feat: implement Phase 1 data pipeline and migration

- Implement kordoc /parse endpoint (HWP/HWPX/PDF via kordoc lib,
  text files direct read, images flagged for OCR)
- Add queue consumer with APScheduler (1min interval, stage chaining
  extract→classify→embed, stale item recovery, retry logic)
- Add extract worker (kordoc HTTP call + direct text read)
- Add classify worker (Qwen3.5 AI classification with think-tag
  stripping and robust JSON extraction from AI responses)
- Add embed worker (GPU server nomic-embed-text, graceful failure)
- Add DEVONthink migration script with folder mapping for 16 DBs,
  dry-run mode, batch commits, and idempotent file_path UNIQUE
- Enhance ai/client.py with strip_thinking() and parse_json_response()

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

app/ai/client.py

@@ -1,11 +1,39 @@
 """AI 추상화 레이어 — 통합 클라이언트. 기본값은 항상 Qwen3.5."""
 
+import json
+import re
 from pathlib import Path
 
 import httpx
 
 from core.config import settings
 
+
+def strip_thinking(text: str) -> str:
+    """Qwen3.5의 <think>...</think> 블록 제거"""
+    return re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL).strip()
+
+
+def parse_json_response(raw: str) -> dict | None:
+    """AI 응답에서 JSON 객체 추출 (think 태그, 코드블록 등 제거)"""
+    cleaned = strip_thinking(raw)
+    # 코드블록 내부 JSON 추출
+    code_match = re.search(r"```(?:json)?\s*(\{.*?\})\s*```", cleaned, re.DOTALL)
+    if code_match:
+        cleaned = code_match.group(1)
+    # 마지막 유효 JSON 객체 찾기
+    matches = list(re.finditer(r"\{[^{}]*(?:\{[^{}]*\}[^{}]*)*\}", cleaned, re.DOTALL))
+    for m in reversed(matches):
+        try:
+            return json.loads(m.group())
+        except json.JSONDecodeError:
+            continue
+    # 최후 시도: 전체 텍스트를 JSON으로
+    try:
+        return json.loads(cleaned)
+    except json.JSONDecodeError:
+        return None
+
 # 프롬프트 로딩
 PROMPTS_DIR = Path(__file__).parent.parent / "prompts"