Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

RuntimeError: Failed to get user input: Failed to get user input: #4975

Open
gagb opened this issue Jan 9, 2025 · 1 comment
Open

RuntimeError: Failed to get user input: Failed to get user input: #4975

gagb opened this issue Jan 9, 2025 · 1 comment

Comments

@gagb
Copy link
Collaborator

gagb commented Jan 9, 2025

What happened?

Error doesn't occur with the --no-hil option.

(.venv-m1) gaganbansal@MacBook-Pro workspace % m1 "hi"
Enter your response: ---------- user ----------
hi
---------- MagenticOneOrchestrator ----------

We are working to address the following user request:

hi


To answer this request we have assembled the following team:

FileSurfer: An agent that can handle local files.
WebSurfer:
    A helpful assistant with access to a web browser.
    Ask them to perform web searches, open pages, and interact with content (e.g., clicking links, scrolling the viewport, etc., filling in form fields, etc.).
    It can also summarize the entire page, or answer questions based on the content of the page.
    It can also be asked to sleep and wait for pages to load, in cases where the pages seem to be taking a while to load.
Coder: A helpful and general-purpose AI assistant that has strong language skills, Python skills, and Linux command line skills.
Executor: A computer terminal that performs no other action than running Python scripts (provided to it quoted in ```python code blocks), or sh shell scripts (provided to it quoted in ```sh code blocks).
User: A huError processing publish message for User/8d19aae6-3888-4890-9cb2-dc14c5d22958
Traceback (most recent call last):
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_user_proxy_agent.py", line 144, in _get_input
    return await async_func(prompt, cancellation_token)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_user_proxy_agent.py", line 24, in cancellable_input
    return await task
           ^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/aioconsole/stream.py", line 297, in ainput
    raise EOFError
EOFError

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_user_proxy_agent.py", line 167, in on_messages
    user_input = await self._get_inputman user


Here is an initial fact sheet to consider:

1. GIVEN OR VERIFIED FACTS
   - The specific request is simply "hi," which provides no specific facts or figures.

2. FACTS TO LOOK UP
   - None required, as the request does not provide any context or mention any factual information that would need verification or supplementation.

3. FACTS TO DERIVE
   - None, as there is no information given in the request to logically deduce further details or insights.

4. EDUCATED GUESSES
   - "hi" is a greeting, so the request could be interpreted as a casual initiation of conversation or inquiry.


Here is the plan to follow as best as possible:

Since the original request is simply "hi," which is a greeting, and does not specify any particular task or objective, here is a short bullet-point plan for addressing the request based on the available team members:

- User: Engage by responding to the greeting to establish further context or clarify any specific needs or questions.
  - "Hello! How can I assist you today?"

- WebSurfer: Remain on standby in case the User follows up with a request that involves needing information from the web.

- FileSurfer: Stand by if the User requires handling or accessing local files in any follow-up request.

- Coder: Be prepared to assist with any programming-related inquiries or tasks if they arise.

- Executor: Remain inactive unless directed by Coder to run a specific script.

This plan focuses on establishing communication and determining the next steps based on User input.

---------- MagenticOneOrchestrator ----------
Hello! How can I assist you today?
(prompt, cancellation_token)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_user_proxy_agent.py", line 154, in _get_input
    raise RuntimeError(f"Failed to get user input: {str(e)}") from e
RuntimeError: Failed to get user input:

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_core/_single_threaded_agent_runtime.py", line 409, in _on_message
    return await agent.on_message(
           ^^^^^^^^^^^^^^^^^^^^^^^
    ...<2 lines>...
    )
    ^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_core/_base_agent.py", line 113, in on_message
    return await self.on_message_impl(message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/teams/_group_chat/_sequential_routed_agent.py", line 48, in on_message_impl
    return await super().on_message_impl(message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_core/_routed_agent.py", line 485, in on_message_impl
    return await h(self, message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_core/_routed_agent.py", line 268, in wrapper
    return_value = await func(self, message, ctx)  # type: ignore
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/teams/_group_chat/_chat_agent_container.py", line 53, in handle_request
    async for msg in self._agent.on_messages_stream(self._message_buffer, ctx.cancellation_token):
    ...<11 lines>...
            )
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_base_chat_agent.py", line 98, in on_messages_stream
    response = await self.on_messages(messages, cancellation_token)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/gaganbansal/workspace/.venv-m1/lib/python3.13/site-packages/autogen_agentchat/agents/_user_proxy_agent.py", line 180, in on_messages
    raise RuntimeError(f"Failed to get user input: {str(e)}") from e
RuntimeError: Failed to get user input: Failed to get user input:
--- Logging error ---

What did you expect to happen?

No errors

How can we reproduce it (as minimally and precisely as possible)?

  • I test on a Mac, iTerm
  • install magentic-one-cli with uv/pip
  • exported an openai key

AutoGen version

v0.4

Which package was this bug in

Core

Model used

No response

Python version

No response

Operating system

No response

Any additional info you think would be helpful for fixing this bug

No response

@victordibia
Copy link
Collaborator

@peterychang , any insights on this?

@ekzhu ekzhu added this to the 0.4.1 milestone Jan 10, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

3 participants