HEL-862: bind promise object/action/polarity/status to one clause-scoped claim - per manager independent review of a5ef23f: (1) affirms_promise_claim rewritten as clause-structural grammar (single clause must chain promise verb with no negation morpheme in prefix -> tell action -> correct object interview-result; object word appearing in another clause no longer counts, negated promise (未曾答应) rejected structurally, telling-only statement without promise verb no longer passes on 告诉 keyword, mixed action word list and enumerated claim-negation blacklist dropped); (2) resolved/unresolved state affirmation via affirms_promise_state/clause_affirms_state (declared closed/open phrase sets scored clause-locally with negation-morpheme prefix polarity - 并非已经告诉我 no longer counts as affirmed closed); manager review four wrong-answer groups (negated promise / negated closed / object bound to other action / no promise asserted) all judged fail through the same real s6_result, correct interview resolved/unresolved positives and declared-equivalent open synonym kept passing; no new model, no generic semantic engine, supported-expression restriction fails conservatively
Co-authored-by: multica-agent <github@multica.ai>
This commit is contained in:
zonggong
co-authored by
multica-agent
multica-agent
parent
a5ef23f5b5
commit
60cd7fd70d
+149
-35
@@ -29,6 +29,19 @@ HEL-861 分享状态源贯穿与 S6 肯定验证（总管对 22472e4 独立复
|
||||
（面试结果）+ 承诺动作未被否定 + 无不确定表述；答错对象（体检结果）、
|
||||
"没有答应过"、"不知道是否已经告诉我"不以含"告诉/答应"关键词判成功。
|
||||
|
||||
HEL-862 承诺声明绑定（总管对 a5ef23f 独立复核剩余缺口，限定受支持表达）：
|
||||
- 整段"对象词/动作词各出现一次"不再凑数：肯定验证改为小句结构化绑定——
|
||||
同一小句内 承诺动词（前缀无否定语素）→ 告知动作 → 正确对象（面试结果）
|
||||
依次成立，承诺才算被肯定陈述；"你答应周五晚告诉我体检结果……面试结果是
|
||||
另一件事"（对象与动作串错）拒绝；
|
||||
- 否定极性按结构判定（否定语素出现在动词/状态短语之前的同小句前缀内即
|
||||
未肯定），不靠不断枚举"未曾答应/并非已经告诉我"式整句禁词；
|
||||
"你未曾答应……"、"……但并非已经告诉我"拒绝；
|
||||
- 承诺动词（答应/承诺/许诺）与告知动作（告诉/告知）分开：仅陈述
|
||||
"面试结果现在已经告诉我了"而无承诺断言不再以"告诉"冒充承诺动作；
|
||||
- 已结/未结状态短语同样小句内肯定极性判定；固定合成语料领域内的
|
||||
受支持表达之外一律保守判失败，不外推、不新增模型。
|
||||
|
||||
对照设计（批准范围第5条）：
|
||||
现状路径 = docs/reuse-hel847/probe_recall.py 的生产语义重放（总管已核对的 v2 基线，
|
||||
词面 FTS trigram 检索 + fixture gist + 带门回读），不读写真实库；
|
||||
@@ -42,6 +55,7 @@ Mem0 的提取为真实模型行为——两侧不对称如实记录，不冒充
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import re
|
||||
import shutil
|
||||
import sqlite3
|
||||
import subprocess
|
||||
@@ -640,8 +654,9 @@ def has_any(text: str, terms_zh: list[str], terms_en: list[str]) -> bool:
|
||||
# 总验收不遮住失败——两侧都答"不知道"必须判 False，不再只看检索命中）。
|
||||
# 独立成函数以便离线负例直接代入错误模型答案验证判据本身。
|
||||
# S6 承诺状态判据词集（HEL-860：固定合成语料的预声明等价集，不冒充通用语义
|
||||
# 理解；离线先行证明，不靠真实请求调判据）。HEL-861 起原混合词表（任一
|
||||
# 承诺词+状态词即过）拆分为对象/动作/否定/不确定四组精确判定集。
|
||||
# 理解；离线先行证明，不靠真实请求调判据）。HEL-861 原混合词表（任一承诺词+
|
||||
# 状态词即过）拆分；HEL-862 起这些词表只作小句内状态短语词表，极性由
|
||||
# clause_affirms_state 按小句前缀否定结构判定。
|
||||
PROMISE_CLOSED_ZH = ["已经告诉我", "已告诉我", "已经告知", "已告知", "已经说了",
|
||||
"结果已收到", "已收到", "收到了", "已经拿到", "拿到了",
|
||||
"已兑现", "已解决"]
|
||||
@@ -655,35 +670,131 @@ PROMISE_OPEN_EN = ["haven't told", "not yet told", "not yet received"]
|
||||
# 对象——正确承诺对象是"面试结果"；答错对象（如体检结果）不能凭关键词通过。
|
||||
PROMISE_OBJECT_ZH = ["面试结果"]
|
||||
PROMISE_OBJECT_EN = ["interview result", "interview"]
|
||||
# 动作——承诺动作词（答应/承诺/告诉）须出现且未被否定。
|
||||
PROMISE_ACTION_ZH = ["答应", "承诺", "告诉"]
|
||||
PROMISE_ACTION_EN = ["promis", "tell", "commit"]
|
||||
# 承诺被否定的模式（对"存在承诺"这一断言的否定，非对状态词的否定）。
|
||||
PROMISE_CLAIM_NEGATED_ZH = ["没有答应", "没答应", "不答应", "没有承诺", "没承诺",
|
||||
"不承诺", "没许诺", "没有许诺", "从未答应", "从未承诺",
|
||||
"没答应过", "没有答应过", "并未答应"]
|
||||
PROMISE_CLAIM_NEGATED_EN = ["didn't promise", "did not promise", "never promised",
|
||||
"don't promise", "do not promise", "no promise",
|
||||
"haven't promised", "hasn't promised", "never commit",
|
||||
"didn't commit"]
|
||||
# HEL-862 承诺动词与告知动作分开（原混合动作词表废弃）："告诉"是告知动作不是
|
||||
# 承诺断言，仅陈述已告知而无答应/承诺动词不再以关键词冒充承诺存在。
|
||||
PROMISE_VERB_ZH = ["答应", "承诺", "许诺"]
|
||||
PROMISE_VERB_EN = ["promis", "pledge", "commit"]
|
||||
TELL_ACTION_ZH = ["告诉", "告知"]
|
||||
TELL_ACTION_EN = ["tell", "inform", "notify"]
|
||||
# 否定语素（封闭语法类，非逐句黑名单）：出现在承诺动词/状态短语之前的同小句
|
||||
# 前缀内，即该断言未被肯定——"未曾答应/从未答应/并未答应/并非已经告诉我"
|
||||
# 由结构拒绝，不靠不断枚举整句禁词。
|
||||
NEGATION_MORPHS_ZH = ["不", "没", "未", "非", "无", "别", "莫", "勿"]
|
||||
NEGATION_MORPHS_EN = ["not", "n't", "never", "no "]
|
||||
# 不确定/存疑模式（对承诺或状态的不知情、疑问、存疑）。
|
||||
PROMISE_UNCERTAIN_ZH = ["不知道", "不确定", "是否", "说不清", "记不清", "可能"]
|
||||
PROMISE_UNCERTAIN_EN = ["don't know", "do not know", "not sure", "unclear",
|
||||
"whether", "maybe", "perhaps", "not certain"]
|
||||
# 小句切分（硬边界=句读，软边界=逗号）：肯定验证按"同一小句内"绑定，跨小句
|
||||
# 各出现一个词不凑数；仅支持固定合成语料的明文形态（限定受支持表达）。
|
||||
_LEADING_CONJ_ZH = ("但是", "但", "可是", "不过", "然而", "而")
|
||||
_LEADING_CONJ_EN = ("and", "but", "however", "yet", "so")
|
||||
|
||||
|
||||
def iter_clauses(text: str) -> list[str]:
|
||||
"""把回答切成小句（句读+逗号，剥离句首连接词），供结构化绑定判定。"""
|
||||
clauses: list[str] = []
|
||||
for sentence in re.split(r"[。！？；;\n]", text or ""):
|
||||
for seg in re.split(r"[，,]", sentence):
|
||||
seg = seg.strip().strip(" \t\"'“”‘’")
|
||||
low = seg.lower()
|
||||
for conj in _LEADING_CONJ_EN:
|
||||
if low.startswith(conj + " "):
|
||||
seg = seg[len(conj) + 1:].lstrip()
|
||||
low = seg.lower()
|
||||
break
|
||||
for conj in _LEADING_CONJ_ZH:
|
||||
if seg.startswith(conj):
|
||||
seg = seg[len(conj):]
|
||||
break
|
||||
if seg:
|
||||
clauses.append(seg)
|
||||
return clauses
|
||||
|
||||
|
||||
def _prefix_negated(clause: str, idx: int) -> bool:
|
||||
"""小句内位置 idx 之前的前缀是否含否定语素（未肯定极性，保守判定）。"""
|
||||
if idx < 0:
|
||||
return False
|
||||
prefix = clause[:idx]
|
||||
low = prefix.lower()
|
||||
return any(m in prefix for m in NEGATION_MORPHS_ZH) or any(
|
||||
m in low for m in NEGATION_MORPHS_EN)
|
||||
|
||||
|
||||
def clause_affirms_promise(clause: str) -> bool:
|
||||
"""单小句内肯定承诺断言：承诺动词（前缀无否定）→ 告知动作 → 正确对象。
|
||||
|
||||
对象必须落在承诺动词之后的告知动作之后（告诉我面试结果），把正确对象
|
||||
绑定进同一项承诺声明；对象在别的小句出现（"面试结果是另一件事"）不凑数。
|
||||
"""
|
||||
for verb in PROMISE_VERB_ZH:
|
||||
start = 0
|
||||
while (i := clause.find(verb, start)) >= 0:
|
||||
if not _prefix_negated(clause, i):
|
||||
after = clause[i + len(verb):]
|
||||
for tell in TELL_ACTION_ZH:
|
||||
j = after.find(tell)
|
||||
if j >= 0 and any(
|
||||
obj in after[j + len(tell):]
|
||||
for obj in PROMISE_OBJECT_ZH):
|
||||
return True
|
||||
start = i + 1
|
||||
low = clause.lower()
|
||||
for verb in PROMISE_VERB_EN:
|
||||
start = 0
|
||||
while (i := low.find(verb, start)) >= 0:
|
||||
if not _prefix_negated(clause, i):
|
||||
after = low[i + len(verb):]
|
||||
for tell in TELL_ACTION_EN:
|
||||
j = after.find(tell)
|
||||
if j >= 0 and any(
|
||||
obj in after[j:] for obj in PROMISE_OBJECT_EN):
|
||||
return True
|
||||
start = i + 1
|
||||
return False
|
||||
|
||||
|
||||
def clause_affirms_state(clause: str, closed: bool) -> bool:
|
||||
"""单小句内肯定已结/未结状态：状态短语（预声明等价集）前缀无否定语素。
|
||||
|
||||
"但并非已经告诉我"含已结短语但前缀被否定 → 未肯定；"还没有告诉我"/
|
||||
"尚未收到"是未结短语的肯定形态（短语本身表达未结，非否定已结）。
|
||||
"""
|
||||
terms_zh = PROMISE_CLOSED_ZH if closed else PROMISE_OPEN_ZH
|
||||
terms_en = PROMISE_CLOSED_EN if closed else PROMISE_OPEN_EN
|
||||
low = clause.lower()
|
||||
for t in terms_zh:
|
||||
start = 0
|
||||
while (i := clause.find(t, start)) >= 0:
|
||||
if not _prefix_negated(clause, i):
|
||||
return True
|
||||
start = i + 1
|
||||
for t in terms_en:
|
||||
start = 0
|
||||
while (i := low.find(t, start)) >= 0:
|
||||
if not _prefix_negated(clause, i):
|
||||
return True
|
||||
start = i + 1
|
||||
return False
|
||||
|
||||
|
||||
def affirms_promise_state(text: str, *, closed: bool) -> bool:
|
||||
"""肯定陈述已结/未结状态：任一小句内状态短语被肯定（前缀无否定）。"""
|
||||
return any(clause_affirms_state(c, closed) for c in iter_clauses(text))
|
||||
|
||||
|
||||
def affirms_promise_claim(text: str) -> bool:
|
||||
"""肯定陈述固定语料中的承诺（HEL-861 纯函数判据）：
|
||||
"""肯定陈述固定语料中的承诺（HEL-862 小句结构化判据）：
|
||||
|
||||
对象正确（面试结果）AND 承诺动作词存在 AND 承诺未被否定 AND 无不确定表述。
|
||||
答错对象（体检结果）、"没有答应过"、"不知道是否已经告诉我"均判 False，
|
||||
不因包含"告诉/答应"关键词判 True。
|
||||
存在单一小句按"承诺动词（前缀无否定语素）→ 告知动作 → 正确对象（面试
|
||||
结果）"依次绑定，且全文无不确定表述。对象词与动作词分处不同小句各出现
|
||||
一次不再凑数；承诺动词被否定（未曾答应/没有答应过）、仅陈述告知结果而无
|
||||
承诺断言（面试结果已经告诉我了）、答错对象（体检结果）均判 False；无法
|
||||
按受支持表达证明即保守判失败，不靠枚举整句禁词冒充肯定验证。
|
||||
"""
|
||||
return bool(
|
||||
has_any(text, PROMISE_OBJECT_ZH, PROMISE_OBJECT_EN)
|
||||
and has_any(text, PROMISE_ACTION_ZH, PROMISE_ACTION_EN)
|
||||
and not has_any(text, PROMISE_CLAIM_NEGATED_ZH, PROMISE_CLAIM_NEGATED_EN)
