Fix SmoothingETA

[jonathanpoelen]

The value of smoothing_algorithm.update() was not used, therefore SmoothingETA was strictly identical to ETA.

I would like to take this opportunity to say that the constructor of SmoothingETA is particularly bad and incorrect in terms of typing:

    def __init__(
        self,
        smoothing_algorithm: type[
            algorithms.SmoothingAlgorithm
        ] = algorithms.ExponentialMovingAverage,
        smoothing_parameters: dict[str, float] | None = None,
        **kwargs,
    )

smoothing_parameters contradicts algorithms.SmoothingAlgorithm.__init__, which takes a dict[str, Any]. This typing also forces all inherited classes to use floats as parameters. This doesn't make sense. Furthermore, the constructor of algorithms.SmoothingAlgorithm throws an exception and forces you to create a __init__ function, even if it's not useful. algorithms.SmoothingAlgorithm shouldn't have a constructor.

The constructor of SmoothingETA should simply take an instance of algorithms.SmoothingAlgorithm and not have this horrible smoothing_parameters, which also makes IDE auto-completion unusable.

While I'm at it, what are the exponential_smoothing and exponential_smoothing_factor members and parameters of AdaptiveETA, since they are not used?

One last thing that's unrelated: time.time() is not monotonic, which creates bugs twice a year following daylight saving time changes or when there is an NTP synchronization that set back.

[gemini-code-assist[bot]]

Summary of Changes

Hello @jonathanpoelen, I'm Gemini Code Assist[^1]! 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 bug in the SmoothingETA widget where its smoothing functionality was not active due to an unassigned return value. By correctly capturing and using the smoothed value, this change ensures that SmoothingETA now functions as intended, providing more accurate and stable estimated times of arrival. The update also includes corresponding adjustments to test expectations and a minor documentation enhancement.

Highlights

• Core Bug Fix: Corrected an issue where SmoothingETA was effectively identical to ETA because the return value of smoothing_algorithm.update() was not being utilized. The fix now assigns the smoothed value back to value, ensuring the smoothing algorithm is actively applied.
• Documentation Update: Added SmoothingETA to the list of widgets in README.rst, improving documentation visibility.
• Test Updates: Updated expected ETA values in test_monitor_progress.py to reflect the correct behavior of SmoothingETA after the bug fix, showing the impact of the active smoothing.

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 :thumbsup: and :thumbsdown: 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.

[^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.

[wolph]

Very good catch! That does look like an improvement. I'm going to test it and get back to you.

With regards to monotonic, that would be a good idea indeed. I remember not using monotonic back when I wrote the code because it wasn't universally available, but I believe that's no longer the case so we can safely use it now.

The smoothing parameters is a legacy thing... I think I should just hide it with kwargs. It's basically meant to not break older code.