@vocmarket/tihao-sop@1.0.2:package.json、package-lock.json、skill-package-manifest.json、.claude-plugin/plugin.json 和 MCP server version 已对齐。real-gap-material-audit 已进入 round:refresh 主链路,当前刷新链路为 29 步,并在 local-seed-to-intake-worklist 后执行三缺口材料审计。latest-form:index、handoff:summary、evidence:index 和 round-deposition 已同步接入 realGapMaterialAudit,接手方可以从 latest form、handoff 和沉淀审计中看到同一份材料审计边界。gapCount=3、materialFoundCount=3、openGapCount=3、canCloseProofGap=false;这说明项目材料已连接,不说明业务证明已完成。@vocmarket/tihao-sop@1.0.2 已正式发布到 npm,并验证 latest 可通过 npx 在 fresh workspace 安装使用。node --check scripts\refresh-round-artifacts.jsnode --check scripts\evidence-index.jsnode --check scripts\latest-form-index.jsnode --check scripts\generate-optimization-handoff.jsnode --check scripts\round-deposition-audit.jsnode --check scripts\real-gap-material-audit.jsnpm.cmd run real-gap:materials:smokenpm.cmd run evidence:index:smoke,当前 fixture total=44、not_business_proof=19、real_evidence=6npm.cmd run task:handoff-index:smokenpm.cmd run round:refresh:smoke,29 步全部 pass,round-deposition.passCount=142、failCount=0npm.cmd run round:refresh -- --output-root outputs --strict,29 步全部 pass,真实 outputs 已刷新npm.cmd run package:contents:smokenpm.cmd run acceptancenpm.cmd publish --dry-run --access public --registry https://registry.npmjs.org/npm.cmd publish --access public --registry https://registry.npmjs.org/ 成功,npm 返回 + @vocmarket/tihao-sop@1.0.2npm.cmd view @vocmarket/tihao-sop@1.0.2 version --registry https://registry.npmjs.org/ 返回 1.0.2npm.cmd view @vocmarket/tihao-sop dist-tags.latest version --registry https://registry.npmjs.org/ 返回 latest=1.0.2npx.cmd --yes @vocmarket/tihao-sop@latest workspace --smoke 通过,fresh workspace 安装写入 .claude/plugins/tihao-sourcing 和 .claude/skills/tihao-creator-sourcing,并输出 tihao smoke ok。proof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3;仍不能宣称提号率提升、客户效果达标或人工补号量下降。@vocmarket/tihao-sop@1.0.0:package.json、package-lock.json、skill-package-manifest.json、.claude-plugin/plugin.json 和 MCP server version 已对齐。docs/release-notes.md 从“未发布版本”改为 1.0.0 正式版发布收尾记录,明确技能包 1.0 可以作为可安装、可验收、可继续补真实材料的交付版本推进,但不能替代业务效果证明。docs/tihao-handoff-index.md 已补入 2026-06-13 当前结论:项目资料已经被接入 proofGapMaterialBridge,但三个真实业务证明缺口仍 open。historical-dataset 连接 history-intake-draft.csv 12 行;video-ab-live-proof 连接 video-resource-worklist.csv、4 条参考种子和 3 条候选视频种子;manual-review-and-customer-effect 连接 manual-review-draft.csv 12 行。@vocmarket/tihao-sop@1.0.0 已正式发布到 npm,并验证 latest 可通过 npx 在 fresh workspace 安装使用。npm.cmd run acceptance 通过。npm.cmd publish --dry-run --access public 通过,确认 tarball 为 @vocmarket/tihao-sop@1.0.0,共 176 个文件,package size 约 598.5 kB。npm.cmd publish --access public --registry https://registry.npmjs.org/ 成功,npm 返回 + @vocmarket/tihao-sop@1.0.0。npm.cmd view @vocmarket/tihao-sop@1.0.0 version --registry https://registry.npmjs.org/ 返回 1.0.0。npm.cmd view @vocmarket/tihao-sop dist-tags.latest version --registry https://registry.npmjs.org/ 返回 dist-tags.latest = '1.0.0'、version = '1.0.0'。npx.cmd --yes @vocmarket/tihao-sop@latest workspace --smoke 通过,fresh workspace 安装写入 .claude/plugins/tihao-sourcing 和 .claude/skills/tihao-creator-sourcing,并输出 tihao smoke ok。proof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3;仍不能宣称提号率提升、客户效果达标或人工补号量下降。proof-gap:closure 和 optimization:completion 已递归发现旧 optimization-pipeline-latest 内嵌的历史审计与客户效果审计产物,并在 summary 顶层 sourceFiles.history、sourceFiles.customerEffect 中记录来源。round-deposition 新增 proof-gap-closure-recursive-proof-artifact-discovery 和 optimization-completion-recursive-proof-artifact-discovery 守卫,沉淀 closure/completion 两侧的 nested history/customer-effect 来源字段。briefCount>=5、items.length>=5、客户决策、拒绝原因和人工补号基线;customer-effect 仍缺 overallPass=true、客户选中率实测、参考链路和人工补号量证明。real-proof-intake-bundle:smoke 也改为校验具体证据/证明要求,避免后续又退回到粗粒度 missing historical-dataset-audit.json 或 missing customer-effect-summary.json。node --check scripts\round-deposition-audit.jsnode --check scripts\round-deposition-smoke.jsnpm.cmd run round:deposition:smoke,passCount=137、failCount=0npm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,round-deposition.passCount=137、failCount=0npm.cmd run task:handoff-index:smokenpm.cmd run hygiene:smokenpm.cmd run proof-gap:intake-bundle:smokenpm.cmd run round:refresh:smokenpm.cmd run acceptanceproof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3、blockingReasonCount=8、missingProofRequirementCount=113、videoAbPreflightReadyForVideoAb=false、videoAbPreflightFailureCount=4。round-deposition 新增并通过 3 个派工链路守卫:proof-gap-operator-pack-video-ab-preflight-context、real-proof-intake-bundle-video-ab-preflight-context、real-proof-closure-work-order-video-ab-preflight-context。video-ab-live-proof 在操作包、真实材料总包、真实证明闭环工单里同时保留 preflight 失败上下文:preflight.readyForVideoAb=false、preflight.failureCount=4、preflight.generatedBy=acceptance:video-ab-preflight、runtimeCredentialPresent=false、companyResolved=false、vocSocialProviderTokenPresent=false、videoAnalysisTokenPresent=false。proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab、runtime/VOC/video analysis provider requirements、videoAbPreflight.readyForVideoAb=true 与 videoAbPreflight.company resolved for live run 必须继续出现在下游派工材料里。round-deposition-smoke 的 fixture 已补齐 operator pack、real proof intake bundle、real proof closure work order 三处 video A/B preflight 上下文,并新增 summary/report 断言,避免只靠单脚本 smoke 而每轮沉淀审计漏守。node --check scripts\round-deposition-audit.jsnode --check scripts\round-deposition-smoke.jsnpm.cmd run round:deposition:smoke,passCount=137、failCount=0npm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,round-deposition.passCount=137、failCount=0npm.cmd run hygiene:smokenpm.cmd run acceptanceproof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3、missingProofRequirementCount=113、videoAbPreflightReadyForVideoAb=false、videoAbPreflightFailureCount=4。video-ab-live-proof,也不能宣称提号率提升、客户效果达标或人工补号量下降。proof-gap-operator-pack:smoke 已新增 video-ab-live-proof 行级断言:当前 evidence 必须保留 preflight.readyForVideoAb=false、preflight.failureCount=4、preflight.generatedBy=acceptance:video-ab-preflight、runtimeCredentialPresent=false、companyResolved=false、vocSocialProviderTokenPresent=false、videoAnalysisTokenPresent=false 等非证明上下文。missingProofRequirements 必须继续列出 live proof 要求:proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab、runtime/provider requirements 以及 videoAbPreflight.readyForVideoAb=true。preflight 仍不能关闭 video-ab-live-proof。proof-gap-operator-pack:smoke 不再硬编码 3 个负责人附件;当前 video-real-candidate 已 closed,因此按 open owner 动态校验 ownerArtifactCount=2,同时继续在总表、CSV 和 by-owner/tech-ai.md/csv 中锁住 video A/B preflight 上下文。real-proof-intake-bundle:smoke 已校验总包的 proof gap 行、CSV 导出行、Markdown/CSV 都保留 video A/B preflight 失败上下文和 live proof 缺失要求。real-proof-closure-work-order 的总报告和负责人附件新增“缺失证明要求”列;real-proof:work-order:smoke 已校验 summary、CSV、总 Markdown 和 by-owner/tech-ai.md 都能看到 video A/B preflight 失败原因及 live proof 要求。node --check scripts\proof-gap-operator-pack-smoke.jsnode --check scripts\real-proof-intake-bundle-smoke.jsnode --check scripts\real-proof-closure-work-order.jsnode --check scripts\real-proof-closure-work-order-smoke.jsnpm.cmd run proof-gap:operator-pack:smokenpm.cmd run proof-gap:intake-bundle:smokenpm.cmd run real-proof:work-order:smokenpm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,最新 round-deposition.counts.pass=137、counts.fail=0。npm.cmd run handoff:summary:smokenpm.cmd run task:handoff-index:smokenpm.cmd run hygiene:smokenpm.cmd run acceptanceproof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3、missingProofRequirementCount=113、videoAbPreflightReadyForVideoAb=false、videoAbPreflightFailureCount=4。handoff:summary 的 latestFormIndex 嵌套区块现在会透传 optimizationCompletion,不再只在 handoff 顶层和 businessExecutionIndex 子区块展示完成度审计。optimization-handoff-report.md 的“最新提号表单索引”段新增“优化完成度审计”小节,显示 readyForClaim=false、proofGapOpenCount=3、videoAbPreflightReadyForVideoAb=false、videoAbPreflightFailureCount=4 等边界。task:handoff-index:smoke 已新增防回退断言:校验当前 latest outputs、临时生成 latest-form、临时生成 handoff、business-execution 行都能看到 video A/B preflight 上下文,且仍保持 directCustomerProof=false 和禁止宣称边界。generate-optimization-handoff:smoke 已同步断言 summary.latestFormIndex.optimizationCompletion 和报告小节,避免只修 task smoke 而漏掉 handoff 自身回归。node --check scripts\generate-optimization-handoff.jsnode --check scripts\generate-optimization-handoff-smoke.jsnode --check scripts\task-handoff-index-smoke.jsnpm.cmd run handoff:summary:smokenpm.cmd run task:handoff-index:smokenpm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,round-deposition.counts.pass=137、counts.fail=0。proof-gap-closure.complete=false、businessOpenCount/openCount=3、optimization-completion.readyForClaim=false。proof-gap:closure 和 optimization:completion 已读取最新 video-hit-rate-preflight-summary.json,在真实 live video-hit-rate-summary.json 缺失或不可关闭时,把 runtime preflight 的失败状态写进 video-ab-live-proof 的 evidence 与 missing requirements。not_business_proof:只记录运行条件布尔状态和失败数量,不记录 token 明文,不关闭 video-ab-live-proof,也不替代 proofContext.mode=live、collectionMode=live、generatedBy=acceptance:video-ab 的真实验收产物。latest-form:index、business-execution:index 和 handoff:summary 已展示 videoAbPreflightReadyForVideoAb、videoAbPreflightFailureCount;当前真实输出为 false/4。round-deposition 已新增 proof-gap-closure-video-ab-preflight-context 与 optimization-completion-video-ab-preflight-context 守卫,沉淀 standalone closure/completion 两边的 preflight 上下文。docs/tihao-handoff-index.md 记录该上下文只是 live proof 缺口解释,不是业务证明;当前 optimization-completion.missingProofRequirementCount=113。node --check scripts\proof-gap-closure-audit.jsnode --check scripts\optimization-completion-audit.jsnode --check scripts\round-deposition-audit.jsnode --check scripts\latest-form-index.jsnode --check scripts\business-execution-index.jsnode --check scripts\generate-optimization-handoff.jsnpm.cmd run proof-gap:closure:smokenpm.cmd run optimization:completion:smokenpm.cmd run business-execution:index:smokenpm.cmd run latest-form:index:smokenpm.cmd run handoff:summary:smokenpm.cmd run round:deposition:smokenpm.cmd run task:handoff-index:smokenpm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,round-deposition.counts.pass=137、counts.fail=0。npm.cmd run hygiene:smokenpm.cmd run acceptanceproof-gap-closure.complete=false、businessOpenCount/openCount=3、closedCount=2、precheckOpenCount=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3、blockingReasonCount=8、missingProofRequirementCount=113、videoAbPreflightReadyForVideoAb=false、videoAbPreflightFailureCount=4。proof-gap:closure 和 optimization:completion 现在会二次校验 historical-dataset-audit.json 的细分门槛,不再只看 acceptance.readyForCustomerEffectProof=true 和 briefCount>=5。parseOk、minBriefsMet、allHaveBriefText、allHaveManualFinalList、allHaveCustomerDecision、allHaveFeedbackReason、allHaveManualSupplementBaseline、categoryCoverageMet、items.length>=5、withCustomerDecision>=5、withRejectionReason>=1、withManualSupplementBaseline>=5。optimization:completion 不再接受只有 complete=true 的薄 proof-gap-closure-summary.json;必须同时满足 closedCount>=5、businessGapCount>=5,并带至少 5 条业务 proof-gap 行。optimization:completion 不再接受只有总数的薄 business-proof-progress-summary.json;必须满足 counts.pass>=15,并带至少 15 条步骤行。optimization:pipeline 现在只有在 proof-gap closure 可声明时才会输出 readyForClaim=true:complete=true、openCount=0、closedCount>=5、businessGapCount>=5。node --check scripts\proof-gap-closure-audit.jsnode --check scripts\optimization-completion-audit.jsnode --check scripts\optimization-pipeline.jsnode --check scripts\proof-gap-closure-smoke.jsnode --check scripts\optimization-completion-smoke.jsnode --check scripts\optimization-pipeline-smoke.jsnpm.cmd run proof-gap:closure:smokenpm.cmd run optimization:completion:smokenpm.cmd run optimization:pipeline:smokenpm.cmd run round:refresh -- --output-root outputs --strictnpm.cmd run acceptanceproof-gap-closure.complete=false、proof-gap-closure.openCount=3、proof-gap-closure.closedCount=2。optimization-completion 仍是 complete=false、readyForClaim=false、proofGapOpenCount=3,且 canClaim.*=false。dha_brief.xlsx、PoC 候选名单、旧 pipeline、worklist 或 smoke 结果替代真实历史 Brief、真实视频 A/B live proof、商务复核和客户效果证明。proof-gap:closure 的 manual-review-and-customer-effect 门槛:不再只看 customerEffect.acceptance.overallPass=true,还要求 customer-effect 摘要包含 reviewPath、historyAuditPath、客户选中率、参考链路客户选中率、历史人工补号基线、本轮人工补号量、人工补号减少率,以及完整 acceptance 子门槛。optimization:completion 的 customer-effect-proof 门槛:完成度审计同样要求 customer-effect 绑定当前 historical-dataset-audit.json;如果 customer-effect 摘要绑定旧 history audit,或只写了薄的 overallPass=true,即使其他 gate 看似通过,也不能进入 readyForClaim=true。sourceFiles 现在记录 history 和 customerEffect 产物路径,用于审计 customer-effect 是否绑定当前历史审计产物,防止旧 history/customer-effect 组合绕过当前 proof-gap closure。node --check scripts\proof-gap-closure-audit.js 通过。node --check scripts\optimization-completion-audit.js 通过。node --check scripts\proof-gap-closure-smoke.js 通过。node --check scripts\optimization-completion-smoke.js 通过。npm.cmd run proof-gap:closure:smoke 通过,新增薄 customer-effect 摘要和旧 history 绑定两个防回归用例。npm.cmd run optimization:completion:smoke 通过,新增薄 customer-effect 摘要和旧 history 绑定两个防回归用例。npm.cmd run round:refresh -- --output-root outputs --strict 通过,28 步全为 pass。