hyungi_document_server/app/main.py

"""hyungi_Document_Server — FastAPI 엔트리포인트"""

from contextlib import asynccontextmanager

from fastapi import FastAPI, Request
from fastapi.responses import RedirectResponse
from sqlalchemy import func, select, text

from api.audio import router as audio_router
from api.auth import router as auth_router
from api.config import router as config_router
from api.dashboard import router as dashboard_router
from api.digest import router as digest_router
from api.document_notes import router as document_notes_router
from api.document_reads import router as document_reads_router
from api.documents import router as documents_router
from api.library import router as library_router
from api.memos import router as memos_router
from api.news import router as news_router
from api.search import router as search_router
from api.setup import router as setup_router
from api.study_question_progress import router as study_question_progress_router
from api.study_questions import router as study_questions_router
from api.study_sessions import router as study_sessions_router
from api.study_topics import router as study_topics_router
from api.video import router as video_router
from core.config import settings
from core.database import async_session, engine, init_db
from models.user import User


@asynccontextmanager
async def lifespan(app: FastAPI):
    """앱 시작/종료 시 실행되는 lifespan 핸들러"""
    import asyncio

    from apscheduler.schedulers.asyncio import AsyncIOScheduler
    from apscheduler.triggers.cron import CronTrigger
    from services.search.query_analyzer import prewarm_analyzer
    from workers.daily_digest import run as daily_digest_run
    from workers.digest_worker import run as global_digest_run
    from workers.file_watcher import watch_inbox
    from workers.law_monitor import run as law_monitor_run
    from workers.mailplus_archive import run as mailplus_run
    from workers.news_collector import run as news_collector_run
    from workers.queue_consumer import consume_queue
    from workers.study_queue_consumer import consume_study_queue
    from workers.study_question_embed_worker import (
        refresh_stale_related as study_q_related_refresh,
        run as study_q_embed_run,
    )
    from workers.tier_backfill import run as tier_backfill_run
    from workers.upload_cleanup import cleanup_orphan_uploads

    # 시작: DB 연결 확인
    await init_db()

    # NAS 마운트 확인 (NFS 미마운트 시 로컬 빈 디렉토리에 쓰는 것 방지)
    from pathlib import Path
    nas_check = Path(settings.nas_mount_path) / "PKM"
    if not nas_check.is_dir():
        raise RuntimeError(
            f"NAS 마운트 확인 실패: {nas_check} 디렉토리 없음. "
            f"NFS 마운트 상태를 확인하세요."
        )

    # APScheduler: 백그라운드 작업
    scheduler = AsyncIOScheduler(timezone="Asia/Seoul")
    # 상시 실행
    scheduler.add_job(consume_queue, "interval", minutes=1, id="queue_consumer")
    scheduler.add_job(watch_inbox, "interval", minutes=5, id="file_watcher")
    scheduler.add_job(cleanup_orphan_uploads, "interval", minutes=10, id="upload_cleanup")
    # PR-4: study_questions 자동 임베딩 (status='none/failed/stale' 행을 batch=10 처리).
    # 별도 큐 테이블 없이 status 자체가 큐. backfill 도 cron 이 'none' 행을 자연스럽게 처리.
    scheduler.add_job(study_q_embed_run, "interval", minutes=1, id="study_q_embed")
    # PR-12-A 후속: related-types 캐시 stale 행 재계산. 임베딩 워커와 분리한 별도 cron.
    # 새 문제 ready / 같은 토픽 invalidation / 임계값 변경 시 NULL 마킹된 행을 batch=20 처리.
    scheduler.add_job(study_q_related_refresh, "interval", minutes=1, id="study_q_related_refresh")
    # Phase 4-A: study_question_jobs 처리 — wrong/unsure AI 풀이 prefetch.
    # MLX gate 직렬화 + BATCH_SIZE=1 로 GPU 부하 통제. STALE_MINUTES=10 자체 복구.
    scheduler.add_job(consume_study_queue, "interval", minutes=1, id="study_queue_consumer")
    # PR-B 레거시 tier 백필 — 30분 주기로 호출되지만 KST 00:00~06:00 시간대만 실제 enqueue.
    # safety > law > manual 우선순위로 25건씩. 6720 레거시 → 야간당 ~150건 → 약 45일 소화.
    scheduler.add_job(tier_backfill_run, "interval", minutes=30, id="tier_backfill")
    # 일일 스케줄 (KST)
    scheduler.add_job(law_monitor_run, CronTrigger(hour=7), id="law_monitor")
    scheduler.add_job(mailplus_run, CronTrigger(hour=7), id="mailplus_morning")
    scheduler.add_job(mailplus_run, CronTrigger(hour=18), id="mailplus_evening")
    scheduler.add_job(daily_digest_run, CronTrigger(hour=20), id="daily_digest")
    scheduler.add_job(global_digest_run, CronTrigger(hour=4, minute=0), id="global_digest")
    scheduler.add_job(news_collector_run, "interval", hours=6, id="news_collector")
    scheduler.start()

