Merge pull request #429 from christianlouis/copilot/fix-complete-status-error

fix(tests): align "completed" test fixtures with terminal-step guard semantics

tests/test_bulk_operations.py

@@ -253,12 +253,13 @@ class TestStatusFilter:
         db_session.add(file_record)
         db_session.flush()
 
-        step = FileProcessingStep(
-            file_id=file_record.id,
-            step_name="extract_text",
-            status="success",
-        )
-        db_session.add(step)
+        for step_name in ("extract_text", "send_to_all_destinations"):
+            step = FileProcessingStep(
+                file_id=file_record.id,
+                step_name=step_name,
+                status="success",
+            )
+            db_session.add(step)
         db_session.commit()
 
         # Test completed filter

tests/test_coverage_polish.py

@@ -477,12 +477,13 @@ class TestFileQueriesDeduplicationEnabled:
         db_session.add(file1)
         db_session.flush()
 
-        step = FileProcessingStep(
-            file_id=file1.id,
-            step_name="check_for_duplicates",
-            status="success",
-        )
-        db_session.add(step)
+        for step_name in ("check_for_duplicates", "send_to_all_destinations"):
+            step = FileProcessingStep(
+                file_id=file1.id,
+                step_name=step_name,
+                status="success",
+            )
+            db_session.add(step)
         db_session.commit()
 
         query = db_session.query(FileRecord)

tests/test_file_listing.py

@@ -187,13 +187,14 @@ class TestFileListingPagination:
         db_session.add(file_record)
         db_session.commit()
 
-        # Add a processing step (used for status determination)
-        step = FileProcessingStep(
-            file_id=file_record.id,
-            step_name="extract_text",
-            status="success",
-        )
-        db_session.add(step)
+        # Add processing steps (used for status determination)
+        for step_name in ("extract_text", "send_to_all_destinations"):
+            step = FileProcessingStep(
+                file_id=file_record.id,
+                step_name=step_name,
+                status="success",
+            )
+            db_session.add(step)
         db_session.commit()
 
         response = client.get("/api/files")
@@ -287,13 +288,14 @@ class TestFileDetailEndpoint:
         assert response.status_code == 200
         assert response.json()["processing_status"]["status"] == "pending"
 
-        # Test 2: Success step = completed
-        step = FileProcessingStep(
-            file_id=file_record.id,
-            step_name="extract_text",
-            status="success",
-        )
-        db_session.add(step)
+        # Test 2: Success step including terminal step = completed
+        for step_name in ("extract_text", "send_to_all_destinations"):
+            step = FileProcessingStep(
+                file_id=file_record.id,
+                step_name=step_name,
+                status="success",
+            )
+            db_session.add(step)
         db_session.commit()
 
         response = client.get(f"/api/files/{file_record.id}")

tests/test_file_queries.py

@@ -76,7 +76,7 @@ def sample_files(db_session):
     )
     db_session.add(step3)
 
-    # File 4: completed (has success step, no failures)
+    # File 4: completed (has success step including terminal step)
     file4 = FileRecord(
         filehash="hash4",
         original_filename="completed.pdf",
@@ -87,10 +87,11 @@ def sample_files(db_session):
     db_session.add(file4)
     db_session.flush()
 
-    step4 = FileProcessingStep(file_id=file4.id, step_name="extract_text", status="success")
-    db_session.add(step4)
+    step4a = FileProcessingStep(file_id=file4.id, step_name="extract_text", status="success")
+    step4b = FileProcessingStep(file_id=file4.id, step_name="send_to_all_destinations", status="success")
+    db_session.add_all([step4a, step4b])
 
-    # File 5: completed with multiple success steps
+    # File 5: completed with multiple success steps including terminal step
     file5 = FileRecord(
         filehash="hash5",
         original_filename="completed2.pdf",
@@ -111,7 +112,12 @@ def sample_files(db_session):
         step_name="extract_metadata_with_gpt",
         status="success",
     )
-    db_session.add_all([step5a, step5b])
+    step5c = FileProcessingStep(
+        file_id=file5.id,
+        step_name="send_to_all_destinations",
+        status="success",
+    )
+    db_session.add_all([step5a, step5b, step5c])
 