npm.cmd run acceptance 通过。proof-gap-closure.complete=false、proof-gap-closure.openCount=3、proof-gap-closure.closedCount=2。optimization-completion.complete=false、optimization-completion.readyForClaim=false、proofGapOpenCount=3,canClaim.tihaoRateImproved=false、canClaim.customerEffectAchieved=false、canClaim.manualSupplementReduced=false。dha_brief.xlsx、DHA PoC 推荐表、社媒参考分析版、旧 pipeline 或本地 worklist 升格为业务证明。dha_brief.xlsx 只有 1 个 DHA Brief、参考账号链接和通用规则;缺至少 5 个真实历史 Brief、客户选中/拒绝、拒绝原因、历史人工补号基线和本轮人工补号量,因此仍只能作为 seed,不能关闭 historical-dataset 或 manual-review-and-customer-effect。evidence:index 防误判:当 customer-effect-summary.json 位于同一个输出目录的 optimization-pipeline-summary.json 下时,只有 pipeline 自身 readyForClaim=true 且 proofGapClosure.complete=true/openCount=0,该 customer-effect 才允许进入 real_evidence;否则即使 customer-effect 字段看似通过,也保持 proofLevel=not_business_proof,并在 summary 里写出 pipelineBlocked 原因。scripts/evidence-index-smoke.js 新增回归用例:构造 pipeline-claim-with-open-closure/customer-effect-audit/customer-effect-summary.json,其中 customer-effect 自身门槛全为 true,但 pipeline proofGapClosure.openCount=1,断言该条仍为 not_business_proof,同时 standalone passing customer-effect 仍保持 real_evidence。node --check scripts\evidence-index.js 通过。node --check scripts\evidence-index-smoke.js 通过。npm.cmd run evidence:index:smoke 通过,新增 fixture 后 summary 为 total=40、real_evidence=5、not_business_proof=16、smoke_or_local=19。proofContext。round:refresh --strict 通过,28 步全部 pass;acceptance 通过;proof-gap-closure.complete=false、openCount=3、closedCount=2;optimization-completion.readyForClaim=false、proofGapOpenCount=3。historical-dataset、video-ab-live-proof、manual-review-and-customer-effect 仍 open;本地直接运行 npm.cmd run acceptance:video-ab 仍因缺 TIHAO_SESSION_TOKEN 等运行凭证停在前置检查,不能产出真实 live proof。proof-gap-closure 已正确把 live-provider-overnight-proof 判为 closed,但 optimization-status 只扫描 outputs 目录末尾 80 个子目录,较旧但可关闭的 outputs/overnight-quality-1780682025651/aggregate-summary.json 可能被窗口挤出,导致 optimization-handoff.externalBlockers 仍误列 live-provider-overnight-proof。scripts/optimization-status-audit.js 不再对输出目录做 slice(-80) 窗口截断,改为按目录 mtime 排序后扫描全部可见输出目录。optimization-status 的 live/provider 判断改为复用可关闭条件:liveEnabled=true、overallPass=true、failureCount=0、failedGateCount=0、tokenLeak=false,与 proof-gap:closure 的 closed 口径保持一致。live-provider-overnight-proof 在 optimization-status 中现在为 passed,但说明边界改为“只证明真实 live/provider overnight 通过;不能替代客户效果、历史数据或视频 A/B proof”。scripts/optimization-status-smoke.js 新增回归用例:构造超过 80 个输出目录,再放入一个较旧但可关闭的 live aggregate,断言 findOutputEvidence + hasLiveProof 仍能识别,防止该误判回归。node --check scripts\optimization-status-audit.js 通过。node --check scripts\optimization-status-smoke.js 通过。npm.cmd run optimization:status:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,最新 optimization-status.counts.passed=31、ready_not_proven=2、blocked_by_external_data=1,optimization-handoff.readyCapabilities=31、externalBlockers=1。npm.cmd run acceptance 通过。live-provider-overnight-proof 不再被交接摘要误列为外部阻塞;当前唯一 optimization-handoff.externalBlockers 是 customer-effect-proof,readyNotProven 是 video-ab-proof 和 historical-dataset。proofContext。proof-gap-closure.openCount=3、closedCount=2,video-real-candidate 与 live-provider-overnight-proof 已关闭,video-resource-readiness.readyForVideoAbPreflight=true、realCandidateRows=1。optimization-completion.complete=false、readyForClaim=false、proofGapOpenCount=3、missingProofRequirementCount=61,仍不能宣称提号率提升、客户效果达标或人工补号量下降。dha_brief.xlsx、DHA PoC 推荐表和社媒参考分析版仍只能作为种子材料;当前统一 intake 模板仍有示例/占位,历史数据不足 5 个真实 Brief,也缺客户选择/拒绝记录、拒绝原因、历史人工补号基线和本轮人工补号量。acceptance.passed=true,但 proofContext.mode、proofContext.collectionMode 和 proofContext.generatedBy 仍为 unknown;本地环境只发现 ANTHROPIC_AUTH_TOKEN,直接运行 npm.cmd run acceptance:video-ab 因缺 TIHAO_SESSION_TOKEN 等运行凭证失败,不能关闭真实视频 A/B live proof。docs/tihao-handoff-index.md 已同步最新事实:proof-gap-request.unresolvedCount=3,closed 缺口在请求包中保留为 ready 证据链,不再回到待补队列。longrun:readiness 当前以 proof-gap-closure.openCount=3 为准,避免旧 request 数量或旧产物造成“已关闭缺口又被当作 open”的误判。optimization-pipeline-latest 已被 optimization-completion 标记为 stale=true,必须在真实材料补齐后重跑;旧 pipeline 不能作为当前完成证据。npm run acceptance:video-ab,并生成 proofContext.generatedBy=acceptance:video-ab、proofContext.mode=live、proofContext.collectionMode=live 的当前 live 产物,旧 A/B 结果不能替代。longrun:readiness 现在默认读取 outputs/live-preflight-latest/live-preflight-summary.json,不再在 preflight 已存在时笼统报“缺 preflight summary”;当前最新 preflight 显示 readyForLiveAcceptance=false、readyForVideoAb=false、failures=2、warnings=3,真实缺口是缺 sessionToken、company 和视频/证据 provider。longrun:readiness 已兼容当前 video-resource-readiness-summary.json 的顶层 readyForVideoAbPreflight=true 字段,避免真实视频资源已 ready 时被旧 summary 结构误判。npm.cmd run task:handoff-index:smoke 通过,交接入口仍对齐当前 3 个 open 缺口、2 个 closed 缺口和 2 份负责人附件。npm.cmd run plan:consistency:smoke 通过,静态 5 类缺口全集与当前 3 条 open action 队列保持一致。npm.cmd run longrun:readiness:smoke 通过;真实 longrun:readiness 刷新后为 ready=false、failCount=9,阻塞原因比之前更具体。npm.cmd run round:refresh -- --output-root outputs --strict 通过,28 步全部 pass,但这只代表工程产物刷新成功,不代表业务证明完成。npm.cmd run acceptance 通过,包级 smoke、计划一致性、每轮刷新 smoke、安全审计、包内容门禁和 workspace install smoke 均保持通过;即使通过,长期优化目标仍必须等 proof-gap-closure.openCount=0 且 optimization-completion.readyForClaim=true。proofContext。video-real-candidate 和 live-provider-overnight-proof。其中视频资源审计为 readyForVideoAbPreflight=true、failureCount=0、realCandidateRows=1;proof-gap closure 为 closedCount=2、openCount=3。optimization-completion.readyForClaim=false、proofGapOpenCount=3、longrun:readiness.ready=false、intake-readiness.failureCount=6。不能宣称提号率提升、客户效果达标或人工补号量下降。business-proof:next-actions 跳过已闭合的视频资源补证动作,当前 businessProofNextActions.actionCount=3,不再把“补真实候选视频资源”拉回待办。proof-gap:operator-pack、real-proof:intake-bundle 和 real-proof:work-order 对 closed 行改为保留证据链;当前 ownerArtifactCount=2、workOrderCount=13、proofGapOpenCount=3、realCandidateRows=1。round:deposition、task:handoff-index:smoke、plan:execution-status:smoke、real-proof:work-order:smoke 和 round:refresh:smoke 从固定 3/4/5 个旧缺口断言改为读取当前 proof-gap、operator-pack、video readiness 和 work-order 产物,防止已关闭缺口被误判回待办。docs/tihao-handoff-index.md 已重写为当前单一事实源:明确 proof-gap-closure.openCount=3、closedCount=2、视频资源已 ready、剩余 3 个业务证明缺口和禁用宣称边界。npm.cmd run task:handoff-index:smoke 通过,交接入口已对齐 3 个 open 缺口、2 个 closed 缺口。npm.cmd run plan:consistency:smoke 通过,静态 5 类缺口全集与当前 3 条 open action 队列不冲突。npm.cmd run round:refresh -- --output-root outputs --strict 通过,27 步全部 pass,刷新后仍为 proof-gap-closure.openCount=3、closedCount=2、video-resource-readiness.readyForVideoAbPreflight=true。npm.cmd run acceptance 通过,包级 smoke、计划一致性、每轮刷新 smoke、安全审计、包内容门禁和 workspace install smoke 均通过。proof-gap:closure 之前只取最新 aggregate-summary.json,会被更新但不可关闭的 smoke/坏 aggregate 覆盖;实际已有可关闭的真实 live/provider overnight aggregate:outputs/overnight-quality-1780682025651/aggregate-summary.json。live-provider-overnight-proof 这一项,长期优化目标仍未完成:proof-gap-closure.openCount=4、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0。proof-gap:closure 和 optimization:completion 均改为优先选择可关闭的 overnight aggregate,并把选中的 source 写入 summary/report;较新的坏 aggregate 不再覆盖较旧但真实可关闭的 aggregate。live-provider-overnight-proof 的关闭条件统一为 liveEnabled=true、overallPass=true、failureCount=0、failedGateCount=0、tokenLeak=false;token leak 会作为缺失证明要求阻塞关闭。round-deposition 的守卫从固定“5 个 open 业务缺口”改为跟随当前未关闭缺口,避免已关闭的 live/provider 行仍被要求带缺失证明或生成下一步行动。plan:consistency:smoke 的当前行动队列检查改为读取 proof-gap-closure-summary.json:静态软件补证表仍保留 5 类业务缺口全集,但下一步行动队列只要求覆盖当前 4 个 open 业务缺口,并禁止已 closed 的 live-provider-overnight-proof 回到待办。proof-gap-closure.closedCount=1、proof-gap-closure.openCount=4、business-proof-next-actions.actionCount=4、real-proof-closure-work-order.workOrderCount=18、proofGapOpenCount=4、optimization-completion.blockingReasonCount=9、missingProofRequirementCount=61。node --check scripts\proof-gap-closure-audit.js、node --check scripts\optimization-completion-audit.js、node --check scripts\proof-gap-closure-smoke.js、node --check scripts\optimization-completion-smoke.js、node --check scripts\round-deposition-audit.js 通过。npm.cmd run proof-gap:closure:smoke、npm.cmd run optimization:completion:smoke、npm.cmd run round:deposition 通过。npm.cmd run plan:consistency:smoke 通过,确认静态 5 类缺口表与当前 4 条 open action 队列不再互相误判。npm.cmd run round:refresh -- --output-root outputs --strict 通过,27 步全部 pass,round-deposition.passCount=127、failCount=0。npm.cmd run acceptance 通过,包级 smoke、计划一致性、每轮刷新 smoke、安全审计、包内容门禁和 workspace install smoke 均保持通过。outputs/overnight-quality-1780682025651/aggregate-summary.json 关闭,当前剩余 4 个业务证明缺口”;不能说提号率已提升、客户效果已达标或人工补号量已下降。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0。round-deposition 和报告能看到 blockingReasonsWithMissingProofRequirements=10、missingProofRequirementCount=65,但 optimization-completion-summary.json 顶层没有直接写这两个计数,下一轮容易从报告或沉淀审计反推。optimization:completion 顶层新增 materialType=optimization_completion_audit、directCustomerProof=false、proofLevel=not_business_proof、blockingReasonCount=10、blockingReasonsWithMissingProofRequirements=10、missingProofRequirementCount=65。latest-form:index、handoff:summary 和 business-execution:index 改为优先读取完成度审计 summary 顶层计数,并在报告/执行总表中展示 missingProofRequirementCount。optimization-completion-smoke、latest-form-index-smoke、generate-optimization-handoff-smoke、business-execution-index-smoke 新增防回退断言,要求完成度审计缺失证明计数可见且保持非业务证明边界。node --check scripts\optimization-completion-audit.js、node --check scripts\optimization-completion-smoke.js、node --check scripts\latest-form-index.js、node --check scripts\latest-form-index-smoke.js、node --check scripts\generate-optimization-handoff.js、node --check scripts\generate-optimization-handoff-smoke.js、node --check scripts\business-execution-index.js、node --check scripts\business-execution-index-smoke.js 通过。npm.cmd run optimization:completion:smoke、npm.cmd run latest-form:index:smoke、npm.cmd run handoff:summary:smoke、npm.cmd run business-execution:index:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 27 步全部 pass;outputs/optimization-completion-latest/optimization-completion-summary.json、latest-form-index-summary.json、optimization-handoff-summary.json 均已透传 blockingReasonsWithMissingProofRequirements=10、missingProofRequirementCount=65、directCustomerProof=false、proofLevel=not_business_proof。real-proof-closure-work-order 不是继续堆说明文档,而是把 intake-readiness、video-resource-readiness、proof-gap-closure、optimization-completion 中仍未关闭的阻塞,拆成负责人、目标文件、目标字段、行范围、种子线索和复验命令,能直接服务商务/投放补真实材料。not_business_proof、directCustomerProof=false、canCloseProofGap=false 边界。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0 仍然成立;不能宣称提号率提升、客户效果达标或人工补号量下降。round:refresh 固定为 27 步,在 local-seed-to-intake-worklist 之后、latest-form-index 之前刷新 real-proof-closure-work-order,确保最新表单索引和交接摘要读到最新工单。evidence:index 已把 real-proof-closure-work-order 归类为 not_business_proof,当前工单 workOrderCount=19、ownerArtifactCount=3、proofGapOpenCount=5、canCloseProofGap=false。latest-form:index 和 handoff:summary 已透传闭环工单的 Markdown、CSV、summary、3 份 by-owner 附件、19 条工单和非证明边界。round-deposition 新增 7 个守卫,覆盖工单 summary 存在、非证明边界、字段级可执行、latest-form 可见、handoff 顶层可见、handoff.latestFormIndex 可见、evidence 台账可见;当前 round-deposition.passCount=127。docs/tihao-handoff-index.md 已同步第 27 步刷新、闭环工单阅读入口、最近复验结果、角色分工、可说/不可说和复验命令。node --check scripts\refresh-round-artifacts-smoke.js、node --check scripts\evidence-index-smoke.js、node --check scripts\latest-form-index-smoke.js、node --check scripts\generate-optimization-handoff-smoke.js、node --check scripts\task-handoff-index-smoke.js、node --check scripts\round-deposition-audit.js、node --check scripts\round-deposition-smoke.js 通过。npm.cmd run real-proof:work-order:smoke 通过,workOrderCount=19、ownerArtifactCount=3、proofGapOpenCount=5。npm.cmd run evidence:index:smoke 通过,临时台账 total=39、not_business_proof=15、real-proof-closure-work-order=1。npm.cmd run latest-form:index:smoke、npm.cmd run handoff:summary:smoke、npm.cmd run round:deposition:smoke、npm.cmd run round:refresh:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 27 步全部 pass,round-deposition.passCount=127,evidenceIndex.byType["real-proof-closure-work-order"]=1。not_business_proof 边界”;不能说提号率已提升、客户效果已达标或人工补号量已下降。history-intake-draft.csv、video-resource-worklist.csv 和 candidate-seed-worklist.csv,减少“只新增索引、不推动补真实表”的漂移。latest-form-index、optimization-handoff、evidence-index、round:refresh 和 round-deposition 都能看见该 worklist。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0,不能宣称提号率提升、客户效果达标或人工补号量下降。latest-form:index 现在展示“本地种子转 intake 补表 worklist”,并透传 Markdown、CSV、summary、历史草稿、视频资源 worklist、候选复核 worklist、行数和 canCloseProofGap=false 边界。handoff:summary 现在在顶层和 latestFormIndex.localSeedToIntakeWorklist 同步该 worklist,并把运行命令加入下一步命令区。round:refresh 顺序固定为 26 步,local-seed-material-index 和 local-seed-to-intake-worklist 都在 latest-form-index 与 optimization-handoff 之前刷新。round-deposition 新增 5 个守卫:worklist summary 存在、worklist 非证明边界、latest-form-index 可见、handoff 顶层可见、handoff.latestFormIndex 可见;当前真实 round-deposition.passCount=120。docs/tihao-handoff-index.md 已同步阅读顺序、最近复验结果、角色分工、可说/不可说和补齐材料后的复验命令,明确 worklist 只能作为补正式 intake 的草稿,不写入正式模板,也不关闭 proof-gap。