[#704] AI agent 역할군과 작업 라우팅 규칙을 정의한다#705
Conversation
There was a problem hiding this comment.
Code Review
This pull request establishes a structured AI role workflow and executable runbooks for the repository, introducing role definitions, model assignments, and workflow gates across AGENTS.md, AGENT_ROLES.md, AGENT_WORKFLOWS.md, and README.md. The feedback points out a hardcoded local absolute path in the role activation template within AGENT_ROLES.md, which should be replaced with a generic placeholder to ensure portability across different environments.
Important
The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.
80cd381 to
ed04e98
Compare
🔗 연관된 이슈
🎯 의도
여러 AI 모델을 역할별로 분리해 사용할 수 있도록 repo-local AI 작업 기준과 실행 워크플로우를 정리하기 위한 변경
📝 작업 내용
📌 요약
AGENT_ROLES.md를 추가해 역할별 책임, 금지 범위, 출력 형식 정의AGENT_WORKFLOWS.md를 추가해 작업 유형별 실행 runbook 정의AGENTS.md에 AI role workflow 진입 규칙 추가README.md에 AI 역할 분리 흐름을 Mermaid diagram과 표로 추가🔍 상세
Planner,Implementer,Architecture Watcher,Code Reviewer,Verification Runner,GitHub/CI Analyst,Documentation Writer역할 정의Primary,Spark,Fast모델 tier와gpt-5.3-codex-spark사용 위치 명시docs/디렉터리는 README 이미지와 draw.io 원본 위치로 유지하는 정책 명시📸 영상 / 이미지 (Optional)