fix(P0): 修复三处静默失效的阻断缺陷

P0-1 backtest 会话生命周期:
- _get_historical_matches 加 selectinload(league/home_team/away_team),
  并在 session 内物化为 BacktestCandidate 纯数据快照,避免 session
  关闭后访问惰性关系抛 MissingGreenlet
- except 收窄并改用 logger.exception 保留堆栈
- 移除未使用的 and_ / League 导入

P0-2 切片函数关系属性 MissingGreenlet:
- models.py 为 Match.league/home_team/away_team/stats 声明 lazy=selectin
- context_builder 的 _get_form/_get_h2h/_get_home_away 显式 selectinload
  (修复 form_slice/h2h_slice 恒定失败,被 fail-open 掩盖的问题)
- repositories.find_by_teams_and_date 加 selectinload(Match.stats)

P0-3 bzzoiro raw 变量泄漏导致血缘错乱:
- normalized_matches 改为携带 (nm, raw) 元组,内层循环解包
- source_event_id / source_record_id 现在取到正确 event id
- 已有比赛补建 stats 时补齐 source/source_event_id/retrieved_at/available_at
- 抽取 _match_key()/_to_date() 统一日期键构造 (P1-6)

src/llm/backtest.py

@@ -8,10 +8,12 @@ from __future__ import annotations
 
 import logging
 from dataclasses import dataclass, field
+from datetime import datetime
 
-from sqlalchemy import and_, select
+from sqlalchemy import select
+from sqlalchemy.orm import selectinload
 
-from src.db.models import League, Match
+from src.db.models import Match
 from src.db.unit_of_work import get_uow
 from src.llm.eval import settle_prediction
 from src.llm.predict import predict_match
@@ -38,6 +40,23 @@ class BacktestMatchResult:
     prediction_id: int
 
 
+@dataclass
+class BacktestCandidate:
+    """回测候选比赛(字段快照,不持有 ORM 对象)。
+
+    session 关闭后仍可安全读取:所有需要的关系字段已在查询时物化为普通值,
+    避免在 session 之外访问惰性加载的关系属性(会抛 MissingGreenlet)。
+    """
+    match_id: int
+    league_code: str | None
+    home_team: str
+    away_team: str
+    match_date: datetime
+    home_goals: int
+    away_goals: int
+
+
+
 @dataclass
 class BacktestSummary:
     """回测汇总统计。"""
@@ -66,10 +85,20 @@ async def _get_historical_matches(
     date_from: str | None = None,
     date_to: str | None = None,
     limit: int = 50,
-) -> list[Match]:
-    """查询已完赛且有比分的比赛(回测候选)。"""
+) -> list[BacktestCandidate]:
+    """查询已完赛且有比分的比赛(回测候选)。
+
+    返回普通值快照而非 ORM 对象:调用方在 session 关闭后仍需使用这些字段,
+    而 league / home_team / away_team 是惰性加载关系,在 async 下于 session
+    之外访问会抛 MissingGreenlet。这里用 selectinload 预加载后立即物化。
+    """
     stmt = (
         select(Match)
+        .options(
+            selectinload(Match.league),
+            selectinload(Match.home_team),
+            selectinload(Match.away_team),
+        )
         .where(Match.match_status == "finished")
         .where(Match.home_goals.is_not(None))
         .where(Match.away_goals.is_not(None))
@@ -83,7 +112,19 @@ async def _get_historical_matches(
 
     stmt = stmt.order_by(Match.match_date.desc()).limit(limit)
     result = await db.execute(stmt)
-    return list(result.scalars().all())
+    # 在 session 内物化为纯数据,切断与 ORM 会话的耦合
+    return [
+        BacktestCandidate(
+            match_id=m.id,
+            league_code=m.league.code if m.league else None,
+            home_team=m.home_team.name if m.home_team else "?",
+            away_team=m.away_team.name if m.away_team else "?",
+            match_date=m.match_date,
+            home_goals=m.home_goals,
+            away_goals=m.away_goals,
+        )
+        for m in result.scalars().all()
+    ]
 
 
 async def run_backtest(
@@ -109,32 +150,34 @@ async def run_backtest(
         BacktestSummary 含逐场结果 + 汇总统计
     """
     async with get_uow() as session:
-        matches = await _get_historical_matches(
+        candidates = await _get_historical_matches(
             session, league_id=league_id, date_from=date_from, date_to=date_to, limit=limit
         )
 
