Fixhancement: better handle empty fields from AI suggestions (#13454)

src/paperless_ai/base_model.py

@@ -1,12 +1,13 @@
 from pydantic import BaseModel
+from pydantic import Field
 
 
 class DocumentClassifierSchema(BaseModel):
     """Schema for document classification suggestions."""
 
     title: str
-    tags: list[str]
-    correspondents: list[str]
-    document_types: list[str]
-    storage_paths: list[str]
-    dates: list[str]
+    tags: list[str] = Field(default_factory=list)
+    correspondents: list[str] = Field(default_factory=list)
+    document_types: list[str] = Field(default_factory=list)
+    storage_paths: list[str] = Field(default_factory=list)
+    dates: list[str] = Field(default_factory=list)

src/paperless_ai/tests/test_base_model.py

@@ -0,0 +1,35 @@
+import pytest
+from pydantic import ValidationError
+
+from paperless_ai.base_model import DocumentClassifierSchema
+
+
+@pytest.mark.parametrize(
+    "omitted_field",
+    [
+        "tags",
+        "correspondents",
+        "document_types",
+        "storage_paths",
+        "dates",
+    ],
+)
+def test_document_classifier_schema_defaults_omitted_list_field(omitted_field):
+    data = {
+        "title": "Test Title",
+        "tags": ["test"],
+        "correspondents": ["Test Correspondent"],
+        "document_types": ["Test Document Type"],
+        "storage_paths": ["Test Storage Path"],
+        "dates": ["2026-07-31"],
+    }
+    del data[omitted_field]
+
+    result = DocumentClassifierSchema(**data)
+
+    assert getattr(result, omitted_field) == []
+
+
+def test_document_classifier_schema_requires_title():
+    with pytest.raises(ValidationError, match="title"):
+        DocumentClassifierSchema()