Feat/claude support

[noamteyssier]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @noamteyssier, 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 enhances developer experience by integrating specific guidance for Claude AI, enabling it to better understand and interact with the codebase. Concurrently, it simplifies the project's configuration setup by removing redundant or outdated tool configurations, contributing to a cleaner and more maintainable project structure.

Highlights

• Claude AI Guidance: Introduced a new CLAUDE.md file to provide comprehensive guidance for Claude AI, detailing the project's overview, architecture, common commands, and development conventions.
• Configuration Streamlining: Streamlined project configuration by removing the [tool.pyright] section from pyproject.toml and deleting the ruff.toml file.

🧠 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

• CLAUDE.md
  • Added a new file providing detailed guidance for Claude AI.
  • Included sections on project overview, common commands, architecture, metrics, CLI, test data utilities, and conventions.
• pyproject.toml
  • Removed the [tool.pyright] configuration block.
• ruff.toml
  • Removed the entire Ruff configuration file.

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 CLAUDE.md file to provide context for an AI assistant and removes some configuration files. My review focuses on improving the clarity of the new documentation and pointing out a potentially unintended side effect of removing the ruff.toml configuration file, which could impact the project's code style and linting enforcement.

I am having trouble creating individual review comments. Click here to see my feedback.

ruff.toml (1-5)

Removing ruff.toml will cause ruff to fall back to its default settings. This is a significant change, as it will, for example, reduce the max-line-length from 120 to 88 and change the set of active linting rules (the ERA rule for commented-out code will be disabled).

If this is unintentional, you should move the configuration to pyproject.toml. Here is how you can do it:

[tool.ruff]
line-length = 120

[tool.ruff.lint]
select = ["E", "F", "ERA"]

This will preserve the project's current code style and linting rules.

CLAUDE.md (68-69)

For better clarity and to ensure the AI assistant can find the exact metrics, it would be beneficial to use the precise metric names as registered in src/cell_eval/metrics/_impl.py, and use wildcards for metric families. This will make the documentation more accurate.

For example:

• discrimination_score is registered as discrimination_score_{distance_metric} (e.g., discrimination_score_l1).
• edistance is registered as pearson_edistance.
• overlap/precision at N corresponds to overlap_at_* and precision_at_*.
• spearman correlations corresponds to de_spearman_* metrics.

- **AnnData metrics** (`_anndata.py`): `pearson_delta`, `mse`, `mae`, `mse_delta`, `mae_delta`, `discrimination_score_*`, `clustering_agreement`, `pearson_edistance`
- **DE metrics** (`_de.py`): `overlap_at_*`, `precision_at_*`, `de_spearman_*`, `de_direction_match`, `de_sig_genes_recall`, `pr_auc`, `roc_auc`