feat: update local code executor to support powershell

[lspinheiro]

Why are these changes needed?

To support powershell on the local code executor.

Related issue number

Closes #5518

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[lspinheiro]

There is a new unit test, but should be skipped in CI. I tested it on the following script ( a variant of the one posted in the issue)

import asyncio
from autogen_ext.models.openai import AzureOpenAIChatCompletionClient
from autogen_agentchat.agents import AssistantAgent, CodeExecutorAgent
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_agentchat.ui import Console
from autogen_ext.code_executors.local import LocalCommandLineCodeExecutor
import os

async def main() -> None:
    # Set up the model client to use the local Ollama model "llama3.2:3b-instruct-fp16"
    model_client = AzureOpenAIChatCompletionClient(
        model="gpt-4o",
        api_key=...,
        azure_deployment="gpt-4o",
        azure_endpoint=...,
        api_version=...
        model_info={
            "vision": False,
            "function_calling": True,
            "json_output": True,
            "family": "unknown",
        },
    )

    # Create a local code executor that will execute code on the local machine.
    # Note: There is no need to call start() or stop() on LocalCommandLineCodeExecutor.
    code_executor = LocalCommandLineCodeExecutor(work_dir="coding")

    # Create a CodeExecutorAgent that executes local code blocks.
    code_agent = CodeExecutorAgent("CodeExecutor", code_executor=code_executor)

    # Create an AssistantAgent specialized for Windows 11 settings changes.
    # The system message instructs the agent to generate safe code (Python or shell)
    # that will, for example, enable dark mode in Windows 11.
    assistant_agent = AssistantAgent(
        "WindowsAdmin",
        model_client=model_client,
        system_message=(
            "You are a Windows 11 system administrator agent. Your task is to generate code that modifies Windows 11 settings using local code execution as a powershell script. Provide only the code, no other text or comments formatted in markdown. The code should be formatted in a way that is easy to copy and paste into a powershell script."
        ),
    )

    # Assemble the team using RoundRobinGroupChat to act as a round-robin orchestrator.
    # Here, max_turns=5 allows for up to 5 rounds of interactions between agents.
    team = RoundRobinGroupChat([assistant_agent, code_agent], max_turns=5)

    # Define the specialized task: change a Windows 11 setting (e.g., enable dark mode).
    task = "Write a powershell script that calculates the sum of all numbers from 1 to 100."

    # Run the team using streaming output via the Console helper.
    result = await Console(team.run_stream(task=task))
    print(result)

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

PS C:\Users\lpinheiro\Github\autogen\python\dev> python .\src\test_ps1_code_executor.py
---------- user ----------
Write a powershell script that calculates the sum of all numbers from 1 to 100.
---------- WindowsAdmin ----------
'''powershell
$sum = 0
for ($i = 1; $i -le 100; $i++) {
    $sum += $i
}
Write-Output "The sum of all numbers from 1 to 100 is $sum"
'''
---------- CodeExecutor ----------
The sum of all numbers from 1 to 100 is 5050

---------- WindowsAdmin ----------

---------- CodeExecutor ----------
No code blocks found in the thread. Please provide at least one markdown-encoded code block to execute (i.e., quoting code in ```python or ```sh code blocks).
---------- WindowsAdmin ----------
'''powershell
$sum = 0
for ($i = 1; $i -le 100; $i++) {
    $sum += $i
}
'''
Write-Output "The sum of all numbers from 1 to 100 is $sum"

TaskResult(messages=[TextMessage(source='user', models_usage=None, metadata={}, content='Write a powershell script that calculates the sum of all numbers from 1 to 100.', type='TextMessage'), TextMessage(source='WindowsAdmin', models_usage=RequestUsage(prompt_tokens=98, completion_tokens=56), metadata={}, content='```powershell\n$sum = 0\nfor ($i = 1; $i -le 100; $i++) {\n    $sum += $i\n}\nWrite-Output "The sum of all numbers from 1 to 100 is $sum"\n```', type='TextMessage'), TextMessage(source='CodeExecutor', models_usage=None, metadata={}, content='The sum of all numbers from 1 to 100 is 5050\r\n', type='TextMessage'), TextMessage(source='WindowsAdmin', models_usage=RequestUsage(prompt_tokens=184, completion_tokens=0), metadata={}, content='', type='TextMessage'), TextMessage(source='CodeExecutor', models_usage=None, metadata={}, content='No code blocks found in the thread. Please provide at least one markdown-encoded code block to execute (i.e., quoting code in ```python or ```sh code blocks).', type='TextMessage'), TextMessage(source='WindowsAdmin', models_usage=RequestUsage(prompt_tokens=233, completion_tokens=56), metadata={}, content='```powershell\n$sum = 0\nfor ($i = 1; $i -le 100; $i++) {\n    $sum += $i\n}\nWrite-Output "The sum of all numbers from 1 to 100 is $sum"\n```', type='TextMessage')], stop_reason='Maximum number of turns 5 reached.')

[codecov]

Codecov Report

Attention: Patch coverage is 77.77778% with 4 lines in your changes missing coverage. Please review.

Project coverage is 75.64%. Comparing base (7d17b22) to head (efc9963).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
...ogen-ext/src/autogen_ext/code_executors/_common.py	0.00%	2 Missing ⚠️
...t/src/autogen_ext/code_executors/local/__init__.py	87.50%	2 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #5884      +/-   ##
==========================================
- Coverage   75.65%   75.64%   -0.02%     
==========================================
  Files         189      189              
  Lines       12784    12794      +10     
==========================================
+ Hits         9672     9678       +6     
- Misses       3112     3116       +4     

Flag	Coverage Δ
unittests	75.64% <77.77%> (-0.02%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.