feat: Sprint 1 - 数据正确性整改

P2-01: 移除 lifespan create_all,改为仅验证连接
       新增 /health/ready 就绪检查
P0-04: LLM 输出严格 Pydantic 校验
       - Agent 输出越界/非法 → parse_error
       - 预测输出自动修正 1X2 与比分一致性
P0-01: injuries cutoff 修复
       - get_injuries_for_match 增加 as_of 参数
       - injuries_slice 使用 as_of 过滤 retrieved_at
       - 防止回测时未来采集数据泄漏
P1-12: 批量入库优化
       - 预加载 teams 到内存 dict
       - 预加载 existing matches 到内存 set
       - 消灭 N+1 查询

src/llm/predict.py

@@ -130,6 +130,13 @@ async def _predict_single(
 
     parsed = resp.parsed or {}
 
+    # 3.5 严格校验 LLM 输出
+    from src.llm.validation import validate_prediction_output
+    try:
+        validated = validate_prediction_output(parsed)
+    except Exception as e:
+        raise RuntimeError(f"LLM 输出校验失败: {e}")
+
     # 4. 存预测(独立 session,因为 context 用的是自己的 session)
     async with AsyncSessionLocal() as db:
         # 验证 match 存在
@@ -145,11 +152,11 @@ async def _predict_single(
             prompt_tokens=resp.prompt_tokens,
             completion_tokens=resp.completion_tokens,
             latency_ms=resp.latency_ms,
-            pred_home_goals=parsed.get("pred_home_goals"),
-            pred_away_goals=parsed.get("pred_away_goals"),
-            pred_1x2=parsed.get("1x2"),
-            confidence=parsed.get("confidence"),
-            reasoning=parsed.get("reasoning"),
+            pred_home_goals=validated.pred_home_goals,
+            pred_away_goals=validated.pred_away_goals,
+            pred_1x2=validated.pred_1x2,
+            confidence=validated.confidence,
+            reasoning=validated.reasoning,
             raw_response=resp.raw,
         )
         db.add(pred)