Skip to content

docs: Lintless Real-time Code Guard RFC 추가#162

Open
RaptBliss wants to merge 1 commit intomainfrom
docs/lintless-realtime-code-guard-rfc
Open

docs: Lintless Real-time Code Guard RFC 추가#162
RaptBliss wants to merge 1 commit intomainfrom
docs/lintless-realtime-code-guard-rfc

Conversation

@RaptBliss
Copy link
Collaborator

요약

  • lint 도구 강제 없이 실시간 코드 품질 감지/피드백을 위한 RFC 문서를 추가했습니다.
  • 문서 경로: docs/plans/22_lintless_realtime_code_guard_rfc.md

포함 내용

  • Activity Stream 기반 코드 이벤트 수집
  • Mandu 내장 Rule Evaluator (순환참조/경계위반/UI 상태누락/중복탐지)
  • 에이전트 Feedback Bus 포맷
  • 승인형 패치 제안/적용 정책
  • Kitchen 탭 구조 (Live Feed / Proposals / Health / Evidence)
  • 단계별 로드맵, KPI, 리스크, Exit Criteria

기대 효과

  • 사후 lint/리뷰 이전에 개발 중 즉시 교정 가능
  • lint 의존 없이도 핵심 품질 규칙을 실시간으로 운영
  • 에이전트 코딩 품질과 재현성 동시 개선

@gemini-code-assist
Copy link

Summary of Changes

Hello @RaptBliss, 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!

이 Pull Request는 Mandu DevTool/Kitchen에 'Lintless Real-time Code Guard' 시스템을 도입하기 위한 RFC 문서를 추가합니다. 이 시스템은 전통적인 lint 도구의 강제 없이 개발 과정에서 실시간으로 코드 품질 문제를 감지하고, 에이전트에게 즉각적인 피드백과 승인형 패치 제안을 제공하여 코드 품질을 선제적으로 개선하는 것을 목표로 합니다. 이를 통해 사후 리뷰 단계에서 발생하는 품질 이슈를 줄이고 개발 효율성을 높일 수 있을 것으로 기대됩니다.

Highlights

  • 새로운 RFC 문서 추가: 기존 lint 도구에 의존하지 않고 실시간으로 코드 품질을 감지하고 피드백하는 'Lintless Real-time Code Guard'에 대한 RFC(Request for Comments) 문서를 추가했습니다.
  • 핵심 기능 정의: 파일/코드 변경 이벤트 실시간 수집, Mandu 내장 룰 엔진을 통한 즉시 평가, 에이전트 피드백 버스를 통한 전달, 승인형 패치 제안, 품질 점수 실시간 갱신 등 시스템의 핵심 기능이 명시되었습니다.
  • 아키텍처 및 룰셋: Activity Stream, Rule Evaluator, Feedback Bus, Suggestion Engine 등으로 구성된 아키텍처와 순환참조, 레이어/경계 위반, UI 상태 누락 등 MVP 룰셋이 정의되었습니다.
  • Kitchen UI 통합 및 로드맵: Live Guard Feed, Proposals, Health, Evidence 탭으로 구성될 Kitchen UI 통합 방안과 단계별 로드맵(Phase 0~4), KPI, 리스크 및 대응 방안, Exit Criteria가 상세히 기술되었습니다.
Changelog
  • docs/plans/22_lintless_realtime_code_guard_rfc.md
    • Mandu Lintless Real-time Code Guard RFC 문서가 추가되었습니다.
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.

@coderabbitai
Copy link

coderabbitai bot commented Feb 17, 2026

Warning

Rate limit exceeded

@konamgil has exceeded the limit for the number of commits that can be reviewed per hour. Please wait 29 minutes and 56 seconds before requesting another review.

⌛ How to resolve this issue?

After the wait time has elapsed, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout.

Please see our FAQ for further information.

📥 Commits

Reviewing files that changed from the base of the PR and between 4f8a0ae and c8d9aa4.

📒 Files selected for processing (1)
  • docs/plans/22_lintless_realtime_code_guard_rfc.md
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment
  • Commit unit tests in branch docs/lintless-realtime-code-guard-rfc

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

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

Lintless Real-time Code Guard를 위한 RFC 문서 추가 잘 보았습니다. 전체적으로 시스템의 목표, 아키텍처, 단계별 로드맵이 명확하게 잘 정리되어 있습니다. 특히 AI 에이전트와의 상호작용을 고려한 실시간 피드백 시스템이라는 방향성이 인상적입니다. 몇 가지 제안 사항을 코멘트로 남겼으니 확인 부탁드립니다. 제안된 포맷의 명확성을 높이면 향후 구현과 확장에 더 도움이 될 것입니다.

"severity": "warn",
"target": "src/client/features/chat/message-list.tsx",
"message": "리스트 화면에 empty state가 없습니다.",
"evidence": ["line:120-168"],

Choose a reason for hiding this comment

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

medium

evidence 필드의 포맷을 좀 더 구조적으로 가져가는 것을 제안합니다. 현재는 ["line:120-168"]와 같이 문자열 배열로 되어 있는데, 이는 파싱하기에 다소 불편하고 확장성이 떨어질 수 있습니다.

예를 들어, 다음과 같은 객체 배열 형태를 사용하면 더 명확하고 기계가 처리하기 용이할 것 같습니다.

"evidence": [
  {
    "start_line": 120,
    "end_line": 168
  }
]

이렇게 하면 여러 개의 분리된 코드 블록을 근거로 제시해야 할 때도 유연하게 대처할 수 있고, target에 파일 경로가 이미 있으므로 중복을 피할 수 있습니다.

"message": "리스트 화면에 empty state가 없습니다.",
"evidence": ["line:120-168"],
"suggestedPatch": "...diff...",
"risk": "low"

Choose a reason for hiding this comment

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

medium

risk 필드의 의미를 문서에 명확히 설명해주는 것이 좋겠습니다. severity 필드와 어떤 차이가 있는지, 그리고 이 필드가 구체적으로 무엇의 위험도를 나타내는지(예: 제안된 패치 적용의 위험도) 명시하면 RFC를 이해하는 데 도움이 될 것입니다.

@konamgil konamgil force-pushed the docs/lintless-realtime-code-guard-rfc branch from 8a609f7 to c8d9aa4 Compare March 3, 2026 04:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant