Our Challenges should use the default list of commands

[waynehamadi]

In the tests/challenges I created so far, I change the commands so that Auto-GPT doesn't get distracted.

But now we should attempt to remove these commands and see if the tests fail. Because a real user doesn't get to pick the commands he wants, at the moment. Also, he shouldn't have to. He should just say what he wants to do and Auto-GPT uses the right tool to do the job.

Task: for each agent defined in the tests/integration/agent_factory.py, use the default list of commands.

For example:

@pytest.fixture
def browser_agent(agent_test_config, memory_none: NoMemory, workspace: Workspace):


    command_registry = CommandRegistry()
    command_registry.import_commands("autogpt.commands.file_operations")
    command_registry.import_commands("autogpt.commands.web_selenium")
    command_registry.import_commands("autogpt.app")
    command_registry.import_commands("autogpt.commands.task_statuses")
    ai_config = AIConfig(
        ai_name="browse_website-GPT",
        ai_role="an AI designed to use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html, answer the question 'What is the price of the book?' and write the price to a file named \"browse_website.txt\", and use the task_complete command to complete the task.",
        ai_goals=[
            "Use the browse_website command to visit http://books.toscrape.com/catalogue/meditations_33/index.html and answer the question 'What is the price of the book?'",
            'Write the price of the book to a file named "browse_website.txt".',
            "Use the task_complete command to complete the task.",
            "Do not use any other commands.",
        ],
    )
    ai_config.command_registry = command_registry

    system_prompt = ai_config.construct_full_prompt()

    agent = Agent(
        ai_name="",
        memory=memory_none,
        full_message_history=[],
        command_registry=command_registry,
        config=ai_config,
        next_action_count=0,
        system_prompt=system_prompt,
        triggering_prompt=DEFAULT_TRIGGERING_PROMPT,
        workspace_directory=workspace.root,
    )

    return agent

Remove the lines that define the commands. instead, just use the default list of commands. If you have to change the prompts to make the tests pass, do it.

[github-actions]

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

[github-actions]

This issue was closed automatically because it has been stale for 10 days with no activity.