feat: replace single-pass enricher with 4-step pipeline

Upgrades content processing from a single LLM call to a structured
5-step document reconstruction pipeline:

  1. Normalize  — 구어체 정제, 문장부호 복원, 핵심 엔티티 추출
  2. Index Tree — 텍스트 전체 스캔 → 계층적 목차(JSON) 생성
  3. Leaf Summarize — 섹션별 상세 요약 (context overlap 300자 적용)
  4. Consistency Check — 누락 엔티티 검증 및 보완
  5. Assemble — 최종 Markdown 문서 조립 (LLM 불필요)

- Short texts (< 3000 chars): simple 1-pass fallback
- Long texts: full pipeline (N+4 LLM calls where N = section count)
- worker.py: uses body_md from enricher as Obsidian note body

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

daemon/worker.py

@@ -55,11 +55,12 @@ def process_item(item: dict) -> None:
         meta = enrich(input_type, yt_title, url, text)
         title = meta.get("title") or yt_title or url or row_id[:8]
 
+        # body_md: 4단계 파이프라인이 생성한 구조화 문서 (없으면 원문 폴백)
         note_path = save_note(
             content_type=input_type,
             title=title,
             summary=meta.get("summary", ""),
-            body=text,
+            body=meta.get("body_md") or text,
             tags=meta.get("tags", []),
             source_url=url,
             author=meta.get("author") or "",