added --test, consolidate files, reports working

[SilenNaihin]

Background

Some quality of life for users and preparation for writing paper.

Changes

• --test TestWriteFile just runs a single test specified such as TestWriteFile in that example
• instead of having config.json, regression_tests.json, 'benchmarks.py', and reports/ all in seperate files, they are now under the agbenchmark folder. Moved local files (regression and config) to agbenchmark/, they are now just used for mocks. If you'd like to run a specific agent, navigate to a submodule and run it from there
• Reports! Simple example:

{
    "command": "agbenchmark start --test TestWriteFile --mock",
    "completion_time": "2023-07-10-21:32",
    "time_elapsed": "0.29 seconds",
    "tests": {
        "TestWriteFile": {
            "difficulty": "basic",
            "dependencies": [],
            "test": "agbenchmark\\challenges\\interface\\write_file",
            "success": true
        }
    },
    "config": {
        "workspace": "autogpt/workspace/auto_gpt_workspace",
        "entry_path": "benchmarks.py",
        "home_path": "",
        "cutoff": 60
    }
}

PR Quality Checklist

• I have run the following commands against my code to ensure it passes our linters:

  black .
  isort .
  mypy .
  autoflake --remove-all-unused-imports --recursive --ignore-init-module-imports --ignore-pass-after-docstring --in-place agbenchmark

[ai-maintainer]

Thank you for your contribution! 

This pull request is too large for automated review.