feat: v2.2.173-193 — 4인 팀 운영 슬래시 13개 + ASTRA 검증 엔진 6종

4인 팀 운영 슬래시 (v2.2.173~189):
- 일과 리듬: /morning, /evening, /weekly, /standup
- 트래커 (event-sourced .astra/*.jsonl): /runway, /customers, /hire
- 작업·결정: /task, /blocked, /onesie, /decisions
- 외부 출력: /draft, /feedback
- 분석: /cohort (MoM 추세)

ASTRA 추론·검색 엔진 (v2.2.183~192):
- v2.2.183 Conflict Surface — scoring.conflictSeverity 를 [CONFLICT WARNINGS] 블록으로
  서피스 + 교차-문서 발산(Jaccard) 감지
- v2.2.184 Chain-of-Verification — [VERIFICATION CHECKLIST] 답변 작성 전 그라운딩 자기 점검
  (instructional, strictMode 옵션)
- v2.2.185 Actionability Scoring — 최근 슬래시 명령 + 열린 파일 신호로 검색 결과 재가중
- v2.2.186 Temporal Markers + Distillation Loop — LongTerm/Episodic 만료 필터 +
  30일+ stale episode → LongTerm 'episode-digest' 승급 (수동 /memory distill + 세션 종료 자동)
- v2.2.187 Hierarchical Context Window + LLM Semantic Re-rank — 3-level 추상도 매칭
  + 토큰 예산 통과 후 LLM 1회로 의도-부합 재정렬 (opt-in)
- v2.2.190 Intent Clarification + Citation Trace — 모호 차원 감지 시 역질문 우선
  + 답변 끝 사용 출처 한 줄 정리
- v2.2.191 Post-hoc Self-Check — 답변 완료 후 별도 LLM 호출 1회로 답함/그라운딩/모순 평가,
  footer 한 줄로 표시 (opt-in, semantic re-rank 와 같은 안전 fallback 패턴)
- v2.2.192 Terminology Dictionary — .astra/glossary.md 사용자 편집 파일 + Term Check
  지침 통합 + /glossary init/path/reload
- v2.2.193 /help — 카테고리별 명령 목록 + 6종 verification 블록 현재 on/off

신규 모듈:
- src/retrieval/{conflictBlock,coveBlock,actionabilityScoring,hierarchicalLevel,
  semanticRerank,intentClarification,citationTrace,terminologyBlock}.ts
- src/memory/distillation.ts + types.ts 에 expiresAt/promoted/episode-digest 추가
- src/agent/postHocSelfCheck.ts
- src/features/{customers,feedback,hire,runway}/*.ts (event-sourced stores)

ASTRA 검증 5종 자동 주입 (buildAstraModeSystemPrompt, casual 모드 제외):
[INTENT CLARIFICATION GUIDANCE] (답변 시작 전) → [TERMINOLOGY DICTIONARY] +
[CONFLICT WARNINGS] + [VERIFICATION CHECKLIST] (작성 중) → [CITATION TRACE] (끝)
+ 6번째: Post-hoc Self-Check footer (답변 완료 후, opt-in)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-05-29 16:05:30 +09:00
parent f3439ddad5
commit 990ea0ae5f
46 changed files with 7172 additions and 136 deletions
@@ -0,0 +1,28 @@
# Development Log: E:\Wiki\connectai 프로젝트에 대해서 이야기 하는거야.
## Purpose
Record the implementation or verification outcome from the current conversation.
## Implementation Summary
결론: `E:\Wiki\connectai` 프로젝트의 맥락에서, 방대한 지식 중 의미 있는 것을 발굴하는 것은 결국 '검색된 정보(Retrieved)와 현재 작업(Active Task) 사이의 논리적 간극을 어떻게 메울 것인가'의 문제입니다. 현재 아스트라는 `connectai` 프로젝트의 구조를 파악하고 있으며, 이 프로젝트의 핵심은 단순한 지식 저장이 아니라 '지능형 에이전트의 실행과 관리'에 있습니다. 따라서 지식을 발굴할 때 다음 세 가지 관점을 적용하면 훨씬 강력한 추론이 가능해집니다. 1. 프로젝트 의존성 기반의 확장 검색 (Dependency-aware Retrieval) - `connectai`는 VS Code Extension이며, `package.json`, `src/agent.ts`, `src/config.ts` 등 상호 연결된 모듈로 구성되어 있습니다. - 지식을 가져올 때 단순히 텍mplate 파일만 보는 것이 아니라, "이 설정(`config.ts`)이 변경...
## Architecture
Captured automatically from the assistant response and active project context.
## Changed Files
- package.json
- src/agent.ts
- src/config.ts
- config.ts
- agent-knowledge-map.json
- architecture.md
- skills/*.md
## Dependency Notes
No new dependency note was captured automatically.
## Bugs
No bugs recorded.
## Lessons
- Automatic project records should be generated in the background when the turn contains durable project knowledge.
@@ -0,0 +1,22 @@
# Development Log: 아스트라를 지금 보다 더 날카롭고 신뢰감이 높은 아이 그리고 나의 의도를 잘 파악하게 하기 위해서는 어떤부분을 강화하는게 좋을까?
## Purpose
Record the implementation or verification outcome from the current conversation.
## Implementation Summary
결론: 아스트라가 사용자의 의도를 정확히 꿰뚫고(Sharpness) 신뢰할 수 있는 답변(Reliability)을 내놓기 위해서는, '추론 전 단계의 맥락 정밀화(Pre-inference Contextualization)'와 '추론 후 검증 루프(Post-inference Verification)'를 강화해야 합니다. 단순히 모델의 성능에 의존하는 것이 아니라, 아스트라가 스스로 '생각의 구조'를 설계할 수 있는 장치를 만드는 것이 핵심입니다. 이를 위한 3가지 강화 전략을 제안합니다. 1. 사용자 의도 파악의 정밀화: Intent-to-Context Mapping 현재 아스트라는 사용자의 질문을 받으면 즉시 답변을 생성하려 합니다. 하지만 '날카로운' 파악을 위해서는 질문 뒤에 숨겨진 '실행 목적'을 먼저 정의해야 합니다. - 강화 방안: 질문이 들어오면 바로 추론하지 않고, [의도 분류 $\rightarrow$ 필요 컨텍스트 식별 $\rightarrow$ 누락된 정보 확인] 단계...
## Architecture
Captured automatically from the assistant response and active project context.
## Changed Files
- src/agent.ts
## Dependency Notes
No new dependency note was captured automatically.
## Bugs
No bugs recorded.
## Lessons
- Automatic project records should be generated in the background when the turn contains durable project knowledge.