node --check scripts\round-deposition-audit.js、node --check scripts\round-deposition-smoke.js、node --check scripts\latest-form-index.js、node --check scripts\generate-optimization-handoff.js 通过。npm.cmd run local-seed-to-intake:worklist:smoke、npm.cmd run latest-form:index:smoke、npm.cmd run handoff:summary:smoke、npm.cmd run round:refresh:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 26 步全部 pass,round-deposition.passCount=120,evidenceIndex.byType["local-seed-to-intake-worklist"]=1。npm.cmd run evidence:index:smoke、npm.cmd run task:handoff-index:smoke、npm.cmd run hygiene:smoke 通过;安全扫描 scannedFiles=173、hitCount=0。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。historyDraftRows=1、referenceSeedRows=4、candidateSeedRows=12、videoWorklistRows=5、videoCandidateNeedsResourceRows=3、canCloseProofGap=false。experience_seed,能辅助校准参考账号拆解、相似链路、主页近作、视觉调性、品类隐性人群、视频深看和客户效果边界。experience-transcript:index,默认读取 ../docs/提号经验 下的 黄圆-AI提号经验逐字稿.md 和 邓发-AI提号经验逐字稿.md,输出 summary、Markdown 和 CSV。evidence:index 新增 experience-transcript-index 分类,固定为 not_business_proof;round:refresh 新增 experience-transcript-index 步骤,位于 local-seed-material-index 和 evidence-index 之间,因此每轮证据台账会读到最新经验逐字稿索引。acceptance 纳入 experience-transcript:index:smoke,防止后续把逐字稿索引误升级为业务证明或泄露原文中的 secret-like 内容。task-handoff-index:smoke 同步为 25 步刷新口径,并新增逐字稿索引 not_business_proof、transcriptCount=2、coveredRuleCount=8 的防回退断言。experience-transcript-index-smoke 的 secret-like 测试夹具改为运行时拼接,保留“不输出敏感文本”的测试意图,同时避免源码触发安全审计。node --check scripts\experience-transcript-index.js 通过。node --check scripts\experience-transcript-index-smoke.js 通过。node --check scripts\task-handoff-index-smoke.js 通过。node --check scripts\evidence-index.js 通过。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。npm.cmd run experience-transcript:index -- --output outputs\experience-transcript-index-latest 通过,transcriptCount=2、coveredRuleCount=8、canCloseProofGap=false。npm.cmd run experience-transcript:index:smoke 通过。npm.cmd run evidence:index:smoke 通过,临时台账中 experience-transcript-index 归类为 not_business_proof。npm.cmd run round:refresh:smoke 通过,临时刷新链路已稳定为 25 步。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 25 步全部 pass,round-deposition.passCount=115,evidence-index.byType["experience-transcript-index"]=1。npm.cmd run task:handoff-index:smoke 通过,交接入口已守住 25 步、逐字稿索引和 readyForClaim=false 边界。npm.cmd run hygiene:smoke 通过,scannedFiles=171、hitCount=0。npm.cmd run acceptance 通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0。not_business_proof 边界”;不能说提号率已提升、客户效果已达标或人工补号量已下降。local-seed-material:index 的工作簿表头、样例行和 signals.sampleUrls 现在会清洗展示 URL,去掉 query/hash 等平台临时分享参数,避免把 xsec_token、access_token、Authorization 等敏感或噪声参数带入索引产物。local-seed-material-index-smoke 新增 URL 清洗和 secret-like redaction 断言,防止后续把分享 token 参数写回本地种子材料索引。outputs/local-seed-material-index-latest/local-seed-material-index-summary.json 中样例 URL 不再包含 query/hash;proofLevel=not_business_proof、directCustomerProof=false、canCloseProofGap=false 保持不变。node --check scripts\local-seed-material-index.js 通过。node --check scripts\local-seed-material-index-smoke.js 通过。npm.cmd run local-seed-material:index:smoke 通过。npm.cmd run local-seed-material:index -- --outputs outputs --output outputs\local-seed-material-index-latest 通过,existingMaterialCount=3、canCloseProofGap=false。Select-String 检查 outputs/local-seed-material-index-latest 的 summary/Markdown/CSV 未发现 xsec_token、access_token、refresh_token、sessionToken 或 Authorization。npm.cmd run round:refresh -- --output-root outputs --strict 通过,24 步全部 pass,round-deposition.passCount=115。npm.cmd run evidence:index:smoke、npm.cmd run round:refresh:smoke、npm.cmd run round:deposition:smoke、npm.cmd run task:handoff-index:smoke、npm.cmd run hygiene:smoke 和 npm.cmd run acceptance 均通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false、intake-readiness.failureCount=9、video-resource-readiness.realCandidateRows=0。local-seed-material:index,把 ../dha_brief.xlsx、../output/dha-tihao-poc/AI提号-DHA小红书推荐名单-PoC.xlsx 和 ../output/dha-tihao-poc/AI提号-DHA小红书推荐名单-社媒参考分析版.xlsx 做成本地种子材料索引。outputs/local-seed-material-index-latest/local-seed-material-index-summary.json、Markdown 和 CSV,当前识别 existingMaterialCount=3、workbookCount=3、promisingLiveAggregateCount=1,并强制保留 proofLevel=not_business_proof、directCustomerProof=false、canCloseProofGap=false。brief/通用提号规则/参考媒体信息,以及 PoC 表的 结论/主推账号/备选复核/参考账号解析/Brief与方法 等 sheet、行数和表头。evidence:index 新增 local-seed-material-index 分类,固定为 not_business_proof;round:refresh 新增 local-seed-material-index 步骤,位于 optimization-handoff 和 evidence-index 之间,因此每轮证据台账会读到最新种子材料索引。node --check scripts\local-seed-material-index.js 通过。node --check scripts\local-seed-material-index-smoke.js 通过。npm.cmd run local-seed-material:index:smoke 通过。npm.cmd run local-seed-material:index -- --outputs outputs --output outputs\local-seed-material-index-latest 通过,existingMaterialCount=3、canCloseProofGap=false。npm.cmd run evidence:index:smoke 通过,临时台账中 local-seed-material-index 归类为 not_business_proof。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。business-proof:next-actions 现在会把 proof-gap-closure 中被主行动吸收的缺口行合并回主行动,避免 step-03、step-04、step-12 有下一步文字但没有结构化关闭条件。missingProofRequirements:真实历史 Brief、真实视频资源、人工复核标注、真实视频 A/B 验收、真实 live/provider 长跑证明。round-deposition 新增 business-proof-next-actions-missing-proof-requirements 防回退守卫,并沉淀 businessProofNextActions.withMissingProofRequirements=5。round-deposition.passCount=115,round:refresh --strict 仍为 23 步全通过。node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过。npm.cmd run business-proof:next-actions:missing-proof:smoke 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过,passCount=115。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 23 步全部 pass,round-deposition.passCount=115。npm.cmd run round:refresh:smoke 通过,roundPassCount=115。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。round-deposition 新增 latest-form-index-client-list-delivery-quality 防回退守卫,要求最新表单索引里的软件候选名单同时满足:directCustomerProof=false、rowCount>0、sourceDuplicateRemovedCount>=0、finalDuplicateGroupCount=0、duplicateCountMeaning=source_duplicate_removed_count、rankContinuous=true。round-deposition 的 observed/report 新增候选名单交付质量字段:latestFormIndex.clientListRowCount、latestFormIndex.clientListSourceDuplicateRemovedCount、latestFormIndex.clientListFinalDuplicateGroupCount、latestFormIndex.clientListDuplicateCountMeaning、latestFormIndex.clientListRankContinuous、latestFormIndex.clientListDirectCustomerProof。round-deposition:smoke 已加入 fixture 和断言,防止后续只保留候选名单路径,却丢失“最终重复组”和“源表去重丢弃”的业务口径。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过,passCount=114。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 23 步全部 pass,已包含 software-client-list 且位于 latest-form-index 之前,round-deposition.passCount=114。npm.cmd run task:handoff-index:smoke、npm.cmd run hygiene:smoke、npm.cmd run round:refresh:smoke 和 npm.cmd run acceptance 均通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。optimization-completion.readyForClaim=false,longrun:readiness.ready=false。software-client-list.final.summary.json 里的兼容字段 duplicateCount=32 表示源表去重丢弃行数,不表示最终软件端名单还有 32 个重复项,容易误导商务或下一轮 AI。software:export summary 新增 sourceDuplicateRemovedCount、finalDuplicateGroupCount、duplicateCountMeaning=source_duplicate_removed_count,保留 legacy duplicateCount 但明确其含义。software:markdown 将顶部摘要改为“源表去重丢弃行数”和“最终名单重复组数”,避免把源表去重丢弃误读成最终名单重复。latest-form:index 已在候选名单入口展示 最终重复组、排名连续 和 源表去重丢弃,并继续标记 directCustomerProof=false。sourceRows=60、outputRows=28、sourceDuplicateRemovedCount=32、finalDuplicateGroupCount=0、rankContinuous=true。node --check scripts\export-software-table.js 通过。node --check scripts\export-software-markdown.js 通过。node --check scripts\software-table-smoke.js 通过。node --check scripts\latest-form-index.js 通过。node --check scripts\latest-form-index-smoke.js 通过。npm.cmd run software:smoke 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 22 步全部 pass,round-deposition.passCount=114。npm.cmd run acceptance 通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。optimization:completion 现在为 10 个完成门槛中的每个 blocked gate 输出结构化 missingProofRequirements,覆盖 intake readiness、真实候选视频、proof-gap closure、视频 A/B live proof、live/provider 长跑、客户效果、pipeline、handoff、15 步补证进度和 longrun readiness。missingProofRequirements,避免在 closed/ready 场景残留旧缺失项。round-deposition 新增 optimization-completion-missing-proof-requirements 防回退守卫,并沉淀 optimizationCompletion.blockingReasonsWithMissingProofRequirements=10、optimizationCompletion.missingProofRequirementCount=65。optimization-completion-report.md 的完成门槛表现在直接展示每个 blocked gate 的“缺失证明”,下一轮不需要只凭 readyForClaim=false 反推关闭条件。node --check scripts\optimization-completion-audit.js 通过。node --check scripts\optimization-completion-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run optimization:completion:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=113。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 22 步全部 pass,round-deposition.passCount=113。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。optimization-completion 和 round-deposition 仍只是完成度审计与防回退入口。proof-gap:closure 现在为每个未关闭行输出结构化 missingProofRequirements:intake readiness、历史数据集、真实候选视频、视频 A/B live proof、live/provider 长跑、商务复核和客户效果都会列出缺哪条证明。proof-gap-operator-pack 和 real-proof-intake-bundle 自动透传每个业务 gap 的缺失证明要求;当前真实输出 operatorPackMissingProofRequirementCount=38,5 个 gap row 中 3 个 open row 均有缺失证明要求,closed 行只保留证据链。round-deposition 新增 proof-gap-closure-missing-proof-requirements 和 proof-gap-operator-pack-missing-proof-by-gap 两个防回退守卫,并沉淀 proofGapClosure.openRowsWithMissingProofRequirements=5、proofGapOperatorPack.openRowsWithMissingProofRequirements=5。docs/tihao-handoff-index.md 已同步当前阅读入口和最近复验结果,当前 round-deposition.passCount=112。node --check scripts\proof-gap-closure-audit.js 通过。node --check scripts\proof-gap-closure-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run proof-gap:closure:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=112。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 22 步全部 pass,round-deposition.passCount=112。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。proof-gap-closure、proof-gap-operator-pack、real-proof-intake-bundle 和 round-deposition 都只是补证协调与防回退审计入口。latest-form:index 的 nextActions 现在同步输出 complete、actionCount、proofOpenCount、ownerGroupCount、ownerArtifactCount、sourceState.proofGapOpenCount 和前 5 个高优先级 topActions。handoff:summary 的 latestFormIndex 现在透传最新表单索引中的下一步行动队列摘要,下一轮 AI 只读交接摘要也能看到 step-03、gap-video-ab-live-proof 等首批补证动作。round-deposition 新增 latest-form-index-next-actions-top-actions 和 handoff-latest-form-index-next-actions-top-actions 两个防回退守卫,并在报告中沉淀 latestFormIndex.nextActionsTopCount、handoff.latestFormIndex.nextActionsTopCount 和对应 proofGapOpenCount。task:handoff-index:smoke 已补充当前产物和临时重生成产物的双层校验,确保 business-proof-next-actions-summary.json、latest-form-index-summary.json 和 optimization-handoff-summary.json 的行动队列摘要链路不断。docs/tihao-handoff-index.md 已同步阅读顺序和最近复验结果,当前 round-deposition.passCount=110、latestFormIndex.nextActionsTopCount=5、handoff.latestFormIndex.nextActionsTopCount=5。node --check scripts\latest-form-index.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。node --check scripts\task-handoff-index-smoke.js 通过。npm.cmd run latest-form:index:smoke 通过,topActionCount=5。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=110、latestFormIndexNextActionsTopCount=5、handoffLatestFormIndexNextActionsTopCount=5。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 中 22 步全部 pass,round-deposition.passCount=110。npm.cmd run task:handoff-index:smoke 通过,当前 latestFormIndexNextActionTopCount=5、handoffLatestFormIndexNextActionTopCount=5。npm.cmd run round:refresh:smoke 通过,临时输出 roundPassCount=110。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过,包内容门禁 entryCount=167,workspace install smoke 通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。latest-form-index、optimization-handoff 和 round-deposition 都只是补证协调与防回退审计入口。latest-form:index 将 outputs/long-run-readiness-latest/long-run-readiness-report.md 和 long-run-readiness-summary.json 纳入一等入口,暴露 ready=false、failCount=6、proofLevel=not_business_proof 和 directCustomerProof=false。handoff:summary 在顶层、latestFormIndex.longRunReadiness 和 businessExecutionIndex.longRunReadiness 同步长跑前置门禁,并把 longrun:readiness 纳入下一轮复验命令。handoff:summary 同步新增顶层 optimizationCompletion 和 businessExecutionIndex.optimizationCompletion,当前 readyForClaim=false、proofGapOpenCount=5、blockingReasonCount=10,继续禁止提号率提升、客户效果达标和人工补号量下降声明。real-proof-intake-bundle 在打开顺序、sourceState 和补齐后复验命令中新增长跑前置门禁入口,当前 longRunReadinessReady=false、longRunReadinessFailCount=6、exportRowCount=34。business-execution-index 将长跑前置门禁和优化完成度审计纳入关键文件行,当前 rowCount=24、fileRowCount=6;长跑前置门禁报告 行为 status=blocked、actionCount=6,优化完成度审计报告 行为 status=blocked、actionCount=10。round-deposition 新增 7 个长跑入口防回退守卫:latest-form-index-longrun-readiness、handoff-longrun-readiness、handoff-latest-form-longrun-readiness、business-execution-index-longrun-readiness、handoff-business-execution-index-longrun-readiness、real-proof-intake-bundle-summary、real-proof-intake-bundle-longrun-readiness。round-deposition 新增 5 个优化完成度审计防回退守卫:optimization-completion-summary、optimization-completion-boundary、business-execution-index-optimization-completion、handoff-optimization-completion、handoff-business-execution-index-optimization-completion。round:refresh 调整执行顺序,先刷新 optimization-completion,再生成 business-execution-index 和 handoff:summary,确保执行总表与交接摘要都能透传完成度审计行。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果、完成判定矩阵和复验命令,明确 longrun:readiness.ready=false 和 optimization-completion.readyForClaim=false 不能被 22 步 refresh 通过或 smoke 通过替代。round:refresh --strict 已刷新真实 outputs,当前 22 步全部 pass;round-deposition 当前 passCount=97、failCount=0,且观测到 businessExecutionIndexOptimizationCompletionReadyForClaim=false、handoffBusinessExecutionIndexOptimizationCompletionStatus=blocked、optimizationCompletionBlockingReasonCount=10。node --check scripts\latest-form-index.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\business-execution-index.js 通过。node --check scripts\business-execution-index-smoke.js 通过。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。node --check scripts\task-handoff-index-smoke.js 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run business-execution:index:smoke 通过,商务执行总表已包含 long-run-readiness-summary.json、optimization-completion-summary.json 来源和对应关键文件行。npm.cmd run proof-gap:intake-bundle:smoke 通过,exportRowCount=34,总包已包含 long-run-readiness-report.md 和 longrun:readiness 复验命令。npm.cmd run round:deposition:smoke 通过,passCount=97、failCount=0。npm.cmd run task:handoff-index:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过,round-refresh-summary.json 显示 22 步全部 pass。npm.cmd run round:refresh:smoke 通过,临时输出中 22 步顺序稳定且 roundPassCount=97。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过;包内容门禁 entryCount=167,workspace install smoke 通过。proof-gap-closure.openCount=5,optimization-completion.readyForClaim=false、blockingReasonCount=10,longrun:readiness.ready=false。real-proof-intake-bundle、proof-gap-request、proof-gap-operator-pack、最新索引、22 步 refresh 或 long-run-readiness 报告当作业务证明。已更新:
scripts/round-deposition-audit.jsscripts/round-deposition-smoke.js处理结果:
round-deposition 新增 latest-form-index-intake-owner-recheck 守卫,要求最新提号表单索引必须保留字段补齐负责人分组和补齐后复验命令。round-deposition 新增 handoff-latest-form-index-intake-owner-recheck 守卫,要求交接摘要同步保留最新表单索引中的负责人分组数和复验命令数。failCount=0。latestFormIndex.intakeFieldChecklistOwnerGroupCount=3、latestFormIndex.intakeFieldChecklistRecheckCommandCount=5、handoff.latestFormIndex.ownerGroupCount=3、handoff.latestFormIndex.recheckCommandCount=5。边界:
proof-gap-closure.openCount=5,optimization-status.complete=false。更新时间:2026-06-06
执行目标:落实 docs/tihao-experience-optimization-plan.md,把商务提号经验转成技能包可执行能力、可验收输出和可持续反馈闭环。
已新增:
docs/business-proof-action-order.md已更新:
scripts/round-deposition-audit.jsscripts/round-deposition-smoke.jsscripts/generate-optimization-handoff.jsscripts/generate-optimization-handoff-smoke.js处理结果:
round:deposition 现在会检查补证操作顺序文档存在,并确认文档包含 intake:readiness、longrun:readiness、customer-effect:audit、sample/smoke 边界和“客户效果不可宣称”口径。handoff:summary 现在会在交接摘要中直接列出 docs/business-proof-action-order.md,下一轮 AI 或商务可以先按这份 15 步清单补齐真实证据。原因:
optimization:status 仍为 complete=false,真实材料预审和长跑就绪度未通过。已新增:
scripts/business-proof-progress.jsscripts/business-proof-progress-smoke.jsbusiness-proof:progressbusiness-proof:progress:smoke处理结果:
pass、pending、fail 或 blocked_by_external_data,避免只同步“总体未完成”而看不出下一步卡在哪里。round:deposition 现在会检查 business-proof-progress-summary.json 是否存在、是否包含 15 步、是否记录 pass/pending/fail/blocked_by_external_data 统计。optimization:status 现在新增 business-proof-progress 稳定状态项,用于标记 15 步进度同步能力已就绪;该项不代表客户效果证明完成。原因:
已新增:
scripts/business-proof-next-actions.jsscripts/business-proof-next-actions-smoke.jsbusiness-proof:next-actionsbusiness-proof:next-actions:smoke处理结果:
business-proof-progress-summary.json、proof-gap-closure-summary.json、intake-readiness-summary.json 和 video-resource-readiness-summary.json 生成下一步行动队列。by-owner/*.md 和 by-owner/*.csv,每个负责人可直接打开自己的补证任务文件。evidence:index 现在会把行动队列识别为 business-proof-next-actions,证明等级为 smoke_or_local。round:deposition 现在会检查行动队列是否存在且至少有一条可分派动作。optimization:status 现在新增 business-proof-next-actions 稳定状态项。acceptance 现在会运行 business-proof:progress:smoke 和 business-proof:next-actions:smoke,发布/总验收时会守住进度同步与行动队列链路。原因:
已新增:
scripts/export-software-table.jsscripts/software-table-smoke.jssoftware:exportsoftware:smoke处理结果:
manual-review-sample.csv,确认旧 overnight 汇总存在跨策略重复。例如 outputs/overnight-quality-1780675711800/manual-review-sample.csv 原始 60 行,按 brief编号 + 平台 + 主页链接/博主名称 去重后 15 行,重复 45 条。outputs/overnight-quality-1780675711800/software-client-list.dedup.csv。software:smoke 已纳入 npm run acceptance,发布前会自动校验表头、去重和连续排名。已更新:
scripts/review-metrics.jsscripts/review-metrics-smoke.jsdocs/manual-review-handoff.mddocs/ai-overnight-optimization-task.md负样本口径调整:
跑偏、硬性规则违规、调性不符、主页质感不符、参考账号不像。归因类型、失败归因 或 归因 任一字段。review:metrics -- --strict 会在负样本缺归因时失败,避免只有人工标签、没有可反哺原因。本轮验证:
node --check scripts/export-software-table.jsnode --check scripts/software-table-smoke.jsnpm.cmd run software:smokenode --check scripts/review-metrics.jsnode --check scripts/review-metrics-smoke.jsnpm.cmd run review:metrics:smokenpm.cmd run acceptance已更新:
scripts/acceptance.jsscripts/optimization-status-audit.js处理结果:
npm run acceptance 现在会执行 npm run acceptance:providers:mock。optimization:status 的“基础发布链路”现在要求:
acceptancesmoke:packagemcp:smokeacceptance:providers:mockacceptance.js 实际调用 provider mock 门禁。原因:
npm run acceptance:providers:mock。已更新:
scripts/export-software-table.jsscripts/overnight-quality-campaign.jsscripts/software-table-smoke.jsdocs/tihao-experience-optimization-plan.mddocs/capability-map.mdREADME.mddocs/release-notes.md处理结果:
brief编号 内的候选从 1 开始连续排名;多个 brief 同表输出时,每个 brief 独立连续。software:smoke 已增加多 brief 样例,防止后续回退为全局排名。已更新:
scripts/smoke-package.jsscripts/optimization-status-audit.js处理结果:
smoke:package 不只检查 needs_token,还会断言:
errors=[]401/403Authorization headersmoke-package 的软件端 CSV 排名断言同步为“每个 brief 内连续”。optimization:status 的基础发布链路现在会检查 smoke-package 是否包含友好鉴权状态断言。原因:
已更新:
scripts/provider-contract-audit.jsscripts/optimization-status-audit.js处理结果:
401/403Authorization headeroptimization:status 的基础发布链路会检查 provider mock 是否包含公开输出安全断言。原因:
已更新:
scripts/hard-rules-smoke.jspackage.jsonscripts/acceptance.jsscripts/optimization-status-audit.js处理结果:
npm run hard-rules:smoke。npm run acceptance 现在会强制执行 hard-rules smoke。已剔除;optimization:status 增加“硬性规则和剔除账号本地验收”项,要求 hard-rules smoke 存在并纳入 acceptance。原因:
已更新:
scripts/reference-rules-smoke.jspackage.jsonscripts/acceptance.jsscripts/optimization-status-audit.js处理结果:
npm run reference-rules:smoke。npm run acceptance 现在会强制执行 reference-rules smoke。referenceUsability.status 必须为 reference_conflict;optimization:status 增加“参考账号冲突和强推荐解释本地验收”项。原因:
已新增:
mcp/src/features/tihao-sourcing/experience-rules.jscriteria.requirementLayerscriteria.categoryRulescriteria.referenceUsabilitycriteria.sourcingStrategy当前支持:
已新增:
mcp/src/features/tihao-sourcing/homepage-evidence.jscandidate.homepageEvidencecandidate.recentContentFitScorecandidate.visualQualityScorecandidate.toneConsistencyScore当前逻辑:
recentEvidence、内容标签、人设标签;已更新:
mcp/src/features/tihao-sourcing/ranker.js变化:
已更新:
mcp/src/features/tihao-sourcing/report.js新增报告章节:
需求三分层与隐性规则参考账号可参考性判断主页最近内容证据CSV 新增字段:
主页证据分视觉质感分调性一致分隐性规则命中隐性规则违规homepageEvidenceNotes修复:
剔除/降级原因 不再把普通备选误写成“不进入商务名单”;已剔除才不能进商务可用名单,需复核必须补证后再判断。已新增:
scripts/import-feedback-memory.jsscripts/feedback-import-smoke.jsfeedback:importfeedback:smoke已更新:
mcp/src/features/tihao-sourcing/preference-memory.js当前支持从 CSV 导入:
brief编号平台博主名称主页链接人工复核标签反馈标签反馈原因归因类型影响范围是否升级为团队规则下一轮动作沉淀到 memory:
feedbackRecordsfeedbackSummarypersonalPreferencesclientBrandPreferencesteamRuleCandidatesblockedCreatorsblockedStyles已通过:
npm run feedback:smoke
npm run acceptance:pm
npm run smoke:briefs
npm run acceptance:providers:mock
npm run mcp:smoke
npm run smoke:package
npm run acceptance
小规模质量矩阵:
$env:TIHAO_OVERNIGHT_FIXTURES="dha-mom-baby,sensitive-skin-repair,healthy-snack"
$env:TIHAO_OVERNIGHT_VARIANTS="baseline-live,result-first,result-first-broad"
$env:TIHAO_OVERNIGHT_MAX_RUNS="9"
$env:TIHAO_OVERNIGHT_FAIL_ON_GATES="false"
npm run overnight:quality
结果:
outputs/overnight-quality-1780730115072liveEnabled=false说明:这次矩阵是 sample/结构性验证,不证明真实 live 命中率。真实结果提升仍需用客户 token 和 live provider 跑矩阵验证。
当前主页证据主要来自候选已有 recentEvidence 和标签。下一步需要接入真实主页最近 10/20 篇内容 provider:
验收:
homepageEvidence.source=provider;当前已能导入 memory。下一步需要做端到端二轮验证:
npm run feedback:import -- --feedback <csv> --memory <json>;tihao_brief_sourcing_run 使用同一 memory;当前已沉淀 teamRuleCandidates,还需要:
需要在有安全 token/额度时跑:
baseline-live,result-first,result-first-broad;reference-account/homepage-evidence 策略;docs/software-client-table-format.md。brief编号 + 平台 + 主页链接 不重复;无主页链接时按 brief编号 + 平台 + 博主名称 去重。homepageEvidenceBaseUrl / homepageProviderBaseUrl。homepageEvidenceFile / homepageEvidenceJsonPath 本地证据。homepageEvidenceToken / homepageProviderToken。criteria.homepageEvidenceStatus。homepage:smoke,用本地 mock provider 真实跑通主页证据接入。feedback:roundtrip,验证反馈 CSV 导入 memory 后,第二轮自动剔除被反馈拉黑/跑偏账号。smoke:package 为中文和软件端表格新契约。fixtures/sample-briefs/skincare-sample.md,避免 npm 脚本中文路径在 Windows 下被命令行编码污染。已通过:
npm run smoke:package
npm run smoke:briefs
npm run feedback:smoke
npm run feedback:roundtrip
npm run homepage:smoke
npm run mcp:smoke
npm run acceptance:pm
npm run acceptance:providers:mock
npm run acceptance
软件端表格抽检:
duplicateKeys=0docs/software-client-table-format.md 一致泄密/乱码扫描:
docs、skills、mcp/src、scripts、fixturesovernight:quality 增加软件端交付表验收:
tihao-sourcing-client-list.csv。overnight:quality 增加主页证据状态验收:
criteria.homepageEvidenceStatus。homepageProviderStatus。softwareDuplicateKeyCountsoftwareRankContinuoushomepageProviderStatus.md 输出加 UTF-8 BOM,避免 Windows 打开乱码。manual-review-sample.csv 表头改为中文复核字段。docs/overnight-quality-runbook.md 已重写为中文手册,包含 sample、受控 live、完整 live、门禁和人工复核说明。小矩阵验证:
$env:TIHAO_OVERNIGHT_LIVE="false"
$env:TIHAO_OVERNIGHT_FIXTURES="sensitive-skin-repair"
$env:TIHAO_OVERNIGHT_VARIANTS="baseline-live,result-first"
$env:TIHAO_OVERNIGHT_MAX_RUNS="2"
$env:TIHAO_OVERNIGHT_FAIL_ON_GATES="true"
npm run overnight:quality
结果:
runs=2failures=0gatePass=truesoftwareDuplicateKeyCount=0softwareRankContinuous=truehomepageProviderStatus=not_requested完整验收:
npm run acceptance
结果:通过。
泄密/乱码扫描:
docs、skills、mcp/src、scripts、fixturesCount=0scripts/live-preflight.js。npm run live:preflight。docs/live-provider-integration-runbook.md 已加入预检、严格模式、live acceptance、video A/B 的执行顺序。预检能力:
doubao-seed-2-0-pro。live-preflight-summary.json,只记录布尔状态、provider 配置状态和下一步动作,不记录密钥明文。本地无真实环境变量时运行:
npm run live:preflight
结果:
outputs/live-preflight-1780733665849readyForLiveAcceptance=falsereadyForVideoAb=falsefailures=2warnings=3完整验收:
npm run acceptance
结果:通过。
live:preflight 不扣费,也不证明 live 提号命中率。scripts/video-hit-rate-audit.js,把参考视频 A/B 从“资源数量检查”升级为门禁化验收。docs/acceptance-checklist.md 和 docs/live-provider-integration-runbook.md,统一视频验收口径。新增门禁:
doubao-seed-2-0-pro。ok。pending、fallback 或“待补证据”占位。新增输出:
video-hit-rate-summary.jsonvideo-hit-rate-report.md已通过:
node --check scripts/video-hit-rate-audit.js
npm run acceptance
npm run acceptance:providers:mock
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0npm run acceptance:video-ab。acceptance:video-ab 在真实环境通过,才可以说“本次样本里视频分析确实提升了提号结果”。mcp/src/features/tihao-sourcing/preference-memory.js。scripts/import-feedback-memory.js。scripts/feedback-import-smoke.js。mcp/src/features/tihao-sourcing/report.js。skills/tihao-creator-sourcing/references/output-format.md。新增能力:
teamRuleSuggestions。feedbackSummary 新增 teamRuleSuggestionCount。反馈记忆与团队规则建议 章节。已通过:
node --check mcp/src/features/tihao-sourcing/preference-memory.js
node --check scripts/import-feedback-memory.js
node --check scripts/feedback-import-smoke.js
npm run feedback:smoke
npm run feedback:roundtrip
npm run acceptance
额外端到端检查:
反馈记忆与团队规则建议;criteria.memory.teamRuleSuggestions.length=1。精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0teamRuleSuggestions 是建议升级,不会静默替代人工决策。scripts/review-metrics.js。scripts/review-metrics-smoke.js。npm run review:metricsnpm run review:metrics:smokenpm run acceptance 已纳入 review:metrics:smoke。docs/manual-review-handoff.md,补充人工复核标签、客户选择字段和质量指标统计方法。新增能力:
可直接发客户 + 商务复核 / 已标注总数。跑偏 + 硬性规则违规 + 调性不符 + 主页质感不符 + 参考账号不像 / 已标注总数。归因类型/失败归因/归因 的负样本 / 负样本总数。客户选中 / 已标注总数。review-metrics-summary.jsonreview-metrics-report.md门禁:
已通过:
node --check scripts/review-metrics.js
node --check scripts/review-metrics-smoke.js
npm run review:metrics:smoke
npm run acceptance
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0客户选择 字段回填后才能验证。scripts/overnight-quality-campaign.js。docs/overnight-quality-runbook.md。新增 overnight 策略:
reference-account:发布候选策略,用于验证参考账号/参考链接补证和相似度链路。homepage-evidence:发布候选策略,用于验证主页最近内容、封面质感和调性一致性链路。aggregate 报告新增:
参考补证状态主页证据状态完整 live 矩阵现已包含:
baseline-live,reference-account,homepage-evidence,video-enhanced,result-first,result-first-risk,result-first-broad
新策略 sample 子集:
$env:TIHAO_OVERNIGHT_LIVE="false"
$env:TIHAO_OVERNIGHT_FIXTURES="sensitive-skin-repair"
$env:TIHAO_OVERNIGHT_VARIANTS="baseline-live,reference-account,homepage-evidence"
$env:TIHAO_OVERNIGHT_MAX_RUNS="3"
$env:TIHAO_OVERNIGHT_FAIL_ON_GATES="true"
npm run overnight:quality
结果:
outputs/overnight-quality-1780734584209runs=3failures=0gatePass=true带参考链接 sample 子集:
