Skip to content

docs: Claude Code 소스코드 한국어 분석 문서 (19개 문서, 6,926줄)#156

Closed
youngjungju wants to merge 4 commits intoultraworkers:mainfrom
youngjungju:docs/ko-upstream
Closed

docs: Claude Code 소스코드 한국어 분석 문서 (19개 문서, 6,926줄)#156
youngjungju wants to merge 4 commits intoultraworkers:mainfrom
youngjungju:docs/ko-upstream

Conversation

@youngjungju
Copy link
Copy Markdown

Summary

Claude Code CLI 소스코드(~1,900 파일, 512K+ 라인 TypeScript)를 체계적으로 분석한 한국어 기술 문서 19개를 추가합니다.

  • Level 1 (입문): 전체 아키텍처 조감도, 요청 생명주기 추적, 15개 핵심 개념 정리
  • Level 2 (시스템 분석): QueryEngine, Tool 시스템, 커맨드 시스템, 권한 시스템, 멀티에이전트 오케스트레이션, React/Ink UI
  • Level 3 (심화): MCP/LSP 프로토콜 연동, IDE 브릿지, 플러그인/스킬 시스템, 컨텍스트 압축, OAuth 인증, 텔레메트리
  • Appendix: 한영 용어 대조표(50+항목), 파일 경로 인덱스, 설계 패턴 모음(8개)

주요 특징

  • 🇰🇷 한국인 개발자 대상: 학술적/기술 문서 톤, 한영 용어 병기
  • 📊 레이어드 구조: 입문 → 중급 → 심화 순서로 자신의 레벨에 맞는 진입점 선택 가능
  • 🔍 소스코드 기반: 모든 문서가 실제 코드를 직접 분석하여 작성 (파일 경로, 라인 번호, 코드 스니펫 포함)
  • 📈 Mermaid 다이어그램: 아키텍처, 시퀀스, 플로우차트 등 GitHub 네이티브 렌더링 지원

문서 구조

docs/ko/
├── README.md                     — 인덱스 & 읽기 가이드
├── level-1-overview/             — 입문 (3개)
│   ├── architecture.md           — 전체 아키텍처 조감도
│   ├── request-lifecycle.md      — 요청 생명주기 (backbone)
│   └── key-concepts.md           — 15개 핵심 개념
├── level-2-systems/              — 시스템 분석 (6개)
│   ├── query-engine.md           — QueryEngine 분석
│   ├── tool-system.md            — Tool 시스템 분석
│   ├── command-system.md         — 커맨드 시스템 분석
│   ├── permission-system.md      — 권한 시스템 분석
│   ├── agent-coordinator.md      — 멀티에이전트 오케스트레이션
│   └── ui-ink-components.md      — React/Ink UI 분석
├── level-3-internals/            — 심화 분석 (6개)
│   ├── mcp-lsp-integration.md    — MCP/LSP 프로토콜 연동
│   ├── bridge-ide.md             — IDE 브릿지
│   ├── plugin-skill-system.md    — 플러그인 & 스킬 시스템
│   ├── context-compression.md    — 컨텍스트 압축
│   ├── oauth-auth.md             — 인증 흐름
│   └── telemetry.md              — 텔레메트리
└── appendix/                     — 부록 (3개)
    ├── glossary.md               — 한영 용어 대조표 (50+항목)
    ├── file-map.md               — 파일 경로 인덱스
    └── design-patterns.md        — 설계 패턴 모음 (8개)

총 규모

  • 19개 문서, 6,926줄
  • 실제 소스코드를 직접 읽고 분석하여 작성

Test plan

  • 모든 19개 마크다운 파일 생성 확인
  • 한국어 문서 톤 및 용어 일관성 검증
  • 내부 링크 구조 확인 (README ↔ 각 문서)
  • GitHub에서 Mermaid 다이어그램 렌더링 확인
  • 오탈자 및 기술적 정확성 최종 리뷰

🤖 Generated with Claude Code

instructkr and others added 4 commits March 31, 2026 03:34
Squash the current repository state back into one baseline commit while
preserving the README reframing and repository contents.

Constraint: User explicitly requested a single squashed commit with subject "asdf"
Confidence: high
Scope-risk: broad
Reversibility: clean
Directive: This commit intentionally rewrites published history; coordinate before future force-pushes
Tested: git status clean; local history rewritten to one commit; force-pushed main to origin and instructkr
Not-tested: Fresh clone verification after push
…926 lines)

Add complete Korean-language technical documentation analyzing Claude Code CLI
internals, organized in a leveled guide structure (Level 1-3 + Appendix).

