Make bus client retry helper generic

[Cloudhabil]

Summary

• make BusClient._with_retry generic and propagate result of retried function
• return request results directly and handle request errors explicitly in run

Testing

• python -m mypy core/bus_client.py
• pytest

---

https://chatgpt.com/codex/tasks/task_e_68bcbecef2e88322b9734f6e94e4675d

[gemini-code-assist]

Summary of Changes

Hello @Cloudhabil, 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 refactors the BusClient's retry mechanism and request handling to enhance robustness and type safety. The changes ensure that network request failures are explicitly propagated or handled, leading to more predictable behavior and clearer error management within the client.

Highlights

• Generic Retry Helper: The _with_retry helper function has been made truly generic, now always returning the result of the retried function or raising the last encountered exception. It no longer returns None on failure, simplifying error handling downstream.
• Direct Request Results: The _request and _arequest methods now directly return an httpx.Response object, removing the possibility of returning None and ensuring a valid response or an exception.
• Explicit Error Handling in run: The run method explicitly handles httpx.RequestError during bus client requests, introducing a sleep and early return on network failures, improving the client's resilience.

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 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 effectively refactors the _with_retry helper to be more generic and robust by propagating exceptions instead of returning None. The changes improve type safety by removing Any and cast in favor of more specific types, and simplify the implementation by removing the need for inspect. The error handling in run is now more explicit. Overall, these are great improvements to code clarity and reliability. I have one suggestion to make the retry logic even more robust against invalid input.

[gemini-code-assist]

To improve robustness, consider handling negative values for retries. A negative number of retries is not meaningful and currently leads to an AssertionError because the retry loop is skipped. It would be safer to treat negative values as 0, ensuring the function behaves predictably even with invalid input.

        if retries < 0:
            retries = 0
        last_exc: Exception | None = None