tzt
324c419c35
- labeler.py：derive_true_tier 纯函数（规则0 人工优先 / plan_multi->T3 / 失败->下一档(T3保持) / 成功->executed / 空结果跳过）+ derive_true_tiers 批量回填 + 180d 留存清理 - calibrate.py：compute_thresholds（τ1/τ3 分组扫描——并列分数整组判定， 精度 >= 1-α 的最大覆盖阈值；<min_labels -> ok=False 沿用 last-good）； save_thresholds 工件落盘+登记；load_active 回退链 active->同kind扫描->last-good->保守值 - store：all_observations/list_artifacts 支撑方法 - 测试 +9（四规则/批量清理/覆盖达标/标签不足/工件往返与回退），全量 395 passed
61 lines
2.4 KiB
Python
61 lines
2.4 KiB
Python
"""夜间 true_tier 推导（T-G3，§4 四条规则，确定性）+ 留存清理。
|
||
|
||
规则（对每条 true_tier 为空的观察，按序判定）：
|
||
0. human_override 非空 -> 以人工为准（规则 4，优先级最高）。
|
||
1. features.plan_multi（consumer=pipeline 发出 brief 的多步信号）-> true=T3。
|
||
2. outcome∈{escalated,failed,user_retry,timeout} -> true = executed 的下一档
|
||
（T1→T2→T3，T3 保持 T3）。
|
||
3. outcome∈{ok,verified} -> true = executed（T1 成功即 T1；T2/T3 同理）。
|
||
4. 其余（outcome 为空等）-> 跳过，等下一轮。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
import time
|
||
from typing import Any, Dict, Optional
|
||
|
||
NEXT_TIER = {"T1": "T2", "T2": "T3", "T3": "T3"}
|
||
SUCCESS = ("ok", "verified")
|
||
FAILURE = ("escalated", "failed", "user_retry", "timeout")
|
||
|
||
|
||
def _features(row: Dict[str, Any]) -> Dict[str, Any]:
|
||
try:
|
||
obj = json.loads(row.get("features") or "{}")
|
||
return obj if isinstance(obj, dict) else {}
|
||
except json.JSONDecodeError:
|
||
return {}
|
||
|
||
|
||
def derive_true_tier(row: Dict[str, Any]) -> Optional[str]:
|
||
"""单行推导（纯函数，测试友好）。返回 None = 暂不判定。"""
|
||
if row.get("human_override"):
|
||
return str(row["human_override"])
|
||
outcome = row.get("outcome") or ""
|
||
executed = row.get("executed_tier") or "T2"
|
||
feats = _features(row)
|
||
if feats.get("plan_multi"):
|
||
return "T3" # 规则 1（pipeline brief 信号）
|
||
if outcome in FAILURE: # 规则 2
|
||
return NEXT_TIER.get(executed, "T3")
|
||
if outcome in SUCCESS: # 规则 3
|
||
return executed
|
||
return None # 规则 4：等待结果
|
||
|
||
|
||
def derive_true_tiers(store, now: Optional[float] = None,
|
||
retention_days: int = 180) -> int:
|
||
"""批量推导（§7 签名）：返回回填条数；顺带 180d 留存清理。"""
|
||
now = time.time() if now is None else now
|
||
rows = store.all_observations()
|
||
count = 0
|
||
for row in rows:
|
||
if row.get("true_tier"):
|
||
continue
|
||
true_tier = derive_true_tier(row)
|
||
if true_tier:
|
||
store.set_true_tier(row["request_id"], true_tier)
|
||
count += 1
|
||
store.purge_older_than(now - retention_days * 86400)
|
||
return count
|