fix(exp): never allow level overflowing over maximum

[olisikh]

Situation:

• Character is at level 399 and 99.99999% experience
• Character annihilates N monsters in a very quick succession
• Experience values are flying into the server
• Without locking the experience calculations, the server may update Attributes[Level] twice (or more times) having a chance to produce 401 level value, which bricks the character (if logged out, character won't be able to login again)

I have experienced 3 times already.

Same applies to a character of any level, there's a chance an extra level (or more) is granted when it shouldn't be, because of the race condition described above.

This PR patches the race condition, making sure experience is summed correctly.

[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 addresses a critical race condition in the character experience system where rapid, concurrent experience gains could cause a character to exceed the maximum allowed level, effectively bricking the character. By implementing thread-safe locking mechanisms and refactoring the experience calculation logic, the changes ensure that level progression is strictly controlled and adheres to server configuration limits.

Highlights

• Race Condition Resolution: Introduced an AsyncLock to the Player class to ensure experience calculations are atomic, preventing race conditions that could lead to invalid level values.
• Experience Calculation Logic: Refactored experience gain logic into core methods that properly handle level caps and prevent overflow when configured to do so.
• Comprehensive Testing: Added a new test suite to verify concurrent experience gains, level cap enforcement, and overflow behavior under various configurations.

🧠 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.

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.

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 thread-safe experience gain by implementing an "AsyncLock" in the "Player" class. It refactors experience addition logic into core methods that utilize a loop to handle potential multi-level gains and experience overflow based on server configuration. Additionally, a comprehensive test suite was added to verify these changes under various scenarios like solo kills, party distribution, and concurrent updates. A redundant level check was identified in the loop logic.

[olisikh]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces thread-safety to the experience gain system by implementing an asynchronous lock and refactors the experience addition logic to better handle level-ups and overflows. Feedback indicates that some redundant level checks were added in the master experience logic and that the overflow termination conditions in the normal experience logic can be simplified as they are already covered by the loop's control flow.