feat(search): Phase 1.3 TEI reranker 통합 (코드 골격)

데이터 흐름 원칙: fusion=doc 기준 / reranker=chunk 기준 — 절대 섞지 말 것.

신규/수정:
- ai/client.py: rerank() 메서드 추가 (TEI POST /rerank API)
- services/search/rerank_service.py:
    - rerank_chunks() — asyncio.Semaphore(2) + 5s soft timeout + RRF fallback
    - _make_snippet/_extract_window — title + query 중심 200~400 토큰
      (keyword 매치 없으면 첫 800자 fallback)
    - apply_diversity() — max_per_doc=2, top score>=0.90 unlimited
    - warmup_reranker() — 10회 retry + 3초 간격 (TEI 모델 로딩 대기)
    - MAX_RERANK_INPUT=200, MAX_CHUNKS_PER_DOC=2 hard cap
- services/search_telemetry.py: compute_confidence_reranked() — sigmoid score 임계값
- api/search.py:
    - ?rerank=true|false 파라미터 (기본 true, hybrid 모드만)
    - 흐름: fused_docs(limit*5) → chunks_by_doc 회수 → rerank_chunks → apply_diversity
    - text-only 매치 doc은 doc 자체를 chunk처럼 wrap (fallback)
    - rerank 활성 시 confidence는 reranker score 기반
- tests/search_eval/run_eval.py: --rerank true|false 플래그

GPU 적용 보류:
- TEI 컨테이너 추가 (docker-compose.yml) — 별도 작업
- config.yaml rerank.endpoint 갱신 — GPU 직접 (commit 없음)
- 재인덱싱 완료 후 build + warmup + 평가셋 측정

tests/search_eval/run_eval.py

@@ -133,6 +133,7 @@ async def call_search(
     mode: str = "hybrid",
     limit: int = 20,
     fusion: str | None = None,
+    rerank: str | None = None,
 ) -> tuple[list[int], float]:
     """검색 API 호출 → (doc_ids, latency_ms)."""
     url = f"{base_url.rstrip('/')}/api/search/"
@@ -140,6 +141,8 @@ async def call_search(
     params: dict[str, str | int] = {"q": query, "mode": mode, "limit": limit}
     if fusion:
         params["fusion"] = fusion
+    if rerank is not None:
+        params["rerank"] = rerank
 
     import time
 
@@ -165,6 +168,7 @@ async def evaluate(
     label: str,
     mode: str = "hybrid",
     fusion: str | None = None,
+    rerank: str | None = None,
 ) -> list[QueryResult]:
     """전체 쿼리셋 평가."""
     results: list[QueryResult] = []
@@ -173,7 +177,7 @@ async def evaluate(
         for q in queries:
             try:
                 returned_ids, latency_ms = await call_search(
-                    client, base_url, token, q.query, mode=mode, fusion=fusion
+                    client, base_url, token, q.query, mode=mode, fusion=fusion, rerank=rerank
                 )
                 results.append(
                     QueryResult(
@@ -404,6 +408,13 @@ def main() -> int:
         choices=["legacy", "rrf", "rrf_boost"],
         help="hybrid 모드 fusion 전략 (Phase 0.5+, 미지정 시 서버 기본값)",
     )
+    parser.add_argument(
+        "--rerank",
+        type=str,
+        default=None,
+        choices=["true", "false"],
+        help="bge-reranker-v2-m3 활성화 (Phase 1.3+, 미지정 시 서버 기본값=true)",
+    )
     parser.add_argument(
         "--token",
         type=str,
@@ -434,6 +445,8 @@ def main() -> int:
     print(f"Mode: {args.mode}", end="")
     if args.fusion:
         print(f" / fusion: {args.fusion}", end="")
+    if args.rerank:
+        print(f" / rerank: {args.rerank}", end="")
     print()
 
     all_results: list[QueryResult] = []
@@ -441,21 +454,21 @@ def main() -> int:
     if args.base_url:
         print(f"\n>>> evaluating: {args.base_url}")
         results = asyncio.run(
-            evaluate(queries, args.base_url, args.token, "single", mode=args.mode, fusion=args.fusion)
+            evaluate(queries, args.base_url, args.token, "single", mode=args.mode, fusion=args.fusion, rerank=args.rerank)
         )
         print_summary("single", results)
         all_results.extend(results)
     else:
         print(f"\n>>> baseline: {args.baseline_url}")
         baseline_results = asyncio.run(
-            evaluate(queries, args.baseline_url, args.token, "baseline", mode=args.mode, fusion=args.fusion)
+            evaluate(queries, args.baseline_url, args.token, "baseline", mode=args.mode, fusion=args.fusion, rerank=args.rerank)
         )
         baseline_summary = print_summary("baseline", baseline_results)
 
         print(f"\n>>> candidate: {args.candidate_url}")
         candidate_results = asyncio.run(
             evaluate(
-                queries, args.candidate_url, args.token, "candidate", mode=args.mode, fusion=args.fusion
+                queries, args.candidate_url, args.token, "candidate", mode=args.mode, fusion=args.fusion, rerank=args.rerank
             )
         )
         candidate_summary = print_summary("candidate", candidate_results)