Properly skip (and log as such) documents without changing updated_at when the md5 hash is unchanged

haiku_rag_slim/haiku/rag/client.py

@@ -219,9 +219,13 @@ class HaikuRAG:
             if title is not None and title != existing_doc.title:
                 existing_doc.title = title
                 updated = True
-            if metadata:
-                existing_doc.metadata = {**(existing_doc.metadata or {}), **metadata}
+
+            # Check if metadata actually changed (beyond contentType and md5)
+            merged_metadata = {**(existing_doc.metadata or {}), **metadata}
+            if merged_metadata != existing_doc.metadata:
+                existing_doc.metadata = merged_metadata
                 updated = True
+
             if updated:
                 return await self.document_repository.update(existing_doc)
             return existing_doc
@@ -290,13 +294,14 @@ class HaikuRAG:
                 if title is not None and title != existing_doc.title:
                     existing_doc.title = title
                     updated = True
+
                 metadata.update({"contentType": content_type, "md5": md5_hash})
-                if metadata:
-                    existing_doc.metadata = {
-                        **(existing_doc.metadata or {}),
-                        **metadata,
-                    }
+                # Check if metadata actually changed (beyond contentType and md5)
+                merged_metadata = {**(existing_doc.metadata or {}), **metadata}
+                if merged_metadata != existing_doc.metadata:
+                    existing_doc.metadata = merged_metadata
                     updated = True
+
                 if updated:
                     return await self.document_repository.update(existing_doc)
                 return existing_doc

haiku_rag_slim/haiku/rag/monitor.py

@@ -113,18 +113,22 @@ class FileWatcher:
         try:
             uri = file.as_uri()
             existing_doc = await self.client.get_document_by_uri(uri)
+
+            result = await self.client.create_document_from_source(str(file))
+            doc = result if isinstance(result, Document) else result[0]
+
             if existing_doc:
-                result = await self.client.create_document_from_source(str(file))
-                # Since we're passing a file (not directory), result should be a single Document
-                doc = result if isinstance(result, Document) else result[0]
-                logger.info(f"Updated document {existing_doc.id} from {file}")
-                return doc
+                # Check if document was actually updated by comparing updated_at timestamps
+                if doc.updated_at > existing_doc.updated_at:
+                    logger.info(f"Updated document {existing_doc.id} from {file}")
+                else:
+                    logger.info(
+                        f"Skipped unchanged document {existing_doc.id} from {file}"
+                    )
             else:
-                result = await self.client.create_document_from_source(str(file))
-                # Since we're passing a file (not directory), result should be a single Document
-                doc = result if isinstance(result, Document) else result[0]
                 logger.info(f"Created new document {doc.id} from {file}")
-                return doc
+
+            return doc
         except Exception as e:
             logger.error(f"Failed to upsert document from {file}: {e}")
             return None

tests/test_client.py

@@ -485,6 +485,28 @@ async def test_client_create_update_no_op_behavior(temp_db_path):
             assert retrieved_doc.content == updated_content
 
 
+@pytest.mark.asyncio
+async def test_client_unchanged_file_keeps_timestamp(temp_db_path):
+    """Test that unchanged files don't update the updated_at timestamp."""
+    async with HaikuRAG(temp_db_path) as client:
+        # Create a temporary file
+        test_content = "Test content for timestamp check."
+        with tempfile.TemporaryDirectory() as temp_dir:
+            temp_path = Path(temp_dir) / "test.txt"
+            temp_path.write_text(test_content)
+
+            # First call - create document
+            doc1 = await client.create_document_from_source(temp_path)
+            assert isinstance(doc1, Document)
+            original_updated_at = doc1.updated_at
+
+            # Second call with same content - should not update timestamp
+            doc2 = await client.create_document_from_source(temp_path)
+            assert isinstance(doc2, Document)
+            assert doc2.id == doc1.id
+            assert doc2.updated_at == original_updated_at  # Timestamp should not change
+
+
 @pytest.mark.asyncio
 async def test_client_url_create_update_no_op_behavior(temp_db_path):
     """Test create/update/no-op behavior for URLs based on MD5 changes."""

tests/test_monitor.py

@@ -243,3 +243,43 @@ async def test_file_watcher_with_include_patterns():
         # Should have only called for the .md file
         assert mock_client.create_document_from_source.call_count == 1
         mock_client.create_document_from_source.assert_called_with(str(md_file))
+
+
+@pytest.mark.asyncio
+async def test_file_watcher_skips_unchanged_document(caplog):
+    """Test FileWatcher skips document when content hasn't changed."""
+    from datetime import datetime
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_path = Path(temp_dir)
+        test_file = temp_path / "test.txt"
+        test_content = "Test content"
+        test_file.write_text(test_content)
+
+        mock_client = AsyncMock(spec=HaikuRAG)
+        # Existing document with a timestamp
+        now = datetime.now()
+        existing_doc = Document(
+            id="1",
+            content=test_content,
+            uri=test_file.as_uri(),
+            created_at=now,
+            updated_at=now,
+        )
+        mock_client.get_document_by_uri.return_value = existing_doc
+        # Client returns same document with same timestamp (unchanged)
+        mock_client.create_document_from_source.return_value = existing_doc
+
+        test_config = AppConfig(monitor=MonitorConfig(directories=[temp_path]))
+        watcher = FileWatcher(client=mock_client, config=test_config)
+
+        with caplog.at_level("INFO"):
+            result = await watcher._upsert_document(test_file)
+
+        assert result is not None
+        assert result.id == "1"
+        # Should log that document was skipped, not updated
+        assert any("Skipped" in record.message for record in caplog.records)
+        assert not any(
+            "Updated document" in record.message for record in caplog.records
+        )