Skip to content

Conversation

@SJTUyh
Copy link
Collaborator

@SJTUyh SJTUyh commented Jan 19, 2026

Thanks for your contribution; we appreciate it a lot. The following instructions will make your pull request healthier and help you get feedback more easily. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
感谢您的贡献,我们非常重视。以下说明将使您的拉取请求更健康,更易于获得反馈。如果您不理解某些项目,请不要担心,只需提交拉取请求并从维护人员那里寻求帮助即可。

PR Type / PR类型

  • Feature(功能新增)
  • Bugfix(Bug 修复)
  • Docs(文档更新)
  • CI/CD(持续集成/持续部署)
  • Refactor(代码重构)
  • Perf(性能优化)
  • Dependency(依赖项更新)
  • Test-Cases(测试用例更新)
  • Other(其他)

Related Issue | 关联 Issue
Fixes #(issue ID / issue 编号) / Relates to #(issue ID / issue 编号)
#114

🔍 Motivation / 变更动机

Please describe the motivation of this PR and the goal you want to achieve through this PR.
请描述您的拉取请求的动机和您希望通过此拉取请求实现的目标。
There some basic syntax errors in MBPPPass@kEvaluator class.

📝 Modification / 修改内容

Please briefly describe what modification is made in this PR.
请简要描述此拉取请求中进行的修改。

Fix some basic syntax errors in MBPPPass@kEvaluator class

📐 Associated Test Results / 关联测试结果

ais_bench --models vllm_api_stream_chat --datasets mbpp_passk_gen_3_shot_chat_prompt --mode eval --debug --reuse 20260119_113305
image

⚠️ BC-breaking (Optional) / 向后不兼容变更(可选)

Does the modification introduce changes that break the backward compatibility of the downstream repositories? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
是否引入了会破坏下游存储库向后兼容性的更改?如果是,请描述它如何破坏兼容性,以及下游项目应该如何修改其代码以保持与此 PR 的兼容性。

⚠️ Performance degradation (Optional) / 性能下降(可选)

If the modification introduces performance degradation, please describe the impact of the performance degradation and the expected performance improvement.
如果引入了性能下降,请描述性能下降的影响和预期的性能改进。

🌟 Use cases (Optional) / 使用案例(可选)

If this PR introduces a new feature, it is better to list some use cases here and update the documentation.
如果此拉取请求引入了新功能,最好在此处列出一些用例并更新文档。

✅ Checklist / 检查列表

Before PR:

  • Pre-commit or other linting tools are used to fix the potential lint issues. / 使用预提交或其他 linting 工具来修复潜在的 lint 问题。
  • Bug fixes are fully covered by unit tests, the case that causes the bug should be added in the unit tests. / 修复的 Bug 已完全由单元测试覆盖,导致 Bug 的情况应在单元测试中添加。
  • The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness. / 此拉取请求中的修改已完全由单元测试覆盖。如果不是,请添加更多单元测试以确保正确性。
  • All relevant documentation (API docs, docstrings, example tutorials) has been updated to reflect these changes. / 所有相关文档(API 文档、文档字符串、示例教程)已更新以反映这些更改。

After PR:

  • If the modification has potential influence on downstream or other related projects, this PR should be tested with those projects. / 如果此拉取请求对下游或其他相关项目有潜在影响,应在那些项目中测试此 PR。
  • CLA has been signed and all committers have signed the CLA in this PR. / CLA 已签署,且本 PR 中的所有提交者均已签署 CLA。

👥 Collaboration Info / 协作信息

  • Suggested Reviewers / 建议审核人: @xxx
  • Relevant Module Owners / 相关模块负责人: @xxx
  • Other Collaboration Notes / 其他协作说明:

🌟 Useful CI Command / 实用的CI命令

Command / 命令 Introduction / 介绍
/gemini review Performs a code review for the current pull request in its current state by Gemini. / 对当前拉取请求在当前状态下由 Gemini 执行代码审核。
/gemini summary Provides a summary of the current pull request in its current state by Gemini. / 对当前拉取请求在当前状态下由 Gemini 提供摘要。
/gemini help Displays a list of available commands of Gemini. / 显示 Gemini 可用命令的列表。
/readthedocs build Triggers a build of the documentation for the current pull request in its current state by Read the Docs. / 触发当前拉取请求在当前状态下由 Read the Docs 构建文档。

@gemini-code-assist
Copy link

Summary of Changes

Hello @SJTUyh, 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 bug in the MBPP evaluator classes by fixing two related initialization issues. It corrects a syntax error in the super() call within MBPPEvaluator and ensures that MBPPPassKEvaluator properly initializes its parent class with the necessary metric argument. These changes ensure the evaluators are correctly configured, likely resolving issues related to missing logger instances or incorrect metric handling.