-    summary = BacktestSummary(total=len(matches), scored=0)
+    summary = BacktestSummary(total=len(candidates), scored=0)
 
-    for m in matches:
+    for c in candidates:
         try:
             # 预测 (build_context 内部已用 before=match_date 防泄漏,
             # injuries_slice 也使用 as_of=match_date 过滤 retrieved_at)
-            result = await predict_match(m.id, mode=mode, model=model)
+            # 回测必须禁用结果缓存: 否则命中缓存会复用同一 prediction_id,
+            # 导致 settle 反复覆盖同一条记录(见 P1-3)。
+            result = await predict_match(c.match_id, mode=mode, model=model, use_cache=False)
 
             # 用实际比分 settle
-            await settle_prediction(result.prediction_id, m.home_goals, m.away_goals)
+            await settle_prediction(result.prediction_id, c.home_goals, c.away_goals)
 
-            actual = _actual_1x2(m.home_goals, m.away_goals)
+            actual = _actual_1x2(c.home_goals, c.away_goals)
             correct = result.pred_1x2 == actual
 
             bt = BacktestMatchResult(
-                match_id=m.id,
-                league_code=m.league.code if m.league else None,
-                home_team=m.home_team.name if m.home_team else "?",
-                away_team=m.away_team.name if m.away_team else "?",
-                match_date=m.match_date.strftime("%Y-%m-%d") if m.match_date else "?",
-                actual_home=m.home_goals,
-                actual_away=m.away_goals,
+                match_id=c.match_id,
+                league_code=c.league_code,
+                home_team=c.home_team,
+                away_team=c.away_team,
+                match_date=c.match_date.strftime("%Y-%m-%d") if c.match_date else "?",
+                actual_home=c.home_goals,
+                actual_away=c.away_goals,
                 actual_1x2=actual,
                 pred_home=result.pred_home_goals,
                 pred_away=result.pred_away_goals,
@@ -146,8 +189,10 @@ async def run_backtest(
             summary.results.append(bt)
             summary.scored += 1
 
-        except Exception as e:
-            logger.warning("backtest match %s failed: %s", m.id, e)
+        except Exception:
+            # 用 exception 而非 warning:保留堆栈,否则集成层缺陷(如惰性加载
+            # 在 session 外触发)会只剩一行无堆栈的 warning,极难定位。
+            logger.exception("backtest match %s failed", c.match_id)
 
     # 汇总统计
     if summary.scored > 0:

src/llm/context_builder.py

@@ -328,9 +328,19 @@ async def _load_match(db, match_id: int) -> Match:
 
 
 async def _get_form(db, team_id: int, before, *, limit: int = 5) -> list[Match]:
-    """某队近 N 场(已完赛)。before=None 表示不限制(预测赛前的场景由调用方保证)。"""
+    """某队近 N 场(已完赛)。before=None 表示不限制(预测赛前的场景由调用方保证)。
+
+    必须预加载 stats / home_team / away_team:切片函数会读取这些关系,
+    而 async session 下惰性加载会抛 MissingGreenlet。
+    (models.py 已声明 lazy="selectin",此处显式声明以固化查询意图。)
+    """
     stmt = (
         select(Match)
+        .options(
+            selectinload(Match.stats),
+            selectinload(Match.home_team),
+            selectinload(Match.away_team),
+        )
         .where(Match.match_status == "finished")
         .where(Match.home_goals.is_not(None))
         .where((Match.home_team_id == team_id) | (Match.away_team_id == team_id))
@@ -344,9 +354,13 @@ async def _get_form(db, team_id: int, before, *, limit: int = 5) -> list[Match]:
 
