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/base.py

@@ -99,36 +99,34 @@ def _stub_no_data(agent: str) -> AgentReport:
 
 
 def _parse_report(agent: str, parsed: dict, resp: LLMResponse, model: str) -> AgentReport:
-    """把 LLM JSON 输出解析为 AgentReport,字段宽容处理。"""
-    def _f(v, default=None):
-        try:
-            return float(v) if v is not None else default
-        except (TypeError, ValueError):
-            return default
+    """把 LLM JSON 输出解析为 AgentReport,经过严格校验。"""
+    from src.llm.validation import validate_agent_output
 
-    suff = str(parsed.get("data_sufficiency", "medium")).lower()
-    if suff not in ("high", "medium", "low", "none"):
-        suff = "medium"
-
-    evidence = parsed.get("key_evidence") or []
-    if isinstance(evidence, str):
-        evidence = [evidence]
-
-    score = parsed.get("probable_score")
-    if isinstance(score, dict):
-        score = f"{score.get('home', '?')}-{score.get('away', '?')}"
+    try:
+        validated = validate_agent_output(parsed)
+    except Exception as e:
+        # 校验失败 → 返回 parse_error 而非静默降级
+        return AgentReport(
+            agent=agent,
+            status="parse_error",
+            analysis=f"输出校验失败: {e}",
+            model=model,
+            latency_ms=resp.latency_ms,
+            prompt_tokens=resp.prompt_tokens,
+            completion_tokens=resp.completion_tokens,
+        )
 
     return AgentReport(
         agent=agent,
         status="ok",
-        data_sufficiency=suff,
-        analysis=str(parsed.get("analysis", ""))[:600],
-        home_edge=_f(parsed.get("home_edge")),
-        confidence=_f(parsed.get("confidence")),
-        key_evidence=[str(e)[:120] for e in evidence[:5]],
-        exp_home_goals=_f(parsed.get("exp_home_goals")),
-        exp_away_goals=_f(parsed.get("exp_away_goals")),
-        probable_score=score if isinstance(score, str) else None,
+        data_sufficiency=validated.data_sufficiency,
+        analysis=validated.analysis,
+        home_edge=validated.home_edge,
+        confidence=validated.confidence,
+        key_evidence=validated.key_evidence,
+        exp_home_goals=validated.exp_home_goals,
+        exp_away_goals=validated.exp_away_goals,
+        probable_score=validated.probable_score,
         model=model,
         latency_ms=resp.latency_ms,
         prompt_tokens=resp.prompt_tokens,

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],
         )