feat(search): Phase 2.3 soft_filter boost (domain/doctype)

## 변경

### fusion_service.py
 - SOFT_FILTER_MAX_BOOST = 0.05 (plan 영구 룰, RRF score 왜곡 방지)
 - SOFT_FILTER_DOMAIN_BOOST = 0.03, SOFT_FILTER_DOCTYPE_BOOST = 0.02
 - apply_soft_filter_boost(results, soft_filters) → int
   - ai_domain 부분 문자열 매칭 (path 포함 e.g. "Industrial_Safety/Legislation")
   - document_type 토큰 매칭 (ai_domain + match_reason 헤이스택)
   - 상한선 0.05 강제
   - boost 후 score 기준 재정렬

### api/search.py
 - fusion 직후 호출 조건:
   - analyzer_cache_hit == True
   - analyzer_tier != "ignore" (confidence >= 0.5)
   - query_analysis.soft_filters 존재
 - notes에 "soft_filter_boost applied=N" 기록

## Phase 2.3 범위
 - hard_filter SQL WHERE는 현재 평가셋에 명시 필터 쿼리 없어 효과 측정 불가 → Phase 2.4 v0.2 확장 후
 - document_type의 file_format 직접 매칭은 의미론적 mismatch → 제외
 - hard_filter는 Phase 2.4 이후 iteration

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

app/api/search.py

@@ -16,7 +16,12 @@ from core.database import get_session
 from core.utils import setup_logger
 from models.user import User
 from services.search import query_analyzer
-from services.search.fusion_service import DEFAULT_FUSION, get_strategy, normalize_display_scores
+from services.search.fusion_service import (
+    DEFAULT_FUSION,
+    apply_soft_filter_boost,
+    get_strategy,
+    normalize_display_scores,
+)
 from services.search.rerank_service import (
     MAX_CHUNKS_PER_DOC,
     MAX_RERANK_INPUT,
@@ -258,6 +263,19 @@ async def search(
                 f"unique_docs={len(chunks_by_doc)}"
             )
 
+            # Phase 2.3: soft_filter boost (cache hit + tier != ignore 일 때만)
+            # analyzer_confidence < 0.5 (tier=ignore)는 비활성.
+            if (
+                analyzer_cache_hit
+                and analyzer_tier != "ignore"
+                and query_analysis
+            ):
+                soft_filters = query_analysis.get("soft_filters") or {}
+                if soft_filters:
+                    boosted = apply_soft_filter_boost(fused_docs, soft_filters)
+                    if boosted > 0:
+                        notes.append(f"soft_filter_boost applied={boosted}")
+
             if rerank:
                 # Phase 1.3: reranker — chunk 기준 입력
                 # fusion 결과 doc_id로 chunks_by_doc에서 raw chunks 회수

app/services/search/fusion_service.py

@@ -219,6 +219,70 @@ def get_strategy(name: str) -> FusionStrategy:
     return cls()
 
 
+# ─── Phase 2.3: soft filter boost ───────────────────────
+
+SOFT_FILTER_MAX_BOOST = 0.05  # plan 룰 (CRITICAL)
+# ↑ RRF score는 0.01~0.05 범위 (k=60). 상한 초과 시 기존 랭킹 왜곡.
+#   기존 RRFWithBoost의 legal article boost(0.05)와 동일 최대값 → 일관성.
+SOFT_FILTER_DOMAIN_BOOST = 0.03
+SOFT_FILTER_DOCTYPE_BOOST = 0.02
+
+
+def apply_soft_filter_boost(
+    results: list["SearchResult"],
+    soft_filters: dict | None,
+) -> int:
+    """Phase 2.3 — QueryAnalyzer soft_filters 기반 score boost.
+
+    ai_domain / ai_tags 매칭 시 소량 boost 적용. 총 boost는
+    SOFT_FILTER_MAX_BOOST(0.05) 상한을 넘지 않음.
+
+    Args:
+        results: fusion 직후 SearchResult 리스트 (in-place 수정)
+        soft_filters: query_analysis.soft_filters = {"domain": [...], "document_type": [...]}
+
+    Returns:
+        int — boost 적용된 결과 개수 (debug/notes용)
+    """
+    if not soft_filters:
+        return 0
+    domain_list = [str(d).lower() for d in soft_filters.get("domain", []) or []]
+    doctype_list = [str(t).lower() for t in soft_filters.get("document_type", []) or []]
+    if not domain_list and not doctype_list:
+        return 0
+
+    boosted_count = 0
+    for r in results:
+        boost = 0.0
+
+        # domain 매칭 — ai_domain 부분 문자열 매칭 (Industrial_Safety/Legislation 같은 경로 매칭)
+        if domain_list and r.ai_domain:
+            ai_dom_lower = r.ai_domain.lower()
+            for d in domain_list:
+                if d in ai_dom_lower or ai_dom_lower in d:
+                    boost += SOFT_FILTER_DOMAIN_BOOST
+                    break  # 한 번만
+
+        # document_type 매칭 — ai_tags JSON 문자열 또는 ai_domain 내 keyword 탐지
+        # (ai_domain에 "Law_Document"는 안 들어감. ai_tags에 law/law_document 같은 태그가 있음.)
+        # 간단화: ai_domain 경로에 keyword가 포함되면 매칭
+        if doctype_list:
+            hay = (r.ai_domain or "").lower() + " " + (getattr(r, "match_reason", "") or "").lower()
+            for t in doctype_list:
+                if t in hay or any(word in hay for word in t.split("_")):
+                    boost += SOFT_FILTER_DOCTYPE_BOOST
+                    break
+
+        if boost > 0:
+            boost = min(boost, SOFT_FILTER_MAX_BOOST)
+            r.score += boost
+            boosted_count += 1
+
+    # boost 적용 후 재정렬
+    results.sort(key=lambda x: x.score, reverse=True)
+    return boosted_count
+
+
 # ─── display score 정규화 ────────────────────────────────