     # File 6: has success but also failure (should be filtered out from completed)
     file6 = FileRecord(

tests/test_file_status_fix.py

@@ -437,7 +437,7 @@ class TestFileStatusMissingCoverage:
         assert result["has_errors"] is False
 
     def test_get_files_processing_status_with_completed_steps(self, db_session):
-        """Covers line 189->188: completed + skipped == total_steps → completed status."""
+        """Covers completed + skipped == total_steps with terminal step → completed status."""
         from datetime import datetime
         from unittest.mock import patch
 
@@ -457,6 +457,7 @@ class TestFileStatusMissingCoverage:
         for step_name, step_status in [
             ("create_file_record", "success"),
             ("finalize_document_storage", "skipped"),
+            ("send_to_all_destinations", "success"),
         ]:
             step = FileProcessingStep(
                 file_id=file_record.id,

tests/test_process_document.py

@@ -743,3 +743,102 @@ startxref
         # Verify that retry was triggered
         # The retry method raises a special exception
         assert exc_info.value is not None
+
+
+@pytest.mark.unit
+@pytest.mark.requires_db
+def test_process_document_initializes_file_steps_for_new_file(db_session, tmp_path):
+    """
+    Test that process_document calls initialize_file_steps for new file records
+    so that all mandatory pipeline steps are pre-created as "pending".
+
+    This ensures status tracking reflects the complete expected pipeline from
+    the start and prevents incomplete files from being falsely marked as
+    "completed" just because the steps that *did* run all succeeded.
+    """
+    # Create a test PDF file with embedded text
+    test_pdf = tmp_path / "test.pdf"
+    pdf_content = b"""%PDF-1.4
+1 0 obj
+<<
+/Type /Catalog
+/Pages 2 0 R
+>>
+endobj
+2 0 obj
+<<
+/Type /Pages
+/Kids [3 0 R]
+/Count 1
+>>
+endobj
+3 0 obj
+<<
+/Type /Page
+/Parent 2 0 R
+/MediaBox [0 0 612 792]
+/Resources <<
+/Font <<
+/F1 <<
+/Type /Font
+/Subtype /Type1
+/BaseFont /Helvetica
+>>
+>>
+>>
+/Contents 4 0 R
+>>
+endobj
+4 0 obj
+<<
+/Length 44
+>>
+stream
+BT
+/F1 12 Tf
+100 700 Td
+(Test content) Tj
+ET
+endstream
+endobj
+xref
+0 5
+0000000000 65535 f
+0000000009 00000 n
+0000000058 00000 n
+0000000115 00000 n
+0000000306 00000 n
+trailer
+<<
+/Size 5
+/Root 1 0 R
+>>
+startxref
+399
+%%EOF
+"""
+    test_pdf.write_bytes(pdf_content)
+
+    with (
+        patch("app.tasks.process_document.SessionLocal") as mock_session_local,
+        patch("app.tasks.process_document.settings") as mock_settings,
+        patch("app.tasks.process_document.log_task_progress"),
+        patch("app.tasks.process_document.extract_metadata_with_gpt") as mock_extract,
+        patch("app.tasks.process_document.initialize_file_steps") as mock_init_steps,
+    ):
+        mock_settings.workdir = str(tmp_path)
+        mock_settings.enable_deduplication = False
+        mock_settings.enable_text_quality_check = False
+        mock_session_local.return_value.__enter__.return_value = db_session
+        mock_session_local.return_value.__exit__.return_value = None
+        mock_extract.delay = MagicMock()
+
+        result = process_document.run(str(test_pdf))
+
+        assert result["status"] == "Text extracted locally"
+        assert "file_id" in result
+
+        # initialize_file_steps must have been called exactly once with the new file's ID
+        mock_init_steps.assert_called_once()
+        called_file_id = mock_init_steps.call_args[0][1]
+        assert called_file_id == result["file_id"]