feat(briefing): add morning briefing schema + services + api (historical off)

야간 수집 뉴스 (KST 00:00~05:00) topic×country 비교 분석 1페이지 카드.
Phase 4 Global Digest 와 코드/로직/테이블 분리, 알고리즘만 services/clustering_common 공유.

Backend 신규:
- migrations/255_morning_briefings.sql: morning_briefings + briefing_topics
  (briefing_date UNIQUE, UNIQUE(briefing_id,topic_rank), FK CASCADE,
  historical_* 3컬럼 nullable, cluster_members JSONB, country_perspectives
  JSONB, status 4-state success|partial|failed|empty)
- app/models/briefing.py: SQLAlchemy ORM
- app/services/briefing/loader.py: KST 5h 윈도우 + news_sources prefix
  fallback (Phase 4 패턴 미러) + historical candidate pool 로더
- app/services/briefing/clustering.py: cluster_global topic-first
  (LAMBDA=ln(2)/2h, MIN_COUNTRIES_PER_TOPIC=2, MAX_TOPICS=7)
- app/services/briefing/comparator.py: call_primary 26B + JSON envelope
  sanitize (cap perspectives 10 / divergences 3 / convergences 2 /
  quotes 5) + fallback row 고정 형태 + retrieve_historical cosine top-K
- app/services/briefing/pipeline.py: load→cluster→select(K=7,λ=0.6)
  →historical→compare→status 4-state→delete+insert transaction
- app/workers/briefing_worker.py: APScheduler/수동 호출 공용 진입점,
  600s hard cap
- app/prompts/briefing_comparative.txt: 한국어 비교 분석 JSON 프롬프트,
  {articles_block} + {historical_block} 2섹션, 인용 금지 라벨
- app/api/briefing.py: GET /latest, GET ?date=, POST /regenerate?date=
  (admin, sync delete+insert tx, regenerated:true)

Backend 수정:
- app/main.py: briefing_router 등록 (/api/briefing prefix). scheduler
  등록은 PR-3 에서.
- app/services/digest/selection.py: select_for_llm 매개변수화 (K, λ
  caller 주입). Phase 4 동작은 default 값으로 보존.

Historical 정책:
- BRIEFING_HISTORICAL_ENABLED env flag, default off.
- flag off → historical_* 컬럼 모두 NULL, prompt {historical_block} 빈
  라벨, retrieval 호출 안 함.
- flag on (PR-1b 에서 enable) → cluster centroid 와 과거 30일 doc
  embedding cosine top-K 5 (sim≥0.70), prompt 에 주입.

Country canonical (실측 확인 후):
- documents.country 컬럼 부재 확정
- document_chunks.country 매칭률 0% (chunks 자체가 뉴스에 안 만들어짐)
- 유일 country 신호 = news_sources prefix 매핑 (Phase 4 와 동일)

Tests:
- tests/test_briefing_historical.py: 3 경로 회귀 (flag off/on with
  fixture/on zero match) + sanitize cap + fallback row 형태.

Verification: PR-1.8 에서 GPU 컨테이너 pytest + 수동 regenerate.

migrations/255_morning_briefings.sql

@@ -0,0 +1,67 @@
+-- 야간 수집 뉴스 브리핑 (Morning Briefing)
+-- 매일 KST 자정~05:00 사이 수집된 뉴스를 topic×country 비교 분석 1페이지 카드.
+-- 트리거: 05:10 KST APScheduler cron (PR-3 에서 등록). Phase 4 와 axis 반대 (topic-first).
+-- 코드/로직/테이블 모두 Phase 4 와 분리. 공통 알고리즘만 services/clustering_common 공유.
+
+-- 부모: 일일 1행
+CREATE TABLE morning_briefings (
+    id                BIGSERIAL PRIMARY KEY,
+    briefing_date     DATE NOT NULL,                    -- KST 기준 (윈도우 자정 시작일)
+    window_start      TIMESTAMPTZ NOT NULL,             -- UTC 환산 자정
+    window_end        TIMESTAMPTZ NOT NULL,             -- UTC 환산 05:00 KST
+    decay_lambda      DOUBLE PRECISION NOT NULL,        -- 실제 사용된 time-decay λ (briefing = ln(2)/2h)
+
+    total_articles    INTEGER NOT NULL DEFAULT 0,
+    total_countries   INTEGER NOT NULL DEFAULT 0,
+    total_topics      INTEGER NOT NULL DEFAULT 0,
+
+    generation_ms     INTEGER,
+    llm_calls         INTEGER NOT NULL DEFAULT 0,
+    llm_failures      INTEGER NOT NULL DEFAULT 0,
+    status            VARCHAR(20) NOT NULL DEFAULT 'success',  -- success | partial | failed | empty
+
+    headline_oneliner TEXT,                             -- 향후 별 단계 (지금은 NULL)
+
+    created_at        TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+
+    UNIQUE (briefing_date)   -- idempotency: regenerate 시 DELETE+INSERT
+);
+
+CREATE INDEX idx_morning_briefings_date ON morning_briefings (briefing_date DESC);
+
+-- 자식: 1 briefing 안 topic_rank 순 (importance_score 내림차순)
+CREATE TABLE briefing_topics (
+    id                     BIGSERIAL PRIMARY KEY,
+    briefing_id            BIGINT NOT NULL REFERENCES morning_briefings(id) ON DELETE CASCADE,
+
+    topic_rank             INTEGER NOT NULL,            -- 1..N
+    topic_label            VARCHAR(120) NOT NULL,       -- "이란-이스라엘 충돌" 등 5~10 단어 한국어
+    headline               TEXT NOT NULL,               -- 1줄 요약
+
+    -- LLM 비교 분석 결과 (JSONB cap: perspectives ≤10, divergences ≤3, convergences ≤2, quotes ≤5)
+    country_perspectives   JSONB NOT NULL DEFAULT '[]'::jsonb,  -- [{country, summary, article_ids}, ...]
+    divergences            JSONB NOT NULL DEFAULT '[]'::jsonb,  -- ["A국 X / B국 Y", ...]
+    convergences           JSONB NOT NULL DEFAULT '[]'::jsonb,  -- ["모두 Z 일치", ...]
+    key_quotes             JSONB NOT NULL DEFAULT '[]'::jsonb,  -- [{country, source, quote}, ...]
+
+    -- Historical context (BRIEFING_HISTORICAL_ENABLED=false default off, PR-1b 에서 on)
+    historical_article_ids JSONB,                       -- [doc_id, ...] top-K 과거 참고 (페이지 노출 X)
+    historical_context     TEXT,                        -- LLM 생성 "지난 흐름" 1~2문장
+    historical_window_days INTEGER,                     -- 사용된 N (기본 30)
+
+    -- Cluster 메타 (LLM 성공/실패와 무관, UI 폴백 link 용)
+    cluster_members        JSONB NOT NULL DEFAULT '[]'::jsonb,  -- [doc_id, ...] cluster 전체 article
+    article_count          INTEGER NOT NULL,
+    country_count          INTEGER NOT NULL,            -- cluster 안 distinct country 수 (MIN_COUNTRIES_PER_TOPIC=2 필터 통과)
+    importance_score       DOUBLE PRECISION NOT NULL,   -- briefing 내 0~1 normalized
+    raw_weight_sum         DOUBLE PRECISION NOT NULL,
+
+    llm_model              VARCHAR(100),
+    llm_fallback_used      BOOLEAN NOT NULL DEFAULT FALSE,
+
+    created_at             TIMESTAMPTZ NOT NULL DEFAULT NOW(),
+
+    UNIQUE (briefing_id, topic_rank)
+);
+
+CREATE INDEX idx_briefing_topics_briefing_rank ON briefing_topics (briefing_id, topic_rank);