Code Review 第二轮修复:前端 HTTP 统一 + 数据采集可靠性

F1: 统一前端 HTTP 客户端
- 新增 frontend/src/lib/http.ts(共享客户端,统一超时/错误/401 处理)
- Matches.tsx 的列表/分页/进行中/预测请求改用 http 客户端
- 公开站与 Admin 行为一致

D2: events 采集按联赛分批提交
- _run_bzzoiro 改为 per-league 独立事务,避免超长事务
- 单联赛失败不影响其他联赛

F3: 仪表盘真实计数
- admin_stats 补充 matches/stats/standings 真实聚合
- Dashboard 展示比赛总数/已完赛/统计行/积分榜

F4: LLM 连通性测试不依赖 match_id=1
- 新增 POST /admin/llm/ping 端点(只发一次 chat,不依赖比赛)
- testLLMConnection 优先调用 ping,失败回退旧方式

F5: 导航改用 React Router Link
- App.tsx 中 <a href> 全部替换为 <Link to>

D5: 删除 away_possession 死代码
- bzzoiro.py 中移除计算与注释

D1: 管线基础设施表文档化
- RawEvent/IngestFailure/DataQualityCheck/DataLineage 添加「预留未启用」注释

Co-Authored-By: new-provider/LongCat-2.0 <<EMAIL>>
This commit is contained in:
shangfangjian
2026-09-21 03:06:52 +08:00
co-authored by new-provider/LongCat-2.0 <
parent 675e176603
commit b6e367a640
10 changed files with 226 additions and 74 deletions
+28 -3
View File
@@ -293,6 +293,21 @@ async def test_datasource(name: str):
raise HTTPException(404, f"未知数据源: {name}")
@router.post("/llm/ping")
async def llm_ping():
"""LLM 连通性测试(不依赖比赛)。只发一次 chat 请求验证配置。"""
from src.llm.provider import get_default_provider
p = await get_default_provider()
resp = await p.chat(
system="你是测试助手。",
user="ping",
max_tokens=10,
)
if resp.error:
return {"ok": False, "message": resp.error}
return {"ok": True, "message": "LLM 连接正常", "model": p.model}
# ── 数据源健康/最近采集状态(只读,不触发采集) ──────────────────────
@@ -387,9 +402,9 @@ def _last_failure_log(source: str) -> dict | None:
@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。"""
"""管理区统计(只读):预测次数 + 比赛覆盖。轻量聚合,无 LLM 调用。"""
from sqlalchemy import func, text
from src.db.models import Prediction
from src.db.models import Prediction, Match, MatchStats, Standing
day_ago = datetime.now(timezone.utc) - timedelta(days=1)
week_ago = datetime.now(timezone.utc) - timedelta(days=7)
r = (
@@ -401,7 +416,17 @@ async def admin_stats(db: AsyncSession = Depends(get_db_read)):
)
)
).one()
return {"predictions": {"total": r.total, "last_24h": r.last_24h, "last_7d": r.last_7d}}
# F3 修复: 补充真实比赛计数(非 limit=100 近似)
match_cnt = (await db.execute(select(func.count()).select_from(Match))).scalar() or 0
finished_cnt = (await db.execute(select(func.count()).where(Match.match_status == "finished"))).scalar() or 0
stats_cnt = (await db.execute(select(func.count()).select_from(MatchStats))).scalar() or 0
standings_cnt = (await db.execute(select(func.count()).select_from(Standing))).scalar() or 0
return {
"predictions": {"total": r.total, "last_24h": r.last_24h, "last_7d": r.last_7d},
"matches": {"total": match_cnt, "finished": finished_cnt},
"stats": {"total": stats_cnt},
"standings": {"total": standings_cnt},
}
# ── 数据完整性分析(可视化数据源) ────────────────────────────────
+13 -12
View File
@@ -58,20 +58,21 @@ async def _run_bzzoiro(task: str, leagues: list[str], req: IngestBzzoiroRequest)
statuses = [req.status] if req.status else ["finished", "scheduled"]
source = get_source("bzzoiro")
