51 lines
3.6 KiB
JSON
51 lines
3.6 KiB
JSON
{
|
||
"baseline_version": "1.11",
|
||
"read_commit": "e31ae2d946829bb1e02be76f5f10c66d61e13e35",
|
||
"task": "HEL-858 补正Mem0对照测试与分享隐私证据(HEL-857 返工)",
|
||
"requirement_ids": [
|
||
"CG-008",
|
||
"CG-009",
|
||
"CG-011",
|
||
"CG-013",
|
||
"CG-014",
|
||
"CG-015",
|
||
"CG-016",
|
||
"CG-021",
|
||
"AM-001",
|
||
"UX-004",
|
||
"UX-006",
|
||
"GOV-001",
|
||
"GOV-002",
|
||
"GOV-003",
|
||
"GOV-004",
|
||
"GOV-005",
|
||
"GOV-006",
|
||
"DEL-001"
|
||
],
|
||
"deliverable": "总管独立复核五项必修的零模型纠错(原hel-857-mem0-spike分支):A/B夹具按(turn,role)完整装载并加逐字逐角色核对门(旧缺陷形态负对照可被抓住);分享桥绑定实际已讲文本spoken_text、部分分享/缺失内容负例、恢复后重跑同套P1-P5/F1-F8;S4/S6已知id编排(metadata回读+prev→new史+新条目不被误改+更新后重新检索装配)并复放run2毒例负对照;S7命中→history推导史→payload来源锚点(含输入指纹)→原文链与未知/无锚点/错来源/未分享伴侣负例及600字装配门;卡级持久嵌入账本与历史用量保守重建(≤100)、_flat修复、S2等价集语义判定、退出码依赖实际结果。新增真实模型请求0次,run1/run2证据、26次账本与余34次额度原样保留。",
|
||
"acceptance": [
|
||
"rework_suite 全部逐项通过(results/rework858_offline.json:R1夹具/重判、R2门禁2全套27键、R3R4编排与链、R5资源账,退出码0)",
|
||
"旧缺陷形态可复现且被新核对门判失败;S1现状侧逐字重验通过",
|
||
"S2现状侧:修复夹具后带门回读恢复'受潮的味道'等价细节(run2假阴性纠正,不记作产品缺点)",
|
||
"F7部分分享:公开写入逐字等于已讲半句,未讲秘密在全量payload与检索均为0;F8缺失已讲文本:拒绝迁入+审计留痕,不整段放行",
|
||
"恢复后P1-P5/F1-F8全套复跑通过(14项restored键,含恢复前telling_log跨恢复幂等)",
|
||
"S4/S6已知id编排全过(含新条目零UPDATE、结果条目无promise_status回读验证);负对照复放证明旧文本选条法选中错误对象",
|
||
"S7链恢复t1用户原句;未知来源/无锚点/输入指纹不符/同轮未分享伴侣全部拒绝;600字装配零私密标记",
|
||
"卡级嵌入账本:历史≤100+本轮65=165≤500(余335);词面另列;真实出站0",
|
||
"check_requirements 对 origin/main 与 origin/agent/agent/de8874a3803b 双基准通过"
|
||
],
|
||
"deferred": [
|
||
"真实A/B复跑(S1 mem0侧、S2/S3/S4/S6模型使用问答、S7真实锚点、S8/S9复验):固定复测方案已交(rework858_offline.json _retest_plan,预计13次≤余34),未经总管核对与主卡批准不执行;零模型补测不冒充真实A/B完成",
|
||
"'严格优于且其他无退化'总验收结论已撤回,待真实复跑按新判据重下",
|
||
"正式采用Mem0或迁移产品:待用户拍板,本卡结果不构成采用决定",
|
||
"中文提取提示词定制、八字情绪/连续生活/主动联系接线、真实语料验收、M5/M6产品接线:继续按R1-R7承接,不以实验代替完整产品验收"
|
||
],
|
||
"requirement_changes": [],
|
||
"verification": [
|
||
"spike/hel857/results/rework858_offline.json(离线全套逐项结果+_retest_plan+资源账)",
|
||
"spike/hel857/README.md《HEL-858 返工修订记录》(旧/新逐项表、结论修订、归责表修订)",
|
||
"原results/*.json与账本未改动(git仅新增文件与实验源码修订);原工作区ledger只读对账26次不变",
|
||
"本轮零网络出站(stub LLM+本地fastembed缓存+假传输);未验证现网/真实档案(本卡范围禁止触及)"
|
||
]
|
||
}
|