Conversation
- 영문으로 작성 - rules로 분리
- testing.md를 참조하여 작성하는 방식으로
- rules에 이미 관련 문서가 있으므로, 중복
whqtker
requested review from
Gyuhyeok99,
Hexeong,
lsy1307 and
wibaek
as code owners
|
Warning Rate limit exceeded
To keep reviews running without waiting, you can enable usage-based add-on for your organization. This allows additional reviews beyond the hourly cap. Account admins can enable it under billing. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the 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. ℹ️ Review info⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (4)
Walkthrough이번 변경사항은 개발 환경 자동화를 정리하고 코드 컨벤션 문서화 체계를 새롭게 구축한 작업입니다. 구체적으로는:
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Suggested reviewers
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
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. Review rate limit: 0/1 reviews remaining, refill in 28 minutes and 7 seconds.Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 6
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In @.claude/rules/database.md:
- Around line 5-7: The rule text "Field name must match DB column name exactly
(snake_case)" contradicts the example using camelCase; update that line to
clarify the intended mapping by replacing it with a phrase like "Field name must
map 1:1 to DB column name; DB column names must be snake_case" so the rule and
the example align; ensure the exact phrase "Field name must map 1:1 to DB column
name; DB column names must be snake_case" (or equivalent) is used in place of
the old sentence to remove ambiguity.
In @.claude/skills/review-pr/SKILL.md:
- Around line 30-31: Update the file reference casing so links match the actual
filename: replace occurrences of "CLAUDE.md" with "claude.md" in
.claude/skills/review-pr/SKILL.md (notably the line containing "Ref: `CLAUDE.md`
- Architecture" and the other occurrence around lines 65–66) to ensure
case-sensitive filesystems won’t break the reference.
- Around line 75-97: The fenced code block in the PR template (the
triple-backtick block that starts with "## PR Review: #{number} - {title}")
lacks a language tag, triggering MD040; update that fenced block to specify a
language (e.g., "md" or "text") after the opening ``` so tools and linters
recognize the block type and the warning is resolved.
In @.claude/skills/test/SKILL.md:
- Around line 82-88: 문서의 주석 "shared test data as fields"가 공유 mutable 상태로 오해될 수
있으니, `@BeforeEach` setUp()와 관련된 주석(예: "shared test data as fields" 및 예시 필드
"private Entity entity;")을 수정하여 테스트 독립성 원칙을 준수하도록 명확히 하세요: 필드로 공유할 수 있는 값은 각
테스트마다 재초기화되는(freshly reinitialized in setUp()) 값이거나 불변(immutable) 값만 허용한다고 명시하고,
mutable 상태를 공유해서는 안 된다는 경고를 추가해 주세요.
- Around line 45-47: The fenced code block containing
"src/test/java/com/example/solidconnection/[domain]/service/[ServiceName]Test.java"
is missing a language tag and triggers MD040; update that fenced block by
changing the opening ``` to include a language (e.g., ```text) so the block
reads like ```text ... ```, ensuring the Markdown linter no longer flags it.
In `@claude.md`:
- Around line 36-39: The fenced code block in claude.md (the Git commit/branch
example) lacks a language tag causing MD040; update the fenced block that
currently contains "Commit : feat|fix|refactor|docs|test|chore|perf:
<description>" and "Branch : type/issue-number-short-desc" to include a language
identifier (e.g., change the opening fence to ```text) so the block is
recognized as plaintext and the markdown linter warning is resolved.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: e79a0ee6-520c-4fe4-b5d5-5ad05f6aca44
📒 Files selected for processing (11)
.claude/hooks/notify.ps1.claude/hooks/notify.py.claude/hooks/post-edit-check.py.claude/rules/code-style.md.claude/rules/database.md.claude/rules/testing.md.claude/settings.json.claude/skills/review-pr/SKILL.md.claude/skills/test/SKILL.md.gitignoreclaude.md
💤 Files with no reviewable changes (4)
- .claude/hooks/notify.ps1
- .claude/settings.json
- .claude/hooks/notify.py
- .claude/hooks/post-edit-check.py
| - Every field requires `@Column(name = "...", nullable = ...)` | ||
| - Field name must match DB column name exactly (snake_case) | ||
| - `@Table(name = "...")` required on every entity class |
There was a problem hiding this comment.
