fix:批量修复了一些问题

src/api/routes/admin_settings.py

@@ -7,7 +7,7 @@ from __future__ import annotations
 
 import logging
 import time
-from datetime import date, datetime, timezone
+from datetime import date, datetime, timedelta, timezone
 
 from fastapi import APIRouter, Depends, HTTPException, Query
 from pydantic import BaseModel
@@ -28,7 +28,7 @@ from src.core.runtime_config import (
     set_runtime_value,
 )
 from src.db.base import AsyncSession, get_db_read
-from src.db.models import Injury, MatchStats
+from src.db.models import Injury, Match, MatchStats
 
 logger = logging.getLogger(__name__)
 
@@ -317,3 +317,123 @@ async def test_datasource(name: str):
         "https://v3.football.api-sports.io/status",
         headers={"x-apisports-key": api_key},
     )
+
+
+# ── 数据源健康/最近采集状态(只读,不触发采集) ──────────────────────
+
+
+@router.get("/ingest/status")
+async def ingest_status(db: AsyncSession = Depends(get_db_read)):
+    """各数据源采集健康概览(只读,不触发任何采集)。
+
+    返回尽量可得的信息;基于现有表近似的数据会标明 approximation。
+    失败追踪目前依赖系统日志缓冲,无专用采集失败表。
+    """
+    # ── bzzoiro: 落库目标是 matches 表,无专用采集时间戳 ──
+    # 近似:以 matches 表最大 match_date(已覆盖的最远比赛日) 与 created_at 作为参考
+    bzzoiro_key = await get_runtime_value("BZZOIRO_KEY")
+    bzzoiro_base = await get_runtime_value("BZZOIRO_BASE")
+    row = (
+        await db.execute(
+            select(
+                func.count().label("cnt"),
+                func.max(Match.match_date).label("latest_match_date"),
+                func.max(Match.created_at).label("latest_row_at"),
+            ).where(Match.match_status == "finished")
+        )
+    ).one()
+    bzzoiro = {
+        "name": "bzzoiro",
+        "label": "Bzzoiro",
+        "key_configured": bool(bzzoiro_key),
+        "base_url": (bzzoiro_base.rstrip("/") if bzzoiro_base else None) or settings.BZZOIRO_BASE,
+        "reachable": None,  # 不主动探测
+        "last_success_at": row.latest_row_at.isoformat() if row.latest_row_at else None,
+        "latest_match_date": row.latest_match_date.isoformat() if row.latest_match_date else None,
+        "recent_count": row.cnt or 0,
+        "note": "approx:基于 matches.finished 表,last_success_at 为行写入时间而非精确采集完成时间",
+        "last_failure": _last_failure_log("bzzoiro"),
+    }
+
+    # ── understat: 落库到 match_stats(source=understat),有精确 retrieved_at ──
+    row = (
+        await db.execute(
+            select(
+                func.count().label("cnt"),
+                func.max(MatchStats.retrieved_at).label("latest_retrieved"),
+            ).where(MatchStats.source == "understat")
+        )
+    ).one()
+    understat = {
+        "name": "understat",
+        "label": "Understat",
+        "key_configured": True,  # 无需 Key
+        "reachable": None,
+        "last_success_at": row.latest_retrieved.isoformat() if row.latest_retrieved else None,
+        "recent_count": row.cnt or 0,
+        "note": "基于 match_stats.source=understat 的 retrieved_at",
+        "last_failure": _last_failure_log("understat"),
+    }
+
+    # ── injuries: 落库到 injuries 表,有精确 retrieved_at;区分 Key/无数据/有数据 ──
+    api_key = await get_runtime_value("API_FOOTBALL_KEY")
+    row = (
+        await db.execute(
+            select(
+                func.count().label("cnt"),
+                func.max(Injury.retrieved_at).label("latest_retrieved"),
+            )
+        )
+    ).one()
+    if not api_key:
+        injuries_status, injuries_note = "key_not_configured", "API_FOOTBALL_KEY 未配置"
+    elif not row.cnt:
+        injuries_status, injuries_note = "no_data", "本地无伤停数据,请先采集"
+    else:
+        injuries_status, injuries_note = "has_data", f"共 {row.cnt} 条伤停记录"
+    injuries = {
+        "name": "injuries",
+        "label": "Injuries (API-Football)",
+        "key_configured": bool(api_key),
+        "reachable": None,
+        "status": injuries_status,
+        "last_success_at": row.latest_retrieved.isoformat() if row.latest_retrieved else None,
+        "recent_count": row.cnt or 0,
+        "note": injuries_note,
+        "last_failure": _last_failure_log("injuries"),
+    }
+
+    return {"sources": [bzzoiro, understat, injuries]}
+
+
+def _last_failure_log(source: str) -> dict | None:
+    """从系统日志缓冲中查找某数据源的最近一次错误(仅作参考,非专用失败表)。"""
+    entries = get_entries(min_level="ERROR", keyword=source, limit=5)
+    if not entries:
+        return None
+    e = entries[0]
+    return {
+        "at": datetime.fromtimestamp(e["ts"]).isoformat(),
+        "logger": e["logger"],
+        "detail": e["message"][:200],
+        "note": "approx:来自内存日志缓冲,非专用采集失败表;进程重启后清零",
+    }
+
+
+@router.get("/stats")
+async def admin_stats(db: AsyncSession = Depends(get_db_read)):
+    """管理区统计(只读):最近预测次数。轻量聚合,无 LLM 调用。"""
+    from sqlalchemy import func, text
+    from src.db.models import Prediction
+    day_ago = datetime.now(timezone.utc) - timedelta(days=1)
+    week_ago = datetime.now(timezone.utc) - timedelta(days=7)
+    r = (
+        await db.execute(
+            select(
+                func.count().label("total"),
+                func.count().filter(Prediction.created_at >= day_ago).label("last_24h"),
+                func.count().filter(Prediction.created_at >= week_ago).label("last_7d"),
+            )
+        )
+    ).one()
+    return {"predictions": {"total": r.total, "last_24h": r.last_24h, "last_7d": r.last_7d}}

