feat: add integration tests for skill-driven extraction functionality

[shahrear33]

• Updated CONTRIBUTING.md to include a command for running tests specific to skill-driven extraction.
• Added a new integration test in skills.test.ts to validate the creation of a skill and its usage for batch document generation.

[gemini-code-assist]

Summary of Changes

Hello, 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!

This pull request introduces new integration tests to ensure the robust functionality of skill-driven extraction. It includes an update to the contributing guidelines to reflect how to run these new tests, alongside a comprehensive test case that verifies the creation of a skill and its subsequent application in batch document generation.

Highlights

• Documentation Update: The CONTRIBUTING.md file was updated to include a new command for running integration tests specifically for skill-driven extraction.
• New Integration Test: A new integration test was added to skills.test.ts to validate the end-to-end flow of creating a skill and then using it for batch document generation.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• docs/CONTRIBUTING.md
  • Added a new command to the testing section for running skill-driven extraction integration tests.
• tests/integration/client/skills.test.ts
  • Imported the PredictionResponse type.
  • Added a new describe block containing an integration test for skill-driven extraction, covering skill creation and document generation.

Activity

• No human activity has been recorded on this pull request yet.

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 👍 and 👎 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.

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

This pull request adds integration tests for the skill-driven extraction functionality and updates the contribution guide with a command to run these new tests. My review includes a suggestion to improve the clarity of the documentation and points out a significant type-safety issue in the new integration test that should be addressed by updating the relevant type definitions and implementation.

[gemini-code-assist]

The use of as any here is a workaround for a type mismatch and should be avoided as it compromises TypeScript's type safety. The config object is being passed a skills property which is not defined in the GenerationConfigParams type.

To address this correctly, the following changes are needed in files not included in this pull request:

1. Update GenerationConfigParams in src/client/types.ts: Add the optional skills property.
2. Update generate method in src/client/predictions.ts: Ensure the skills property from the config is passed through to the API request. The current implementation appears to filter unknown properties from the config object.

I recommend including these changes in this pull request to ensure the new test is valid and type-safe.

[gemini-code-assist]

For better readability and consistency with other examples in this file, please add a comment explaining what this command does.

Suggested change

	npm run test:integration -- --testPathPatterns="skills" -t "skill-driven extraction"
	# Run just the skill-driven extraction integration tests
	npm run test:integration -- --testPathPatterns="skills" -t "skill-driven extraction"