refactor: Sprint 3 - 引入 UnitOfWork + Repository 架构

新增:
- src/db/unit_of_work.py: UnitOfWork 事务封装
- src/db/repositories.py: Match/Team/League/Prediction Repository

重构:
- 删除 src/data/match_lookup.py(由 Repository 替代)
- 数据源(bzzoiro/understat/injuries)不再自行 commit
- API 路由(ingest)改用 UnitOfWork
- LLM 服务(predict/orchestrator/eval/backtest)改用 UnitOfWork

事务边界统一由调用方控制,数据层不再自行决定 commit。

src/data/bzzoiro.py

@@ -1,6 +1,7 @@
 """Bzzoiro 数据源:抓取 + 入库。
 
 迁移自旧项目 app/data/sources/bzzoiro/,改成 async + 简化入库。
+使用 Repository 模式进行数据访问,不直接控制事务。
 """
 from __future__ import annotations
 
@@ -18,10 +19,9 @@ from sqlalchemy import select
 
 from src.core.config import settings
 from src.data.config import BZZOIRO_LEAGUE_IDS, LEAGUE_COUNTRIES, LEAGUE_NAMES, REQUEST_INTERVAL
-from src.data.match_lookup import find_existing_match, get_or_create_team
 from src.data.normalize import normalize_bzzoiro
 from src.data.sources import register
-from src.db.models import League, Match, MatchStats
+from src.db.models import League, Match, MatchStats, Team
 
 logger = logging.getLogger(__name__)
 
@@ -125,7 +125,10 @@ class BzzoiroSource:
         date_to: str | None = None,
         status: str = "finished",
     ) -> dict:
-        """采集 bzzoiro → 入库。返回统计。"""
+        """采集 bzzoiro → 入库。返回统计。
+
+        注意: 本方法不控制事务(commit/rollback),由调用方通过 UnitOfWork 控制。
+        """
         result: dict = {"leagues": {}, "total_inserted": 0, "total_updated": 0, "errors": []}
 
         for code in leagues:
@@ -159,29 +162,19 @@ class BzzoiroSource:
                         all_team_names.add(nm.away_team)
 
                 if all_team_names:
-                    from sqlalchemy import select
-                    from src.db.models import Team
                     stmt = select(Team).where(Team.name.in_(all_team_names))
                     teams = (await db.execute(stmt)).scalars().all()
                     team_name_to_id = {t.name: t.id for t in teams}
 
-                # 预加载已有比赛 (league_id + home_id + away_id + date)
-                # 需要先获取球队 ID,所以分批处理
-                date_strs = set()
-                for raw in raw_events:
-                    nm = normalize_bzzoiro(raw, code)
-                    if nm and nm.date:
-                        date_strs.add(nm.date.date().isoformat() if hasattr(nm.date, "date") else str(nm.date))
-
-                if date_strs:
-                    from sqlalchemy import func
-                    stmt = (
-                        select(Match.home_team_id, Match.away_team_id, func.date(Match.match_date).label("d"))
-                        .where(Match.league_id == league.id)
-                    )
-                    rows = (await db.execute(stmt)).all()
-                    for row in rows:
-                        existing_match_keys.add((row.home_team_id, row.away_team_id, str(row.d)))
+                # 预加载已有比赛
+                from sqlalchemy import func
+                stmt = (
+                    select(Match.home_team_id, Match.away_team_id, func.date(Match.match_date).label("d"))
+                    .where(Match.league_id == league.id)
+                )
+                rows = (await db.execute(stmt)).all()
+                for row in rows:
+                    existing_match_keys.add((row.home_team_id, row.away_team_id, str(row.d)))
 
             for raw in raw_events:
                 try:
@@ -255,7 +248,6 @@ class BzzoiroSource:
                     league_r["inserted"] += 1
                 else:
                     # 已有比赛: 需要查询对象来更新
-                    # 注意: 这里为了简化仍查询一次,但只在"已有"时触发
                     from sqlalchemy import func
                     stmt = (
                         select(Match)
@@ -297,7 +289,7 @@ class BzzoiroSource:
                     if changed:
                         league_r["updated"] += 1
 
-            await db.commit()
+            # 注意: 不在此处 commit,由调用方 UnitOfWork 控制事务
             result["leagues"][code] = league_r
             result["total_inserted"] += league_r["inserted"]
             result["total_updated"] += league_r["updated"]