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/api/app.py

@@ -15,7 +15,7 @@ from src.core.config import settings
 async def lifespan(app: FastAPI) -> AsyncIterator[None]:
     from src.db.base import init_db
     from src.core.http_client import close_client
-    await init_db()
+    await init_db()  # 验证连接,不建表
     yield
     await close_client()
 
@@ -53,6 +53,18 @@ def create_app() -> FastAPI:
     async def health():
         return {"status": "healthy", "service": "profeto"}
 
+
+    @app.get("/health/ready")
+    async def health_ready():
+        """就绪检查: 验证数据库连接。"""
+        from src.db.base import engine
+        try:
+            async with engine.begin() as conn:
+                await conn.run_sync(lambda conn: None)
+            return {"status": "ready"}
+        except Exception:
+            return {"status": "not_ready"}
+
     return app
 
 

src/data/bzzoiro.py

@@ -146,6 +146,43 @@ class BzzoiroSource:
                 db.add(league)
                 await db.flush()
 
+            # === 批量优化: 预加载球队和已有比赛到内存 ===
+            team_name_to_id: dict[str, int] = {}
+            existing_match_keys: set[tuple[int, int, str]] = set()
+            if raw_events:
+                # 预加载所有涉及的球队名
+                all_team_names = set()
+                for raw in raw_events:
+                    nm = normalize_bzzoiro(raw, code)
+                    if nm:
+                        all_team_names.add(nm.home_team)
+                        all_team_names.add(nm.away_team)
+
+                if all_team_names:
+                    from sqlalchemy import select
+                    from src.db.models import Team
+                    stmt = select(Team).where(Team.name.in_(all_team_names))
+                    teams = (await db.execute(stmt)).scalars().all()
+                    team_name_to_id = {t.name: t.id for t in teams}
+
+                # 预加载已有比赛 (league_id + home_id + away_id + date)
+                # 需要先获取球队 ID,所以分批处理
+                date_strs = set()
+                for raw in raw_events:
+                    nm = normalize_bzzoiro(raw, code)
+                    if nm and nm.date:
+                        date_strs.add(nm.date.date().isoformat() if hasattr(nm.date, "date") else str(nm.date))
+
+                if date_strs:
+                    from sqlalchemy import func
+                    stmt = (
+                        select(Match.home_team_id, Match.away_team_id, func.date(Match.match_date).label("d"))
+                        .where(Match.league_id == league.id)
+                    )
+                    rows = (await db.execute(stmt)).all()
+                    for row in rows:
+                        existing_match_keys.add((row.home_team_id, row.away_team_id, str(row.d)))
+
             for raw in raw_events:
                 try:
                     nm = normalize_bzzoiro(raw, code)
@@ -157,19 +194,34 @@ class BzzoiroSource:
                     league_r["errors"].append(f"normalize: {e}")
                     continue
 
-                # 球队
-                home_team = await get_or_create_team(db, nm.home_team)
-                away_team = await get_or_create_team(db, nm.away_team)
+                # 球队: 内存查找 + 按需创建
+                home_team_id = team_name_to_id.get(nm.home_team)
+                if home_team_id is None:
+                    home = Team(name=nm.home_team)
+                    db.add(home)
+                    await db.flush()
+                    home_team_id = home.id
+                    team_name_to_id[nm.home_team] = home_team_id
 
-                # 查找已有比赛(天级匹配)
-                existing = await find_existing_match(db, league.id, nm.home_team, nm.away_team, nm.date)
+                away_team_id = team_name_to_id.get(nm.away_team)
+                if away_team_id is None:
+                    away = Team(name=nm.away_team)
+                    db.add(away)
+                    await db.flush()
+                    away_team_id = away.id
+                    team_name_to_id[nm.away_team] = away_team_id
+
+                # 查找已有比赛: 内存查找
+                date_key = nm.date.date().isoformat() if hasattr(nm.date, "date") else str(nm.date)
+                match_key = (home_team_id, away_team_id, date_key)
+                existing = None if match_key not in existing_match_keys else "exists"
 