src/api/routes/backtest.py

@@ -28,13 +28,16 @@ async def backtest(req: BacktestRequest):
     """对历史比赛运行回测。
 
     该接口会对每场已完赛比赛各发起一次 LLM 预测,成本高 —— 因此需要
-    `X-API-Key` 鉴权(见审查报告 P2-7)。
+    管理员鉴权(require_admin)。
 
     对每场已完赛比赛:
-      1. 用比赛之前的数据构建上下文 (防未来信息泄漏)
-      2. 调 LLM 预测
-      3. 用实际比分回填
+      1. 用比赛之前的数据构建上下文 (防未来信息泄漏,cutoff=match_date-1天)
+      2. 调 LLM 预测(强制 use_cache=False,避免缓存命中导致反复 settle 同一行)
+      3. 用实际比分回填(settle)
       4. 统计准确率 / RMSE / 校准度
+
+    限流:单请求上限 200 场(默认 20),避免一次打爆 LLM 额度。
+    回测写入 run_type='backtest',与实盘(live)互不覆盖(唯一键含 run_type)。
     """
     try:
         summary = await run_backtest(
@@ -53,10 +56,11 @@ async def backtest(req: BacktestRequest):
         "summary": {
             "total": summary.total,
             "scored": summary.scored,
+            "success": summary.success,
+            "degraded": summary.degraded,
             "accuracy_1x2": summary.accuracy_1x2,
             "avg_score_rmse": summary.avg_score_rmse,
             "avg_subjective_confidence": summary.avg_subjective_confidence,
-            "calibration": summary.calibration,
         },
         "results": [
             {

src/api/routes/eval.py

@@ -19,13 +19,19 @@ router = APIRouter(prefix="/api/v1", tags=["eval"])
 async def settle(req: SettleRequest, db: AsyncSession = Depends(get_db)):
     """回填实际结果。
 
-    status 为 degraded/failed 的预测无法结算。
+    status 为 degraded/failed 的预测无法结算(返回 400);
+    记录不存在返回 404。
     """
     try:
         pred = await settle_prediction(req.prediction_id, req.home_goals, req.away_goals)
         return {"id": pred.id, "settled": pred.settled}
     except ValueError as e:
-        logger.warning("settle failed: %s", e)
+        msg = str(e)
+        # degraded/failed 拒绝:明确的 400,而非与"未找到"混为一谈
+        if "无法结算" in msg:
+            logger.warning("settle rejected: %s", msg)
+            raise HTTPException(400, msg)
+        logger.warning("settle failed: %s", msg)
         raise HTTPException(404, "预测记录不存在")
     except Exception as e:
         logger.exception("settle error")

