chore(tools/serverlessspark): decouple source config from tools

[Yuan325]

Within Invoke() and RequiresClientAuthorization(), get Source from ResourceManager and use it to call functions directly.

[gemini-code-assist[bot]]

Summary of Changes

Hello @Yuan325, I'm Gemini Code Assist[^1]! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly refactors the internal Serverless Spark tools by abstracting their dependency on the concrete serverlessspark.Source implementation. By introducing a compatibleSource interface and dynamically retrieving source information, the changes enhance modularity and reduce tight coupling, making the tools more flexible and easier to maintain. This refactoring ensures that tools interact with sources through a well-defined contract, improving the overall design of the system.

Highlights

• Decoupling Source Configuration: The pull request decouples the direct dependency of Serverless Spark tools on the serverlessspark.Source type, promoting a more modular architecture.
• Introduction of compatibleSource Interface: A new compatibleSource interface has been introduced in the Serverless Spark tools, defining the necessary methods (GetOperationsClient, GetBatchControllerClient, GetProject, GetLocation) that tools require from a source.
• Dynamic Source Retrieval: Tools now retrieve their associated source dynamically via resourceMgr.GetSource() and cast it to the compatibleSource interface, rather than holding a direct reference to a concrete serverlessspark.Source.
• New Methods in serverlessspark.Source: The serverlessspark.Source struct now includes GetProject() and GetLocation() methods to expose project and location details, which are utilized by the refactored tools.
• Updated Tool Method Signatures: The RequiresClientAuthorization and GetAuthTokenHeaderName methods in the Serverless Spark tools have been updated to return an error in addition to their previous return values, aligning with a common pattern for operations that might fail.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with :thumbsup: and :thumbsdown: on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

[^1]: Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.