    # Phase 2.1 (async 구조): QueryAnalyzer prewarm.
    # 대표 쿼리 15~20개를 background task로 분석해 cache 적재.
    # 첫 사용자 요청부터 cache hit rate 70~80% 목표.
    # 논블로킹 — startup을 막지 않음. MLX 부하 완화 위해 delay_between=0.5.
    prewarm_task = asyncio.create_task(prewarm_analyzer())
    prewarm_task.add_done_callback(
        lambda t: t.exception() and None  # 예외는 query_analyzer 내부에서 로깅
    )

    yield

    # 종료: 스케줄러 → DB 순서로 정리
    scheduler.shutdown(wait=False)
    await engine.dispose()


app = FastAPI(
    title="hyungi_Document_Server",
    description="Self-hosted PKM 웹 애플리케이션 API",
    version="2.0.0",
    lifespan=lifespan,
)

# ─── 라우터 등록 ───
app.include_router(setup_router, prefix="/api/setup", tags=["setup"])
app.include_router(config_router, prefix="/api/config", tags=["config"])
app.include_router(auth_router, prefix="/api/auth", tags=["auth"])
app.include_router(documents_router, prefix="/api/documents", tags=["documents"])
# 회독 카운트 — /api/documents/{id}/read* 경로. documents_router 와 prefix 같아 충돌 없음.
app.include_router(document_reads_router, prefix="/api/documents", tags=["document-reads"])
app.include_router(document_notes_router, prefix="/api/documents", tags=["document-notes"])
app.include_router(search_router, prefix="/api/search", tags=["search"])

app.include_router(memos_router, prefix="/api/memos", tags=["memos"])
app.include_router(dashboard_router, prefix="/api/dashboard", tags=["dashboard"])
app.include_router(library_router, prefix="/api/library", tags=["library"])
app.include_router(news_router, prefix="/api/news", tags=["news"])
app.include_router(digest_router, prefix="/api/digest", tags=["digest"])
app.include_router(audio_router, prefix="/api/audio", tags=["audio"])
app.include_router(video_router, prefix="/api/video", tags=["video"])
app.include_router(study_sessions_router, prefix="/api/study-sessions", tags=["study-sessions"])
app.include_router(study_topics_router, prefix="/api/study-topics", tags=["study-topics"])
# study_questions: 라우터 안에서 /study-topics/{id}/questions 와 /study-questions/{id} 두 줄기를 모두 정의하므로 prefix=/api 로 등록
app.include_router(study_questions_router, prefix="/api", tags=["study-questions"])
# Phase 1: 학습 진행 상태 (review-complete + review-queue). prefix=/api/study-topics 안에 정의됨.
app.include_router(study_question_progress_router, prefix="/api", tags=["study-progress"])

# TODO: Phase 5에서 추가
# app.include_router(tasks.router, prefix="/api/tasks", tags=["tasks"])
# app.include_router(export.router, prefix="/api/export", tags=["export"])


# ─── 셋업 미들웨어: 유저 0명이면 /setup으로 리다이렉트 ───
SETUP_BYPASS_PREFIXES = (
    "/api/setup", "/api/config", "/setup", "/health", "/docs", "/openapi.json", "/redoc",
)


@app.middleware("http")
async def setup_redirect_middleware(request: Request, call_next):
    path = request.url.path
    # 바이패스 경로는 항상 통과
    if any(path.startswith(p) for p in SETUP_BYPASS_PREFIXES):
        return await call_next(request)

    # 유저 존재 여부 확인
    try:
        async with async_session() as session:
            result = await session.execute(select(func.count(User.id)))
            user_count = result.scalar()
        if user_count == 0:
            return RedirectResponse(url="/setup")
    except Exception:
        pass  # DB 연결 실패 시 통과 (health에서 확인 가능)

    return await call_next(request)


# ─── 셋업 페이지 라우트 (API가 아닌 HTML 페이지) ───
@app.get("/setup")
async def setup_page_redirect(request: Request):
    """셋업 위자드 페이지로 포워딩"""
    from api.setup import setup_page
    from core.database import get_session

    async for session in get_session():
        return await setup_page(request, session)


@app.get("/health")
async def health_check():
    """헬스체크 — DB 연결 상태 포함"""
    db_ok = False
    try:
        async with engine.connect() as conn:
            await conn.execute(text("SELECT 1"))
        db_ok = True
    except Exception:
        pass

    return {
        "status": "ok" if db_ok else "degraded",
        "version": "2.0.0",
        "database": "connected" if db_ok else "disconnected",
    }