feat: add project infrastructure for software engineering best practices

[BioInfo]

• Add GitHub Actions CI/CD workflow with check, fmt, clippy, test, doc, deny, and MSRV jobs
• Add rustfmt.toml for consistent code formatting
• Add clippy.toml with Rust lint configuration
• Add deny.toml for cargo-deny dependency security checks
• Add CONTRIBUTING.md with development guidelines and TDD workflow
• Add GitHub issue templates (bug report, feature request)
• Add GitHub pull request template
• Add unit tests for Block, TreeNode, and TokenMask
• Fix clippy warnings across codebase
• Add missing flashinfer.rs module stub
• Export TreeSearchConfig and ScoringMethod from prelude

[gemini-code-assist]

Summary of Changes

Hello @BioInfo, 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 establishes a robust foundation for software engineering best practices within the project. It integrates automated CI/CD pipelines, enforces consistent code style and quality through dedicated configuration files, and provides clear guidelines for future contributions. These changes aim to improve code maintainability, reduce bugs, and facilitate a more collaborative development environment, while also laying the groundwork for future performance optimizations like the FlashInfer integration.

Highlights

• Project Infrastructure: Added comprehensive project infrastructure including GitHub Actions CI/CD workflows for checks, formatting, linting, testing, documentation, dependency security (cargo-deny), and Minimum Supported Rust Version (MSRV enforcement.
• Code Quality Tools: Introduced rustfmt.toml for consistent code formatting and clippy.toml with specific Rust lint configurations to maintain high code quality standards.
• Contribution Guidelines: Created CONTRIBUTING.md with detailed development guidelines, including a Test-Driven Development (TDD) workflow, and added GitHub issue and pull request templates to streamline community contributions.
• Unit Testing: Implemented initial unit tests for core components such as Block, TreeNode, and TokenMask to ensure correctness and stability.
• Codebase Refinements: Fixed existing Clippy warnings across the codebase, added a stub for the flashinfer.rs module, and exported TreeSearchConfig and ScoringMethod from the prelude for easier access.

🧠 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.

Ignored Files

• Ignored by pattern: .github/workflows/** (1)
  • .github/workflows/ci.yml

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 introduces a comprehensive set of software engineering best practices and infrastructure for the project. The changes are of high quality and establish a solid foundation for future development. Key additions include GitHub Actions workflows, configuration for rustfmt, clippy, and cargo-deny, and detailed contribution guidelines with templates. The codebase has been updated to adhere to the new linting rules, with improvements like using div_ceil for clarity. Crucially, extensive unit tests have been added for core data structures like Block and TreeNode, ensuring their correctness. The introduction of stubs for features like the FlashInferBackend is a good way to structure upcoming work. Overall, this is an excellent foundational PR with no issues of medium or higher severity found.