diff --git a/reme_ai/context/offload/context_compact_op.py b/reme_ai/context/offload/context_compact_op.py
index 3f9a0dcb..9f5a81ef 100644
--- a/reme_ai/context/offload/context_compact_op.py
+++ b/reme_ai/context/offload/context_compact_op.py
@@ -141,5 +141,5 @@ class ContextCompactOp(BaseAsyncOp):
             tool_message.content = compact_result
 
         # Return the compacted messages as JSON
-        self.context.response.answer = json.dumps([x.model_dump() for x in messages], ensure_ascii=False, indent=2)
+        self.context.response.answer = json.dumps([x.simple_dump() for x in messages], ensure_ascii=False, indent=2)
         logger.info(f"Context compaction completed: {len(write_file_dict)} tool messages were compacted")
diff --git a/test_op/test_context_compact_op.py b/test_op/test_context_compact_op.py
new file mode 100644
index 00000000..5cdf8b96
--- /dev/null
+++ b/test_op/test_context_compact_op.py
@@ -0,0 +1,79 @@
+"""Test script for ContextCompactOp.
+
+This script provides test cases for ContextCompactOp class.
+It can be run directly with: python test_context_compact_op.py
+"""
+
+import asyncio
+
+from flowllm.core.enumeration import Role
+from flowllm.core.schema import Message
+
+from reme_ai.context.offload.context_compact_op import ContextCompactOp
+from reme_ai.main import ReMeApp
+
+
+async def async_main():
+    """Test function for ContextCompactOp."""
+    async with ReMeApp():
+        # Create test messages with system, user, assistant, tool sequence
+        messages = [
+            Message(role=Role.SYSTEM, content="You are a helpful assistant."),
+            Message(role=Role.USER, content="What is the weather today?"),
+            Message(
+                role=Role.ASSISTANT,
+                content="I'll check the weather for you.",
+            ),
+            Message(
+                role=Role.TOOL,
+                content="A" * 5000,  # Large tool message that should be compacted
+                tool_call_id="call_001",
+            ),
+            Message(
+                role=Role.ASSISTANT,
+                content="Let me also check the forecast.",
+            ),
+            Message(
+                role=Role.TOOL,
+                content="B" * 5000,  # Another large tool message
+                tool_call_id="call_002",
+            ),
+            Message(
+                role=Role.USER,
+                content="What about tomorrow?",
+            ),
+            Message(
+                role=Role.ASSISTANT,
+                content="I'll check tomorrow's weather.",
+            ),
+            Message(
+                role=Role.TOOL,
+                content="C" * 5000,  # Third large tool message
+                tool_call_id="call_003",
+            ),
+            Message(
+                role=Role.TOOL,
+                content="Recent result",  # Recent tool message (should be kept)
+                tool_call_id="call_004",
+            ),
+        ]
+
+        # Create op with lower thresholds for testing
+        op = ContextCompactOp(
+            all_token_threshold=1000,  # Low threshold to trigger compaction
+            tool_token_threshold=100,  # Low threshold to compact tool messages
+            tool_left_char_len=50,  # Keep 50 chars in preview
+            keep_recent=1,  # Keep 1 recent tool message
+            storage_path="./test_compact_storage",
+        )
+
+        # Execute the compaction
+        await op.async_call(messages=[m.model_dump() for m in messages])
+
+        # Print results
+        result = op.context.response.answer
+        print(f"Context compaction result: {result}")
+
+
+if __name__ == "__main__":
+    asyncio.run(async_main())