shangfangjian/Profeto
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(P2): no_data 结构化、权重校验、鉴权与前端竞态

Browse Source 
P2-1 no_data 门控依赖文案子串(脆弱):
- context_builder 新增 SliceResult(text/has_data/n_records),
  5 个切片函数改为显式声明 has_data
- base._slice_has_data() 优先取结构化结果,str 返回仍走文案回退
  (兼容既有测试 mock 与自定义切片)
- build_context 的 has_stats/has_injuries 直接取切片声明

P2-2 agent_weights 无校验即落库:
- validation 新增 AgentWeightsSchema / validate_agent_weights:
  未知专家名丢弃、越界值钳制、总和非 1 时归一化
- orchestrator 落库前对 agent_weights 做校验

P2-3 1x2 与比分不一致被静默修正:
- 仍以比分修正,但补 logger.warning 暴露 LLM 自相矛盾

P2-5/P2-6 prompt 缓存不可刷新 + 缓存键不含模板内容:
- 新增 clear_prompt_cache() 供改模板后显式失效
- 缓存键纳入模板内容 hash,模板一改缓存自动失效

P2-7 ingest/backtest/settle 接口无鉴权:
- 新增 require_admin_key 依赖(X-API-Key),
  ADMIN_API_KEY 未设置时放行并告警(不破坏本地开发)
- 挂到 3 个 ingest 接口 + backtest + eval/settle

P2-8 前端请求竞态 + 未使用游标分页:
- Matches.tsx 用递增 seq 丢弃过期响应,避免旧筛选结果覆盖新筛选
- 接入后端已有的 cursor 分页 + 「加载更多」按钮

