diff --git a/ms_agent/llm/deepseek_llm.py b/ms_agent/llm/deepseek_llm.py
index e565308bc..9cdd36aff 100644
--- a/ms_agent/llm/deepseek_llm.py
+++ b/ms_agent/llm/deepseek_llm.py
@@ -37,7 +37,7 @@ def _call_llm_for_continue_gen(self,
         messages = self.format_input_message(messages)
         stop = kwargs.pop('stop', []).append('```')
         return self._call_llm(
-            messages=messages, tools=tools, stop=stop, **kwargs)
+            messages=messages, tools=self.format_tools(tools), stop=stop, **kwargs)
 
 
 if __name__ == '__main__':
diff --git a/ms_agent/llm/openai_llm.py b/ms_agent/llm/openai_llm.py
index dadc1bf1c..b4c2974fd 100644
--- a/ms_agent/llm/openai_llm.py
+++ b/ms_agent/llm/openai_llm.py
@@ -343,9 +343,10 @@ def _stream_continue_generate(self,
                     # The stream may end without a final usage chunk, which is acceptable.
                     pass
                 first_run = not messages[-1].to_dict().get('partial', False)
-                if chunk.choices[0].finish_reason in [
+                if (not message.tool_calls
+                        and chunk.choices[0].finish_reason in [
                         'length', 'null'
-                ] and (max_runs is None or max_runs != 0):
+                ] and (max_runs is None or max_runs != 0)):
                     logger.info(
                         f'finish_reason: {chunk.choices[0].finish_reason}, continue generate.'
                     )
@@ -499,7 +500,7 @@ def _call_llm_for_continue_gen(self,
             messages[-1].partial = True
         messages[-1].api_calls += 1
 
-        return self._call_llm(messages, tools, **kwargs)
+        return self._call_llm(messages, self.format_tools(tools), **kwargs)
 
     def _continue_generate(self,
                            messages: List[Message],
@@ -522,6 +523,8 @@ def _continue_generate(self,
             Message: A fully formed Message object containing the complete response.
         """
         new_message = self._format_output_message(completion)
+        if new_message.tool_calls:
+            return new_message
         if completion.choices[0].finish_reason in [
                 'length', 'null'
         ] and (max_runs is None or max_runs != 0):