Direct Response with Team History

This example demonstrates a team where the team leader routes requests to the appropriate member, and the members respond directly to the user.

In addition, the team has access to the conversation history through add_history_to_context=True.

respond_directly_with_history.py

from agno.agent import Agent
from agno.db.sqlite import SqliteDb
from agno.models.openai import OpenAIResponses
from agno.team.team import Team


def get_weather(city: str) -> str:
    return f"The weather in {city} is sunny."


weather_agent = Agent(
    name="Weather Agent",
    role="You are a weather agent that can answer questions about the weather.",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[get_weather],
)


def get_news(topic: str) -> str:
    return f"The news about {topic} is that it is going well!"


news_agent = Agent(
    name="News Agent",
    role="You are a news agent that can answer questions about the news.",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[get_news],
)


def get_activities(city: str) -> str:
    return f"The activities in {city} are that it is going well!"


activities_agent = Agent(
    name="Activities Agent",
    role="You are a activities agent that can answer questions about the activities.",
    model=OpenAIResponses(id="gpt-5.2"),
    tools=[get_activities],
)


geo_search_team = Team(
    name="Geo Search Team",
    model=OpenAIResponses("gpt-5.2"),
    respond_directly=True,
    members=[
        weather_agent,
        news_agent,
        activities_agent,
    ],
    instructions="You are a geo search agent that can answer questions about the weather, news and activities in a city.",
    db=SqliteDb(
        db_file="tmp/geo_search_team.db"
    ),  # Add a database to store the conversation history
    add_history_to_context=True,  # Ensure that the team leader knows about previous requests
)


geo_search_team.print_response(
    "I am doing research on Tokyo. What is the weather like there?", stream=True
)

geo_search_team.print_response(
    "Is there any current news about that city?", stream=True
)

geo_search_team.print_response("What are the activities in that city?", stream=True)

Usage

1. Create a Python file

   Create respond_directly_with_history.py with the code above.

2. Set up your virtual environment

   Mac

   uv venv --python 3.12
   source .venv/bin/activate
   
3. Install dependencies

   uv pip install -U agno openai
   
4. Export your OpenAI API key

   Mac/Linux

   export OPENAI_API_KEY="your_openai_api_key_here"
   
5. Run Team

   python respond_directly_with_history.py