附带: .env.example 补齐 LLM_TIMEOUT / 分档模型 / ADMIN_API_KEY;
tests 新增 10 个用例覆盖 P2-1/2/3。
This commit is contained in:
WorkBuddy
2026-09-15 16:54:05 +08:00
parent 71bf723a10
commit c89bfe2af7
13 changed files with 406 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llm/context_builder.py
+57 -35
View File
@@ -39,6 +39,22 @@ def _is_stats_available(stats, before) -> bool:
return stats.available_at <= before
@dataclass
class SliceResult:
"""数据切片的显式结果(替代「靠文案子串猜有无数据」)。
旧实现用 `"无数据" in slice_text` 判断,依赖具体文案 —— 一旦某个切片
写成「无比分数据」「无伤停数据」这类变体,判断就会静默失配
(见审查报告 P2-1)。这里让切片函数直接声明 `has_data`,不再猜。
"""
text: str
has_data: bool
n_records: int = 0
def __str__(self) -> str: # 让老调用点可直接当 str 用
return self.text
@dataclass
class MatchContext:
match_id: int
@@ -98,16 +114,18 @@ def header_text(h: MatchHeader) -> str:
# 切片函数: 每个领域 agent 一个
# ============================================================
async def h2h_slice(header: MatchHeader, *, limit: int = 8, before=None) -> str:
async def h2h_slice(header: MatchHeader, *, limit: int = 8, before=None) -> SliceResult:
"""E - 历史交锋切片: 过去数年 + 近期交手数据,提取交手规律。before=match_date 用于回测。"""
async with AsyncSessionLocal() as db:
h2h = await _get_h2h(db, header.home_team_id, header.away_team_id, before=before, limit=limit)
lines = [f"── 历史交锋(近 {limit} 次) ──"]
n_with_score = 0
if h2h:
home_wins = draws = away_wins = 0
for hm in h2h:
d = hm.match_date.strftime("%Y-%m") if hm.match_date else "?"
if hm.home_goals is not None:
n_with_score += 1
if hm.home_goals > hm.away_goals: home_wins += 1
elif hm.home_goals == hm.away_goals: draws += 1
else: away_wins += 1
@@ -119,15 +137,17 @@ async def h2h_slice(header: MatchHeader, *, limit: int = 8, before=None) -> str:
lines.append(f" 总计 {total} 场: 主队 {home_wins}胜 {draws}平 {away_wins}负")
else:
lines.append(" 无数据")
return "\n".join(lines)
# has_data 以「有比分的交锋」为准:仅有对阵无比分时不足以支撑分析
return SliceResult(text="\n".join(lines), has_data=n_with_score > 0, n_records=n_with_score)
async def form_slice(header: MatchHeader, *, limit: int = 5, before=None) -> str:
async def form_slice(header: MatchHeader, *, limit: int = 5, before=None) -> SliceResult:
"""A - 近期状态切片: 两队近 N 场赛果、关键事件、走势判断。before=match_date 用于回测。"""
async with AsyncSessionLocal() as db:
home_form = await _get_form(db, header.home_team_id, before=before, limit=limit)
away_form = await _get_form(db, header.away_team_id, before=before, limit=limit)
lines = []
n_scored = 0
for label, name, form, side in (
("主队", header.home_name, home_form, "home"),
("客队", header.away_name, away_form, "away"),
@@ -140,6 +160,8 @@ async def form_slice(header: MatchHeader, *, limit: int = 5, before=None) -> str
if o == "W": wins += 1
elif o == "D": draws += 1
else: losses += 1
if fm.home_goals is not None:
n_scored += 1
score = f"{fm.home_goals}-{fm.away_goals}" if fm.home_goals is not None else "vs"
xg = ""
if fm.stats and _is_stats_available(fm.stats, before) and fm.stats.home_xg is not None:
@@ -150,15 +172,16 @@ async def form_slice(header: MatchHeader, *, limit: int = 5, before=None) -> str
lines.append(f" 近 {len(form)} 场: {wins}胜 {draws}平 {losses}负")
else:
lines.append(" 无数据")
return "\n".join(lines)
return SliceResult(text="\n".join(lines), has_data=n_scored > 0, n_records=n_scored)
async def stats_slice(header: MatchHeader, *, limit: int = 10, before=None) -> str:
async def stats_slice(header: MatchHeader, *, limit: int = 10, before=None) -> SliceResult:
"""B - 攻防数据切片: 进球、射门、控球,评估攻防强度。before=match_date 用于回测。"""
async with AsyncSessionLocal() as db:
home_form = await _get_form(db, header.home_team_id, before=before, limit=limit)
away_form = await _get_form(db, header.away_team_id, before=before, limit=limit)
lines = [f"── 攻防数据(近 {limit} 场) ──"]
n_total = 0
for label, name, form, side in (
("主队", header.home_name, home_form, "home"),
("客队", header.away_name, away_form, "away"),
@@ -184,6 +207,7 @@ async def stats_slice(header: MatchHeader, *, limit: int = 10, before=None) -> s
xg += fm.stats.home_xg if side == "home" else fm.stats.away_xg
xga += fm.stats.away_xg if side == "home" else fm.stats.home_xg
n_xg += 1
n_total += n
if n > 0:
lines.append(f" {label} {name}:")
lines.append(f" 场均进球 {gf/n:.2f}, 场均失球 {ga/n:.2f}")
@@ -194,15 +218,16 @@ async def stats_slice(header: MatchHeader, *, limit: int = 10, before=None) -> s
lines.append(f" {label} {name}: 无比分数据")
else:
lines.append(f" {label} {name}: 无数据")
return "\n".join(lines)
