安全加固 + 数据管线修复 + 质量改进(第2批)
安全加固: - /api/v1/predict 限流改用 get_client_ip 防 X-Forwarded-For 伪造 - 新增 TRUST_PROXY_HEADERS/REQUIRE_ADMIN_AUTH 配置,默认 fail-closed - 生产环境管理接口未配置鉴权时拒绝(503),不再放行 数据管线修复: - injuries IntegrityError 改用 begin_nested(SAVEPOINT)隔离批次 - injuries 空名单 vs 未配置语义区分(has_data 精确标记) - bzzoiro 统计字段映射(shots/possession/cards) + 入库条件放宽 - available_at 语义收紧(回测防泄漏) - team_names NFKD 去变音双重查找 + 补齐变体键 预测系统改进: - multi-agent 全专家失败时 status=degraded 跳过终裁 - agent_weights 独立持久化到 predictions 表 新增迁移: - 0014_predictions_agent_weights.py 新增测试(8个文件): - test_ip_spoofing.py: 限流防伪造 - test_require_admin_fail_closed.py: 生产 fail-closed - test_injuries_integrity_rollback.py: SAVEPOINT 隔离 - test_injuries_slice_semantic.py: 空名单 vs 未配置 - test_available_at.py: 回测防泄漏 - test_bzzoirot_stats.py: 统计字段映射 - test_team_names_normalize.py: NFKD 变体 - test_multi_agent_degraded.py: 全失败 degraded - test_agent_weights_persist.py: 权重持久化
This commit is contained in:
+17
-4
@@ -266,8 +266,12 @@ class BzzoiroSource:
|
||||
db.add(m)
|
||||
await db.flush()
|
||||
existing_matches[match_key] = m # 防止同批重复
|
||||
if nm.home_xg is not None or nm.away_xg is not None:
|
||||
# 存在任一统计字段即可创建 MatchStats(不再强制要求 xG)
|
||||
if any(getattr(nm, f) is not None for f 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']):
|
||||
now = datetime.now(timezone.utc)
|
||||
# available_at 语义:统计「可被使用」的最早时间,至少不早于比赛结束
|
||||
# 局限:用 match_date(开球时间)近似,实际完赛时间约为 +2 小时
|
||||
available_at = nm.date if nm.date else now
|
||||
stats = MatchStats(
|
||||
match_id=m.id,
|
||||
home_xg=nm.home_xg,
|
||||
@@ -286,7 +290,7 @@ class BzzoiroSource:
|
||||
source="bzzoiro",
|
||||
source_record_id=str(raw.get("id", "")),
|
||||
retrieved_at=now,
|
||||
available_at=now,
|
||||
available_at=available_at,
|
||||
)
|
||||
db.add(stats)
|
||||
league_r["inserted"] += 1
|
||||
@@ -305,14 +309,23 @@ class BzzoiroSource:
|
||||
if existing_match.match_stage is None and nm.match_stage:
|
||||
existing_match.match_stage = nm.match_stage
|
||||
changed = True
|
||||
if existing_match.stats is None and (nm.home_xg is not None or nm.away_xg is not None):
|
||||
# 存在任一统计字段即可创建 MatchStats(不再强制要求 xG)
|
||||
if existing_match.stats is None and (
|
||||
nm.home_xg is not None or nm.away_xg is not None
|
||||
or nm.home_shots is not None or nm.away_shots is not None
|
||||
or nm.home_corners is not None or nm.away_corners is not None
|
||||
or nm.home_possession is not None
|
||||
):
|
||||
now = datetime.now(timezone.utc)
|
||||
# available_at 语义:统计「可被使用」的最早时间,至少不早于比赛结束
|
||||
# 局限:用 match_date(开球时间)近似,实际完赛时间约为 +2 小时
|
||||
available_at = nm.date if nm.date else now
|
||||
existing_match.stats = MatchStats(
|
||||
match_id=existing_match.id,
|
||||
source="bzzoiro",
|
||||
source_record_id=str(raw.get("id", "")),
|
||||
retrieved_at=now,
|
||||
available_at=now,
|
||||
available_at=available_at,
|
||||
)
|
||||
db.add(existing_match.stats)
|
||||
await db.flush()
|
||||
|
||||
Reference in New Issue
Block a user