PRD.md §2.1-②·§3.1 P0 갭 우선순위 #2. close/formal 2종 관계 티어를 추가하고,
초안 생성 시 상대별 톤을 다르게 낸다.
- core-backend: TwinSettings.RelationshipTier(전역 기본값, 안전 우선 formal
기본), Contact.RelationshipTier(1:1 연락처별 오버라이드, nullable).
persona.go의 resolveRelationshipTier()가 연락처 오버라이드 → 전역 기본값 →
formal 순으로 해석하고, 그룹 대화는 상대가 여럿이라 항상 전역 기본값만 사용.
POST /conversations/:id/draft는 기존에 인증을 요구하지 않던 동작을 깨지
않도록 currentUser(..., false)로 선택적 인증 처리 후 티어를 주입.
- 안전 관련 부수 수정: 그룹 대화에서는 전역 자율성 레벨(L1/L2)과 무관하게
와카뷰 자동 발송을 무조건 차단(단톡 따라잡기는 L0 고정이 맞음).
- ai-service: RELATIONSHIP_TIER_INSTRUCTIONS + system_prompt_for_tier()로
Gemini system_instruction에 관계 톤 지침을 주입. 에스컬레이션/정체성 게이팅
로직은 티어와 무관하게 그대로 유지.
- mobile: 온보딩(말투 샘플 다음 단계)과 자율성 설정 화면에 전역 기본값
SegmentedButton, 연락처 추가/수정 다이얼로그에 _RelationshipTierPicker로
상대별 오버라이드 추가.
- 테스트: core-backend persona_test.go 6개(해석 순서·그룹 예외·비인증
기본값 포함), ai-service 6개(system_prompt_for_tier + draft_reply 경로)
전부 추가, 기존 스위트 모두 통과(go test, pytest 47/47, flutter analyze/test).
실제 Flutter 빌드 + Playwright로 온보딩→연락처 오버라이드→목록 표시까지
전체 라운드트립 시각 검증 완료.
- docs: roadmap.md §2.7-B, deploy-checklist.md N4-C2a~d 완료 처리. 다음
우선순위는 Track C3(스팸/도배 감지 최소 버전).
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014YSB5PqF38raTxP5ABgr9m
Closes the biggest content gap found against PRD.md §3.1 P0: group chat
catch-up was one of only two v1 MVP scenarios and had zero implementation.
Backend (core-backend):
- ConversationParticipant.LastReadMessageID read marker.
- POST /conversations/:id/read advances the caller's marker (never backward).
- GET /conversations/:id/summary builds context from messages since that
marker and calls ai-service's new POST /summarize; returns unread_count
and needs_reply.
- GET /conversations now reports unread_count per room.
- Safety: group conversations now unconditionally block twin-authored
sends (POST /conversations/:id/messages), regardless of the sender's
global autonomy level. PRD.md §2.3-③ requires this scenario stay L0-fixed
with no auto-send; autonomy level is a per-user global setting today, so
this closes the only path a global L2 whitelist match could otherwise
auto-send into a group.
AI service (ai-service): new summarize.py module (same Gemini-call shape as
generation.py's draft_reply, no escalation/identity gating since nothing
generated here is ever sent) + POST /summarize.
Mobile: "새 대화" dialog now supports adding/removing multiple peer fields
(2+ peers -> is_group:true automatically); unread badge on conversation
rows; ChatScreen takes isGroup and renders its L1 panel as L0-locked for
groups; new "안 본 동안 요약" AppBar action opens a dialog with the summary
and, when a reply looks needed, a button that feeds straight into the
existing draft-request flow.
Verified with a real Flutter build against a live core-backend + ai-service
instance (Playwright driving 3 demo accounts through group creation, unread
badges, and the summary dialog) — this caught a real ordering bug: marking
the read marker on chat *open* meant the summary was always empty by the
time you could tap it, since opening the room already advanced the marker
past everything you'd come to catch up on. Fixed by marking read on screen
*exit* (dispose) instead, so the marker reflects what was unread that whole
visit and updates once you leave.
go test / pytest / flutter analyze+test all pass.
Add PATCH contact for missing peer IDs, contacts banner and edit UI,
enrich /demo with pairing steps, and update tester/signup guidance.
Co-authored-by: okuma <o0kuma@users.noreply.github.com>
Add conversation/contact/history/escalation-log endpoints, contact-scoped
whitelist matching, bearer sessions, ADMIN_API_TOKEN guards, and
`go run . migrate`. Update Flutter client to persist/send session tokens
and mark A1/A2 complete in the prioritized checklist.
Co-authored-by: okuma <o0kuma@users.noreply.github.com>
Claude
Cursor Agent