Addition of Ability Register and Sample Ability

[Swiftyos]

In this PR, we have introduced an AbilityRegister class and a sample ability. The AbilityRegister is designed to manage and execute abilities, which are essentially callable methods with metadata.

The AbilityRegister class has the following key methods:

• register_abilities: This method scans the abilities directory and imports all Python files as modules. It then checks each module for functions that have been decorated with the ability decorator and adds them to the register.

• list_abilities: This method returns a list of all registered abilities.

• abilities_description: This method returns a string representation of all registered abilities, grouped by category.

• run_ability: This method executes a specified ability with the provided arguments and keyword arguments.

The ability decorator is used to annotate functions that should be treated as abilities. It takes the following parameters: name, description, parameters, and output_type. The decorator checks that the function's parameters match the provided parameters and then attaches an Ability instance to the function.

The Ability class represents an ability in the system. It includes metadata about the ability such as its name, description, parameters, and output type. The Ability class can be called like a function, executing the underlying method.

A sample ability has been added to demonstrate how to create an ability. More abilities can be added by creating new Python files in the abilities directory and using the ability decorator to annotate functions.

This new feature enhances the modularity and extensibility of our system, allowing new abilities to be added easily and in a structured manner.

[github-actions]

PR Analysis

• 🎯 Main theme: Addition of an Ability Register and a Sample Ability
• 📝 PR summary: This PR introduces an AbilityRegister class and a sample ability. The AbilityRegister is designed to manage and execute abilities, which are essentially callable methods with metadata. The ability decorator is used to annotate functions that should be treated as abilities. A sample ability has been added to demonstrate how to create an ability.
• 📌 Type of PR: Enhancement
• 🧪 Relevant tests added: No
• 🔒 Security concerns: No security concerns found

PR Feedback

• 💡 General suggestions: The PR is well-structured and the code is clean. However, it would be beneficial to add tests to ensure the functionality of the new features. Also, it would be better to handle exceptions in a more specific way rather than catching all exceptions.

• 🤖 Code feedback:

  • relevant file: forge/autogpt/sdk/abilities/registry.py
    suggestion: Instead of catching all exceptions, it would be better to handle specific exceptions that you expect might occur. This can help with debugging and prevent masking of unexpected errors. [important]
    relevant line: except Exception as e:

  • relevant file: forge/autogpt/sdk/abilities/registry.py
    suggestion: It would be better to use logging instead of print statements for debugging and error messages. This allows for better control over message formatting, output level, and where output is directed. [medium]
    relevant line: print(f"Error occurred while registering abilities: {str(e)}")

  • relevant file: forge/autogpt/sdk/abilities/registry.py
    suggestion: It would be better to remove the main execution block at the end of the file. If testing is needed, it's better to have a separate test file. [medium]
    relevant line: if name == "main":

  • relevant file: forge/autogpt/sdk/abilities/registry.py
    suggestion: It would be better to add error handling or a default return value in case the ability_name does not exist in the abilities dictionary. This can prevent potential KeyError exceptions. [important]
    relevant line: ability = self.abilities[ability_name]

How to use

To invoke the PR-Agent, add a comment using one of the following commands:
/review [-i]: Request a review of your Pull Request. For an incremental review, which only considers changes since the last review, include the '-i' option.
/describe: Modify the PR title and description based on the contents of the PR.
/improve [--extended]: Suggest improvements to the code in the PR. Extended mode employs several calls, and provides a more thorough feedback.
/ask <QUESTION>: Pose a question about the PR.
/update_changelog: Update the changelog based on the PR's contents.

To edit any configuration parameter from configuration.toml, add --config_path=new_value
For example: /review --pr_reviewer.extra_instructions="focus on the file: ..."
To list the possible configuration parameters, use the /config command.