Python: [Bug]: FoundryChatClient doesn’t support async with, built_in_chat_clients sample fails

[buonamico]

Description

FoundryChatClient sample uses async with but client is not an async context manager

Summary

Running the "built-in chat clients" sample with client_name="foundry_chat" fails with:

TypeError: FoundryChatClient object does not support the asynchronous context manager protocol (missed __aexit__ method)

The sample wraps the Foundry client in async with client:, but the installed FoundryChatClient implementation does not implement the async context manager protocol (__aenter__ / __aexit__), so execution fails.

Code Sample

#working solution

import asyncio
import os
from random import randint
from typing import Annotated, Any, Literal

from agent_framework import Agent, Message, SupportsChatGetResponse, tool
from agent_framework.foundry import FoundryChatClient
from agent_framework.openai import OpenAIChatClient, OpenAIChatCompletionClient
from azure.identity import AzureCliCredential
from dotenv import load_dotenv
from pydantic import Field

# Load environment variables from .env file
load_dotenv()

"""
Built-in Chat Clients Example

This sample demonstrates how to run the same prompt flow against different built-in
chat clients using a single `get_client` factory.

Select one of these client names:
- openai_chat
- openai_chat_completion
- anthropic
- ollama
- bedrock
- azure_openai_chat
- azure_openai_chat_completion
- foundry_chat
"""

ClientName = Literal[
    "openai_chat",
    "openai_chat_completion",
    "anthropic",
    "ollama",
    "bedrock",
    "azure_openai_chat",
    "azure_openai_chat_completion",
    "foundry_chat",
]


# NOTE: approval_mode="never_require" is for sample brevity.
@tool(approval_mode="never_require")
def get_weather(
    location: Annotated[str, Field(description="The location to get the weather for.")],
) -> str:
    """Get the weather for a given location."""
    conditions = ["sunny", "cloudy", "rainy", "stormy"]
    return f"The weather in {location} is {conditions[randint(0, 3)]} with a high of {randint(10, 30)}°C."


def get_client(client_name: ClientName) -> SupportsChatGetResponse[Any]:
    """Create a built-in chat client from a name."""
    from agent_framework.amazon import BedrockChatClient
    from agent_framework.anthropic import AnthropicClient
    from agent_framework.ollama import OllamaChatClient

    if client_name == "openai_chat":
        return OpenAIChatClient()
    if client_name == "openai_chat_completion":
        return OpenAIChatCompletionClient()
    if client_name == "anthropic":
        return AnthropicClient()
    if client_name == "ollama":
        return OllamaChatClient()
    if client_name == "bedrock":
        return BedrockChatClient()
    if client_name == "azure_openai_chat":
        return OpenAIChatClient(credential=AzureCliCredential())
    if client_name == "azure_openai_chat_completion":
        return OpenAIChatCompletionClient(credential=AzureCliCredential())
    if client_name == "foundry_chat":
        return FoundryChatClient(
            project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
            model=os.environ["FOUNDRY_MODEL"],
            credential=AzureCliCredential(),
        )

    raise ValueError(f"Unsupported client name: {client_name}")


async def main(client_name: ClientName = "openai_chat") -> None:
    """Run a basic prompt using a selected built-in client."""
    client = get_client(client_name)

    message = Message("user", contents=["What's the weather in Amsterdam and in Paris?"])
    stream = os.getenv("STREAM", "false").lower() == "true"
    print(f"Client: {client_name}")
    print(f"User: {message.text}")

    if isinstance(client, FoundryChatClient):
        agent = Agent(
            client=client,
            instructions="You are a helpful assistant.",
            tools=get_weather,
        )

        if stream:
            print("Assistant: ", end="")
            async for chunk in agent.run(message.text, stream=True):
                if chunk.text:
                    print(chunk.text, end="")
            print("")
        else:
            print(f"Assistant: {await agent.run(message.text)}")
        return

    if stream:
        response_stream = client.get_response([message], stream=True, options={"tools": get_weather})
        print("Assistant: ", end="")
        async for chunk in response_stream:
            if chunk.text:
                print(chunk.text, end="")
        print("")
    else:
        print(f"Assistant: {await client.get_response([message], stream=False, options={'tools': get_weather})}")


if __name__ == "__main__":
    asyncio.run(main("foundry_chat"))

Error Messages / Stack Traces

Client: foundry_chat
User: What's the weather in Amsterdam and in Paris?
Traceback (most recent call last):
  File "/Users/damian/Projects/personal/agent-framework-test/build_in_chat_clients.py", line 123, in <module>
    asyncio.run(main("foundry_chat"))
    ~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/Cellar/python@3.14/3.14.3_1/Frameworks/Python.framework/Versions/3.14/lib/python3.14/asyncio/runners.py", line 204, in run
    return runner.run(main)
           ~~~~~~~~~~^^^^^^
  File "/opt/homebrew/Cellar/python@3.14/3.14.3_1/Frameworks/Python.framework/Versions/3.14/lib/python3.14/asyncio/runners.py", line 127, in run
    return self._loop.run_until_complete(task)
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^
  File "/opt/homebrew/Cellar/python@3.14/3.14.3_1/Frameworks/Python.framework/Versions/3.14/lib/python3.14/asyncio/base_events.py", line 719, in run_until_complete
    return future.result()
           ~~~~~~~~~~~~~^^
  File "/Users/damian/Projects/personal/agent-framework-test/build_in_chat_clients.py", line 97, in main
    async with client:
               ^^^^^^
TypeError: 'agent_framework_foundry._chat_client.FoundryChatClient' object does not support the asynchronous context manager protocol (missed __aexit__ method)

Package Versions

agent-framework-core Version: 1.0.1; agent-framework-foundry Version: 1.0.1

Python Version

Python: 3.14.3 (Homebrew)

Additional Context

The official Foundry sample 02-agents/built_in_chat_clients.py in this repo uses FoundryChatClient without async with client:; it wraps the client in an Agent and calls await agent.run(...). This suggests that FoundryChatClient may not be intended to be used as an async context manager, making the built-in clients sample inconsistent.

Workaround
Remove the async with client: block for Foundry clients and call await client.get_response(...) directly, OR follow the pattern used in built_in_chat_clients.py (wrap in Agent and call await agent.run(...)).
Environment

OS: macOS (Apple Silicon)
Azure Functions Core Tools: 4.9.0 (not required to reproduce this specific error)
Auth: AzureCliCredential (az login)