Multi agent example not working

[tocab]

Hi, I tried out the following code from the example here.

model = LiteLLMModel(model_id="ollama/deepseek-r1:8b", num_ctx=10000)
web_agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)

managed_web_agent = ManagedAgent(
    agent=web_agent,
    name="web_search",
    description="Runs web searches for you. Give it your query as an argument."
)

manager_agent = CodeAgent(
    tools=[], model=model, managed_agents=[managed_web_agent]
)

manager_agent.run("Who is the CEO of Hugging Face?")

And get the same response for 5 iterations:

hugging_face_ceo = web_search(query="CEO of Hugging Face 2023")                                                  
print(f"The CEO of Hugging Face is {hugging_face_ceo}.")                                                         
final_answer(hugging_face_ceo)  

The agent is called in the wrong way and therefore this results in that error:

Code execution failed at line 'hugging_face_ceo = web_search(query="CEO of Hugging Face 2023")' due to: 
TypeError:ManagedAgent.__call__() missing 1 required positional argument: 'request'

What could be the reason? Is the model too weak to understand how to call the managed agent?

[elsolo5000-2]

The llm did not put the correct argument in the response while calling for the managed agent.?