Use GPT-4 in Agent loop by default

[Pwuts]

• Use GPT-4 as default smart LLM in Agent
• Rename (smart|fast)_llm_model to (smart|fast)_llm everywhere

Background

OpenAI just announced GPT-4 general availability: https://openai.com/blog/gpt-4-api-general-availability

UPDATE: "general availability" only applies to existing developers "with a history of successful payments" for now. :(

Warning
While testing manually, I experienced a one-time anomaly where it told me openai.error.InvalidRequestError: The model: 'gpt-4' does not exist. Subsequent attempts were successful.

Changes

• Set GPT-4 as the default Smart LLM
• Use the Smart LLM in the main Agent loop
• Rename smart_llm_model to smart_llm and fast_llm_model to fast_llm everywhere (with backwards compatibility)

Documentation

yes

Test Plan

CI

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 ready!

Name	Link
🔨 Latest commit	816ad18
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/64a76142ad41020008cdf7f5
😎 Deploy Preview	https://deploy-preview-4899--auto-gpt-docs.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[netlify]

✅ Deploy Preview for auto-gpt-docs canceled.

Name	Link
🔨 Latest commit	0b13cdd
🔍 Latest deploy log	https://app.netlify.com/sites/auto-gpt-docs/deploys/64a76725d0f346000887585d

[Auto-GPT-Bot]

You changed AutoGPT's behaviour. The cassettes have been updated and will be merged to the submodule when this Pull Request gets merged.

[codecov]

Codecov Report

Patch coverage: 80.00% and project coverage change: -0.05 ⚠️

Comparison is base (ac17518) 50.21% compared to head (0b13cdd) 50.17%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #4899      +/-   ##
==========================================
- Coverage   50.21%   50.17%   -0.05%     
==========================================
  Files         116      116              
  Lines        4809     4809              
  Branches      645      645              
==========================================
- Hits         2415     2413       -2     
- Misses       2215     2216       +1     
- Partials      179      180       +1     

Impacted Files	Coverage Δ
autogpt/llm/chat.py	66.23% <0.00%> (-2.60%)	⬇️
autogpt/setup.py	79.71% <ø> (ø)
autogpt/llm/utils/__init__.py	49.25% <33.33%> (ø)
autogpt/agent/agent.py	59.18% <50.00%> (ø)
autogpt/config/config.py	83.89% <100.00%> (ø)
autogpt/configurator.py	30.37% <100.00%> (ø)
autogpt/memory/message_history.py	84.69% <100.00%> (ø)
autogpt/processing/text.py	33.96% <100.00%> (ø)

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.

[Boostrix]

not sure if this still being capped for some users ?
If so, we would be crippling agpt for those if they exceed the limit, so probably need a fallback in case GPT4 is being capped ?