generic source-to-infospace generator

src/infospace_bench/workflow.py

@@ -273,10 +273,12 @@ class WorkflowStageRecord:
     input_artifact_id: str
     output_artifact_id: str = ""
     message: str = ""
+    provider: str = ""
+    metadata: dict[str, Any] = field(default_factory=dict)
 
     def to_dict(self) -> dict[str, Any]:
         data = asdict(self)
-        return {key: value for key, value in data.items() if value != ""}
+        return {key: value for key, value in data.items() if value not in ("", {}, [])}
 
 
 @dataclass(frozen=True)
@@ -442,6 +444,7 @@ def _execute_workflow(
                     infospace.root,
                     dry_run=False,
                     provider=result.provider,
+                    provider_metadata=result.metadata,
                 )
                 outputs.append(output)
                 stage_outputs[stage.id] = {
@@ -458,6 +461,8 @@ def _execute_workflow(
                         status="completed",
                         input_artifact_id=input_record.artifact_id,
                         output_artifact_id=output.artifact_id,
+                        provider=result.provider,
+                        metadata=result.metadata,
                     )
                 )
             elif stage.kind == "split_entities":
@@ -645,6 +650,7 @@ def _resolve_output(
     *,
     dry_run: bool,
     provider: str = "",
+    provider_metadata: dict[str, Any] | None = None,
 ) -> WorkflowOutputRecord:
     if stage.output is None:
         raise InfospaceError(
@@ -673,6 +679,11 @@ def _resolve_output(
                     "stage_id": stage.id,
                     "input_artifact_id": input_record.artifact_id,
                     **({"provider": provider} if provider else {}),
+                    **(
+                        {"provider_metadata": provider_metadata}
+                        if provider_metadata
+                        else {}
+                    ),
                 },
                 relationships=[
                     {