Challenges should be using the automatic AI Config generation

[waynehamadi]

Duplicates

• I have searched the existing issues

Summary 💡

Our challenges should use the default Auto-GPT mode. In the default mode, we generate the AI Config automatically.

pick one test, for example test_browse_website.and attempt to generate the AI Config automatically at the beginning of the test. You will need to define a prompt that makes the test pass.
replace the browser_agent located in tests/integration/agent_factory.py by this :

@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  = generate_aiconfig_automatic(user_desire)
    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

pick the correct user_desire that makes the test pass.

Apply the same logic for all the tests located in the goal_oriented and challenges folders. Create a PR for each test so it's easier to review.

[anonhostpi]

Related: #3907

[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.