feat: modernize packaging with pyproject.toml and uv

[taeold]

Summary

Modernize Python packaging by migrating to pyproject.toml and adopting uv for faster dependency management.

Changes

• Migrate to pyproject.toml: Move all package metadata from setup.py to modern pyproject.toml (PEP 621)
• Add uv package manager: 10-100x faster than pip, with lock file for reproducible builds
• Update CI/CD workflows: All workflows now use uv sync and uv run commands
• Update docs: CONTRIBUTING.md now shows uv-based development workflow
• Add .python-version: Ensures consistent Python 3.10 usage

Benefits

• Faster dependency installation and CI runs
• Modern Python packaging standards
• Reproducible builds with uv.lock
• Simpler maintenance

Notes

• Based on chore: use ruff for linting and formatting #246 (ruff PR) to avoid conflicts
• setup.py kept for now, can be removed later
• No functionality changes

Test plan

• Tests pass: uv run pytest
• Build works: uv run python -m build
• CI passes with new workflows

[gemini-code-assist]

Summary of Changes

Hello @taeold, 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 overhauls the Python packaging and development environment to align with modern best practices, significantly improving dependency management speed, build reproducibility, and code quality tooling. These changes are foundational, aiming to streamline development and CI processes without altering core functionality.

Highlights

• Modernized Python Packaging: This pull request significantly modernizes the Python packaging setup by migrating from setup.py to pyproject.toml (PEP 621) for package metadata and configuration.
• Introduction of uv Package Manager: The project now adopts uv as its primary package manager, promising 10-100x faster dependency management and reproducible builds via uv.lock.
• CI/CD and Development Workflow Updates: All CI/CD workflows have been updated to leverage uv sync and uv run commands, and the CONTRIBUTING.md documentation has been revised to guide developers through the new uv-based development setup.
• Code Formatting and Linting Standard: The project transitions from yapf and pylint to ruff for code formatting and linting, with corresponding updates in .vscode/settings.json and pyproject.toml.
• Consistent Python Versioning: A .python-version file has been added to ensure consistent usage of Python 3.10 across the development environment.

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.

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. ↩

[taeold]

/gemini review

[gemini-code-assist]

Code Review

This pull request modernizes the project's packaging and dependency management by migrating to pyproject.toml and adopting uv. The changes are well-organized, and the updates to CI workflows and documentation are excellent. Consider committing the uv.lock file and using the standard [project.optional-dependencies] table for development dependencies.

[gemini-code-assist]

Code Review

This pull request modernizes the project's packaging by adopting pyproject.toml and uv. The changes are well-structured and move the project in the right direction. I've identified a few critical and high-severity issues related to the new packaging and dependency management setup that should be addressed to ensure correctness, maintainability, and reproducibility.

[taeold]

/gemini review

[gemini-code-assist]

Code Review

This is a great step forward in modernizing the project's packaging and dependency management. The migration to pyproject.toml and adoption of uv will certainly improve the developer experience and CI performance. I've left a few comments to enhance compatibility and maintainability, mainly concerning the pyproject.toml configuration and a small improvement to the contribution guide. Once these points are addressed, this PR will be in excellent shape.