Support `a2a` for `smolagents`

[femto]

Hello I followed the a2a tutorial at https://mozilla-ai.github.io/any-agent/cookbook/serve_a2a/
the server can't persist and seemed to exit quit quickly

time = await AnyAgent.create_async(
        "smolagents",  # See all options in https://mozilla-ai.github.io/any-agent/
        
        agent_config
    )
    time_handle = await time.serve_async(A2AServingConfig(port=0))

    server_port = time_handle.port

it outputs

Server is ready at http://localhost:58354
ERROR:    Traceback (most recent call last):
  File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/starlette/routing.py", line 701, in lifespan
    await receive()
  File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/uvicorn/lifespan/on.py", line 137, in receive
    return await self.receive_queue.get()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/femtozheng/.pyenv/versions/3.12.3/lib/python3.12/asyncio/queues.py", line 158, in get
    await getter
asyncio.exceptions.CancelledError

[daavoo]

Hi @femto , it seems that the issue here is because you are using smolagents framework, which is currently the only framework for which we don't have a2a support.

[femto]

ok, then I use tinyagent time = await AnyAgent.create_async( "tinyagent", # See all options in https://mozilla-ai.github.io/any-agent/ AgentConfig( model_id="azureopenai/gpt-4o", description="I'm an agent to help with getting the time", tools=[time_tool], ), ) I think tinyagent uses any-llm, not sure "azureopenai/gpt-4o" is correct, but now Server is ready at http://localhost:49792 ERROR: Traceback (most recent call last): File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/starlette/routing.py", line 701, in lifespan await receive() File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/uvicorn/lifespan/on.py", line 137, in receive return await self.receive_queue.get() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/femtozheng/.pyenv/versions/3.12.3/lib/python3.12/asyncio/queues.py", line 158, in get await getter asyncio.exceptions.CancelledError an error occurred during closing of asynchronous generator <async_generator object stdio_client at 0x1168e3b50> asyncgen: <async_generator object stdio_client at 0x1168e3b50> + Exception Group Traceback (most recent call last): | File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 781, in __aexit__ | raise BaseExceptionGroup( | BaseExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception) +-+---------------- 1 ---------------- | Traceback (most recent call last): | File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/mcp/client/stdio/__init__.py", line 189, in stdio_client | yield read_stream, write_stream | GeneratorExit +------------------------------------ During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/mcp/client/stdio/__init__.py", line 182, in stdio_client async with ( File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 787, in __aexit__ if self.cancel_scope.__exit__(type(exc), exc, exc.__traceback__): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/femtozheng/python-project/any-agent/venv/lib/python3.12/site-packages/anyio/_backends/_asyncio.py", line 459, in __exit__ raise RuntimeError( RuntimeError: Attempted to exit cancel scope in a different task than it was entered in

…

On Mon, Oct 13, 2025 at 5:13 PM David de la Iglesia Castro < ***@***.***> wrote: *daavoo* left a comment (mozilla-ai/any-agent#829) <#829 (comment)> Hi @femto <https://github.com/femto> , it seems that the issue here is because you are using smolagents framework, which is currently the only framework for which we don't have a2a support. — Reply to this email directly, view it on GitHub <#829 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAABWGUMKTL7ZSAO6HTUJYT3XNUKZAVCNFSM6AAAAACI5E7IM2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTGOJWGU3DINZTGQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Best Regards femto

[daavoo]

@femto in which context (like, is it in a script that you run with python script.py, is it inside a noteboolk, ) are you running the codeblock you've shared?

[femto]

Hello, in a script.

…

On Mon, Oct 13, 2025 at 7:47 PM David de la Iglesia Castro < ***@***.***> wrote: *daavoo* left a comment (mozilla-ai/any-agent#829) <#829 (comment)> @femto <https://github.com/femto> in which context (like, is it in a script that you run with python script.py, is it inside a noteboolk, ) are you running the codeblock you've shared? — Reply to this email directly, view it on GitHub <#829 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAABWGRH5KHIBY33UUFQ7ED3XOGNZAVCNFSM6AAAAACI5E7IM2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTGOJXGE4DGNBSGU> . You are receiving this because you were mentioned.Message ID: ***@***.***>

-- Best Regards femto