Enhance conversation history and runtime variable management

- Update ConversationRecorder to include source and nodeId metadata in transcripts for better context tracking.
- Introduce optional variable handling in DynamicVariableStore, allowing for unset variables to be rendered as empty without raising errors.
- Refactor WorkflowBrain to apply turn configurations and manage interaction policies dynamically, improving agent responsiveness.
- Implement tests to ensure proper handling of updated session variables and workflow metadata in various scenarios.

backend/tests/test_conversation_history.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+import unittest
+from unittest.mock import AsyncMock
+
+from services.conversation_history import ConversationRecorder
+
+
+class ConversationRecorderTest(unittest.IsolatedAsyncioTestCase):
+    async def test_fixed_reply_transcript_keeps_workflow_metadata(self):
+        recorder = ConversationRecorder("conv_test")
+        recorder._append = AsyncMock()
+
+        await recorder.record_transport_message(
+            {
+                "type": "transcript",
+                "role": "assistant",
+                "content": "请稍等，我正在处理。",
+                "timestamp": "2026-07-14T10:00:00+08:00",
+                "source": "workflow-fixed-reply",
+                "nodeId": "agent_service",
+            }
+        )
+
+        recorder._append.assert_awaited_once_with(
+            "assistant",
+            "请稍等，我正在处理。",
+            "2026-07-14T10:00:00+08:00",
+            {
+                "source": "workflow-fixed-reply",
+                "node_id": "agent_service",
+            },
+        )
+
+
+if __name__ == "__main__":
+    unittest.main()