Clarify README project status

[kiankyars]

Summary

• clarify that the trainer/RL surface is still early
• add a short current-status section covering what is stable today
• keep the README aligned with the current SDK surface without changing code

Testing

• not run (README-only change)

cc @abhishekg999

---

[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 updates the project's README to provide greater clarity regarding the maturity and stability of various features, particularly the Reinforcement Learning (RL) trainer surface. The changes aim to set accurate user expectations by distinguishing between stable functionalities and those still under active development, thereby improving the overall user experience and guiding new users more effectively.

Highlights

• Clarity on RL/Trainer Status: The README now explicitly clarifies that the trainer/Reinforcement Learning (RL) surface is still in early development, setting appropriate expectations for users.
• New 'Current Status' Section: A dedicated 'Current Status' section has been added to provide a clear overview of which features are stable today (e.g., tracing, online evaluation) and which are under active development (e.g., trainer/RL surface).
• README Alignment: The documentation has been updated to align with the current SDK surface, ensuring that the README accurately reflects the maturity and recommended usage paths of different features without requiring code changes.

🧠 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

• README.md
  • Updated the heading for the Agent Reinforcement Learning section to explicitly state its experimental nature.
  • Modified the description of the RL feature to highlight that it includes an 'early trainer/RL surface' and that its APIs are 'still under active development'.
  • Replaced a general statement about automatic trajectory management with a more detailed explanation, emphasizing the early development stage of trainer APIs.
  • Introduced a new 'Current Status' section, detailing stable features (tracing, online evaluation, custom scorers) and features in early/active development (trainer/RL surface).
  • Revised the 'Why Judgeval?' section's RL bullet point to reflect its experimental status and recommend cookbook examples for initial use.
  • Removed outdated commented-out TODOs related to documentation.

Activity

• The changes are README-only, so no specific testing was run.
• The pull request is CC'd to @abhishekg999 for review or awareness.

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. ↩

[propel-code-bot]

No issues found in this documentation-only update; changes appear clear and aligned.

Status: No Issues Found | Risk: Low

Review Details

📁 1 files reviewed | 💬 0 comments

[propel-code-bot]

✔️ Propel has finished reviewing this change.

[devin-ai-integration]

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.

[gemini-code-assist]

Code Review

This pull request effectively clarifies the project's status in the README, particularly noting that the reinforcement learning features are experimental. Adding a 'Current Status' section is a great improvement for user clarity. The changes are consistent and well-executed. I've included one suggestion to further improve the readability of the new section.

[gemini-code-assist]

For better readability, consider breaking this long list of stable features into a nested list. This will make it easier for users to quickly scan and understand the stable components.

Suggested change

	- Stable today: tracing and provider instrumentation, online evaluation, custom scorers, scorer upload, and the core project-scoped factories for datasets, prompts, and evaluations.
	- Stable today:
	- tracing and provider instrumentation
	- online evaluation
	- custom scorers
	- scorer upload
	- the core project-scoped factories for datasets, prompts, and evaluations.