$env:TIHAO_OVERNIGHT_LIVE="false"
$env:TIHAO_OVERNIGHT_FIXTURES="dha-mom-baby"
$env:TIHAO_OVERNIGHT_VARIANTS="baseline-live,reference-account"
$env:TIHAO_OVERNIGHT_MAX_RUNS="2"
$env:TIHAO_OVERNIGHT_FAIL_ON_GATES="true"
npm run overnight:quality
结果:
outputs/overnight-quality-1780734606550runs=2failures=0gatePass=trueneeds_social_analysis_enrichment,不会误报真实补证完成。完整验收:
npm run acceptance
结果:通过。
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0reference-account、homepage-evidence 已在真实 provider 下提升命中率。scripts/overnight-quality-campaign.js。docs/overnight-quality-runbook.md。新增环境门禁:
TIHAO_GATE_REQUIRE_REFERENCE_PROVIDER=true
reference-account 策略的参考补证状态必须为 ok。TIHAO_GATE_REQUIRE_HOMEPAGE_PROVIDER=true
homepage-evidence 策略的主页证据状态必须为 ok。这两个门禁默认关闭,不影响 sample smoke 和普通发布验收。真实 provider 联调或 live 长跑验收时应打开。
默认门禁小矩阵:
$env:TIHAO_OVERNIGHT_LIVE="false"
$env:TIHAO_OVERNIGHT_FIXTURES="dha-mom-baby"
$env:TIHAO_OVERNIGHT_VARIANTS="baseline-live,reference-account"
$env:TIHAO_OVERNIGHT_MAX_RUNS="2"
$env:TIHAO_OVERNIGHT_FAIL_ON_GATES="true"
npm run overnight:quality
结果:
outputs/overnight-quality-1780734793179runs=2failures=0gatePass=true严格参考 provider 门禁:
$env:TIHAO_GATE_REQUIRE_REFERENCE_PROVIDER="true"
npm run overnight:quality
结果:
outputs/overnight-quality-1780734793371gatePass=falsereference-provider-okneeds_social_analysis_enrichmentok严格主页 provider 门禁:
$env:TIHAO_GATE_REQUIRE_HOMEPAGE_PROVIDER="true"
npm run overnight:quality
结果:
outputs/overnight-quality-1780734804090gatePass=false完整验收:
npm run acceptance
结果:通过。
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0reference-provider-ok=pass 或 homepage-provider-ok=pass。scripts/historical-dataset-audit.js。scripts/historical-dataset-audit-smoke.js。docs/historical-dataset-guide.md。npm run history:auditnpm run history:audit:smokenpm run acceptance 已纳入 history:audit:smoke。新增能力:
historical-dataset-audit.jsonhistorical-dataset-audit.md已通过:
node --check scripts/historical-dataset-audit.js
node --check scripts/historical-dataset-audit-smoke.js
npm run history:audit:smoke
npm run acceptance
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0history:audit 后再验证。docs/ai-overnight-optimization-task.md,同步到当前完整 SOP。新版任务书已包含:
npm run acceptancenpm run acceptance:providers:mocknpm run live:preflight -- --strictnpm run history:auditreference-account 和 homepage-evidence 策略;TIHAO_GATE_REQUIRE_REFERENCE_PROVIDER=trueTIHAO_GATE_REQUIRE_HOMEPAGE_PROVIDER=truenpm run acceptance:video-abnpm run review:metrics已通过:
npm run acceptance
精确泄密/乱码扫描:
docs、scripts、mcp/src、skills、fixturesCount=0README.md。docs/install-guide.md。docs/capability-map.md。docs/release-notes.md。同步内容:
npm run live:preflightnpm run review:metricsnpm run history:auditteamRuleSuggestions;已通过:
npm run acceptance
精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesnode_modules、.claude 本地安装副本Count=0scripts/optimization-status-audit.js。npm run optimization:status。README.md。docs/ai-overnight-optimization-task.md。新增能力:
passed:当前代码、脚本或本地验收已覆盖;ready_not_proven:入口已具备,但需要真实 token/provider/数据证明;blocked_by_external_data:需要真实 live 权限、provider 或客户选择数据;missing:实现缺失。optimization-status-summary.jsonoptimization-status-report.md已通过:
node --check scripts/optimization-status-audit.js
npm run optimization:status
状态审计结果:
passed=8ready_not_proven=2blocked_by_external_data=2complete=false未完成项:
精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesnode_modules、.claude 本地安装副本Count=0scripts/optimization-status-audit.js,导出 buildStatusSummary。scripts/optimization-status-smoke.js。npm run optimization:status:smoke。npm run acceptance 已纳入 optimization:status:smoke。Smoke 校验:
passed 项。ready_not_proven 项。blocked_by_external_data 项。已通过:
node --check scripts/optimization-status-audit.js
node --check scripts/optimization-status-smoke.js
npm run optimization:status:smoke
npm run acceptance
精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesnode_modules、.claude 本地安装副本Count=0scripts/overnight-quality-campaign.js:
off-topic-rate 改为 negative-risk-rate。TIHAO_GATE_MAX_NEGATIVE_RISK_RATE,并兼容旧变量 TIHAO_GATE_MAX_OFF_TOPIC_RATE。offTopicRate 输出字段作为历史兼容字段,同时新增/优先使用 negativeRiskRate。negativeRiskRate 当前仍来自 fixture 的 offTopicTerms 自动规则,只能作为夜跑风险门禁;真实业务负样本率仍以人工复核表为准。scripts/optimization-status-audit.js:
id。title,默认等于中文 requirement。ID 列,方便软件端或自动化任务读取。scripts/optimization-status-smoke.js:
video-ab-proof、customer-effect-proof 等关键项稳定 id。id/title。已通过:
node --check scripts\optimization-status-audit.js
node --check scripts\optimization-status-smoke.js
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0scripts/historical-dataset-audit.js:
manualSupplementBaseline、manualSupplementCount、manualAddedCount 和 metrics.manualSupplementCount 识别。withManualSupplementBaseline 统计。acceptance.allHaveManualSupplementBaseline。acceptance.readyForCustomerEffectProof,用于区分“可长期长跑”和“可证明客户效果/人工补号减少”。scripts/historical-dataset-audit-smoke.js:
readyForCustomerEffectProof。scripts/optimization-status-audit.js:
historical-dataset 状态项现在检查客户选择、拒绝原因和人工补号量基线门禁是否存在。docs/historical-dataset-guide.md:
manualSupplementBaseline。已通过:
node --check scripts\historical-dataset-audit.js
node --check scripts\historical-dataset-audit-smoke.js
npm run history:audit:smoke
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0scripts/video-hit-rate-audit.js:
computeVideoAcceptance,让视频 A/B 验收逻辑可以被本地 smoke 复用。buildAcceptanceGates、computeVideoAcceptance、summarizeResourceEvidence、summarizeEvidenceQuality、summarizeRun。require() 该脚本时不再触发真实 live 请求。scripts/video-hit-rate-audit-smoke.js:
package.json:
npm run acceptance:video-ab:smoke。scripts/acceptance.js:
acceptance:video-ab:smoke。scripts/optimization-status-audit.js:
video-ab-proof 状态项现在检查 live 脚本和 smoke 是否覆盖关键 A/B 门禁。已通过:
node --check scripts\video-hit-rate-audit.js
node --check scripts\video-hit-rate-audit-smoke.js
npm run acceptance:video-ab:smoke
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0acceptance:video-ab 仍需要真实 token/company/provider 才能证明视频分析对真实提号命中率有提升。scripts/feedback-roundtrip-smoke.js:
跑偏、调性不符、主页质感不符、参考账号不像。blockedCreators 写入记忆。blockedStyles。teamRuleSuggestions。scripts/optimization-status-audit.js:
feedback-roundtrip 状态项现在检查多标签负样本、二轮剔除、blocked style 和团队规则建议覆盖。已通过:
node --check scripts\feedback-roundtrip-smoke.js
npm run feedback:roundtrip
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0review:metrics 和 live 矩阵,才能证明真实负样本率下降。scripts/homepage-evidence-provider-smoke.js:
POST /homepage-evidencecontractVersion=tihao-homepage-evidence-v1requestedCapabilities 包含 recent_posts、cover_quality、category_consistency、tone_consistency、risk_reviewdisplayName、profileUrl,并遵守 creators limitokunauthorized_or_quotamcp/src/features/tihao-sourcing/report.js:
scripts/optimization-status-audit.js:
homepage-provider-entry 状态项现在检查请求契约、成功补证、未授权降级和公开输出安全。已通过:
node --check mcp\src\features\tihao-sourcing\report.js
node --check scripts\homepage-evidence-provider-smoke.js
npm run homepage:smoke
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0scripts/platform-sourcing-strategy-smoke.js:
reference_similarity。keyword_or_recruitment。package.json:
npm run platform:strategy:smoke。scripts/acceptance.js:
platform:strategy:smoke。scripts/optimization-status-audit.js:
reference-rules 状态项现在同时检查参考冲突 smoke 和分平台策略 smoke。已通过:
node --check scripts\platform-sourcing-strategy-smoke.js
npm run platform:strategy:smoke
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0mcp/src/features/tihao-sourcing/report.js:
tihao-sourcing-client-list.csv 继续按 brief编号 + 平台 + 主页链接/博主名称 去重。targetCount 时,软件端可复核候选池改为 Math.ceil(targetCount * 1.5)。reviewPoolTarget,方便软件端或自动化任务读取。scripts/candidate-pool-smoke.js:
package.json:
npm run candidate-pool:smoke。scripts/acceptance.js:
npm run acceptance 纳入 candidate-pool:smoke。scripts/optimization-status-audit.js:
software-table 状态项现在检查 1.5 倍候选池逻辑和 smoke 是否接入默认验收。docs/ai-optimization-task-software-table.md:
已通过:
node --check mcp\src\features\tihao-sourcing\report.js
node --check scripts\candidate-pool-smoke.js
node --check scripts\optimization-status-audit.js
npm run software:smoke
npm run optimization:status:smoke
npm run candidate-pool:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0scripts/overnight-quality-campaign.js:
manual-review-sample.csv 在软件端 17 列后新增 客户选择、归因类型、反馈原因 三列。可直接发客户、商务复核、可投但需补证、跑偏、硬性规则违规、调性不符、主页质感不符、参考账号不像。归因类型,并给出可优化归因:需求解析错、隐性规则漏、召回关键词错、主页证据不足、视频证据误判、排序权重错、输出解释错、软件端表重复或排名不连续。客户选择:客户选中、客户拒绝、待客户反馈。scripts/overnight-manual-review-smoke.js:
manual-review-sample.csv 已写出。人工复核标签、客户选择、归因类型、反馈原因。review:metrics 读取。aggregate-report.md 明确说明客户选择、归因类型和参考账号不像标签。package.json:
npm run overnight:review:smoke。scripts/acceptance.js:
npm run acceptance 纳入 overnight:review:smoke。scripts/optimization-status-audit.js:
review-metrics 状态项现在检查夜跑人工复核表是否预置客户选择、归因和反馈字段。docs/manual-review-handoff.mddocs/overnight-quality-runbook.mddocs/ai-overnight-optimization-task.mddocs/ai-optimization-task-software-table.mddocs/acceptance-checklist.md已通过:
node --check scripts\overnight-quality-campaign.js
node --check scripts\overnight-manual-review-smoke.js
node --check scripts\optimization-status-audit.js
npm run overnight:review:smoke
npm run review:metrics:smoke
npm run optimization:status:smoke
npm run optimization:status
npm run acceptance
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0review:metrics 验证。mcp/src/features/tihao-sourcing/ranker.js:
homepageEvidenceHitPoints。homepageEvidenceHitPoints 从主页 matched terms、有效 review notes 和真实 provider 状态中提取。scripts/reference-rules-smoke.js:
briefHitConditions。referenceStyleHitPoints 或 homepageEvidenceHitPoints。scripts/product-acceptance-audit.js:
homepageEvidenceHitPoints。scripts/overnight-quality-campaign.js:
homepageEvidenceHitPoints 和 referenceStyleHitPoints,方便后续人工抽检和策略对比。scripts/optimization-status-audit.js:
reference-rules 状态项现在检查参考风格或主页证据的结构化命中门禁。docs/tihao-experience-optimization-plan.mddocs/acceptance-checklist.mddocs/ai-optimization-task-software-table.md已通过:
node --check mcp\src\features\tihao-sourcing\ranker.js
node --check scripts\reference-rules-smoke.js
node --check scripts\product-acceptance-audit.js
node --check scripts\overnight-quality-campaign.js
node --check scripts\optimization-status-audit.js
npm run reference-rules:smoke
npm run acceptance:pm
npm run optimization:status:smoke
npm run acceptance
npm run optimization:status
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0review:metrics 验证。mcp/src/features/tihao-sourcing/homepage-evidence.js:
visualRiskSignals 识别,覆盖 封面下沉、封面混乱、画面模糊、排版混乱、低质、低质量、搬运、粗糙、杂乱、硬广感。visualRiskSignals 扣分。reviewNotes 会输出 主页质感风险:...。mcp/src/features/tihao-sourcing/ranker.js:
homepageQualityRisks。homepageQualityRisks,且 visualQualityScore >= 55。主页质感风险 或 视觉质感分低于强推荐门槛。mcp/src/features/tihao-sourcing/homepage-evidence-provider.js:
visualRiskSignals 会被透传并参与强推荐降级。scripts/hard-rules-smoke.js:
homepageQualityRisks 包含 封面下沉。主页质感风险。scripts/homepage-evidence-provider-smoke.js:
visualRiskSignals 后候选不能强推荐。scripts/optimization-status-audit.js:
hard-rules 状态项现在检查低质主页风险降级。docs/tihao-experience-optimization-plan.mddocs/acceptance-checklist.mddocs/ai-optimization-task-software-table.md已通过:
node --check mcp\src\features\tihao-sourcing\homepage-evidence.js
node --check mcp\src\features\tihao-sourcing\ranker.js
node --check mcp\src\features\tihao-sourcing\homepage-evidence-provider.js
node --check scripts\hard-rules-smoke.js
node --check scripts\homepage-evidence-provider-smoke.js
npm run hard-rules:smoke
npm run homepage:smoke
npm run optimization:status:smoke
npm run acceptance
npm run optimization:status
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCount=0review:metrics 验证。mcp/src/features/tihao-sourcing/ranker.js:
referenceStyleHitPoints 只保留真实匹配到的参考信号。需补相似账号证据、待补参考风格证据 等弱提示进入 referenceFallbackHitPoints。referenceEvidenceSource 和 referenceEvidenceConcrete。参考待补,与真实 参考/风格命中 区分。scripts/reference-rules-smoke.js:
referenceStyleHitPoints 不得包含 待补、需补 等占位证据。referenceEvidenceConcrete=false,且不能进入强推荐。docs/tihao-experience-optimization-plan.mddocs/acceptance-checklist.mddocs/ai-optimization-task-software-table.mdscripts/export-software-markdown.js:
package.json:
npm run software:markdown。outputs/overnight-quality-1780682025651/manual-review-sample.csv 输出软件端去重表:
outputs/overnight-quality-1780682025651/software-client-list.dedup.csvoutputs/overnight-quality-1780682025651/software-client-list.dedup.mdoutputs/overnight-quality-1780682025651/software-client-list.dedup.summary.jsonbrief编号 + 平台 + 主页链接;没有主页链接时使用 brief编号 + 平台 + 博主名称。true已通过:
node --check mcp\src\features\tihao-sourcing\ranker.js
node --check scripts\reference-rules-smoke.js
node --check scripts\overnight-quality-campaign.js
node --check scripts\optimization-status-audit.js
node --check scripts\export-software-markdown.js
npm run reference-rules:smoke
npm run acceptance:pm
npm run optimization:status:smoke
npm run software:smoke
npm run acceptance
npm run optimization:status
状态审计结果:
passed=10ready_not_proven=2blocked_by_external_data=2complete=false精确泄密/乱码扫描:
docs、README.md、scripts、mcp/src、skills、fixturesCOUNT=0scripts/leak-mojibake-audit.js:
