Do not load disabled commands (faster exec & benchmark runs)

[lc0rp]

Background

Disabled commands need to be unregistered after initializing the registry.

get_command_registry() wasn't doing this, leading to more prolonged execution and benchmark runs when the disabled command was loaded, failed, and then the correct one was loaded.

For example (with no Google API key), we typically see:

• google => fail => web_search => pass

Changes

Swapped get_command_registry for CommandRegistry.with_command_modules

Documentation

N/A

Test Plan

Local testing

PR Quality Checklist

• My pull request is atomic and focuses on a single change.
• I have thoroughly tested my changes with multiple different prompts.
• I have considered potential risks and mitigations for my changes.
• I have documented my changes clearly and comprehensively.
• I have not snuck in any "extra" small tweaks changes.
• 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 autogpt tests --in-place

[netlify]

❌ Deploy Preview for auto-gpt-docs failed.

Name	Link
🔨 Latest commit	f9e5b4b
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/64c5f5ea39d11e0008706902