_composite_workflow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -378,6 +378,27 @@ def test_composite_workflow_rejects_duplicate_output_processor_names(
)


def test_composite_workflow_rejects_duplicate_names_within_output_processors(
stub_artifact_path: Path,
stub_model_providers: list[ModelProvider],
stub_model_configs: list[ModelConfig],
) -> None:
stage = _category_builder(stub_model_configs)
workflow = _data_designer(stub_artifact_path, stub_model_providers).compose_workflow(
name="duplicate-within-output-processors"
)

with pytest.raises(DataDesignerWorkflowError, match="distinct within output_processors"):
workflow.add_stage(
"base",
stage,
output_processors=[
DropColumnsProcessorConfig(name="drop_scratch", column_names=["scratch"]),
DropColumnsProcessorConfig(name="drop_scratch", column_names=["other_scratch"]),
],
)


def test_composite_workflow_rejects_duplicate_stage_names(
stub_artifact_path: Path,
stub_model_providers: list[ModelProvider],
Expand Down
Loading