docs、README.md、scripts、mcp/src、skills、fixtures。package.json:
npm run hygiene:smoke。scripts/acceptance.js:
npm run acceptance 纳入 hygiene:smoke。scripts/optimization-status-audit.js:
output-hygiene 状态项。hygiene:smoke 是否存在、是否覆盖 sessionToken 和乱码模式、是否进入默认 acceptance。已通过:
node --check scripts\leak-mojibake-audit.js
node --check scripts\optimization-status-audit.js
npm run hygiene:smoke
npm run optimization:status:smoke
npm run acceptance
npm run optimization:status
hygiene:smoke 结果:
scannedFiles=80hitCount=0状态审计结果:
passed=11ready_not_proven=2blocked_by_external_data=2complete=falsescripts/review-metrics.js:
byStrategy。strategyComparison,把 reference-account、homepage-evidence、video-enhanced 归为参考/证据增强链路,把 baseline-live、brief-only、keyword-only 归为关键词/基础基线链路。referenceCustomerSelectedRatePass:当参考/证据增强链路有客户选择数据时,要求客户选中率 >= 40%。referencePassRateHigherThanKeyword:当参考链路和关键词基线都有标注样本时,要求参考链路商务可用率高于关键词/基础基线。review-metrics-report.md 新增“分策略指标”和“参考链路对照”章节。scripts/review-metrics-smoke.js:
baseline-live 与 reference-account/homepage-evidence 标注样本时,参考链路通过率对照能正确计算并通过。scripts/optimization-status-audit.js:
review-metrics 状态项现在检查参考链路对照逻辑和 smoke 覆盖。docs/manual-review-handoff.mddocs/tihao-experience-optimization-plan.md已通过:
node --check scripts\review-metrics.js
node --check scripts\review-metrics-smoke.js
npm run review:metrics:smoke
npm run optimization:status:smoke
npm run acceptance
npm run optimization:status
状态审计结果:
passed=11ready_not_proven=2blocked_by_external_data=2complete=false人工复核标签、客户选择、归因类型 后运行 npm run review:metrics -- --input <已标注CSV> --strict。scripts/long-run-readiness-audit.js:
smoke、live-subset、full-matrix、video-ab、customer-effect 模式。live-preflight-summary.json,检查 readyForLiveAcceptance、sessionToken、company、Parse 用户解析和视频模型。historical-dataset-audit.json,检查真实历史 Brief 是否可用于完整矩阵和客户效果证明。video-ab 模式要求 readyForVideoAb=true 且模型为 doubao-seed-2-0-pro。customer-effect 模式要求历史数据达到 readyForCustomerEffectProof=true,并具备人工补号量基线。long-run-readiness-summary.json 和 long-run-readiness-report.md。scripts/long-run-readiness-smoke.js:
package.json:
npm run longrun:readiness。npm run longrun:readiness:smoke。scripts/acceptance.js:
longrun:readiness:smoke。scripts/optimization-status-audit.js:
long-run-readiness 状态项。docs/ai-overnight-optimization-task.mddocs/overnight-quality-runbook.md已通过:
node --check scripts\long-run-readiness-audit.js
node --check scripts\long-run-readiness-smoke.js
node --check scripts\optimization-status-audit.js
npm run longrun:readiness:smoke
npm run longrun:readiness -- --mode smoke --output outputs\long-run-readiness-smoke-check
npm run acceptance
npm run optimization:status
长跑就绪度 smoke 报告:
outputs/long-run-readiness-smoke-check/long-run-readiness-summary.jsonoutputs/long-run-readiness-smoke-check/long-run-readiness-report.md状态审计结果:
passed=12ready_not_proven=2blocked_by_external_data=2complete=falselive-preflight-summary.json、historical-dataset-audit.json 和客户标注结果时,仍不能证明真实命中率、客户选中率或人工补号量改善。scripts/evidence-index.js:
outputs 下的关键 summary。overnight-qualityoptimization-statuslong-run-readinessreview-metricshistorical-datasetvideo-abreal_evidencesmoke_or_localnot_business_proofevidence-index-summary.json 和 evidence-index-report.md。scripts/evidence-index-smoke.js:
package.json:
npm run evidence:index。npm run evidence:index:smoke。scripts/acceptance.js:
evidence:index:smoke。scripts/optimization-status-audit.js:
evidence-index 状态项。docs/ai-overnight-optimization-task.mddocs/overnight-quality-runbook.md已生成当前 outputs 证据台账:
outputs/evidence-index-latest/evidence-index-summary.jsonoutputs/evidence-index-latest/evidence-index-report.md本次扫描结果:
total=74realEvidence=15smokeOrLocal=17notProof=42已通过:
node --check scripts\evidence-index.js
node --check scripts\evidence-index-smoke.js
node --check scripts\optimization-status-audit.js
npm run evidence:index:smoke
npm run evidence:index -- --output outputs\evidence-index-latest
npm run acceptance
npm run optimization:status
状态审计结果:
passed=13ready_not_proven=2blocked_by_external_data=2complete=falsereal_evidence 只表示有真实证明入口,不自动等同于客户选中率、人工补号量减少或视频 A/B 已达标。scripts/evidence-index.js:
overnight-quality 只有同时满足以下条件才标为 real_evidence:manifest.liveEnabled=trueacceptance.overallPass=truefailureCount=0failedGateCount=0not_business_proof。video-ab 只有同时满足以下关键门禁才标为 real_evidence:acceptance.passed=truescripts/evidence-index-smoke.js:
real_evidence。scripts/optimization-status-audit.js:
evidence-index 状态项同步检查新的严格 smoke 文案。已通过:
node --check scripts\evidence-index.js
node --check scripts\evidence-index-smoke.js
node --check scripts\optimization-status-audit.js
npm run evidence:index:smoke
npm run evidence:index -- --output outputs\evidence-index-latest
npm run acceptance
npm run optimization:status
npm run hygiene:smoke
最新证据台账结果:
total=76realEvidence=5smokeOrLocal=17notProof=54状态审计结果:
passed=13ready_not_proven=2blocked_by_external_data=2complete=falsereal_evidence。real_evidence 仍不是“长期目标完成”的同义词;客户选中率、人工补号量减少和真实业务效果仍要看 review:metrics、历史数据和客户选择字段。
scripts/customer-effect-audit.js:
historical-dataset-audit.json 中的历史人工补号量基线。--current-manual-supplement-count 传入本轮人工补号量。本轮人工补号量、当前人工补号量、人工补号量、manualSupplementCount 等列读取本轮补号量。customer-effect-summary.json 和 customer-effect-report.md。scripts/customer-effect-audit-smoke.js:
package.json:
customer-effect:audit。customer-effect:smoke。scripts/acceptance.js:
customer-effect:smoke。scripts/optimization-status-audit.js:
customer-effect-audit-entry 状态项,用于区分“审计入口已具备”和“真实客户效果已证明”。customer-effect-proof,必须有 customer-effect-summary.json 且 overallPass=true 才能算证明。docs/manual-review-handoff.mddocs/historical-dataset-guide.mddocs/tihao-experience-optimization-plan.mdscripts/evidence-index.js:
customer-effect 证据类型。customer-effect-summary.json。customer-effect-audit/customer-effect-summary.json 子目录。real_evidence。not_business_proof。scripts/evidence-index-smoke.js:
real_evidence,缺证据样本不能进入真实证明。scripts/long-run-readiness-audit.js:
customer-effect 模式下一步命令补充 customer-effect:audit。evidence:index 命令,确保客户效果产物进入证据台账。scripts/optimization-status-audit.js:
evidence-index 状态项同步检查 customer-effect 类型覆盖。已通过:
node --check scripts\evidence-index.js
node --check scripts\evidence-index-smoke.js
node --check scripts\long-run-readiness-audit.js
node --check scripts\optimization-status-audit.js
npm run evidence:index:smoke
npm run longrun:readiness:smoke
npm run optimization:status:smoke
customer-effect-summary.json 且 overallPass=true 时,长期目标仍不会被判定完成。scripts/evidence-index.js:
live-preflight 证据类型。live-preflight-summary.json。readyForLiveAcceptance、readyForVideoAb 和检查项 fail/warn 数量。readyForLiveAcceptance=true 时标记为 smoke_or_local,表示只证明 live 启动前置条件。not_business_proof。scripts/evidence-index-smoke.js:
scripts/optimization-status-audit.js:
evidence-index 状态项同步检查 live-preflight 类型覆盖。docs/overnight-quality-runbook.md:
live-preflight-summary.json 会进入证据台账。scripts/history-dataset-from-csv.js:
brief编号 合并为 per-brief JSON 历史样本。history-dataset-from-csv-summary.json。scripts/history-dataset-from-csv-smoke.js:
history:audit 逻辑,验证可用于长期优化长跑和客户效果证明。package.json:
history:from-csv。history:from-csv:smoke。scripts/acceptance.js:
history:from-csv:smoke。scripts/optimization-status-audit.js:
history-csv-import 状态项。docs/historical-dataset-guide.mddocs/tihao-experience-optimization-plan.mdscripts/optimization-pipeline.js:
--history-csv 自动运行 history:from-csv。history:audit。longrun:readiness。--review-csv 时自动运行 review:metrics 和 customer-effect:audit。evidence:index。--dry-run 只生成计划。--strict 遇到失败即中止并返回非 0。scripts/optimization-pipeline-smoke.js:
package.json:
optimization:pipeline。optimization:pipeline:smoke。scripts/acceptance.js:
optimization:pipeline:smoke。scripts/optimization-status-audit.js:
optimization-pipeline 状态项。docs/overnight-quality-runbook.mddocs/tihao-experience-optimization-plan.mdlive:preflight 和 longrun:readiness。没有真实客户选择、历史人工补号基线和本轮人工补号量时,pipeline 不会宣称业务效果完成。
scripts/export-software-table.js:
小红书、抖音 等中文展示名。brief编号 + 平台 + 规范化博主名称 去重。scripts/export-software-markdown.js:
scripts/software-table-smoke.js:
docs/software-client-table-format.md:
outputs/overnight-quality-1780682025651/software-client-list.final.csvoutputs/overnight-quality-1780682025651/software-client-list.final.mdoutputs/overnight-quality-1780682025651/software-client-list.final.summary.json客户选择率、人工补号减少和视频分析带来的真实业务提升,仍需依赖真实历史数据、商务复核 CSV 和 live A/B 证据。
docs/tihao-experience-optimization-plan.md:
docs/ai-optimization-task-software-table.md:
docs/ai-overnight-optimization-task.md:
真实业务效果仍需真实历史数据、商务复核和客户选择数据证明。
docs/tihao-experience-implementation-log.mddocs/tihao-experience-optimization-plan.mddocs/ai-overnight-optimization-task.mdscripts/leak-mojibake-audit.js:
npm.cmd run hygiene:smoke:
scannedFiles=90hitCount=0-Encoding UTF8 时,终端预览可能显示乱码;这不代表文件实际内容损坏。后续判断文档是否乱码,以 hygiene:smoke 和 UTF-8 读取结果为准。
scripts/evidence-index.js:
optimization-pipeline-summary.json 分类。smoke_or_local,失败时标记为 not_business_proof。readyForClaim=true,pipeline 本身也不直接标为 real_evidence;客户效果仍以 customer-effect 产物单独判定。scripts/evidence-index-smoke.js:
smoke_or_local。not_business_proof。scripts/optimization-pipeline.js 报告模板:
optimization-pipeline-report.md 改为可读中文。scripts/optimization-status-audit.js:
optimization-pipeline 类型。npm.cmd run evidence:index:smoke:
total=12real_evidence=4smoke_or_local=2not_business_proof=6npm.cmd run optimization:pipeline:smoke 通过。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run optimization:status:
passed=16ready_not_proven=2blocked_by_external_data=2complete=false客户选中率、视频分析真实提升、人工补号减少仍需真实数据和独立审计产物证明。
scripts/create-data-intake-pack.js:
history-data-template.csv,用于整理真实历史 Brief、人工名单、客户选择、拒绝原因和历史人工补号量基线。manual-review-template.csv,用于整理本轮 AI 候选、商务复核、客户选择、归因类型、反馈原因和本轮人工补号量。README.md,说明填写规则、审计命令和客户效果证明边界。scripts/create-data-intake-pack-smoke.js:
data:intake-templatedata:intake-template:smokenpm run acceptance 已纳入 data:intake-template:smoke。optimization:status 新增 data-intake-pack 状态项,并显示为 passed。docs/historical-dataset-guide.mddocs/manual-review-handoff.mdoutputs/data-intake-pack-latest/history-data-template.csvoutputs/data-intake-pack-latest/manual-review-template.csvoutputs/data-intake-pack-latest/README.md客户效果证明仍必须等待真实客户选择、历史人工补号基线和本轮人工补号量通过 customer-effect:audit。
scripts/evidence-index.js:
data-intake-pack。history-data-template.csv、manual-review-template.csv 和 README.md 时,登记为数据收集包。smoke_or_local,不作为业务效果证明。scripts/evidence-index-smoke.js:
smoke_or_local。real_evidence。scripts/optimization-status-audit.js:
evidence-index 状态项要求覆盖 data-intake-pack 类型。npm.cmd run evidence:index:smoke:
total=13real_evidence=4smoke_or_local=3not_business_proof=6npm.cmd run optimization:status:
passed=17ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run acceptance 通过。total=99real_evidence=5smoke_or_local=19not_business_proof=75data-intake-pack=1真实客户效果仍必须等待商务填写后的历史数据、客户选择和人工补号量审计。
scripts/generate-optimization-handoff.js:
optimization:status、evidence:index、数据收集包路径和下一轮命令。optimization-handoff-report.md 和结构化 optimization-handoff-summary.json。scripts/generate-optimization-handoff-smoke.js:
customer-effect:audit 等下一步命令。handoff:summaryhandoff:summary:smokenpm run acceptance 已纳入 handoff:summary:smoke。scripts/evidence-index.js:
optimization-handoff-summary.json。smoke_or_local,不作为真实业务证明。scripts/optimization-status-audit.js:
optimization-handoff 状态项。outputs/optimization-handoff-latest/optimization-handoff-summary.jsonoutputs/optimization-handoff-latest/optimization-handoff-report.mdnpm.cmd run handoff:summary:smoke 通过:
readyCapabilities=18readyNotProven=2externalBlockers=2npm.cmd run evidence:index:smoke 通过:
total=14real_evidence=4smoke_or_local=4not_business_proof=6npm.cmd run optimization:status:smoke 通过。npm.cmd run hygiene:smoke 通过:
scannedFiles=94hitCount=0npm.cmd run optimization:status:
passed=18ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=102realEvidence=5smokeOrLocal=20notProof=77npm.cmd run acceptance 通过,新增 handoff:summary:smoke 已进入默认发布验收。长期目标仍未完成,不能调用完成状态。
docs/tihao-experience-optimization-plan.mddocs/ai-optimization-task-software-table.mdskills/tihao-creator-sourcing/references/output-format.md平台 + 规范化主页链接 不重复。平台 + 规范化博主名称 不重复。scripts/plan-consistency-smoke.js:
brief编号 + 平台 + 主页链接/博主名称 去重口径重新进入当前规范。plan:consistency:smokenpm run acceptance 已纳入 plan:consistency:smoke。optimization:status 新增 plan-consistency 状态项。npm.cmd run plan:consistency:smoke 通过:
scannedFiles=4hits=[]npm.cmd run software:smoke 通过:
duplicateCount=3outputRows=4npm.cmd run optimization:status:smoke 通过。npm.cmd run optimization:status:
passed=19ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=104realEvidence=5smokeOrLocal=20notProof=79scripts/generate-optimization-handoff.js 和 scripts/generate-optimization-handoff-smoke.js:
complete=false。scripts/round-deposition-audit.js:
optimization-status-report.md、最新证据台账和最新交接摘要是否齐全。failureCount、failedGateCount、overallPass、软件端重复键和排名连续性、人工复核或客户指标、仍未证明边界。round-deposition-summary.json 和 UTF-8 BOM 中文 round-deposition-report.md。scripts/round-deposition-smoke.js:
round:depositionround:deposition:smokenpm run acceptance 已纳入 round:deposition:smoke。scripts/evidence-index.js 已识别 round-deposition-summary.json:
smoke_or_local。not_business_proof。scripts/optimization-status-audit.js 已新增 round-deposition 状态项,并要求 acceptance 覆盖该 smoke gate。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=20readyNotProven=2externalBlockers=2npm.cmd run round:deposition:smoke 通过:
passCount=24failCount=0npm.cmd run evidence:index:smoke 通过:
total=15real_evidence=4smoke_or_local=5not_business_proof=6npm.cmd run optimization:status:smoke 通过。npm.cmd run optimization:status:
passed=20ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=107realEvidence=5smokeOrLocal=21notProof=81npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=20externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=24warnCount=0failCount=0npm.cmd run hygiene:smoke 通过:
scannedFiles=97hitCount=0npm.cmd run acceptance 通过,新增 round:deposition:smoke 已进入默认发布前验收。outputs/optimization-handoff-latest/optimization-handoff-summary.jsonoutputs/optimization-handoff-latest/optimization-handoff-report.mdoutputs/round-deposition-latest/round-deposition-summary.jsonoutputs/round-deposition-latest/round-deposition-report.mdround-deposition 只证明每轮沉淀和交接材料完整,不证明真实客户效果。acceptance:video-ab。review:metrics 与 customer-effect:audit。scripts/create-video-intake-pack.js:
video-resource-template.csv。README.md。视频链接、封面链接、字幕或ASR文本、帧图链接、是否真实资源、资源角色、风格调性标签、画面人设场景信号 和 风险提示。scripts/create-video-intake-pack-smoke.js:
acceptance:video-ab 和视频证明边界。video:intake-templatevideo:intake-template:smokenpm run acceptance 已纳入 video:intake-template:smoke。scripts/evidence-index.js 已识别 video-resource-template.csv:
smoke_or_local。scripts/optimization-status-audit.js 已新增 video-intake-pack 状态项。scripts/generate-optimization-handoff.js 已在下一轮命令中加入:
npm run video:intake-template -- --output outputs\video-intake-pack-latestnpm run acceptance:video-abnpm.cmd run video:intake-template:smoke 通过:
files=2npm.cmd run evidence:index:smoke 通过:
total=16real_evidence=4smoke_or_local=6not_business_proof=6npm.cmd run optimization:status:smoke 通过。npm.cmd run optimization:status:
passed=21ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run video:intake-template -- --output outputs\video-intake-pack-latest 已生成:
outputs/video-intake-pack-latest/video-resource-template.csvoutputs/video-intake-pack-latest/README.mdnpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=110realEvidence=5smokeOrLocal=22notProof=83npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=21externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=24warnCount=0failCount=0npm.cmd run hygiene:smoke 通过:
scannedFiles=99hitCount=0npm.cmd run acceptance 通过,新增 video:intake-template:smoke 已进入默认发布前验收。outputs/video-intake-pack-latest/video-resource-template.csvoutputs/video-intake-pack-latest/README.mdoutputs/evidence-index-latest/evidence-index-summary.jsonoutputs/evidence-index-latest/evidence-index-report.mdoutputs/optimization-handoff-latest/optimization-handoff-summary.jsonoutputs/optimization-handoff-latest/optimization-handoff-report.mdoutputs/round-deposition-latest/round-deposition-summary.jsonoutputs/round-deposition-latest/round-deposition-report.mdacceptance:video-ab。customer-effect:audit。scripts/video-resource-readiness-audit.js:
video-resource-template.csv。video-resource-readiness-summary.json 和 UTF-8 BOM 中文 video-resource-readiness-report.md。scripts/video-resource-readiness-smoke.js:
video:resource-readinessvideo:resource-readiness:smokenpm run acceptance 已纳入 video:resource-readiness:smoke。scripts/evidence-index.js 已识别 video-resource-readiness-summary.json:
readyForVideoAbPreflight=true 时归为 smoke_or_local。not_business_proof。scripts/optimization-status-audit.js 已新增 video-resource-readiness 状态项。scripts/generate-optimization-handoff.js 已在下一轮命令中加入 video:resource-readiness。npm.cmd run video:resource-readiness:smoke 通过:
passFailureCount=0failFailureCount=4npm.cmd run evidence:index:smoke 通过:
total=18real_evidence=4smoke_or_local=7not_business_proof=7npm.cmd run optimization:status:smoke 通过。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=22readyNotProven=2externalBlockers=2npm.cmd run video:resource-readiness -- --input outputs\video-intake-pack-latest\video-resource-template.csv --output outputs\video-resource-readiness-latest:
readyForVideoAbPreflight=falsefailureCount=1realReferenceRows=1realCandidateRows=0videoUrlRows=1否,因此不具备真实 A/B 前置资源。npm.cmd run optimization:status:
passed=22ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=111realEvidence=5smokeOrLocal=22notProof=84npm.cmd run hygiene:smoke 通过:
scannedFiles=101hitCount=0npm.cmd run acceptance 通过,新增 video:resource-readiness:smoke 已进入默认发布前验收。outputs/video-resource-readiness-latest/video-resource-readiness-summary.jsonoutputs/video-resource-readiness-latest/video-resource-readiness-report.mdoutputs/evidence-index-latest/evidence-index-summary.jsonoutputs/evidence-index-latest/evidence-index-report.mdnot_business_proof,因为模板样例缺真实候选视频。acceptance:video-ab。customer-effect:audit。scripts/generate-proof-gap-request.js:
proof-gap-request-summary.json、UTF-8 BOM 中文 proof-gap-request-report.md 和 proof-gap-request-table.csv。scripts/generate-proof-gap-request-smoke.js:
proof-gap:requestproof-gap:request:smokenpm run acceptance 已纳入 proof-gap:request:smoke。scripts/evidence-index.js 已识别 proof-gap-request-summary.json:
smoke_or_local。scripts/optimization-status-audit.js 已新增 proof-gap-request 状态项。scripts/generate-optimization-handoff.js 已在下一轮命令中加入 proof-gap:request。npm.cmd run proof-gap:request:smoke 通过:
gapCount=5unresolvedCount=5npm.cmd run evidence:index:smoke 通过:
total=19real_evidence=4smoke_or_local=8not_business_proof=7npm.cmd run optimization:status:smoke 通过。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=23readyNotProven=2externalBlockers=2npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
gapCount=5unresolvedCount=5complete=falsenpm.cmd run optimization:status:
passed=23ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=114realEvidence=5smokeOrLocal=23notProof=86npm.cmd run hygiene:smoke 通过:
scannedFiles=103hitCount=0npm.cmd run acceptance 通过,新增 proof-gap:request:smoke 已进入默认发布前验收。outputs/proof-gap-request-latest/proof-gap-request-summary.jsonoutputs/proof-gap-request-latest/proof-gap-request-report.mdoutputs/proof-gap-request-latest/proof-gap-request-table.csvscripts/long-run-readiness-audit.js:
smoke、live-subset、full-matrix、video-ab、customer-effect 模式。long-run-readiness-report.md。--video-readiness <video-resource-readiness-summary.json> 参数。--proof-gap <proof-gap-request-summary.json> 参数。video-ab 模式现在会检查:doubao-seed-2-0-pro。full-matrix / customer-effect 模式现在会检查:scripts/long-run-readiness-smoke.js:
scripts/optimization-status-audit.js 已更新 long-run-readiness 状态项,检查 proof-gap 和 video readiness 门禁。npm.cmd run longrun:readiness:smoke 通过。npm.cmd run optimization:status:smoke 通过。npm.cmd run longrun:readiness -- --mode video-ab --video-readiness outputs\video-resource-readiness-latest\video-resource-readiness-summary.json --output outputs\long-run-readiness-video-ab-latest:
ready=falsefailCount=5npm.cmd run longrun:readiness -- --mode full-matrix --proof-gap outputs\proof-gap-request-latest\proof-gap-request-summary.json --output outputs\long-run-readiness-full-matrix-latest:
ready=falsefailCount=3npm.cmd run hygiene:smoke 通过:
scannedFiles=103hitCount=0npm.cmd run acceptance 通过。npm.cmd run optimization:status:
passed=23ready_not_proven=2blocked_by_external_data=2complete=falseoutputs/long-run-readiness-video-ab-latest/long-run-readiness-summary.jsonoutputs/long-run-readiness-video-ab-latest/long-run-readiness-report.mdoutputs/long-run-readiness-full-matrix-latest/long-run-readiness-summary.jsonoutputs/long-run-readiness-full-matrix-latest/long-run-readiness-report.mddocs/ai-optimization-job-dedup-software-format.md:
docs/software-client-table-format.md 的固定 17 列输出 AI 长跑优化任务。token 泄露为 0、软件端重复键为 0、排名连续、sample/smoke 不算业务证明、客户效果不可宣称 等要求合并到唯一任务项。brief编号 承载任务编号,博主名称 承载任务项名称,主页链接 承载文档或命令入口,便于软件端或任务系统直接展示。npm.cmd run optimization:statusnpm.cmd run evidence:index -- --output outputs\evidence-index-latestnpm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latestnpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latestnpm.cmd run round:deposition -- --output outputs\round-deposition-latestnpm.cmd run optimization:status:
passed=23ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=119realEvidence=5smokeOrLocal=23notProof=91npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
gapCount=5unresolvedCount=5complete=falsenpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=23externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=29failCount=0warnCount=0proofGapUnresolvedCount=5docs/ai-optimization-job-dedup-software-format.mdoutputs/evidence-index-latest/evidence-index-summary.jsonoutputs/evidence-index-latest/evidence-index-report.mdoutputs/proof-gap-request-latest/proof-gap-request-summary.jsonoutputs/proof-gap-request-latest/proof-gap-request-report.mdoutputs/proof-gap-request-latest/proof-gap-request-table.csvoutputs/optimization-handoff-latest/optimization-handoff-summary.jsonoutputs/optimization-handoff-latest/optimization-handoff-report.mdoutputs/round-deposition-latest/round-deposition-summary.jsonoutputs/round-deposition-latest/round-deposition-report.mdhistory:audit、video:resource-readiness、acceptance:video-ab、真实 live/provider 长跑和 customer-effect:audit 全部用真实数据通过。scripts/plan-consistency-smoke.js:
docs/ai-optimization-job-dedup-software-format.md。OPT-001 到 OPT-012 共 12 个任务项必须存在且不重复。软件端重复键为 0sample/smoke/provider fallback 不算业务证明客户效果不可宣称brief编号 + 平台 + 主页链接 这类错误去重方式。npm.cmd run optimization:statusnpm.cmd run evidence:index -- --output outputs\evidence-index-latestnpm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latestnpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latestnpm.cmd run round:deposition -- --output outputs\round-deposition-latestnpm.cmd run plan:consistency:smoke 通过:
ok=truescannedFiles=5hits=[]npm.cmd run hygiene:smoke 通过:
scannedFiles=104hitCount=0npm.cmd run optimization:status:smoke 通过。npm.cmd run round:deposition:smoke 通过:
passCount=29failCount=0proofGapUnresolvedCount=5npm.cmd run optimization:status:
passed=23ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=120realEvidence=5smokeOrLocal=23notProof=92npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
gapCount=5unresolvedCount=5complete=falsenpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=23readyNotProven=2externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=29failCount=0warnCount=0scripts/optimization-status-audit.js:
docs/ai-optimization-job-dedup-software-format.md 加入状态审计文件存在性检查。plan-consistency 状态项现在会检查:plan-consistency-smoke 包含固定 17 列表头校验。plan-consistency-smoke 包含 12 个 OPT 任务项数量校验。plan-consistency-smoke 包含新去重任务表路径。npm.cmd run plan:consistency:smoke 通过:
ok=truescannedFiles=5hits=[]npm.cmd run optimization:status:smoke 通过。npm.cmd run optimization:status:
passed=23ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=121realEvidence=5smokeOrLocal=23notProof=93npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
gapCount=5unresolvedCount=5complete=falsenpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=23externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=29failCount=0warnCount=0scripts/proof-gap-closure-audit.js:
historical-dataset-audit.json、video-resource-readiness-summary.json、video-hit-rate-summary.json、aggregate-summary.json、customer-effect-summary.json。historical-datasetvideo-real-candidatevideo-ab-live-prooflive-provider-overnight-proofmanual-review-and-customer-effectproof-gap-closure-summary.json 和 proof-gap-closure-report.md。open 时,complete=false,不得宣布长期目标完成。scripts/proof-gap-closure-smoke.js:
package.json:
proof-gap:closureproof-gap:closure:smokescripts/acceptance.js:
proof-gap:closure:smoke。scripts/evidence-index.js 和 scripts/evidence-index-smoke.js:
proof-gap-closure-summary.json。complete=true 时归类为 real_evidence。not_business_proof。scripts/optimization-status-audit.js:
proof-gap-closure 状态项。evidence-index 状态项同步检查 proof-gap closure 分类。npm.cmd run proof-gap:closure:smoke 通过:
openCount=5closedCount=5npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run evidence:index:smoke 通过:
total=21real_evidence=5smoke_or_local=8not_business_proof=8npm.cmd run optimization:status:smoke 通过。npm.cmd run hygiene:smoke 通过:
scannedFiles=106hitCount=0npm.cmd run optimization:status:
passed=24ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=124realEvidence=5smokeOrLocal=23notProof=96npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=29failCount=0warnCount=0proof-gap:request 仍会继续请求 5 类材料;proof-gap:closure 用于判断这些材料是否已被真实产物关闭。openCount=0,并且 optimization:status complete=true。scripts/generate-optimization-handoff.js:
nextCommands 新增 npm run proof-gap:closure -- --output outputs\proof-gap-closure-latest。openCount=0 才能进入长期完成判断。scripts/generate-optimization-handoff-smoke.js:
proof-gap:closure 命令。scripts/round-deposition-audit.js:
