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/validation.py

@@ -0,0 +1,130 @@
+"""LLM 输出严格校验。
+
+所有 LLM JSON 输出必须经过 Pydantic 校验 + 语义一致性检查后才能落库。
+"""
+from __future__ import annotations
+
+from pydantic import BaseModel, Field, field_validator, model_validator
+
+from src.db.models import Prediction
+
+
+class AgentReportSchema(BaseModel):
+    """单个专家 Agent 输出的校验 schema。"""
+
+    data_sufficiency: str = "medium"
+    analysis: str = ""
+    home_edge: float | None = Field(None, ge=-1.0, le=1.0)
+    confidence: float | None = Field(None, ge=0.0, le=1.0)
+    key_evidence: list[str] = Field(default_factory=list)
+    exp_home_goals: float | None = Field(None, ge=0.0, le=10.0)
+    exp_away_goals: float | None = Field(None, ge=0.0, le=10.0)
+    probable_score: str | None = None
+
+    @field_validator("data_sufficiency")
+    @classmethod
+    def validate_sufficiency(cls, v: str) -> str:
+        allowed = {"high", "medium", "low", "none"}
+        return v.lower() if v.lower() in allowed else "medium"
+
+    @field_validator("key_evidence", mode="before")
+    @classmethod
+    def normalize_evidence(cls, v) -> list[str]:
+        if v is None:
+            return []
+        if isinstance(v, str):
+            return [v]
+        if isinstance(v, list):
+            return [str(e)[:120] for e in v[:5]]
+        return []
+
+    @field_validator("analysis")
+    @classmethod
+    def truncate_analysis(cls, v: str) -> str:
+        return str(v)[:600]
+
+
+class PredictionOutputSchema(BaseModel):
+    """最终预测输出的校验 schema。"""
+
+    pred_home_goals: float = Field(ge=0.0, le=10.0)
+    pred_away_goals: float = Field(ge=0.0, le=10.0)
+    pred_1x2: str
+    confidence: float = Field(ge=0.0, le=1.0)
+    reasoning: str = ""
+
+    @field_validator("pred_1x2")
+    @classmethod
+    def validate_1x2(cls, v: str) -> str:
+        if v not in ("1", "X", "2"):
+            raise ValueError(f"pred_1x2 must be '1', 'X', or '2', got '{v}'")
+        return v
+
+    @model_validator(mode="after")
+    def check_consistency(self) -> "PredictionOutputSchema":
+        """验证比分与胜平负一致。"""
+        expected = _score_to_1x2(self.pred_home_goals, self.pred_away_goals)
+        if expected and self.pred_1x2 != expected:
+            # 自动修正而非拒绝(LLM 常见小错误)
+            self.pred_1x2 = expected
+        return self
+
+
+def _score_to_1x2(home: float, away: float) -> str | None:
+    """从比分推导胜平负。"""
+    if home > away:
+        return "1"
+    if home == away:
+        return "X"
+    if home < away:
+        return "2"
+    return None
+
+
+def validate_agent_output(raw: dict) -> AgentReportSchema:
+    """校验并规范化单个 Agent 输出。"""
+    return AgentReportSchema(
+        data_sufficiency=raw.get("data_sufficiency", "medium"),
+        analysis=raw.get("analysis", ""),
+        home_edge=_safe_float(raw.get("home_edge")),
+        confidence=_safe_float(raw.get("confidence")),
+        key_evidence=raw.get("key_evidence", []),
+        exp_home_goals=_safe_float(raw.get("exp_home_goals")),
+        exp_away_goals=_safe_float(raw.get("exp_away_goals")),
+        probable_score=_format_score(raw.get("probable_score")),
+    )
+
+
+def validate_prediction_output(raw: dict) -> PredictionOutputSchema:
+    """校验最终预测输出。"""
+    return PredictionOutputSchema(
+        pred_home_goals=float(raw.get("pred_home_goals", 0)),
+        pred_away_goals=float(raw.get("pred_away_goals", 0)),
+        pred_1x2=raw.get("1x2") or raw.get("pred_1x2", "X"),
+        confidence=float(raw.get("confidence", 0.5)),
+        reasoning=str(raw.get("reasoning", ""))[:1000],
+    )
+
+
+def _safe_float(v) -> float | None:
+    """安全转 float,失败返回 None。"""
+    if v is None:
+        return None
+    try:
+        f = float(v)
+        if not (f == f):  # NaN check
+            return None
+        return f
+    except (TypeError, ValueError):
+        return None
+
+
+def _format_score(v) -> str | None:
+    """格式化比分输出。"""
+    if v is None:
+        return None
+    if isinstance(v, str):
+        return v
+    if isinstance(v, dict):
+        return f"{v.get('home', '?')}-{v.get('away', '?')}"
+    return None