diff --git a/app/llm.py b/app/llm.py
index 18a13af..47e18ab 100644
--- a/app/llm.py
+++ b/app/llm.py
@@ -59,6 +59,7 @@ class LLM:
 
             # Add token counting related attributes
             self.total_input_tokens = 0
+            self.total_completion_tokens = 0
             self.max_input_tokens = (
                 llm_config.max_input_tokens
                 if hasattr(llm_config, "max_input_tokens")
@@ -129,12 +130,15 @@ class LLM:
 
         return token_count
 
-    def update_token_count(self, input_tokens: int) -> None:
+    def update_token_count(self, input_tokens: int, completion_tokens: int = 0) -> None:
         """Update token counts"""
         # Only track tokens if max_input_tokens is set
         self.total_input_tokens += input_tokens
+        self.total_completion_tokens += completion_tokens
         logger.info(
-            f"Token usage: Input={input_tokens}, Cumulative Input={self.total_input_tokens}"
+            f"Token usage: Input={input_tokens}, Completion={completion_tokens}, "
+            f"Cumulative Input={self.total_input_tokens}, Cumulative Completion={self.total_completion_tokens}, "
+            f"Total={input_tokens + completion_tokens}, Cumulative Total={self.total_input_tokens + self.total_completion_tokens}"
         )
 
     def check_token_limit(self, input_tokens: int) -> bool:
@@ -271,7 +275,9 @@ class LLM:
                     raise ValueError("Empty or invalid response from LLM")
 
                 # Update token counts
-                self.update_token_count(response.usage.prompt_tokens)
+                self.update_token_count(
+                    response.usage.prompt_tokens, response.usage.completion_tokens
+                )
 
                 return response.choices[0].message.content
 
@@ -282,9 +288,11 @@ class LLM:
             response = await self.client.chat.completions.create(**params)
 
             collected_messages = []
+            completion_text = ""
             async for chunk in response:
                 chunk_message = chunk.choices[0].delta.content or ""
                 collected_messages.append(chunk_message)
+                completion_text += chunk_message
                 print(chunk_message, end="", flush=True)
 
             print()  # Newline after streaming
@@ -292,6 +300,13 @@ class LLM:
             if not full_response:
                 raise ValueError("Empty response from streaming LLM")
 
+            # 对于流式响应，估算completion tokens
+            completion_tokens = self.count_tokens(completion_text)
+            logger.info(
+                f"Estimated completion tokens for streaming response: {completion_tokens}"
+            )
+            self.total_completion_tokens += completion_tokens
+
             return full_response
 
         except TokenLimitExceeded:
@@ -412,7 +427,9 @@ class LLM:
                 raise ValueError("Invalid or empty response from LLM")
 
             # Update token counts
-            self.update_token_count(response.usage.prompt_tokens)
+            self.update_token_count(
+                response.usage.prompt_tokens, response.usage.completion_tokens
+            )
 
             return response.choices[0].message
 
diff --git a/app/tool/file_saver.py b/app/tool/file_saver.py
index 96d64b3..7d92a02 100644
--- a/app/tool/file_saver.py
+++ b/app/tool/file_saver.py
@@ -2,8 +2,8 @@ import os
 
 import aiofiles
 
-from app.tool.base import BaseTool
 from app.config import WORKSPACE_ROOT
+from app.tool.base import BaseTool
 
 
 class FileSaver(BaseTool):