Highlights

  • Bugfix: super() call syntax: Corrected a syntax error in the MBPPEvaluator.__init__ method, changing super.__init__() to super().__init__() for proper parent class initialization.
  • Bugfix: MBPPPassKEvaluator initialization: Modified the MBPPPassKEvaluator.__init__ method to accept a metric argument and correctly pass it to the parent MBPPEvaluator class during initialization, ensuring proper setup.

🧠 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.

Ignored Files
  • Ignored by pattern: .github/workflows/** (1)
    • .github/workflows/auto_label_pr.yml
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.

Copy link

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request correctly fixes a bug in MBPPEvaluator and MBPPPassKEvaluator where the parent class constructor was not being called, leading to issues like a missing logger. The syntax for the super().__init__() call is corrected, and a missing call is added. The changes are accurate and resolve the issue. I have one minor suggestion regarding documentation for the new parameter.

"""

def __init__(self, k=(1, 10, 100)) -> None:
def __init__(self, k=(1, 10, 100), metric: str = 'MBPP') -> None:

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

With the addition of the metric parameter, the class docstring for MBPPPassKEvaluator is now out of sync. Please update the docstring to include documentation for the new metric parameter to improve code clarity and maintainability.

Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR fixes critical syntax errors in the MBPPPassKEvaluator class that prevented it from functioning properly. The main issue was a missing super().__init__() call that prevented the evaluator from properly inheriting logger functionality from the parent MBPPEvaluator class.

Changes:

  • Fixed incorrect super.__init__() syntax to proper super().__init__() call
  • Corrected debug log messages to use the correct task_id variable instead of undefined index
  • Added metric parameter to MBPPPassKEvaluator constructor to allow passing metric type to parent class

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.

File Description
ais_bench/benchmark/datasets/mbpp.py Fixed syntax errors in MBPPEvaluator and MBPPPassKEvaluator classes including super().init() call, variable references in logger statements, and added metric parameter support
.github/workflows/run-ut-on-pr-py.yml Added 'run' label to CI runner configuration (unrelated to the bugfix)

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

"""Better use for pass k evaluation.
Args:
k(Tuple[int]): Choices of Pass@k. Defaults to (1, 10, 100)
Copy link

Copilot AI Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The docstring should be updated to document the new 'metric' parameter that was added to the constructor. Include the parameter type, description, and default value to maintain consistency with documentation standards.

Suggested change
k(Tuple[int]): Choices of Pass@k. Defaults to (1, 10, 100)
k(Tuple[int]): Choices of Pass@k. Defaults to (1, 10, 100).
metric (str): Name of the evaluation metric. Defaults to 'MBPP'.

Copilot uses AI. Check for mistakes.
Comment on lines +431 to +435
def __init__(self, k=(1, 10, 100), metric: str = 'MBPP') -> None:
if not isinstance(k, Sequence):
k = (k, )
self.k = k
super().__init__(metric=metric)
Copy link

Copilot AI Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The new metric parameter lacks test coverage. Consider adding test cases to verify that the metric parameter is correctly passed to the parent MBPPEvaluator class and that both 'MBPP' and 'MBPPPlus' values work correctly with MBPPPassKEvaluator.

Copilot uses AI. Check for mistakes.
jobs:
pr_run_test:
runs-on: [self-hosted, Linux]
runs-on: [self-hosted, Linux, run]
Copy link

Copilot AI Jan 19, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This workflow configuration change appears unrelated to the bugfix described in the PR title and description. The PR is specifically about fixing syntax errors in the MBPPPass@kEvaluator class, but this change modifies CI/CD runner configuration. Consider removing this change or creating a separate PR for infrastructure updates.

Suggested change
runs-on: [self-hosted, Linux, run]
runs-on: ubuntu-latest

Copilot uses AI. Check for mistakes.
@SJTUyh SJTUyh merged commit 99bcd21 into AISBench:master Jan 19, 2026
15 checks passed
@SJTUyh SJTUyh linked an issue Jan 19, 2026 that may be closed by this pull request
4 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Bug] 测试mbpp数据集精度时报错找不到logger

2 participants