Level 1 (입문): architecture overview, request lifecycle, key concepts
Level 2 (시스템): QueryEngine, Tool system, Command system, Permission system,
  Agent coordinator, UI/Ink components
Level 3 (심화): MCP/LSP integration, IDE bridge, Plugin/Skill system,
  Context compression, OAuth/Auth, Telemetry
Appendix: Korean-English glossary, file map, design patterns

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Fix cross-references that pointed to non-existent directory paths:
- key-concepts.md: 15 links → correct level-2-systems/level-3-internals paths
- request-lifecycle.md: 7 links → correct level-2-systems paths
- bridge-ide.md, context-compression.md, oauth-auth.md: level-2-architecture → level-1-overview
- mcp-lsp-integration.md: sibling refs → correct ../level-2-systems/ paths
- command-system.md: index.md → README.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Fix "Anthropics" → "Anthropic" typo in query-engine.md Mermaid diagram
- Fix permission-system.md "이전" nav link to point to command-system.md

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
phoenix20162016 pushed a commit to phoenix20162016/claw-code that referenced this pull request Apr 26, 2026
…hase 2 of ultraworkers#77)

ROADMAP entry for natural Phase 2 follow-up to ultraworkers#77 Phase 1 (JSON error kind
classification). Text-mode errors currently prose-only with no structured
class; observability tools parsing stderr need the kind token.

Two implementation options:
- Prefix line before error prose: [error-kind: missing_credentials]
- Suffix comment: # error_class=missing_credentials

Scope: ~20 lines. Non-breaking (adds classification, doesn't change error text).

Source: Cycle 11 dogfood probe at 23:18 KST — product surface clean after
today's batch, identified natural next step for error-classification symmetry.
phoenix20162016 pushed a commit to phoenix20162016/claw-code that referenced this pull request Apr 26, 2026
…hase 2 of ultraworkers#77)

## Problem

ultraworkers#77 Phase 1 added machine-readable error `kind` discriminants to JSON error
payloads. Text-mode (stderr) errors still emit prose-only output with no
structured classification.

Observability tools (log aggregators, CI error parsers) parsing stderr can't
distinguish error classes without regex-scraping the prose.

## Fix

Added `[error-kind: <class>]` prefix line to all text-mode error output.
The prefix appears before the error prose, making it immediately parseable by
line-based log tools without any substring matching.

**Examples:**

## Impact

- Stderr observers (log aggregators, CI systems) can now parse error class
  from the first line without regex or substring scraping
- Same classifier function used for JSON (ultraworkers#77 P1) and text modes
- Text-mode output remains human-readable (error prose unchanged)
- Prefix format follows syslog/structured-logging conventions

## Tests

All 179 rusty-claude-cli tests pass. Verified on 3 different error classes.

Closes ROADMAP ultraworkers#156.
phoenix20162016 pushed a commit to phoenix20162016/claw-code that referenced this pull request Apr 26, 2026
…nts (Phase 3 of ultraworkers#77)

## Gap

ultraworkers#77 Phase 1 added machine-readable error kind discriminants and ultraworkers#156 extended
them to text-mode output. However, the hint field is still prose derived from
splitting existing error text — not a stable registry-backed remediation
contract.

Downstream claws inspecting the hint field still need to parse human wording
to decide whether to retry, escalate, or terminate.

## Fix Shape

1. Remediation registry: remediation_for(kind, operation) -> Remediation struct
   with action (retry/escalate/terminate/configure), target, and stable message
2. Stable hint outputs per error class (no more prose splitting)
3. Golden fixture tests replacing split_error_hint() string hacks

## Source

gaebal-gajae dogfood sweep 2026-04-22 05:30 KST
code-yeongyu added a commit that referenced this pull request Apr 27, 2026
…ection validation, mcp/agents soft-warning)
code-yeongyu added a commit that referenced this pull request Apr 27, 2026
…ection validation, mcp/agents soft-warning)
code-yeongyu added a commit that referenced this pull request Apr 28, 2026
…ection validation, mcp/agents soft-warning)
code-yeongyu added a commit to code-yeongyu/claw-code-1 that referenced this pull request Apr 28, 2026
…sign questions (config section validation, mcp/agents soft-warning)
code-yeongyu added a commit that referenced this pull request Apr 28, 2026
…ection validation, mcp/agents soft-warning)
code-yeongyu added a commit to code-yeongyu/claw-code-1 that referenced this pull request Apr 29, 2026
…sign questions (config section validation, mcp/agents soft-warning)
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.

2 participants