1) 규칙 문구가 예시와 충돌합니다 (Line 6)
현재 문구(Field name must match DB column name exactly (snake_case))는 아래 예시 코드의 camelCase 필드와 모순됩니다. “필드명과 컬럼명이 1:1 매핑되어야 하며, 컬럼명은 snake_case”처럼 표현을 바꾸는 편이 정확합니다.
수정 제안
-- Field name must match DB column name exactly (snake_case)
+- Java field names should map 1:1 to DB columns via `@Column(name = "...")`, and DB column names must use snake_case🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/rules/database.md around lines 5 - 7, The rule text "Field name must
match DB column name exactly (snake_case)" contradicts the example using
camelCase; update that line to clarify the intended mapping by replacing it with
a phrase like "Field name must map 1:1 to DB column name; DB column names must
be snake_case" so the rule and the example align; ensure the exact phrase "Field
name must map 1:1 to DB column name; DB column names must be snake_case" (or
equivalent) is used in place of the old sentence to remove ambiguity.
| - Ref: `CLAUDE.md` - Architecture | ||
|
|
There was a problem hiding this comment.
1) 문서 참조 파일명 대소문자를 실제 파일과 맞춰 주세요 (Line 30, Line 65)
현재 CLAUDE.md로 참조하고 있는데, 변경 파일은 claude.md입니다. 케이스 민감 환경(Linux)에서 링크/참조가 깨질 수 있습니다.
수정 제안
-- Ref: `CLAUDE.md` - Architecture
+- Ref: `claude.md` - Architecture
...
-- Ref: `CLAUDE.md` - Git
+- Ref: `claude.md` - GitAlso applies to: 65-66
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/review-pr/SKILL.md around lines 30 - 31, Update the file
reference casing so links match the actual filename: replace occurrences of
"CLAUDE.md" with "claude.md" in .claude/skills/review-pr/SKILL.md (notably the
line containing "Ref: `CLAUDE.md` - Architecture" and the other occurrence
around lines 65–66) to ensure case-sensitive filesystems won’t break the
reference.
| ``` | ||
| ## PR Review: #{number} - {title} | ||
|
|
||
| **수집할 정보:** | ||
| - PR 제목 및 설명 | ||
| - 관련 이슈 번호 | ||
| - 변경된 파일 목록 | ||
| - CI/CD 체크 상태 | ||
|
|
||
| ### 2단계: 변경 파일 분석 | ||
|
|
||
| **도구 우선순위:** | ||
| Link: {url} | ||
| Author: {author} Branch: {branch} CI: {pass/fail} | ||
|
|
||
| 1. **Serena MCP** (Java 코드 분석에 최적화) | ||
| - `mcp__serena__get_symbols_overview <파일경로>` - 파일의 클래스/메서드 구조 파악 | ||
| - `mcp__serena__find_symbol <심볼명>` - 특정 심볼 검색 | ||
| - `mcp__serena__search_for_pattern <패턴>` - 컨벤션 위반 패턴 검색 | ||
| ### Summary | ||
| {brief description of what the PR does} | ||
|
|
||
| 2. **Read/Grep** (보조 분석) | ||
| - `Read <파일경로>` - 파일 전체 읽기 | ||
| - `Grep --pattern <패턴>` - 패턴 검색 | ||
| ### Passed | ||
| - {item} | ||
|
|
||
| ### 3단계: 체크리스트 검증 | ||
|
|
||
| 아래 체크리스트를 순서대로 확인합니다. | ||
|
|
||
| --- | ||
| ### Suggestions (non-blocking) | ||
| - {file:line} — {problem} — {suggestion} | ||
|
|
||
| ## 리뷰 체크리스트 | ||
| ### Required changes | ||
| - {file:line} — {problem} — {fix direction} | ||
|
|
||
| 각 항목의 상세 컨벤션은 참조 문서를 확인하세요. | ||
| ### Overall | ||
| {conclusion} | ||
|
|
||
| ### 1. 아키텍처 및 계층 구조 | ||
|
|
||
| **검증 항목:** | ||
| - 계층형 아키텍처 준수 (Controller → Service → Repository) | ||
| - 역계층 참조 금지 | ||
| - 순환 의존성 없음 | ||
|
|
||
| 👉 **참고:** `CLAUDE.md` - "아키텍처" 섹션 | ||
