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/agents/orchestrator.py

@@ -183,6 +183,13 @@ async def predict_match_multi(
         if m is None:
             raise ValueError(f"match {match_id} not found")
 
+        # 严格校验终裁输出
+        from src.llm.validation import validate_prediction_output
+        try:
+            validated = validate_prediction_output(final)
+        except Exception as e:
+            raise RuntimeError(f"终裁输出校验失败: {e}")
+
         agent_weights = final.get("agent_weights")
         pred = Prediction(
             match_id=match_id,
@@ -193,11 +200,11 @@ async def predict_match_multi(
             prompt_tokens=sum(r.prompt_tokens or 0 for r in reports) + agg_prompt_tokens,
             completion_tokens=sum(r.completion_tokens or 0 for r in reports) + agg_completion_tokens,
             latency_ms=latency_ms,
-            pred_home_goals=final.get("pred_home_goals"),
-            pred_away_goals=final.get("pred_away_goals"),
-            pred_1x2=final.get("1x2"),
-            confidence=final.get("confidence"),
-            reasoning=final.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=final,
             agent_outputs=[r.to_dict() for r in reports],
         )