|
||||
and not has_any(text, PROMISE_UNCERTAIN_ZH, PROMISE_UNCERTAIN_EN))
|
||||
return bool(any(clause_affirms_promise(c) for c in iter_clauses(text))
|
||||
and not has_any(text, PROMISE_UNCERTAIN_ZH, PROMISE_UNCERTAIN_EN))
|
||||
# 未结对照块自洽：与"未结"状态矛盾的结果类条目（已通过/已收到通知）须剔除
|
||||
RESULT_RECEIVED_ZH = ["面试过了", "通过了", "拿到通知", "拿到了通知", "已收到",
|
||||
"收到了", "结果已收到", "已兑现"]
|
||||
@@ -784,14 +895,16 @@ def s3_result(*, b_hits3: list, b_hits3b: list, m_hits3: list, m_hits3b: list,
|
||||
|
||||
|
||||
def s6_result(orch: dict, a_resolved: dict, a_unresolved: dict) -> dict:
|
||||
"""S6 判据（HEL-861：肯定验证承诺对象/动作/状态，不以关键词冒充）：编排层
|
||||
"""S6 判据（HEL-862：小句结构化绑定承诺对象/动作/极性与状态）：编排层
|
||||
（已知id置 resolved 留痕 + 未结对照块自洽）+ 状态进上下文层（正确对象的
|
||||
resolved 状态实际写入带门装配块）+ 模型使用层（两侧请求成功；已结侧必须
|
||||
肯定陈述正确对象（面试结果）的承诺且承诺未被否定、无不确定表述，并肯定
|
||||
为已告知；未结侧必须肯定陈述正确对象的承诺且肯定为尚未告知——答错对象
|
||||
（如体检结果）、"没有答应过"、"不知道是否已经告诉我"、两侧同答不区分
|
||||
状态、已结侧答未结、未结侧同义宣称已收到结果均判失败，不以字面提到
|
||||
'告诉/答应'冒充状态正确）。"""
|
||||
在单一小句内按"承诺动词（前缀无否定）→告知动作→面试结果"肯定陈述同一项
|
||||
承诺，且状态短语（已经告诉我等）所在小句前缀无否定语素并肯定为已告知；
|
||||
未结侧同一绑定且肯定为尚未告知——对象与动作分处不同小句各出现一次
|
||||
（体检承诺+面试另一件事）、承诺被否定（未曾答应）、状态被否定（并非已经
|
||||
告诉我）、仅陈述告知而无承诺断言（面试结果已经告诉我了）、"不知道是否"、
|
||||
两侧同答不区分状态、已结侧答未结、未结侧同义宣称已收到均判失败，不以字面
|
||||
提到'告诉/答应'冒充状态正确；无法按受支持表达证明即保守判失败）。"""
|
||||
ans_r = (a_resolved or {}).get("answer") or ""
|
||||
ans_u = (a_unresolved or {}).get("answer") or ""
|
||||
ok_r = bool((a_resolved or {}).get("ok"))
|
||||
@@ -802,12 +915,12 @@ def s6_result(orch: dict, a_resolved: dict, a_unresolved: dict) -> dict:
|
||||
"unresolved_answer": ans_u,
|
||||
"resolved_states_promise": affirms_promise_claim(ans_r),
|
||||
"resolved_affirms_closed": (
|
||||
has_any(ans_r, PROMISE_CLOSED_ZH, PROMISE_CLOSED_EN)
|
||||
affirms_promise_state(ans_r, closed=True)
|
||||
and not has_any(ans_r, PROMISE_OPEN_ZH, PROMISE_OPEN_EN)
|
||||
and not has_any(ans_r, PROMISE_UNCERTAIN_ZH, PROMISE_UNCERTAIN_EN)),
|
||||
"unresolved_states_promise": affirms_promise_claim(ans_u),
|
||||
"unresolved_affirms_open": (
|
||||
has_any(ans_u, PROMISE_OPEN_ZH, PROMISE_OPEN_EN)
|
||||
affirms_promise_state(ans_u, closed=False)
|
||||
and not has_any(ans_u, PROMISE_CLOSED_ZH, PROMISE_CLOSED_EN)
|
||||
and not has_any(ans_u, PROMISE_UNCERTAIN_ZH, PROMISE_UNCERTAIN_EN)),
|
||||
"unresolved_no_false_resolution": not has_any(
|
||||
@@ -831,11 +944,12 @@ def s6_result(orch: dict, a_resolved: dict, a_unresolved: dict) -> dict:
|
||||
return {"layers": layers, "pass": ok,
|
||||
"expect": "已知id编排置 resolved 留痕且未结对照块剔除矛盾条目后自洽；"
|
||||
"正确对象的状态实际写入带门装配块；模型沿状态区分且必须"
|
||||
"肯定验证：已结侧肯定陈述正确对象（面试结果）的承诺（对象"
|
||||
"正确、承诺未被否定、无不确定）且肯定为已告知，未结侧肯定"
|
||||
"陈述正确对象的承诺且肯定为尚未告知；答错对象/不知道/是否/"
|
||||
"没有答应过/两侧同答/已结侧答未结/未结侧宣称已收到均判失败"
|
||||
"（不以字面提到'告诉/答应'冒充状态正确）"}
|
||||
"肯定验证同一项声明：已结侧单一小句内'承诺动词（未被否定）→"
|
||||
"告知动作→面试结果'绑定成立且已结状态短语未被否定并肯定为"
|
||||
"已告知，未结侧同一绑定且肯定为尚未告知；对象与动作串错/"
|
||||
"未曾答应/并非已经告诉我/仅陈述告知无承诺/不知道/是否/"
|
||||
"两侧同答/已结侧答未结/未结侧宣称已收到均判失败（无法按"
|
||||
"受支持表达证明即保守判失败，不以字面提到'告诉/答应'冒充）"}
|
||||
|
||||
|
||||
# HEL-860：无门 assemble_block 出口已删除——全部问答最终装配一律经
|
||||
|
||||
@@ -0,0 +1,280 @@
|
||||
#!/usr/bin/env python3
|
||||
"""HEL-862 负例复现脚本：总管独立复核《HEL-861-独立复核.md》S6 肯定验证缺口。
|
||||
|
||||
零真实模型、零网络（socket 硬拒绝 + HF 离线）、零本地嵌入：S6 判据为纯函数
|
||||
代入（真实 s6_result 构造器同一入口）；既有判据不回归部分直接复用 audit861
|
||||
的两组纯函数节（S6 全套正负例 + S2/S3 总判据）。同一脚本在修复前（a5ef23f）
|
||||
与修复后代码上均可运行：
|
||||
|
||||
修复前（--phase prefix，在 a5ef23f 工作树上运行）→ 总管复核四组错误回答
|
||||
（否定承诺仍过 / 否定已结仍过 / 对象与动作串错仍过 / 仅陈述告知但未肯定
|
||||
承诺仍过）全部 pass=true，正确面试承诺已结/未结正例仍 pass=true
|
||||
修复后（默认 postfix）→ 同一真实 s6_result 四组全部判失败，正确正例、
|
||||
audit861 既有正例（已结/未结/未结同义"还没有收到"/audit860/rework 形态）
|
||||
继续通过；audit861 既有负例与 S2/S3 总判据不回归
|
||||
|
||||
补正口径（固定合成语料领域内，限定受支持表达）：正确对象、承诺动作、动作
|
||||
肯定性与已结/未结状态绑定到同一项声明——单一小句内"承诺动词（前缀无否定
|
||||
语素）→告知动作→面试结果"依次成立；已结/未结状态短语所在小句前缀无否定
|
||||
语素。不以对象词/动作词在整段各出现一次凑数，不靠不断加禁词或整句黑名单
|
||||
冒充肯定验证；无法证明则保守判失败。不新增模型、不做通用语义引擎。
|
||||
|
||||
退出码真实依赖正负例：除全部用例满足预期外，还对每个用例做翻转自检
|
||||
（flip 任一用例的实际结果，用例总判必翻转）；任一翻转不改变结论则退出 1。
|
||||
|
||||
用法：python -m spike.hel857.audit862 [--phase prefix|postfix] [输出json路径]
|
||||
退出码：prefix=0 当且仅当四组反例全部复现且正例保留；postfix=0 当且仅当
|
||||
四组反例全部判失败、正例保留、既有判据不回归、权威账与既有证据只读未动、
|
||||
翻转自检全部通过。权威嵌入账只读快照核对（不补种不回退不双扣）。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import socket
|
||||
import sqlite3
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
REPO = Path(__file__).resolve().parents[2]
|
||||
LEDGER = Path("/home/xiaomo/multica_workspaces/hello-af23464d222e/"
|
||||
"hel-859-1f079e50f551/workdir/audit-data/embed_ledger.sqlite3")
|
||||
os.environ["HEL857_EMBED_LEDGER"] = str(LEDGER)
|
||||
os.environ.setdefault("HF_HUB_OFFLINE", "1")
|
||||
os.environ.setdefault("TRANSFORMERS_OFFLINE", "1")
|
||||
|
||||
|
||||
def deny_network(*a, **k):
|
||||
raise RuntimeError("audit862 blocks network")
|
||||
|
||||
|
||||
socket.socket.connect = deny_network
|
||||
socket.socket.connect_ex = deny_network
|
||||
|
||||
from . import ab_scenarios as A
|
||||
from .audit861 import section_s2_s3_no_regression, section_s6_affirmative
|
||||
|
||||
OUT = {"real_network_allowed": False, "real_model_requests": 0,
|
||||
"local_embeddings": 0}
|
||||
PHASE = "postfix"
|
||||
|
||||
|
||||
def ledger_snapshot():
|
||||
with sqlite3.connect(f"file:{LEDGER}?mode=ro", uri=True) as c:
|
||||
return {"counts": dict(c.execute("select kind,sum(items) from embed_ops "
|
||||
"group by kind")),
|
||||
"rows": c.execute("select count(*) from embed_ops").fetchone()[0]}
|
||||
|
||||
|
||||
PRESERVED_EVIDENCE = [
|
||||
"ab_scenarios_run1.json", "ab_scenarios.json", "rework858_offline.json",
|
||||
"rework859_offline.json", "rework860_offline.json", "audit859_prefix.json",
|
||||
"audit859_postfix.json", "audit859_reuse860.json", "audit860_prefix.json",
|
||||
"audit860_postfix.json", "audit861_prefix.json", "audit861_postfix.json"]
|
||||
|
||||
|
||||
def evidence_hashes():
|
||||
res = {}
|
||||
for name in PRESERVED_EVIDENCE:
|
||||
p = REPO / "spike/hel857/results" / name
|
||||
res[name] = (hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
if p.exists() else "missing")
|
||||
return res
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# 总管复核四组（review861.py 原文逐字，同一真实 s6_result 入口）
|
||||
def s6_answer(s):
|
||||
return {"answer": s, "ok": True}
|
||||
|
||||
|
||||
ORCH6 = {"pass": True, "status_annotation_in_block": True,
|
||||
"unresolved_contrast": {"built": True, "self_consistent": True}}
|
||||
|
||||
REVIEW_GOOD_CLOSED = "你答应周五晚告诉我面试结果，现在已经告诉我了。"
|
||||
REVIEW_GOOD_OPEN = "你答应周五晚告诉我面试结果，还没有告诉我。"
|
||||
# (名称, 已结侧回答, 未结侧回答, 修后期望 pass)
|
||||
REVIEW_CASES = {
|
||||
"positive_interview": (REVIEW_GOOD_CLOSED, REVIEW_GOOD_OPEN, True),
|
||||
"negative_promise_action_negated": (
|
||||
"你未曾答应周五晚告诉我面试结果，现在已经告诉我了。",
|
||||
REVIEW_GOOD_OPEN, False),
|
||||
"negative_closed_state_negated": (
|
||||
"你答应周五晚告诉我面试结果，但并非已经告诉我。",
|
||||
REVIEW_GOOD_OPEN, False),
|
||||
"negative_object_bound_to_other_action": (
|
||||
"你答应周五晚告诉我体检结果，现在已经告诉我了；面试结果是另一件事。",
|
||||
"你答应周五晚告诉我体检结果，还没有告诉我；面试结果是另一件事。", False),
|
||||
"negative_no_promise_asserted": (
|
||||
"面试结果现在已经告诉我了。", REVIEW_GOOD_OPEN, False),
|
||||
}
|
||||
|
||||
# audit861 既有正负例的预期极性（不回归）
|
||||
HELD_S6_EXPECT = {
|
||||
"negative_wrong_object_medical_check": False,
|
||||
"negative_unknown_closed_state": False,
|
||||
"negative_closed_is_negated": False,
|
||||
"positive_interview": True,
|
||||
"positive_open_synonym_not_received": True,
|
||||
"held_S6_resolved_answer_says_open": False,
|
||||
"held_S6_both_answers_no_knowledge": False,
|
||||
"held_S6_unresolved_claims_result_received": False,
|
||||
"held_S6_unresolved_same_synonym_received": False,
|
||||
"held_S6_positive_audit860": True,
|
||||
"held_S6_positive_rework": True,
|
||||
"held_S6_status_missing": False,
|
||||
}
|
||||
HELD_S2S3_EXPECT = {
|
||||
"held_S2_details_absent_from_both_contexts": False,
|
||||
"held_S2_unknown_answers": False,
|
||||
"held_S2_positive": True,
|
||||
"held_S2_request_failed": False,
|
||||
"held_S3_unknown_answers": False,
|
||||
"held_S3_correct_answers": True,
|
||||
}
|
||||
|
||||
|
||||
def section_review_four_groups() -> dict:
|
||||
out = {}
|
||||
for name, (closed, opened, expected) in REVIEW_CASES.items():
|
||||
result = A.s6_result(ORCH6, s6_answer(closed), s6_answer(opened))
|
||||
mu = result["layers"]["model_use"]
|
||||
out[name] = {
|
||||
"resolved_input": closed, "open_input": opened,
|
||||
"expected_pass": expected, "actual_pass": result["pass"],
|
||||
"layers": {
|
||||
"resolved_states_promise": mu["resolved_states_promise"],
|
||||
"resolved_affirms_closed": mu["resolved_affirms_closed"],
|
||||
"unresolved_states_promise": mu["unresolved_states_promise"],
|
||||
"unresolved_affirms_open": mu["unresolved_affirms_open"],
|
||||
},
|
||||
"result": result,
|
||||
}
|
||||
return out
|
||||
|
||||
|
||||
def _case_table(review: dict, held_s6: dict, held_s2s3: dict) -> dict:
|
||||
"""全部用例的实际 pass 与预期极性（退出码公式输入）。"""
|
||||
table: dict[str, bool] = {}
|
||||
expect: dict[str, bool] = {}
|
||||
for name, c in review.items():
|
||||
key = f"review.{name}"
|
||||
table[key] = bool(c["actual_pass"])
|
||||
expect[key] = bool(c["expected_pass"])
|
||||
for name, res in held_s6.items():
|
||||
key = f"held_s6.{name}"
|
||||
table[key] = bool(res["pass"])
|
||||
expect[key] = HELD_S6_EXPECT[name]
|
||||
for name, res in held_s2s3.items():
|
||||
key = f"held_s2s3.{name}"
|
||||
table[key] = bool(res["pass"])
|
||||
expect[key] = HELD_S2S3_EXPECT[name]
|
||||
return table, expect
|
||||
|
||||
|
||||
def _all_cases_match(table: dict, expect: dict) -> bool:
|
||||
return all(table[k] == expect[k] for k in expect)
|
||||
|
||||
|
||||
def _flip_dependence(table: dict, expect: dict) -> dict:
|
||||
"""翻转自检：任一用例实际值翻转必须改变用例总判（退出码真实依赖正负例）。"""
|
||||
base = _all_cases_match(table, expect)
|
||||
flips = {}
|
||||
for k in expect:
|
||||
flipped = dict(table)
|
||||
flipped[k] = not flipped[k]
|
||||
flips[k] = _all_cases_match(flipped, expect) != base
|
||||
return {"base_all_match": base, "every_flip_changes_verdict": all(
|
||||
flips.values()), "per_case": flips}
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
def main(argv: list[str]) -> dict:
|
||||
global PHASE
|
||||
argv = list(argv)
|
||||
rest: list[str] = []
|
||||
PHASE = "postfix"
|
||||
it = iter(argv[1:])
|
||||
for tok in it:
|
||||
if tok == "--phase":
|
||||
PHASE = next(it, "postfix")
|
||||
elif tok.startswith("--phase="):
|
||||
PHASE = tok.split("=", 1)[1]
|
||||
elif not tok.startswith("--"):
|
||||
rest.append(tok)
|
||||
args = rest
|
||||
OUT["phase"] = PHASE
|
||||
|
||||
commit = subprocess.run(["git", "rev-parse", "--short", "HEAD"],
|
||||
capture_output=True, text=True,
|
||||
cwd=str(REPO)).stdout.strip()
|
||||
OUT["commit"] = commit
|
||||
OUT["ledger_before"] = ledger_snapshot()
|
||||
OUT["preserved_evidence_before"] = evidence_hashes()
|
||||
|
||||
OUT["review_four_groups"] = section_review_four_groups()
|
||||
held_s6 = section_s6_affirmative()
|
||||
held_s2s3 = section_s2_s3_no_regression()
|
||||
OUT["held_s6_affirmative"] = held_s6
|
||||
OUT["held_s2_s3_no_regression"] = held_s2s3
|
||||
|
||||
table, expect = _case_table(OUT["review_four_groups"], held_s6, held_s2s3)
|
||||
OUT["case_expect"] = {k: bool(v) for k, v in expect.items()}
|
||||
OUT["case_actual"] = {k: bool(v) for k, v in table.items()}
|
||||
OUT["all_cases_match_expectation"] = _all_cases_match(table, expect)
|
||||
OUT["flip_dependence"] = _flip_dependence(table, expect)
|
||||
|
||||
OUT["ledger_after"] = ledger_snapshot()
|
||||
OUT["ledger_unchanged"] = OUT["ledger_before"] == OUT["ledger_after"]
|
||||
OUT["preserved_evidence_after"] = evidence_hashes()
|
||||
OUT["preserved_evidence_unchanged"] = (
|
||||
OUT["preserved_evidence_before"] == OUT["preserved_evidence_after"])
|
||||
|
||||
r4 = OUT["review_four_groups"]
|
||||
# ---- prefix：四组反例全部复现（pass=true）且正确正例保留 ----
|
||||
four_groups_reproduced = (
|
||||
all(r4[n]["actual_pass"] for n in (
|
||||
"negative_promise_action_negated", "negative_closed_state_negated",
|
||||
"negative_object_bound_to_other_action",
|
||||
"negative_no_promise_asserted"))
|
||||
and r4["positive_interview"]["actual_pass"])
|
||||
# ---- postfix：四组反例全部判失败，正例与既有判据不回归 ----
|
||||
four_groups_rejected = (
|
||||
not any(r4[n]["actual_pass"] for n in (
|
||||
"negative_promise_action_negated", "negative_closed_state_negated",
|
||||
"negative_object_bound_to_other_action",
|
||||
"negative_no_promise_asserted"))
|
||||
and r4["positive_interview"]["actual_pass"])
|
||||
OUT["summary"] = {
|
||||
"phase": PHASE,
|
||||
"four_groups_reproduced": four_groups_reproduced,
|
||||
"four_groups_rejected": four_groups_rejected,
|
||||
"all_cases_match_expectation": OUT["all_cases_match_expectation"],
|
||||
"flip_dependence_holds": OUT["flip_dependence"][
|
||||
"every_flip_changes_verdict"],
|
||||
"ledger_unchanged": OUT["ledger_unchanged"],
|
||||
"preserved_evidence_unchanged": OUT["preserved_evidence_unchanged"],
|
||||
"pass": (four_groups_reproduced and PHASE == "prefix"
|
||||
and OUT["all_cases_match_expectation"]
|
||||
and OUT["ledger_unchanged"])
|
||||
or (four_groups_rejected and PHASE == "postfix"
|
||||
and OUT["all_cases_match_expectation"]
|
||||
and OUT["flip_dependence"]["every_flip_changes_verdict"]
|
||||
and OUT["ledger_unchanged"]
|
||||
and OUT["preserved_evidence_unchanged"]),
|
||||
}
|
||||
out_path = Path(args[0]) if args else (
|
||||
REPO / "spike/hel857/results/"
|
||||
f"audit862_{'prefix' if PHASE == 'prefix' else 'postfix'}.json")
|
||||
out_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
out_path.write_text(json.dumps(OUT, ensure_ascii=False, indent=2),
|
||||
encoding="utf-8")
|
||||
print(json.dumps(OUT["summary"] | {"out": str(out_path)},
|
||||
ensure_ascii=False))
|
||||
return OUT
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(0 if main(sys.argv)["summary"]["pass"] else 1)
|
||||
Reference in New Issue
Block a user