feat(engine): implement self-reflection (reflector) stage in multi-agent pipeline

- Added ReflectorAgent for meta-cognition and critical review between Research and Writing
- Updated WriterAgent to explicitly address reflection critiques
- Introduced 'g1nation.enableReflection' configuration setting
- Added comprehensive integration tests for the self-reflection stage
- Documented design decisions in ADR-0010 and related discussion records
This commit is contained in:
g1nation
2026-05-14 01:47:28 +09:00
parent e075779635
commit 8da9532ca1
18 changed files with 610 additions and 124 deletions
@@ -0,0 +1,19 @@
# ADR: /Volumes/Data/project/Antigravity/ConnectAI self reflection 기능이 적용되었는지 확인해줘. 1인 ...
## Status
accepted
## Context
/Volumes/Data/project/Antigravity/ConnectAI self reflection 기능이 적용되었는지 확인해줘. 1인 기업 기능에.
## Decision
확인했습니다. 현재 제공된 프로젝트 기록과 아키텍처 문서를 바탕으로 `/Volumes/Data/project/Antigravity/ConnectAI` 내의 '자체 성찰(Self-Reflection)' 기능 적용 여부를 분석하겠습니다. **결론부터 말씀드리자면, 시스템 설계 상으로는 자체 성찰 및 피드백 루프를 위한 강력한 기반이 구축되어 있습니다.** 하지만 실제 실행 환경에서 이 기능이 완벽하게 작동하고 있는지에 대한 **실행 결과(Execution Trace)**는 별도로 확인해야 합니다. ### 상세 분석 1. **아키텍처적 기반 (Foundation):** * `AgentEngine Architecture Document`에 따르면, 시스템은 Planner → Researcher → Writer의 3단계 멀티 에이전트 워크플로우를 통해 요청을 분할 처리합니다. 이는 단순 실행을 넘어 **메타인지(Meta-cognition)**와 **결과 검증** 단계가 필요함을 내포하고 있습...
## Reason
Captured automatically because the conversation contained decision-oriented language.
## Alternatives
Not captured yet.
## Consequences
- Future prompts should treat this as project context unless the user changes direction.