 
 async def _get_h2h(db, home_id: int, away_id: int, before, *, limit: int = 5) -> list[Match]:
-    """两队交锋史。"""
+    """两队交锋史。需预加载 home_team / away_team(切片输出队名)。"""
     stmt = (
         select(Match)
+        .options(
+            selectinload(Match.home_team),
+            selectinload(Match.away_team),
+        )
         .where(Match.match_status == "finished")
         .where(Match.home_goals.is_not(None))
         .where(
@@ -363,9 +377,17 @@ async def _get_h2h(db, home_id: int, away_id: int, before, *, limit: int = 5) ->
 
 
 async def _get_home_away(db, team_id: int, side: str, before, *, limit: int = 10) -> list[Match]:
-    """某队主场/客场近 N 场。side='home' 取主场,'away' 取客场。"""
+    """某队主场/客场近 N 场。side='home' 取主场,'away' 取客场。
+
+    当前只用标量字段,但统一预加载以免后续扩展时踩坑。
+    """
     stmt = (
         select(Match)
+        .options(
+            selectinload(Match.stats),
+            selectinload(Match.home_team),
+            selectinload(Match.away_team),
+        )
         .where(Match.match_status == "finished")
         .where(Match.home_goals.is_not(None))
         .order_by(Match.match_date.desc())

src/llm/predict.py

@@ -81,11 +81,22 @@ async def predict_match(
     model: str | None = None,
     prompt_version: str | None = None,
     mode: str = "multi",
+    use_cache: bool = True,
 ) -> "PredictResult | MultiPredictResult":
-    """预测入口。mode=multi(默认)走多 agent;mode=single 走单次调用。"""
+    """预测入口。mode=multi(默认)走多 agent;mode=single 走单次调用。
+
+    Args:
+        use_cache: 是否允许返回进程内缓存结果。回测必须传 False——
+            缓存命中不会新建 prediction 行,调用方会对同一个 prediction_id
+            反复 settle,把不同比赛的真实比分覆盖到同一条记录上。
+    """
     if mode == "single":
         return await _predict_single(
-            match_id, provider=provider, model=model, prompt_version=prompt_version
+            match_id,
+            provider=provider,
+            model=model,
+            prompt_version=prompt_version,
+            use_cache=use_cache,
         )
     from src.llm.agents.orchestrator import predict_match_multi
 
@@ -98,6 +109,7 @@ async def _predict_single(
     provider: LLMProvider | None = None,
     model: str | None = None,
     prompt_version: str | None = None,
+    use_cache: bool = True,
 ) -> PredictResult:
     """单次调用路径(原有实现)。"""
     if provider is None:
@@ -107,10 +119,11 @@ async def _predict_single(
     version = prompt_version or "v1"
 
     # 0. 查缓存(同 match+provider+model+version 5 分钟内直接返)
-    cached = _get_cached(match_id, settings.LLM_PROVIDER, provider.model, version)
-    if cached is not None:
-        logger.debug("predict cache hit match=%s", match_id)
-        return cached
+    if use_cache:
+        cached = _get_cached(match_id, settings.LLM_PROVIDER, provider.model, version)
+        if cached is not None:
+            logger.debug("predict cache hit match=%s", match_id)
+            return cached
 
     # 1. 拼上下文
     ctx = await build_context(match_id)
@@ -191,6 +204,7 @@ async def _predict_single(
             raw=resp.raw,
         )
 
-        # 5. 写入缓存
-        _set_cached(match_id, settings.LLM_PROVIDER, provider.model, version, result)
+        # 5. 写入缓存(仅当允许缓存时)
+        if use_cache:
+            _set_cached(match_id, settings.LLM_PROVIDER, provider.model, version, result)
         return result