Improvement/add_unit_tests

[hahwul]

No description provided.

[gemini-code-assist]

Hello @hahwul, I'm Gemini Code Assist¹! 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!

Summary of Changes

This pull request adds unit tests for the LLM module, specifically focusing on ensuring that the FILTER_PROMPT, FILTER_FORMAT, ANALYZE_PROMPT, and ANALYZE_FORMAT constants are not nil. This enhances the test coverage for the LLM module.

Highlights

• Unit Tests: Adds unit tests for LLM constants to ensure they are defined.
• LLM Module: Focuses on testing constants within the LLM module related to prompts and formats.

Changelog

• spec/unit_test/llm/prompt_spec.cr
  • Added a new spec file to test LLM constants.
  • Included tests to verify that FILTER_PROMPT, FILTER_FORMAT, ANALYZE_PROMPT, and ANALYZE_FORMAT constants are not nil.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

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.

---

Did you know?

Crystal's syntax is heavily inspired by Ruby, aiming to provide similar developer experience with improved performance due to static typing and compilation.

Footnotes

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. ↩

[gemini-code-assist]

Code Review

The pull request adds unit tests for the LLM module, specifically for the FILTER_PROMPT, FILTER_FORMAT, ANALYZE_PROMPT, and ANALYZE_FORMAT constants. This is a good start to ensuring the stability and correctness of these important components.

Merge Readiness

The pull request adds basic unit tests for the LLM constants. While the tests ensure that the constants are not nil, they do not validate the content or format of the constants. I would recommend adding more comprehensive tests to validate the content of the constants. I am unable to directly approve the pull request, and users should have others review and approve this code before merging.

[gemini-code-assist]

This test only checks that ANALYZE_PROMPT is not nil. Consider adding an assertion to check that it contains expected content or matches a specific format. For example, you could check if it includes the string "Input Code:".

    LLM::ANALYZE_PROMPT.should_not be_nil
    LLM::ANALYZE_PROMPT.should include("Input Code:")

[gemini-code-assist]

This test only checks that ANALYZE_FORMAT is not nil. Consider adding an assertion to check that it contains expected content or matches a specific format. For example, you could check if it includes the string "name": "analyze_endpoints".

    LLM::ANALYZE_FORMAT.should_not be_nil
    LLM::ANALYZE_FORMAT.should include("name": "analyze_endpoints")