87777975c7
actor/judge prompt eval 闭合: actor 3.0.5 正文强化+baseline(7轮); judge 3.0.14 正文强化+anyTerms同义词补全+baseline(judge-a 13轮/judge-b 33轮); registry/checker 版本对齐+顺序锚点 fail-closed 双保险 W-GOLD-LIVE live_prompt: play-loop 契约开口(request/3+provenance/3+ReferenceAssetRecord/1+Registry/1+迁移清单15条); cheap_verify 切v3+消费对账六闸(只消费active)+生成prompt注入接线(0 active不注入); Node runner playtest-v3.cdp.cjs 升/3+绊线恢复; 真模型回归验向后兼容 full_gate+三批基线: full_gate.py 集成runner串六子门+降级+22测; baseline_gates.py fresh25阈值+historical11预期表(2 needs_human交创始人定标)+shadow20框架+38测 注: registry cheap-system 登记 1.8.0→1.8.1 同步此前在途 cheap-system.md frontmatter 升版(修 pre-commit 版本漂移); cheap_verify/cheap_studio/validate/test_acceptance_v3/test_cheap_service_driver 为在途M含本会话叠加+此前W-AXIS在途(同一线无法hunk分离); 3红测试根因与raw审计未入本提交
103 lines
4.5 KiB
JSON
103 lines
4.5 KiB
JSON
{
|
||
"schemaVersion": "historical-expectations/1",
|
||
"topic": "cheap-gen-acceptance-v3-historical-11",
|
||
"canonicalSource": "docs/agent-specs/2026-07-13-生成线验收v3-可信证据闭环-设计.md §5.2",
|
||
"description": "历史 11 局固定预期表（机器可读 fixture）。v3 切换前的历史重放闸门据此逐局对账：3 个 narrative 正例应保留（expect=accept）；5 个旧假阳在没有新硬证时不得 accept（expect=not_accept，accept 即确认假阳放行）；puzzle-r2 真代码 bug 应 reject（expect=reject）；2 个疑似假阴必须先经真人真浏览器定标（expect=needs_human，定标前闸门不得自动 accept、不计真好通过率）。gid 沿用波 3 复核命名（见设计档 §5.2 与父 plan 失效模式三案）。",
|
||
"gatePolicy": {
|
||
"falsePositiveReleaseMax": 0,
|
||
"perGameExpectationMatchRequired": true,
|
||
"needsHumanAutoAcceptAllowed": false,
|
||
"testerErrorIsMismatch": true
|
||
},
|
||
"expectations": [
|
||
{
|
||
"gid": "narrative-r1",
|
||
"genre": "narrative",
|
||
"expected": "accept",
|
||
"category": "positive_control",
|
||
"critical": false,
|
||
"rationale": "narrative 正例应保留：v2 时代加落点回显后 12 步真玩通到结局卡，v3 必须仍能 accept，否则是验收器回退"
|
||
},
|
||
{
|
||
"gid": "narrative-r2",
|
||
"genre": "narrative",
|
||
"expected": "accept",
|
||
"category": "positive_control",
|
||
"critical": false,
|
||
"rationale": "narrative 正例应保留：有后果分支选择 + 明确结局的硬证齐全，v3 必须 accept"
|
||
},
|
||
{
|
||
"gid": "narrative-r3",
|
||
"genre": "narrative",
|
||
"expected": "accept",
|
||
"category": "positive_control",
|
||
"critical": false,
|
||
"rationale": "narrative 正例应保留：结局与已走分支一致的有序事件链可复算，v3 必须 accept"
|
||
},
|
||
{
|
||
"gid": "trpg-r1",
|
||
"genre": "trpg",
|
||
"expected": "not_accept",
|
||
"category": "known_false_positive",
|
||
"critical": true,
|
||
"rationale": "旧假阳：v2 自证循环下被接受（战斗局卡在升级页仍 accept）。没有新硬证时不得 accept；reject 或 inconclusive 均可"
|
||
},
|
||
{
|
||
"gid": "puzzle-r1",
|
||
"genre": "puzzle",
|
||
"expected": "not_accept",
|
||
"category": "known_false_positive",
|
||
"critical": true,
|
||
"rationale": "旧假阳：解谜局未归位仍被接受。没有新硬证（真实归位事件链 + 终盘截图）时不得 accept"
|
||
},
|
||
{
|
||
"gid": "trpg-r2",
|
||
"genre": "trpg",
|
||
"expected": "not_accept",
|
||
"category": "known_false_positive",
|
||
"critical": true,
|
||
"rationale": "旧假阳：局部动画/插件日志被当成输入有效。没有新硬证时不得 accept"
|
||
},
|
||
{
|
||
"gid": "heritage-r2",
|
||
"genre": "heritage",
|
||
"expected": "not_accept",
|
||
"category": "known_false_positive",
|
||
"critical": true,
|
||
"rationale": "旧假阳：非遗局零成品仍被接受。没有新硬证（成品画面 + 工序有序系列）时不得 accept"
|
||
},
|
||
{
|
||
"gid": "sim-business-r2",
|
||
"genre": "sim-business",
|
||
"expected": "not_accept",
|
||
"category": "known_false_positive",
|
||
"critical": true,
|
||
"rationale": "旧假阳：经营局零订单仍被接受（失效模式三案之一）。没有新硬证（order-served 事件链）时不得 accept"
|
||
},
|
||
{
|
||
"gid": "puzzle-r2",
|
||
"genre": "puzzle",
|
||
"expected": "reject",
|
||
"category": "true_bug",
|
||
"critical": true,
|
||
"rationale": "真代码 bug：硬证已证明可复现的产物缺陷，应 reject（accept 即假阳放行；inconclusive 与固定预期不符，需查验收器为何拿不到硬证）"
|
||
},
|
||
{
|
||
"gid": "heritage-r1",
|
||
"genre": "heritage",
|
||
"expected": "needs_human",
|
||
"category": "suspected_false_negative",
|
||
"critical": false,
|
||
"rationale": "疑似假阴：必须先经真人真浏览器定标，未定标前不进入真好通过率；闸门对 accept 判失败（定标前不得自动 accept），reject/inconclusive 挂起等创始人定标，不自动放行也不自动通过"
|
||
},
|
||
{
|
||
"gid": "sim-business-r1",
|
||
"genre": "sim-business",
|
||
"expected": "needs_human",
|
||
"category": "suspected_false_negative",
|
||
"critical": false,
|
||
"rationale": "疑似假阴：节奏窗口在模型推理期间耗尽可能误拒好游戏，必须先真人真浏览器定标；定标前闸门不得自动 accept，其余结果挂起等创始人定标"
|
||
}
|
||
]
|
||
}
|