Error: Cannot process your request due to Exception: 'NoneType' object has no attribute 'content'

Human: what time is it
>>> [INIT_PLAN]
1. Fetch the current system time
>>> [PLAN]
1. Fetch the current system time
>>> [CURRENT_PLAN_STEP]
Fetch the current system time
>>> [SEND_TO]
CodeInterpreter
>>> [MESSAGE]
Please provide the current system time.
>>> [PLANNER->CODEINTERPRETER]
Please provide the current system time.
Error: Cannot process your request due to Exception: 'NoneType' object has no attribute 'content' 
 Traceback (most recent call last):
  File "/home/bene/Pojects/TaskWeaver/taskweaver/session/session.py", line 125, in send_message
    post = _send_message(post.send_to, post)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bene/Pojects/TaskWeaver/taskweaver/session/session.py", line 107, in _send_message
    reply_post = self.code_interpreter.reply(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/bene/Pojects/TaskWeaver/taskweaver/code_interpreter/code_interpreter.py", line 68, in reply
    code.content,
    ^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'content'

Environment Information (please complete the following information):

OS: Ubuntu 23.10
Python 3.11.6
LLM that you're using: GPT-4-preview
code_verification: true

Add a Critic role

Is your feature request related to a problem? Please describe.
Having dabbled in TaskWeaver and AutoGen, I think that AutoGen's use of a "Critic" agent which weighs in on both plans and code can frequently improve the agent's overall ability to satisfy a user request.

Describe the solution you'd like
Add an additional role of Critic w/in TaskWeaver. The critic would review both Plans and Code before those roles passed them along.

Describe alternatives you've considered
N/A

Additional context
N/A

no config dir, linux

cant find the config directory (using linux). also in the installation instructions you use cd taskweaver, but its actually being extracted into the directory TaskWeaver

also had to install 2 extra modules. now im stuck here:

pip install injector
pip install ijson

python -m taskweaver -p ./project/
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "/home/user/TaskWeaver/taskweaver/main.py", line 1, in
from .cli import main
File "/home/user/TaskWeaver/taskweaver/cli/main.py", line 1, in
from .cli import taskweaver
File "/home/user/TaskWeaver/taskweaver/cli/cli.py", line 3, in
from ..app import TaskWeaverApp
File "/home/user/TaskWeaver/taskweaver/app/init.py", line 1, in
from .app import TaskWeaverApp
File "/home/user/TaskWeaver/taskweaver/app/app.py", line 12, in
from taskweaver.session.session import Session
File "/home/user/TaskWeaver/taskweaver/session/init.py", line 1, in
from .session import Session
File "/home/user/TaskWeaver/taskweaver/session/session.py", line 7, in
from taskweaver.code_interpreter import CodeInterpreter
File "/home/user/TaskWeaver/taskweaver/code_interpreter/init.py", line 1, in
from .code_interpreter import CodeInterpreter
File "/home/user/TaskWeaver/taskweaver/code_interpreter/code_interpreter.py", line 6, in
from taskweaver.code_interpreter.code_generator import (
File "/home/user/TaskWeaver/taskweaver/code_interpreter/code_generator/init.py", line 1, in
from .code_generator import CodeGenerator, CodeGeneratorConfig, format_code_revision_message
File "/home/user/TaskWeaver/taskweaver/code_interpreter/code_generator/code_generator.py", line 8, in
from taskweaver.llm import LLMApi
File "/home/user/TaskWeaver/taskweaver/llm/init.py", line 6, in
from openai import AzureOpenAI, OpenAI
ImportError: cannot import name 'AzureOpenAI' from 'openai' (/home/user/.venv/lib/python3.11/site-packages/openai/init.py)

pip freeze: openai==0.28.1

Contributors' Setup

Describe the solution you'd like
I was trying to set up the environment for TaskWeaver contributions and think the following two aspects could help:

Having a .devcontainer (e.g., https://github.com/microsoft/autogen/tree/main/.devcontainer) so that the contributors could quickly reproduce the environment.
Maybe we are missing the .linters folder in this repo? I wasn't able to run pre-commit run --all-files successfully, but it might be due to me setting it up wrong.

this program needs the ability to resume a previous session

when trying to build a program with taskweaver it got stuck in a weird loop and i had to close the program. i spent liek 14$ on gpt4 credits to get to that point. since this program is so new i suspect other users will experience the same fate unless there is a way to resume sessions.

also, being able to ctrl-c to cancel the current step and re-instruct the agents would maybe have prevented the need for this.

i love this project and i am stoked to see more!

Great package and want to explore. Is that possible to work in VS code instead of console?

I use Anaconda and I like to work in VS code. Is that possible?

Thank you and love to explore this package.

klarna_search

any time I ask taskweaver to pull data from a web source I see this error. even if its something simple like create a chart showing how Microsoft stock has trended over the last year. Please let me know if I'm missing something.

Cell In[1], line 2
klarna_search_result = klarna_search(query='Microsoft stock price', size=1)

NameError: name 'klarna_search' is not defined

thank you

Very slow inference (with local LLM) during agent work

Describe the bug
Very slow inference during agent work in comparison to usual LLM interaction
I'm using local setup with API connection to TextGen WebUI in local network
Each iteration of TaskWeaver is very-very slow
generation speed is drastically decreased to around 1-2 t/s (usual speed on same setup 15-20 t/s)

At this communication rate this tool is net very useful, simple coding task like print numbers executed in 20-30 mins.
Is there any tweak to solve it. I guess it could because of relatively large context in each request?

