Step call func

app.py

@@ -1,6 +1,5 @@
 from smolagents import ToolCallingAgent, CodeAgent, DuckDuckGoSearchTool, LiteLLMModel
 import os
-import requests
 #import litellm
 #litellm._turn_on_debug()  # Enable debugging for litellm
 
@@ -14,40 +13,17 @@ model = LiteLLMModel(
     temperature=0.5,
     api_base="https://api.sambanova.ai/v1",  # Specify the base URL for Sambanova, as in your working requests example
 )
-print(dir(model))
 
-# Создание модели с обработкой лимитов
-def model_call(query, tools_to_call_from=None, stop_sequences=None):
-    print(query)
-    print(tools_to_call_from)
-    print(stop_sequences)
-    try:
-        url = "https://api.sambanova.ai/v1/chat/completions"  # Проверьте, что это правильная конечная точка
-        headers = {
-            "Authorization": f"Bearer {os.getenv('sambanova_token')}",
-            "Content-Type": "application/json"
-        }
-        data = {
-            "model": "Qwen2.5-Coder-32B-Instruct",
-            "messages": query,
-            "tools": tools_to_call_from,
-            "max_tokens": 2096
-        }
-
-        response = requests.post(url, headers=headers, json=data)
-        print(response.status_code)
-        print(response.text)
-        return response.choices[0].message.content
-    except openai.RateLimitError:
-        time.sleep(60)  # Ждем 60 секунд перед повторной попыткой
-        return model_call(query)  # Рекурсивный вызов
-    except Exception as e:
-        return f"An unexpected error occurred: {str(e)}"
+my_paused = 
+def my_paused(step_log: ActionStep, agent: CodeAgent) -> None:
+    sleep(5.0) 
+    return
 
 # Create the agent
 agent = ToolCallingAgent(
     tools=[DuckDuckGoSearchTool()],
-    model=model_call
+    model=model,
+    step_callbacks=[my_paused],
 )
 
 # Когда запуск идет через streamlingt то ответы переводятс в json автоматом