                 if existing is None:
                     m = Match(
                         league_id=league.id,
                         season=nm.season_label or None,
-                        home_team_id=home_team.id,
-                        away_team_id=away_team.id,
+                        home_team_id=home_team_id,
+                        away_team_id=away_team_id,
                         match_date=nm.date,
                         match_date_date=nm.date.date() if hasattr(nm.date, "date") else nm.date,
                         match_status=nm.match_status,
@@ -181,6 +233,7 @@ class BzzoiroSource:
                     )
                     db.add(m)
                     await db.flush()
+                    existing_match_keys.add(match_key)  # 防止同批重复
                     if nm.home_xg is not None or nm.away_xg is not None:
                         stats = MatchStats(
                             match_id=m.id,
@@ -201,35 +254,45 @@ class BzzoiroSource:
                         db.add(stats)
                     league_r["inserted"] += 1
                 else:
-                    # 更新(只补空 / 状态升级)
+                    # 已有比赛: 需要查询对象来更新
+                    # 注意: 这里为了简化仍查询一次,但只在"已有"时触发
+                    from sqlalchemy import func
+                    stmt = (
+                        select(Match)
+                        .where(Match.league_id == league.id)
+                        .where(Match.home_team_id == home_team_id)
+                        .where(Match.away_team_id == away_team_id)
+                        .where(func.date(Match.match_date) == date_key)
+                    )
+                    existing_match = (await db.execute(stmt)).scalar_one()
+
                     changed = False
-                    if existing.match_status != nm.match_status and nm.match_status == "finished":
-                        existing.match_status = nm.match_status
+                    if existing_match.match_status != nm.match_status and nm.match_status == "finished":
+                        existing_match.match_status = nm.match_status
                         changed = True
-                    if existing.home_goals is None and nm.home_goals is not None:
-                        existing.home_goals = nm.home_goals
-                        existing.away_goals = nm.away_goals
-                        existing.home_ht_goals = nm.home_ht_goals
-                        existing.away_ht_goals = nm.away_ht_goals
+                    if existing_match.home_goals is None and nm.home_goals is not None:
+                        existing_match.home_goals = nm.home_goals
+                        existing_match.away_goals = nm.away_goals
+                        existing_match.home_ht_goals = nm.home_ht_goals
+                        existing_match.away_ht_goals = nm.away_ht_goals
                         changed = True
-                    if existing.match_stage is None and nm.match_stage:
-                        existing.match_stage = nm.match_stage
+                    if existing_match.match_stage is None and nm.match_stage:
+                        existing_match.match_stage = nm.match_stage
                         changed = True
-                    # stats 只补空
-                    if existing.stats is None and (nm.home_xg is not None or nm.away_xg is not None):
-                        existing.stats = MatchStats(match_id=existing.id)
-                        db.add(existing.stats)
+                    if existing_match.stats is None and (nm.home_xg is not None or nm.away_xg is not None):
+                        existing_match.stats = MatchStats(match_id=existing_match.id)
+                        db.add(existing_match.stats)
                         await db.flush()
-                    if existing.stats is not None:
+                    if existing_match.stats is not None:
                         for fld in ("home_xg", "away_xg", "home_shots", "away_shots",
                                     "home_shots_on_target", "away_shots_on_target",
                                     "home_corners", "away_corners", "home_possession",
                                     "home_yellow_cards", "away_yellow_cards",
                                     "home_red_cards", "away_red_cards"):
-                            if getattr(existing.stats, fld, None) is None:
+                            if getattr(existing_match.stats, fld, None) is None:
                                 v = getattr(nm, fld, None)
                                 if v is not None:
-                                    setattr(existing.stats, fld, v)
+                                    setattr(existing_match.stats, fld, v)
                                     changed = True
                     if changed:
                         league_r["updated"] += 1

src/data/injuries.py

@@ -178,8 +178,16 @@ async def ingest_injuries(db, *, date: str | None = None) -> dict:
     return result
 