|
|
||
| --- | ||
|
|
||
| ### 2. 네이밍 컨벤션 | ||
|
|
||
| **검증 항목:** | ||
| - API 엔드포인트: kebab-case 사용 (예: `/user-profile`) | ||
| - DTO 변환 메서드: 단일 파라미터 `from()`, 다중 파라미터 `of()` | ||
| - Request/Response: `XXXRequest`, `XXXResponse` 형식 | ||
| - 테스트 메서드: 한국어, `어떤_것을_하면_어떤_결과가_나온다()` 패턴 | ||
|
|
||
| 👉 **참고:** `CLAUDE.md` - "네이밍 컨벤션" 섹션 | ||
|
|
||
| --- | ||
|
|
||
| ### 3. 코드 스타일 | ||
|
|
||
| **검증 항목:** | ||
| - 와일드카드(`*`) import 금지 | ||
| - 클래스 선언 전 빈 줄 존재 | ||
| - private 메서드는 호출하는 public 메서드 바로 아래 위치 | ||
| - Controller: 모든 파라미터 줄바꿈 필수 | ||
| - 일반 메서드: 3개 이상 파라미터 시 줄바꿈 | ||
| - 파일 끝 개행 문자 | ||
|
|
||
| **패턴 검색 예제:** | ||
| ```bash | ||
| mcp__serena__search_for_pattern "import.*\\*" # 와일드카드 import 검색 | ||
| Verdict: Approved / Approved with suggestions / Changes requested | ||
| ``` |
There was a problem hiding this comment.
2) 출력 포맷 코드 블록에도 언어를 지정해 주세요 (Line 75)
MD040 경고 대상입니다. fenced block에 언어를 명시하면 문서 품질과 도구 호환성이 좋아집니다.
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 75-75: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/review-pr/SKILL.md around lines 75 - 97, The fenced code
block in the PR template (the triple-backtick block that starts with "## PR
Review: #{number} - {title}") lacks a language tag, triggering MD040; update
that fenced block to specify a language (e.g., "md" or "text") after the opening
``` so tools and linters recognize the block type and the warning is resolved.
| ``` | ||
|
|
||
| **편의 메서드 작성 팁:** | ||
|
|
||
| - 한국어 메서드명 사용 (가독성) | ||
| - 자주 사용되는 기본값 조합만 제공 | ||
| - Builder를 조합하여 필요한 데이터 설정 | ||
|
|
||
| ### 테스트에서 사용 | ||
|
|
||
| ```java | ||
| @TestContainerSpringBootTest | ||
| class ChatServiceTest { | ||
|
|
||
| @Autowired | ||
| private ChatRoomFixture chatRoomFixture; | ||
|
|
||
| @Test | ||
| void 채팅방을_생성할_수_있다() { | ||
| // 편의 메서드 사용 | ||
| ChatRoom room = chatRoomFixture.채팅방(false); | ||
|
|
||
| // Builder 직접 사용 | ||
| ChatRoom customRoom = chatRoomFixture.chatRoomFixtureBuilder.chatRoom() | ||
| .isGroup(true) | ||
| .mentoringId(100L) | ||
| .create(); | ||
| } | ||
| } | ||
| src/test/java/com/example/solidconnection/[domain]/service/[ServiceName]Test.java | ||
| ``` |
There was a problem hiding this comment.
1) 코드 블록 언어 지정이 필요합니다 (Line 45)
마크다운 린트(MD040) 경고 대상입니다. fenced block에 언어를 지정해 주세요.
수정 제안
-```
+```text
src/test/java/com/example/solidconnection/[domain]/service/[ServiceName]Test.java</details>
<details>
<summary>🧰 Tools</summary>
<details>
<summary>🪛 markdownlint-cli2 (0.22.1)</summary>
[warning] 45-45: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
</details>
</details>
<details>
<summary>🤖 Prompt for AI Agents</summary>
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/test/SKILL.md around lines 45 - 47, The fenced code block
containing
"src/test/java/com/example/solidconnection/[domain]/service/[ServiceName]Test.java"
is missing a language tag and triggers MD040; update that fenced block by
changing the opening to include a language (e.g.,text) so the block
reads like text ... , ensuring the Markdown linter no longer flags it.
