Optimizing Responsibilities of Class Objects

[lengweiping1983]

Background

1. AIConfig and Prompt two classes has interdependence.

The construct_prompt function in prompt.py is to call the construct_full_prompt function of the AlConfig object,
And the construct_full_prompt function needs to call the get_prompt function in prompt.py.

2. variable assignment

I saw the code in the script of cli.py (called main.py yesterday), as follows:

        ai_name = ""
	
        other code ......	
        
        agent = Agent(
            ai_name=ai_name,
            memory=memory,
            full_message_history=full_message_history,

Where is the value of the ai_name variable obtained, it cannot be seen here.

So need Optimizing Responsibilities of Class Objects.

Changes

Optimizing Responsibilities of Class Objects:
AIConfig only config, not generate prompt.
Prompt is responsible generate prompt.
Setup script is responsible to get AIConfig (either from user input or from ai_settings_file).

Documentation

Test Plan

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

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[github-actions]

Conflicts have been resolved! 🎉 A maintainer will review the pull request shortly.

[github-actions]

This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request.

[lengweiping1983]

@nponeccop @BillSchumacher

The PR I optimized two days ago has conflicts again.
Just synchronized the code, saw a lot of changes, added command plugins, this function is very good.

However, it is still possible to perform the following optimizations:
a. Optimizing Responsibilities of Class Objects.

b. command_registry belongs to AIConfig and PromptGenerator, which can be optimized. AI Config would be better with only user input data.

c. There are two command lists,
1. PromptGenerator has a command list
2. The CommandRegistry has a command list.
It would be better to just need a list.

d. There are two command objects.
1. command.py Command
2. build_default_prompt_generator commands.
It would be better to only need a Command object.

e. PromptGenerator commands is list , dict will be better, query is faster.

f. Now there are many files involved in optimization, such as generator.py, prompt.py, ai_config.py, agent.py, app.py, cli.py My changes will conflicts.

If it is possible for me to optimize it, just let me know.

[p-i-]

This is a mass message from the AutoGPT core team.
Our apologies for the ongoing delay in processing PRs.
This is because we are re-architecting the AutoGPT core!

For more details (and for infor on joining our Discord), please refer to:
https://github.com/Significant-Gravitas/Auto-GPT/wiki/Architecting

[Pwuts]

Thanks for submitting, this kind of clean-up is appreciated! A lot of similar work has been done since this PR was submitted, which has caused extensive conflicts with master. I have tried resolving them, but without luck. It's too much. :/

I'll close this pull request, although we would be happy to keep you involved. Feel free to submit pull requests again or bring existing ones to our attention. We are working to get to a balance between our capacity to process PRs and the rate at which we receive them.