feat(search): Phase 1.2-C chunks 기반 vector retrieval + raw chunks 보존

retrieval_service.search_vector를 documents.embedding → document_chunks.embedding로 전환.
fetch_limit = limit*5로 raw chunks를 넓게 가져온 후 doc 기준 압축.

신규: compress_chunks_to_docs(chunks, limit) → (doc_results, chunks_by_doc)
- doc_id 별 best score chunk만 doc_results (fusion 입력)
- 모든 raw chunks는 chunks_by_doc dict에 보존 (Phase 1.3 reranker용)
- '같은 doc 중복으로 RRF가 false boost' 방지

SearchResult: chunk_id / chunk_index / section_title optional 필드 추가.
- text 검색 결과는 None (doc-level)
- vector 검색 결과는 채워짐 (chunk-level)

search.py 흐름:
1. raw_chunks = await search_vector(...)
2. vector_results, chunks_by_doc = compress_chunks_to_docs(raw_chunks, limit)
3. fusion(text_results, vector_results) — doc 기준
4. (Phase 1.3) chunks_by_doc → reranker — chunk 기준

debug notes: raw=N compressed=M unique_docs=K로 흐름 검증.

데이터 의존: 재인덱싱(reindex_all_chunks.py 진행 중) 완료 후 평가셋으로 검증.

app/api/search.py

@@ -16,7 +16,7 @@ from core.database import get_session
 from core.utils import setup_logger
 from models.user import User
 from services.search.fusion_service import DEFAULT_FUSION, get_strategy, normalize_display_scores
-from services.search.retrieval_service import search_text, search_vector
+from services.search.retrieval_service import compress_chunks_to_docs, search_text, search_vector
 from services.search_telemetry import (
     compute_confidence,
     compute_confidence_hybrid,
@@ -30,7 +30,14 @@ router = APIRouter()
 
 
 class SearchResult(BaseModel):
-    id: int
+    """검색 결과 단일 행.
+
+    Phase 1.2-C: chunk-level vector retrieval 도입으로 chunk 메타 필드 추가.
+    text 검색 결과는 chunk_id 등이 None (doc-level).
+    vector 검색 결과는 chunk_id 등이 채워짐 (chunk-level).
+    """
+
+    id: int  # doc_id (text/vector 공통)
     title: str | None
     ai_domain: str | None
     ai_summary: str | None
@@ -38,6 +45,10 @@ class SearchResult(BaseModel):
     score: float
     snippet: str | None
     match_reason: str | None = None
+    # Phase 1.2-C: chunk 메타 (vector 검색 시 채워짐)
+    chunk_id: int | None = None
+    chunk_index: int | None = None
+    section_title: str | None = None
 
 
 # ─── Phase 0.4: 디버그 응답 스키마 ─────────────────────────
@@ -99,16 +110,20 @@ async def search(
     timing: dict[str, float] = {}
     notes: list[str] = []
     text_results: list[SearchResult] = []
-    vector_results: list[SearchResult] = []
+    vector_results: list[SearchResult] = []  # doc-level (압축 후, fusion 입력)
+    raw_chunks: list[SearchResult] = []  # chunk-level (raw, Phase 1.3 reranker용)
+    chunks_by_doc: dict[int, list[SearchResult]] = {}  # Phase 1.3 reranker용 보존
 
     t_total = time.perf_counter()
 
     if mode == "vector":
         t0 = time.perf_counter()
-        vector_results = await search_vector(session, q, limit)
+        raw_chunks = await search_vector(session, q, limit)
         timing["vector_ms"] = (time.perf_counter() - t0) * 1000
-        if not vector_results:
+        if not raw_chunks:
             notes.append("vector_search_returned_empty (AI client error or no embeddings)")
+        # vector 단독 모드도 doc 압축해서 다양성 확보 (chunk 중복 방지)
+        vector_results, chunks_by_doc = compress_chunks_to_docs(raw_chunks, limit)
         results = vector_results
     else:
         t0 = time.perf_counter()
@@ -117,8 +132,14 @@ async def search(
 
         if mode == "hybrid":
             t1 = time.perf_counter()
-            vector_results = await search_vector(session, q, limit)
+            raw_chunks = await search_vector(session, q, limit)
             timing["vector_ms"] = (time.perf_counter() - t1) * 1000
+
+            # chunk-level → doc-level 압축 (raw chunks는 chunks_by_doc에 보존)
+            t1b = time.perf_counter()
+            vector_results, chunks_by_doc = compress_chunks_to_docs(raw_chunks, limit)
+            timing["compress_ms"] = (time.perf_counter() - t1b) * 1000
+
             if not vector_results:
                 notes.append("vector_search_returned_empty — text-only fallback")
 
@@ -127,6 +148,10 @@ async def search(
             results = strategy.fuse(text_results, vector_results, q, limit)
             timing["fusion_ms"] = (time.perf_counter() - t2) * 1000
             notes.append(f"fusion={strategy.name}")
+            notes.append(
+                f"chunks raw={len(raw_chunks)} compressed={len(vector_results)} "
+                f"unique_docs={len(chunks_by_doc)}"
+            )
         else:
             results = text_results