To Reproduce
Steps to reproduce the behavior:

Start the service
Type the user query "any listed query from example description"
Wait for the response forever

Expected behavior
Similar inference speed as Autogen

Environment Information (please complete the following information):

OS: MacOS
Python Version 3.11
LLM that you're using: number of different 7b models

Error when trying to run taskweaver from command line

Error while trying to run this command -> python3 -m taskweaver -p ./project

Traceback (most recent call last):
File "/opt/homebrew/Cellar/[email protected]/3.9.12/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/opt/homebrew/Cellar/[email protected]/3.9.12/Frameworks/Python.framework/Versions/3.9/lib/python3.9/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/TaskWeaver/taskweaver/main.py", line 1, in
from .cli import main
File "/TaskWeaver/taskweaver/cli/main.py", line 1, in
from .cli import taskweaver
File "/TaskWeaver/taskweaver/cli/cli.py", line 3, in
from ..app import TaskWeaverApp
File "/TaskWeaver/taskweaver/app/init.py", line 1, in
from .app import TaskWeaverApp
File "/TaskWeaver/taskweaver/app/app.py", line 9, in
from taskweaver.module.execution_service import ExecutionServiceModule
File "/TaskWeaver/taskweaver/module/execution_service.py", line 6, in
from taskweaver.ces import code_execution_service_factory
File "/TaskWeaver/taskweaver/ces/init.py", line 2, in
from taskweaver.ces.manager.sub_proc import SubProcessManager
File "/TaskWeaver/taskweaver/ces/manager/sub_proc.py", line 7, in
from taskweaver.ces.environment import Environment
File "/TaskWeaver/taskweaver/ces/environment.py", line 90, in
class TaskWeaverMultiKernelManager(MultiKernelManager):
File "/TaskWeaver/taskweaver/ces/environment.py", line 93, in TaskWeaverMultiKernelManager
kernel_name: str | None,
TypeError: unsupported operand type(s) for |: 'type' and 'NoneType'

Allow to install any python package

Is there a way to enable TaskWeaver to autonomously install any Python package it requires, rather than restricting it to the ones pre-defined in code_verification.allowed_modules?

Currently, predicting the exact packages TaskWeaver might need for a given task can be challenging. This limitation significantly narrows the tool's practical utility. By allowing more flexibility in package installation, TaskWeaver's adaptability and effectiveness could be substantially improved.

Discord invitation link shows Invite Invalid

The Discord link is invalid.
Link: https://discord.com/invite/nvFMRbzA
It shows:
This invite may be expired, or you might not have permission to join. Is there any restriction?

unable to run with lm studio

Describe the bug
my current config to access lm studio

{
"llm.api_base": "http://localhost:1234/v1",
"llm.api_key": "0",
"llm.model": "local-model",
"llm.response_format": null
}

i get this error

Error: Cannot process your request due to Exception: OpenAI API request failed to connect: Connection error.
Traceback (most recent call last):
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_exceptions.py", line 10, in map_exceptions
yield
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/http11.py", line 130, in _send_request_headers
event = h11.Request(
^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_events.py", line 96, in init
self, "headers", normalize_and_validate(headers, _parsed=_parsed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_headers.py", line 164, in normalize_and_validate
validate(_field_value_re, value, "Illegal header value {!r}", value)
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_util.py", line 91, in validate
raise LocalProtocolError(msg)
h11._util.LocalProtocolError: Illegal header value b'Bearer '

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

Traceback (most recent call last):
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_transports/default.py", line 60, in map_httpcore_exceptions
yield
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_transports/default.py", line 218, in handle_request
resp = self._pool.handle_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py", line 262, in handle_request
raise exc
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/connection_pool.py", line 245, in handle_request
response = connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/connection.py", line 96, in handle_request
return self._connection.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/http11.py", line 121, in handle_request
raise exc
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/http11.py", line 88, in handle_request
self._send_request_headers(**kwargs)
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/http11.py", line 129, in _send_request_headers
with map_exceptions({h11.LocalProtocolError: LocalProtocolError}):
File "/usr/local/lib/python3.11/contextlib.py", line 158, in exit
self.gen.throw(typ, value, traceback)
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_exceptions.py", line 14, in map_exceptions
raise to_exc(exc) from exc
httpcore.LocalProtocolError: Illegal header value b'Bearer '

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

Traceback (most recent call last):
File "/home/vscode/.local/lib/python3.11/site-packages/openai/_base_client.py", line 877, in _request
response = self._client.send(
^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_client.py", line 901, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_client.py", line 929, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_client.py", line 966, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_client.py", line 1002, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_transports/default.py", line 217, in handle_request
with map_httpcore_exceptions():
File "/usr/local/lib/python3.11/contextlib.py", line 158, in exit
self.gen.throw(typ, value, traceback)
File "/home/vscode/.local/lib/python3.11/site-packages/httpx/_transports/default.py", line 77, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.LocalProtocolError: Illegal header value b'Bearer '

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_exceptions.py", line 10, in map_exceptions
yield
File "/home/vscode/.local/lib/python3.11/site-packages/httpcore/_sync/http11.py", line 130, in _send_request_headers
event = h11.Request(
^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_events.py", line 96, in init
self, "headers", normalize_and_validate(headers, _parsed=_parsed)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_headers.py", line 164, in normalize_and_validate
validate(_field_value_re, value, "Illegal header value {!r}", value)
File "/home/vscode/.local/lib/python3.11/site-packages/h11/_util.py", line 91, in validate
raise LocalProtocolError(msg)
h11._util.LocalProtocolError: Illegal header value b'Bearer '