src/api/routes/ingest.py

@@ -73,6 +73,7 @@ async def _run_bzzoiro(leagues: list[str], date_from: str | None, date_to: str |
             logger.warning("bzzoiro 部分联赛存在错误: %s", sample)
         if merged["errors"]:
             logger.warning("bzzoiro 采集错误 %d 条: %s", len(merged["errors"]), merged["errors"][:3])
+        logger.debug("bzzoiro 采集明细: leagues=%s", list(merged["leagues"].keys()))
     except Exception:
         logger.exception("bzzoiro 采集任务失败")
 

src/api/routes/matches.py

@@ -4,13 +4,13 @@ from __future__ import annotations
 from datetime import datetime, timedelta
 
 from fastapi import APIRouter, Depends, HTTPException, Query
-from sqlalchemy import select
+from sqlalchemy import or_, select
 from sqlalchemy.orm import selectinload
 
 from src.api.deps import require_admin
-from src.api.schemas import MatchListOut, MatchOut
+from src.api.schemas import MatchListOut, MatchOut, PredictionOut
 from src.db.base import AsyncSession, get_db_read
-from src.db.models import League, Match
+from src.db.models import League, Match, Prediction
 
 router = APIRouter(prefix="/api/v1", tags=["data"])
 
@@ -114,12 +114,26 @@ async def list_matches(
 async def get_match(match_id: int, db: AsyncSession = Depends(get_db_read)):
     stmt = (
         select(Match)
-        .options(selectinload(Match.league), selectinload(Match.home_team), selectinload(Match.away_team))
+        .options(
+            selectinload(Match.league),
+            selectinload(Match.home_team),
+            selectinload(Match.away_team),
+            selectinload(Match.stats),
+        )
         .where(Match.id == match_id)
     )
     m = (await db.execute(stmt)).scalar_one_or_none()
     if m is None:
         raise HTTPException(404, "match not found")
+    # 最近预测(倒序,最多 5 条)——复用 PredictionOut 结构,只读,不触发 LLM
+    preds = (
+        await db.execute(
+            select(Prediction)
+            .where(Prediction.match_id == match_id)
+            .order_by(Prediction.created_at.desc())
+            .limit(5)
+        )
+    ).scalars().all()
     return MatchOut(
         id=m.id,
         league_code=m.league.code if m.league else None,
@@ -135,4 +149,94 @@ async def get_match(match_id: int, db: AsyncSession = Depends(get_db_read)):
         match_stage=m.match_stage,
         home_xg=m.stats.home_xg if m.stats else None,
         away_xg=m.stats.away_xg if m.stats else None,
+        recent_predictions=[
+            PredictionOut(
+                id=p.id, match_id=p.match_id, provider=p.provider, model=p.model,
+                prompt_version=p.prompt_version, mode=p.mode or "single",
+                pred_home_goals=p.pred_home_goals, pred_away_goals=p.pred_away_goals,
+                alt_pred_home_goals=p.alt_pred_home_goals, alt_pred_away_goals=p.alt_pred_away_goals,
+                pred_1x2=p.pred_1x2, subjective_confidence=p.subjective_confidence,
+                reasoning=p.reasoning, status=p.status or "success",
+                agent_outputs=p.agent_outputs, agent_weights=p.agent_weights,
+                created_at=p.created_at, actual_home_goals=p.actual_home_goals,
+                actual_away_goals=p.actual_away_goals, settled=p.settled,
+            )
+            for p in preds
+        ],
     )
+
+
+@router.get("/matches/{match_id}/context", dependencies=[Depends(require_admin)])
+async def match_context(match_id: int, db: AsyncSession = Depends(get_db_read)):
+    """比赛上下文(只读,不触发 LLM):双方近况 + 历史交锋。
+
+    全部基于现有数据聚合:
+      - recent_home / recent客队:该队最近 5 场已完赛(进球/结果)
+      - h2h:双方最近 5 次交手
+    若数据不足,对应列表为空(前端展示空态)。
+    """
+    m = (
+        await db.execute(
+            select(Match)
+            .options(selectinload(Match.home_team), selectinload(Match.away_team))
+            .where(Match.id == match_id)
+        )
+    ).scalar_one_or_none()
+    if m is None:
+        raise HTTPException(404, "match not found")
+    home_id = m.home_team_id
+    away_id = m.away_team_id
+
+    def _row_to_dict(row):
+        return {
+            "match_date": row.match_date.isoformat() if row.match_date else None,
+            "home_team": row.home_team.name_zh or row.home_team.name if row.home_team else None,
+            "away_team": row.away_team.name_zh or row.away_team.name if row.away_team else None,
+            "home_goals": row.home_goals,
+            "away_goals": row.away_goals,
+        }
+
+    # 主队近况(已完赛,含主/客场)
+    home_recent = (
+        await db.execute(
+            select(Match)
+            .where(Match.match_status == "finished", Match.home_team_id == home_id)
+            .order_by(Match.match_date.desc())
+            .limit(5)
+            .options(selectinload(Match.home_team), selectinload(Match.away_team))
+        )
+    ).scalars().all()
+
+    # 客队近况
+    away_recent = (
+        await db.execute(
+            select(Match)
+            .where(Match.match_status == "finished", Match.away_team_id == away_id)
+            .order_by(Match.match_date.desc())
+            .limit(5)
+            .options(selectinload(Match.home_team), selectinload(Match.away_team))
+        )
+    ).scalars().all()
+
+    # 历史交锋(双方已完赛)
+    h2h = (
+        await db.execute(
+            select(Match)
+            .where(
+                Match.match_status == "finished",
+                or_(
+                    (Match.home_team_id == home_id) & (Match.away_team_id == away_id),
+                    (Match.home_team_id == away_id) & (Match.away_team_id == home_id),
+                ),
+            )
+            .order_by(Match.match_date.desc())
+            .limit(5)
+            .options(selectinload(Match.home_team), selectinload(Match.away_team))
+        )
+    ).scalars().all()
+
+    return {
+        "home_recent": [_row_to_dict(r) for r in home_recent],
+        "away_recent": [_row_to_dict(r) for r in away_recent],
+        "h2h": [_row_to_dict(r) for r in h2h],
+    }