return SliceResult(text="\n".join(lines), has_data=n_total > 0, n_records=n_total)
async def home_away_slice(header: MatchHeader, *, limit: int = 10, before=None) -> str:
async def home_away_slice(header: MatchHeader, *, limit: int = 10, before=None) -> SliceResult:
"""C - 主客因素切片: 主场战绩 vs 客场战绩,评估地理优势影响。before=match_date 用于回测。"""
async with AsyncSessionLocal() as db:
home_home = await _get_home_away(db, header.home_team_id, "home", before=before, limit=limit)
away_away = await _get_home_away(db, header.away_team_id, "away", before=before, limit=limit)
lines = ["── 主客因素 ──"]
n_total = 0
for label, name, matches, side in (
("主队主场", header.home_name, home_home, "home"),
("客队客场", header.away_name, away_away, "away"),
@@ -218,6 +243,7 @@ async def home_away_slice(header: MatchHeader, *, limit: int = 10, before=None)
gf += m.home_goals if side == "home" else m.away_goals
ga += m.away_goals if side == "home" else m.home_goals
n = wins + draws + losses
n_total += n
if n > 0:
pct = wins / n * 100
lines.append(f" {label} {name}(近 {n} 场): {wins}胜 {draws}平 {losses}负, 胜率 {pct:.0f}%")
@@ -226,10 +252,10 @@ async def home_away_slice(header: MatchHeader, *, limit: int = 10, before=None)
lines.append(f" {label} {name}: 无比分数据")
else:
lines.append(f" {label} {name}: 无数据")
return "\n".join(lines)
return SliceResult(text="\n".join(lines), has_data=n_total > 0, n_records=n_total)
async def injuries_slice(header: MatchHeader, *, before=None) -> str:
async def injuries_slice(header: MatchHeader, *, before=None) -> SliceResult:
"""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。
@@ -242,10 +268,10 @@ async def injuries_slice(header: MatchHeader, *, before=None) -> str:
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
n_records = 0
for label, injuries in (("主队", home_injuries), ("客队", away_injuries)):
if injuries:
has_data = True
n_records += len(injuries)
lines.append(f" {label}伤停({len(injuries)}人):")
for inj in injuries[:8]: # 最多显示 8 条
reason = inj.reason or inj.injury_type or "未知"
@@ -255,10 +281,10 @@ async def injuries_slice(header: MatchHeader, *, before=None) -> str:
else:
lines.append(f" {label}: 无伤停数据")
if not has_data:
return "── 阵容完整性 ──\n 无数据"
if n_records == 0:
return SliceResult(text="── 阵容完整性 ──\n 无数据", has_data=False, n_records=0)
return "\n".join(lines)
return SliceResult(text="\n".join(lines), has_data=True, n_records=n_records)
# ============================================================
@@ -266,42 +292,38 @@ async def injuries_slice(header: MatchHeader, *, before=None) -> str:
# ============================================================
async def build_context(match_id: int, *, form_last: int = 5, h2h_last: int = 5) -> MatchContext:
"""单 agent 路径的完整上下文: 拼接全部切片(before=比赛时间,防未来信息)。"""
"""单 agent 路径的完整上下文: 拼接全部切片(before=比赛时间,防未来信息)。
has_stats / has_injuries 直接取切片显式声明的 has_data,
不再靠文案子串匹配(见审查报告 P2-1)。
"""
header = await load_match_header(match_id)
parts = [header_text(header), ""]
has_stats = False
has_injuries = False
form_text = await form_slice(header, limit=form_last, before=header.match_dt)
if "无数据" not in form_text:
has_stats = True
parts.append(form_text)
form_res = await form_slice(header, limit=form_last, before=header.match_dt)
parts.append(form_res.text)
parts.append("")
h2h_text = await h2h_slice(header, limit=h2h_last, before=header.match_dt)
parts.append(h2h_text)
h2h_res = await h2h_slice(header, limit=h2h_last, before=header.match_dt)
parts.append(h2h_res.text)
parts.append("")
stats_text = await stats_slice(header, before=header.match_dt)
if "无数据" not in stats_text:
has_stats = True
parts.append(stats_text)
stats_res = await stats_slice(header, before=header.match_dt)
parts.append(stats_res.text)
parts.append("")
home_away_text = await home_away_slice(header, before=header.match_dt)
parts.append(home_away_text)
home_away_res = await home_away_slice(header, before=header.match_dt)
parts.append(home_away_res.text)
parts.append("")
injuries_text = await injuries_slice(header, before=header.match_dt)
if "无数据" not in injuries_text:
has_injuries = True
parts.append(injuries_text)
injuries_res = await injuries_slice(header, before=header.match_dt)
parts.append(injuries_res.text)
return MatchContext(
match_id=match_id,
text="\n".join(parts),
has_stats=has_stats,
has_injuries=has_injuries,
has_stats=form_res.has_data or stats_res.has_data,
has_injuries=injuries_res.has_data,
match_dt=header.match_dt,
)