</details>
<!-- fingerprinting:phantom:triton:hawk:ee26ecc8-0a68-4195-8018-1d934623aad5 -->
<!-- d98c2f50 -->
<!-- This is an auto-generated comment by CodeRabbit -->
| // shared test data as fields if reused across @Nested classes | ||
| // private Entity entity; | ||
|
|
||
| ```java | ||
| @TestContainerSpringBootTest | ||
| class ChatServiceTest { | ||
| @BeforeEach | ||
| void setUp() { | ||
| // initialize shared fixtures here | ||
| } |
There was a problem hiding this comment.
2) 테스트 독립성 규칙과 충돌 소지가 있는 표현입니다 (Line 82-88)
“shared test data as fields”는 공유 mutable state를 허용하는 것으로 오해될 수 있습니다. 테스트 독립성 원칙에 맞게 “재초기화되는 값 또는 immutable 값만 허용”으로 문구를 명확히 해주세요.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In @.claude/skills/test/SKILL.md around lines 82 - 88, 문서의 주석 "shared test data
as fields"가 공유 mutable 상태로 오해될 수 있으니, `@BeforeEach` setUp()와 관련된 주석(예: "shared
test data as fields" 및 예시 필드 "private Entity entity;")을 수정하여 테스트 독립성 원칙을 준수하도록
명확히 하세요: 필드로 공유할 수 있는 값은 각 테스트마다 재초기화되는(freshly reinitialized in setUp()) 값이거나
불변(immutable) 값만 허용한다고 명시하고, mutable 상태를 공유해서는 안 된다는 경고를 추가해 주세요.
| ``` | ||
|
|
||
| **규칙:** | ||
| - `@Column` 필수 (모든 필드) | ||
| - 필드명과 DB 컬럼명 일치 | ||
| - nullable 명시 | ||
|
|
||
| ### Repository | ||
|
|
||
| ```java | ||
| public interface ChatRoomRepository extends JpaRepository<ChatRoom, Long> { | ||
| Optional<ChatRoom> findByMentoringId(Long mentoringId); | ||
| List<ChatRoom> findByIsGroup(boolean isGroup); | ||
| } | ||
| Commit : feat|fix|refactor|docs|test|chore|perf: <description> | ||
| Branch : type/issue-number-short-desc | ||
| ``` |
There was a problem hiding this comment.
1) Git 예시 코드 블록에 언어를 지정해 주세요 (Line 36)
MD040 경고를 없애려면 fenced code block에 언어를 지정하는 것이 좋습니다.
수정 제안
-```
+```text
Commit : feat|fix|refactor|docs|test|chore|perf: <description>
Branch : type/issue-number-short-desc</details>
<!-- suggestion_start -->
<details>
<summary>📝 Committable suggestion</summary>
> ‼️ **IMPORTANT**
> Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
```suggestion
🧰 Tools
🪛 markdownlint-cli2 (0.22.1)
[warning] 36-36: Fenced code blocks should have a language specified
(MD040, fenced-code-language)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@claude.md` around lines 36 - 39, The fenced code block in claude.md (the Git
commit/branch example) lacks a language tag causing MD040; update the fenced
block that currently contains "Commit : feat|fix|refactor|docs|test|chore|perf:
<description>" and "Branch : type/issue-number-short-desc" to include a language
identifier (e.g., change the opening fence to ```text) so the block is
recognized as plaintext and the markdown linter warning is resolved.
- 관련 파일 작업 시에만 로드되도록
1 participant
관련 이슈
작업 내용
쾌적한 클로드코드 사용을 위해 best practice 관점에서 문서들을 수정했습니다. 작업 내용은 아래와 같습니다.
CLAUDE.md 내용 대폭 감소
권장은 200 라인입니다. 이에 맞게 수정했고, 초과분은 rules 로 분리했습니다. 불필요한 내용(==
build.gradle과 같이 다른 파일로 유추할 수 있는 내용들)들은 제거했습니다.이모지 같은 것들도 제거했습니다.
문서 영문으로 작성
한글이 영문 대비 토큰을 2 ~ 3배 소모한다고 합니다. 이에 클로드코드가 로드하는 문서 전체를 영문으로 작성했습니다.
SKILL.md 보완
알림 관련 훅 제거
전역 설정으로 빼는 데 합당하다고 판단했습니다. 필요하신 분들은
~/.claude에 설정하는 것이 좋을 것 같습니다.컨벤션 검증 훅 제거
rules에 이미 명시되었기에 중복이라고 판단했고 제거했습니다.
특이 사항
리뷰 요구사항 (선택)