src/api/routes/predict.py

@@ -42,7 +42,7 @@ async def predict(req: PredictRequest):
         if m.match_status == "finished":
             raise HTTPException(400, "该比赛已完赛,不再支持预测")
 
-    # 2. LLM 调用(不持有任何 DB 连接)
+    # 2. 预测调用(不持有任何 DB 连接)
     try:
         result = await predict_match(
             req.match_id,
@@ -63,32 +63,77 @@ async def predict(req: PredictRequest):
         logger.exception("predict unexpected error")
         raise HTTPException(500, "预测失败,请查看服务器日志")
 
+    # baseline 模式:结果已是 dict,需独立落库(prediction_id)
+    if req.mode == "baseline":
+        prediction_id = await _persist_baseline(req.match_id, result)
+    else:
+        prediction_id = result.prediction_id
+
     # 3. 结果映射(无 DB 访问)
     logger.info(
         "预测完成 match=%s mode=%s pred=%s:%s (%s)",
-        req.match_id, req.mode, result.pred_home_goals, result.pred_away_goals, result.pred_1x2,
+        req.match_id, req.mode,
+        result.get("pred_home_goals") if isinstance(result, dict) else result.pred_home_goals,
+        result.get("pred_away_goals") if isinstance(result, dict) else result.pred_away_goals,
+        result.get("pred_1x2") if isinstance(result, dict) else result.pred_1x2,
     )
 