merged: dict = {"leagues": {}, "total_inserted": 0, "total_updated": 0, "errors": []}
async with get_uow() as session:
# D2 修复: 按联赛分批提交,避免超长事务
for code in leagues:
for st in statuses:
r = await source.ingest(
session, leagues=leagues,
date_from=req.date_from, date_to=req.date_to, status=st,
)
merged["total_inserted"] += r.get("total_inserted", 0)
merged["total_updated"] += r.get("total_updated", 0)
merged["errors"].extend(r.get("errors", []))
for code, stat in r.get("leagues", {}).items():
async with get_uow() as session:
r = await source.ingest(
session, leagues=[code],
date_from=req.date_from, date_to=req.date_to, status=st,
)
merged["total_inserted"] += r.get("total_inserted", 0)
merged["total_updated"] += r.get("total_updated", 0)
merged["errors"].extend(r.get("errors", []))
acc = merged["leagues"].setdefault(code, {"inserted": 0, "updated": 0, "errors": []})
acc["inserted"] += stat.get("inserted", 0)
acc["updated"] += stat.get("updated", 0)
acc["errors"].extend(stat.get("errors", []))
acc["inserted"] += r.get("inserted", 0)
acc["updated"] += r.get("updated", 0)
acc["errors"].extend(r.get("errors", []))
logger.info(
"bzzoiro 比赛采集完成: 新增 %d, 更新 %d, 联赛 %d 个, 状态 %s",
merged["total_inserted"], merged["total_updated"], len(merged["leagues"]), statuses,
-2
View File
@@ -541,7 +541,6 @@ def _stats_from_payload(payload: dict) -> dict:
p = _to_float_or_none(poss)
if p is not None:
out["home_possession"] = p
out["away_possession"] = round(100 - p, 1) if 0 <= p <= 100 else None
for src, (h_fld, a_fld) in _STATS_FIELD_MAP.items():
if src in ("xg", "ball_possession"):
@@ -642,7 +641,6 @@ async def ingest_bzzoiro_event_stats(
m.stats.available_at = m.match_date + timedelta(hours=2)
for fld, v in fields.items():
# away_possession 为计算字段,模型无此列,跳过
if hasattr(m.stats, fld):
setattr(m.stats, fld, v)
+20 -4
View File
@@ -284,7 +284,11 @@ class Schedule(Base):
class RawEvent(Base):
"""Bronze 层:采集到的原始事件存档,便于重放与审计。"""
"""Bronze 层:采集到的原始事件存档,便于重放与审计。
⚠️ 预留未启用:当前 bzzoiro 管线不写入此表。
未来接线计划:events 采集成功后写入 raw_payload,支持重放与审计。
"""
__tablename__ = "raw_events"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
@@ -301,7 +305,11 @@ class RawEvent(Base):
class IngestFailure(Base):
"""采集失败死信:记录失败原因、重试次数与下次重试时间。"""
"""采集失败死信:记录失败原因、重试次数与下次重试时间。
⚠️ 预留未启用:当前 bzzoiro 管线不写入此表。
未来接线计划:采集失败时写入,支持按 next_retry_at 自动重试。
"""
__tablename__ = "ingest_failures"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
@@ -327,7 +335,11 @@ class IngestFailure(Base):
class DataQualityCheck(Base):
"""数据质量监控:记录每次质量检查的结果。"""
"""数据质量监控:记录每次质量检查的结果。
⚠️ 预留未启用:当前 bzzoiro 管线不写入此表。
未来接线计划:定时检查比赛/统计/积分榜完整性,写入检查结果。
"""
__tablename__ = "data_quality_checks"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)
@@ -348,7 +360,11 @@ class DataQualityCheck(Base):
class DataLineage(Base):
"""ETL 血缘追踪:记录从源到目标的转换过程。"""
"""ETL 血缘追踪:记录从源到目标的转换过程。
⚠️ 预留未启用:当前 bzzoiro 管线不写入此表。
未来接线计划:每次采集写入 source_record_id → target_table/id 映射。
"""
__tablename__ = "data_lineage"
id: Mapped[int] = mapped_column(BigInteger, primary_key=True)