페르소나 소스팩 동기화 정리

apps/api/app/routes/kb.py

@@ -22,7 +22,7 @@ from pydantic import BaseModel, Field
 
 from ..db import acquire, get_pool
 from ..deps import AIView, Principal, Role, require_role
-from ..services import live_coach, rag
+from ..services import rag, source_pack_sync
 
 router = APIRouter(prefix="/kb", tags=["kb"])
 
@@ -326,6 +326,8 @@ async def index_document(
         # 관리자 인덱싱은 RLS 미적용(쓰기 — kb 스키마 직접). role 주입 없이 acquire.
         async with acquire() as conn:
             result = await rag.index_document(conn, req)
+    except rag.IndexPolicyViolation as e:
+        raise HTTPException(status.HTTP_422_UNPROCESSABLE_ENTITY, detail=str(e)) from e
     except rag.NotConfigured as e:
         raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail=f"RAG not configured: {e}")
     except RuntimeError as e:
@@ -354,64 +356,36 @@ async def sync_live_coach_source_packs(
     evaluator RAG 검색에도 올린다. source row를 먼저 upsert한 뒤 content_hash 기반 증분 색인을
     수행한다. 임베딩 모델 미가용 시 BM25-only degraded 색인으로 이어진다.
     """
-    source_rows = live_coach.build_rag_source_rows()
-    index_payloads = live_coach.build_rag_index_payloads()
+    source_rows, index_payloads = source_pack_sync.build_repo_source_pack_manifest()
     if not source_rows or not index_payloads:
         raise HTTPException(
             status.HTTP_422_UNPROCESSABLE_ENTITY,
             detail="live coach source packs are empty",
         )
 
-    items: list[LiveCoachSourcePackSyncItem] = []
-    source_row_by_id = {row["source_id"]: row for row in source_rows}
     try:
         async with acquire() as conn:
-            for row in source_rows:
-                await conn.execute(
-                    """
-                    INSERT INTO kb.source
-                      (source_id, title, kb_kind, license_class, origin_path, citation, external_llm_ok)
-                    VALUES ($1, $2, $3, $4, $5, $6, $7)
-                    ON CONFLICT (source_id) DO UPDATE SET
-                      title = EXCLUDED.title,
-                      kb_kind = EXCLUDED.kb_kind,
-                      license_class = EXCLUDED.license_class,
-                      origin_path = EXCLUDED.origin_path,
-                      citation = EXCLUDED.citation,
-                      external_llm_ok = EXCLUDED.external_llm_ok
-                    """,
-                    row["source_id"],
-                    row["title"],
-                    row["kb_kind"],
-                    row["license_class"],
-                    row["origin_path"],
-                    row["citation"],
-                    row["external_llm_ok"],
-                )
-            for payload in index_payloads:
-                if payload["source_id"] not in source_row_by_id:
-                    continue
-                result = await rag.index_document(conn, rag.IndexRequest(**payload))
-                items.append(
-                    LiveCoachSourcePackSyncItem(
-                        source_id=payload["source_id"],
-                        doc_id=result.doc_id,
-                        chunks_indexed=result.chunks_indexed,
-                        skipped_unchanged=result.skipped_unchanged,
-                        embedded=result.embedded,
-                        degraded=result.degraded,
-                    )
-                )
+            result = await source_pack_sync.sync_repo_source_packs(conn, apply=True)
     except rag.NotConfigured as exc:
         raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail=f"RAG not configured: {exc}") from exc
     except RuntimeError as exc:
         raise HTTPException(status.HTTP_503_SERVICE_UNAVAILABLE, detail=f"DB not ready: {exc}") from exc
 
     return LiveCoachSourcePackSyncResponse(
-        sources_upserted=len(source_rows),
-        chunks_indexed=sum(item.chunks_indexed for item in items),
-        skipped_unchanged=sum(1 for item in items if item.skipped_unchanged),
-        embedded=all(item.embedded for item in items) if items else False,
-        degraded=any(item.degraded for item in items),
-        items=items,
+        sources_upserted=result.sources_upserted,
+        chunks_indexed=result.chunks_indexed,
+        skipped_unchanged=result.skipped_unchanged,
+        embedded=result.embedded,
+        degraded=result.degraded,
+        items=[
+            LiveCoachSourcePackSyncItem(
+                source_id=item.source_id,
+                doc_id=item.doc_id,
+                chunks_indexed=item.chunks_indexed,
+                skipped_unchanged=item.skipped_unchanged,
+                embedded=item.embedded,
+                degraded=item.degraded,
+            )
+            for item in result.items
+        ],
     )