+    result_dict = result if isinstance(result, dict) else None
+
     return PredictOut(
-        prediction_id=result.prediction_id,
-        provider=result.provider,
-        model=result.model,
-        prompt_version=getattr(result, "prompt_version", None),
-        mode=getattr(result, "mode", "single"),
-        pred_home_goals=result.pred_home_goals,
-        pred_away_goals=result.pred_away_goals,
-        alt_pred_home_goals=result.alt_pred_home_goals,
-        alt_pred_away_goals=result.alt_pred_away_goals,
-        pred_1x2=result.pred_1x2,
-        subjective_confidence=result.subjective_confidence,
-        reasoning=result.reasoning,
-        agent_outputs=getattr(result, "agent_outputs", None),
-        agent_weights=getattr(result, "agent_weights", None),
-        context=result.context,
-        latency_ms=result.latency_ms,
+        prediction_id=prediction_id,
+        provider=result.get("provider") if result_dict else result.provider,
+        model=result.get("model") if result_dict else result.model,
+        prompt_version=result.get("prompt_version") if result_dict else getattr(result, "prompt_version", None),
+        mode=req.mode,
+        pred_home_goals=result.get("pred_home_goals") if result_dict else result.pred_home_goals,
+        pred_away_goals=result.get("pred_away_goals") if result_dict else result.pred_away_goals,
+        alt_pred_home_goals=result.get("alt_pred_home_goals") if result_dict else result.alt_pred_home_goals,
+        alt_pred_away_goals=result.get("alt_pred_away_goals") if result_dict else result.alt_pred_away_goals,
+        pred_1x2=result.get("pred_1x2") if result_dict else result.pred_1x2,
+        subjective_confidence=result.get("subjective_confidence") if result_dict else result.subjective_confidence,
+        reasoning=result.get("reasoning") if result_dict else result.reasoning,
+        status=result.get("status", "success") if result_dict else getattr(result, "status", "success"),
+        agent_outputs=result.get("agent_outputs") if result_dict else getattr(result, "agent_outputs", None),
+        agent_weights=result.get("agent_weights") if result_dict else getattr(result, "agent_weights", None),
+        context=result.get("context", "") if result_dict else result.context,
+        latency_ms=result.get("latency_ms", 0) if result_dict else result.latency_ms,
+        prompt_tokens=result.get("prompt_tokens") if result_dict else getattr(result, "prompt_tokens", None),
+        completion_tokens=result.get("completion_tokens") if result_dict else getattr(result, "completion_tokens", None),
+        rate_limit_remaining=_predict_limiter.remaining(get_client_ip(request)),
     )
 
 
+async def _persist_baseline(match_id: int, baseline: dict) -> int:
+    """将基线预测结果写入 prediction 表,复用 upsert 语义。"""
+    from src.db.unit_of_work import get_uow
+    from src.llm.predict import _upsert_prediction
+
+    async with get_uow() as session:
+        pred = await _upsert_prediction(
+            session,
+            match_id=match_id,
+            provider_name="baseline",
+            model="baseline",
+            mode="baseline",
+            run_type="baseline",
+            values={
+                "prompt_version": "baseline_v1",
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "latency_ms": 0,
+                "pred_home_goals": baseline["pred_home_goals"],
+                "pred_away_goals": baseline["pred_away_goals"],
+                "pred_1x2": baseline["pred_1x2"],
+                "subjective_confidence": baseline["subjective_confidence"],
+                "reasoning": baseline["reasoning"],
+                "raw_response": baseline.get("raw", baseline),
+                "status": "success",
+            },
+        )
+        return pred.id
+
+
 @router.get("/predictions", response_model=list[PredictionOut], dependencies=[Depends(require_admin)])
 async def list_predictions(
     match_id: int | None = None,
@@ -110,10 +155,14 @@ async def list_predictions(
             mode=p.mode or "single",
             pred_home_goals=p.pred_home_goals,
             pred_away_goals=p.pred_away_goals,
+            alt_pred_home_goals=p.alt_pred_home_goals,
+            alt_pred_away_goals=p.alt_pred_away_goals,
             pred_1x2=p.pred_1x2,
             subjective_confidence=p.subjective_confidence,
             reasoning=p.reasoning,
+            status=p.status or "success",
             agent_outputs=p.agent_outputs,
+            agent_weights=p.agent_weights,
             created_at=p.created_at,
             actual_home_goals=p.actual_home_goals,
             actual_away_goals=p.actual_away_goals,
@@ -137,10 +186,14 @@ async def get_prediction(prediction_id: int, db: AsyncSession = Depends(get_db_r
         mode=p.mode or "single",
         pred_home_goals=p.pred_home_goals,
         pred_away_goals=p.pred_away_goals,
+        alt_pred_home_goals=p.alt_pred_home_goals,
+        alt_pred_away_goals=p.alt_pred_away_goals,
         pred_1x2=p.pred_1x2,
         subjective_confidence=p.subjective_confidence,
         reasoning=p.reasoning,
+        status=p.status or "success",
         agent_outputs=p.agent_outputs,
+        agent_weights=p.agent_weights,
         created_at=p.created_at,
         actual_home_goals=p.actual_home_goals,
         actual_away_goals=p.actual_away_goals,