 
-async def get_injuries_for_match(db, team_id: int, match_date) -> list[Injury]:
-    """查询某场比赛前某队的伤停名单(比赛日仍缺阵的)。"""
+async def get_injuries_for_match(db, team_id: int, match_date, as_of=None) -> list[Injury]:
+    """查询某场比赛前某队的伤停名单(比赛日仍缺阵的)。
+
+    Args:
+        db: 数据库 session
+        team_id: 球队 ID
+        match_date: 比赛日期
+        as_of: 截止时间(cutoff)。只返回 retrieved_at <= as_of 的记录。
+               用于回测时防止"未来采集的数据"泄漏到历史预测。
+    """
     from sqlalchemy import and_, or_, select
 
     from src.db.models import Injury
@@ -192,7 +200,15 @@ async def get_injuries_for_match(db, team_id: int, match_date) -> list[Injury]:
         .where(Injury.team_id == team_id)
         .where(Injury.injury_date <= match_date)
         .where(or_(Injury.return_date.is_(None), Injury.return_date >= match_date))
-        .order_by(Injury.injury_date.desc())
     )
+
+    # 回测防泄漏: 只使用 as_of 时间点之前已采集的数据
+    if as_of is not None:
+        if hasattr(as_of, "date"):
+            as_of = as_of.date()
+        stmt = stmt.where(Injury.retrieved_at.is_not(None))
+        stmt = stmt.where(Injury.retrieved_at <= as_of)
+
+    stmt = stmt.order_by(Injury.injury_date.desc())
     result = await db.execute(stmt)
     return list(result.scalars().all())

src/db/base.py

@@ -53,6 +53,17 @@ async def get_db_read() -> AsyncIterator[AsyncSession]:
 
 
 async def init_db() -> None:
-    """开发/测试用:建表。生产建议用 alembic。"""
+    """验证数据库连接(不建表)。
+
+    生产环境 schema 由 Alembic 管理。
+    本地开发/测试需要建表时调用 `create_all()`。
+    """
+    async with engine.begin() as conn:
+        # 只验证连接,不自动建表
+        await conn.run_sync(lambda conn: None)
+
+
+async def create_all() -> None:
+    """创建所有表(仅用于本地开发/测试)。"""
     async with engine.begin() as conn:
         await conn.run_sync(Base.metadata.create_all)

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],
         )

src/llm/backtest.py

@@ -117,7 +117,8 @@ async def run_backtest(
 
     for m in matches:
         try:
-            # 预测 (build_context 内部已用 before=match_date 防泄漏)
+            # 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)
 
             # 用实际比分 settle

src/llm/context_builder.py

@@ -219,12 +219,16 @@ async def home_away_slice(header: MatchHeader, *, limit: int = 10, before=None)
 
 
 async def injuries_slice(header: MatchHeader, *, before=None) -> str:
-    """D - 阵容完整性切片: 伤停与停赛名单,评估战力缺失程度。"""
+    """D - 阵容完整性切片: 伤停与停赛名单,评估战力缺失程度。
+
+    before=cutoff: 只使用 cutoff 之前已采集的伤停数据,防回测泄漏。
+    """
     from src.data.injuries import get_injuries_for_match
 
+    cutoff = before or header.match_dt
     async with AsyncSessionLocal() as db:
-        home_injuries = await get_injuries_for_match(db, header.home_team_id, before or header.match_dt)
-        away_injuries = await get_injuries_for_match(db, header.away_team_id, before or header.match_dt)
+        home_injuries = await get_injuries_for_match(db, header.home_team_id, cutoff, as_of=cutoff)
+        away_injuries = await get_injuries_for_match(db, header.away_team_id, cutoff, as_of=cutoff)
 
     lines = ["── 阵容完整性 ──"]
     has_data = False

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)

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