proof-gap-closure-summary.json。proofGapClosure.openCount。proof-gap:closure 命令。observed 中新增:proofGapClosureCompleteproofGapClosureOpenCountproofGapClosureRowsscripts/round-deposition-smoke.js:
npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=24readyNotProven=2externalBlockers=2npm.cmd run round:deposition:smoke 通过:
passCount=33failCount=0proofGapUnresolvedCount=5npm.cmd run optimization:status:smoke 通过。npm.cmd run proof-gap:closure:smoke 通过。npm.cmd run hygiene:smoke 通过:
scannedFiles=106hitCount=0npm.cmd run optimization:status:
passed=24ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=125realEvidence=5smokeOrLocal=23notProof=97npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
gapCount=5unresolvedCount=5complete=falsenpm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=33failCount=0warnCount=0closure-command-recorded 失败。openCount=4,长期目标仍不能标完成。scripts/proof-gap-closure-audit.js 的关闭报告可执行化字段:
验证命令。期望产物。下一步 同时包含命令和期望产物,便于下一轮 AI 或商务直接补证。scripts/proof-gap-closure-smoke.js:
验证命令 和 期望产物 两列。docs/ai-optimization-job-dedup-software-format.md:
npm.cmd run proof-gap:closure:smoke 通过:
ok=trueopenCount=5closedCount=5npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest 通过生成产物:
complete=falseclosedCount=1openCount=4验证命令 和 期望产物 两列。npm.cmd run hygiene:smoke 通过:
scannedFiles=106hitCount=0npm.cmd run evidence:index:smoke 通过:
total=21real_evidence=5smoke_or_local=8not_business_proof=8npm.cmd run optimization:status:smoke 通过。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=24readyNotProven=2externalBlockers=2npm.cmd run round:deposition:smoke 通过:
passCount=33failCount=0proofGapUnresolvedCount=5npm.cmd run optimization:status:
outputs/optimization-status-1780809383717passed=24ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=125realEvidence=5smokeOrLocal=23notProof=97npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
complete=falseunresolvedCount=5npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2nextCommands 已包含 proof-gap:closure。npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=33failCount=0warnCount=0proofGap.unresolvedCount=5proofGapClosure.openCount=4historical-dataset-audit.json,需要 history:audit 显示 readyForCustomerEffectProof=true。realReference=1、realCandidate=0、failureCount=1,需要 video:resource-readiness 严格通过。liveEnabled=false、overallPass=false,需要真实 provider 下 overnight:quality 产物显示 liveEnabled=true、overallPass=true、failureCount=0、failedGateCount=0。customer-effect-summary.json,需要 customer-effect:audit 显示 overallPass=true。acceptance:video-ab 已有通过产物,但 closure 报告仍保留其他真实证明缺口;不得用视频 A/B 单项关闭替代完整客户效果证明。scripts/generate-proof-gap-request.js:
proof-gap-request-summary.json 每个缺口新增 templateCommand 和 templateArtifact。proof-gap-request-report.md 的请求明细表新增 模板命令 和 模板产物 两列。proof-gap-request-table.csv 新增 模板命令 和 模板产物 两列。data:intake-template。video:intake-template。scripts/generate-proof-gap-request-smoke.js:
data:intake-template。video:intake-template。模板命令、模板产物 字段。outputs/data-intake-pack-latest/history-data-template.csvoutputs/data-intake-pack-latest/manual-review-template.csvoutputs/data-intake-pack-latest/README.mdoutputs/video-intake-pack-latest/video-resource-template.csvoutputs/video-intake-pack-latest/README.mdnpm.cmd run proof-gap:request:smoke 通过:
gapCount=5unresolvedCount=5npm.cmd run data:intake-template:smoke 通过:
files=3npm.cmd run video:intake-template:smoke 通过:
files=2npm.cmd run data:intake-template -- --output outputs\data-intake-pack-latest 通过,生成历史数据和人工复核模板。npm.cmd run video:intake-template -- --output outputs\video-intake-pack-latest 通过,生成视频资源模板。npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest 通过:
complete=falsegapCount=5unresolvedCount=5模板命令 和 模板产物 两列。npm.cmd run hygiene:smoke 通过:
scannedFiles=106hitCount=0npm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=126realEvidence=5smokeOrLocal=23notProof=98npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2proof-gap:request 仍有 5 个 unresolved 缺口,proof-gap:closure 仍有 4 个 open 缺口。outputs/data-intake-pack-latest 和 outputs/video-intake-pack-latest 可交给商务/投放补真实数据;补完后必须重新跑对应审计命令。scripts/round-deposition-audit.js:
proof-gap-template-entry-recorded,要求 proof-gap-request-summary.json 每个缺口行都包含 templateCommand 和 templateArtifact。proof-gap-template-columns-exported,要求 proof-gap-request-report.md 和 proof-gap-request-table.csv 都导出 模板命令、模板产物 两列。observed 新增 proofGapTemplateRowsReady 和 proofGapTemplateColumnsReady。proofGapRows 记录每个缺口是否有模板命令和模板产物。scripts/round-deposition-smoke.js:
proofGap.templateRowsReady 和 proofGap.templateColumnsReady。npm.cmd run round:deposition:smoke 通过:
passCount=35failCount=0proofGapUnresolvedCount=5npm.cmd run proof-gap:request:smoke 通过:
gapCount=5unresolvedCount=5npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
complete=falsegapCount=5unresolvedCount=5npm.cmd run hygiene:smoke 通过:
scannedFiles=106hitCount=0npm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=126realEvidence=5smokeOrLocal=23notProof=98npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2scripts/intake-readiness-audit.js:
--data-pack <目录> 和 --video-pack <目录>。history-data-template.csv、manual-review-template.csv、video-resource-template.csv。example.com、示例、候选博主、待确认、人工待补 等模板占位内容。intake-readiness-summary.json 和 intake-readiness-report.md。scripts/intake-readiness-smoke.js:
package.json:
npm run intake:readiness。npm run intake:readiness:smoke。scripts/acceptance.js:
intake:readiness:smoke。scripts/evidence-index.js 和 scripts/evidence-index-smoke.js:
intake-readiness 类型。overallReady=true 只记为 smoke_or_local 前置证明。overallReady=false 记为 not_business_proof。scripts/generate-optimization-handoff.js 和 smoke:
npm run intake:readiness -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-readiness-latest。npm.cmd run intake:readiness:smoke 通过:
templateFailureCount=9realFailureCount=0npm.cmd run data:intake-template:smoke 通过。npm.cmd run video:intake-template:smoke 通过。npm.cmd run intake:readiness -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-readiness-latest:
overallReady=falsereadyForHistoryAudit=falsereadyForVideoResourceAudit=falsereadyForReviewMetrics=falsereadyForCustomerEffectAudit=falsefailureCount=9npm.cmd run evidence:index:smoke 通过:
total=23real_evidence=5smoke_or_local=9not_business_proof=9npm.cmd run hygiene:smoke 通过:
scannedFiles=108hitCount=0npm.cmd run handoff:summary:smoke 通过。npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=24externalBlockers=2npm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=127realEvidence=5smokeOrLocal=23notProof=99npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4intake:readiness 是正式审计前的“半成品拦截器”,不能替代 history:audit、video:resource-readiness、review:metrics 或 customer-effect:audit。scripts/optimization-status-audit.js:
scripts/intake-readiness-audit.js 和 scripts/intake-readiness-smoke.js。intake-readiness,用于确认真实材料半成品预审能力已接入。evidence-index 状态项同步检查 intake-readiness-summary.json 和 type: 'intake-readiness'。plan-consistency 状态项文案从 12 个 OPT 行更新为 9 个去重后 OPT 行。scripts/optimization-status-smoke.js:
intake-readiness。scripts/plan-consistency-smoke.js:
docs/ai-optimization-job-dedup-software-format.md:
软件端重复键为 0。sample/smoke/provider fallback 不算业务证明。客户效果不可宣称。npm.cmd run plan:consistency:smoke 通过:
scannedFiles=5hits=[]npm.cmd run optimization:status:smoke 通过。npm.cmd run evidence:index:smoke 通过:
total=23real_evidence=5smoke_or_local=9not_business_proof=9npm.cmd run intake:readiness:smoke 通过:
templateFailureCount=9realFailureCount=0npm.cmd run hygiene:smoke 通过:
scannedFiles=108hitCount=0npm.cmd run optimization:status:
outputs/optimization-status-1780810669737passed=25ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=128realEvidence=5smokeOrLocal=23notProof=100npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest:
complete=falsegapCount=5unresolvedCount=5npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest:
complete=falseclosedCount=1openCount=4npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=25externalBlockers=2intake-readiness 是能力项通过,不代表当前模板已具备真实业务数据。outputs/intake-readiness-latest 仍显示 overallReady=false,所以不能进入真实长跑证明或客户效果证明。scripts/proof-gap-closure-audit.js:
--intake-readiness / TIHAO_INTAKE_READINESS_SUMMARY / 最新 intake-readiness-summary.json。intake-readiness 行,展示 overallReady、failureCount、history/video/review/customerEffect readiness。intake-readiness 作为补证预审行展示,不计入 5 类真实业务缺口的 openCount。Intake 预审是否就绪。scripts/proof-gap-closure-smoke.js:
scripts/long-run-readiness-audit.js:
--intake-readiness。full-matrix 和 customer-effect 模式下,如果提供 intake readiness,则要求 overallReady=true 且 failureCount=0。video-ab 模式下,如果提供 intake readiness,则要求 videoReady=true。npm run intake:readiness。scripts/long-run-readiness-smoke.js:
scripts/optimization-status-audit.js:
long-run-readiness 状态项检查 intake readiness 门禁。proof-gap-closure 状态项检查 closure 已包含 intake readiness 行和 intakeReady 字段。npm.cmd run proof-gap:closure:smoke 通过:
openCount=5closedCount=5npm.cmd run longrun:readiness:smoke 通过。npm.cmd run optimization:status:smoke 通过。npm.cmd run hygiene:smoke 通过:
scannedFiles=108hitCount=0npm.cmd run longrun:readiness -- --mode full-matrix --intake-readiness outputs\intake-readiness-latest\intake-readiness-summary.json --proof-gap outputs\proof-gap-request-latest\proof-gap-request-summary.json --output outputs\long-run-readiness-latest:
ready=falsefailCount=5warnCount=0npm.cmd run optimization:status:
outputs/optimization-status-1780810937378passed=25ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run proof-gap:closure -- --intake-readiness outputs\intake-readiness-latest\intake-readiness-summary.json --output outputs\proof-gap-closure-latest:
complete=falseintakeReady=falseclosedCount=1openCount=4npm.cmd run evidence:index -- --output outputs\evidence-index-latest:
total=130realEvidence=5smokeOrLocal=23notProof=102npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest:
complete=falsereadyCapabilities=25externalBlockers=2openCount 仍只统计真实业务证明缺口。intakeReady=false、longrun ready=false、proof-gap closure openCount=4,长期目标仍不能标完成。scripts/round-deposition-audit.js:
intake-readiness-summary.json。long-run-readiness-summary.json。intake-readiness-summary。intake-readiness-boundary-recorded。longrun-readiness-summary。longrun-readiness-intake-gate。sources 新增 intake readiness 和 longrun readiness 两个来源。observed 新增 intakeReadinessReady、intakeReadinessFailureCount、longRunReadinessMode、longRunReadinessReady、longRunReadinessFailCount。scripts/round-deposition-smoke.js:
npm.cmd run round:deposition:smoke 通过:
passCount=39failCount=0proofGapUnresolvedCount=5npm.cmd run hygiene:smoke 通过:
scannedFiles=108hitCount=0npm.cmd run round:deposition -- --output outputs\round-deposition-latest:
passed=truepassCount=39failCount=0warnCount=0npm.cmd run evidence:index:smoke 通过:
total=23real_evidence=5smoke_or_local=9not_business_proof=9npm.cmd run optimization:status:smoke 通过。outputs/round-deposition-latest/round-deposition-summary.json:
passed=truepass=39fail=0proofGap.unresolvedCount=5intakeReadiness.ready=falseintakeReadiness.failureCount=9longRunReadiness.mode=full-matrixlongRunReadiness.ready=falselongRunReadiness.failCount=5proofGapClosure.openCount=4intakeReadiness.ready=false 和 longRunReadiness.ready=false 是当前真实边界,长期优化目标仍未完成。scripts/generate-optimization-handoff.js:
outputs/business-proof-next-actions-latest/business-proof-next-actions-summary.json 中的 ownerGroups 和 ownerArtifacts。businessProofNextActions 下输出负责人分组和负责人专属文件。scripts/generate-optimization-handoff-smoke.js:
ownerArtifacts。by-owner/ 文件入口。docs/ai-optimization-job-dedup-software-format.md:
sample/smoke/provider fallback 不算业务证明、客户效果不可宣称。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=8topAction=填真实历史 Briefnpm.cmd run optimization:status:smoke 通过。npm.cmd run plan:consistency:smoke 通过:
scannedFiles=6hits=0npm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run acceptance 通过:
npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=137realEvidence=5smokeOrLocal=25notProof=107npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0outputs/business-proof-next-actions-latest/by-owner/business.mdoutputs/business-proof-next-actions-latest/by-owner/business.csvoutputs/business-proof-next-actions-latest/by-owner/media-business.mdoutputs/business-proof-next-actions-latest/by-owner/media-business.csvoutputs/business-proof-next-actions-latest/by-owner/business-media.mdoutputs/business-proof-next-actions-latest/by-owner/business-media.csvscripts/business-proof-next-actions.js:
history 字段缺口合并到“填真实历史 Brief”。video 字段缺口合并到“填真实视频资源”。review 字段缺口合并到“人工复核标注”。proof-gap-closure 的同类 open 项不再重复进入行动队列。scripts/business-proof-next-actions-smoke.js:
node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=5topAction=填真实历史 Briefnpm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
actionCount=8ownerArtifacts=3topAction=填真实历史 Briefnpm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run plan:consistency:smoke 通过:
hits=0npm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=138realEvidence=5smokeOrLocal=25notProof=108npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0填真实历史 Brief人工复核标注填真实视频资源intakeReadiness.ready=false、真实历史数据和真实视频资源未闭合,客户效果审计仍缺真实客户选择和人工补号量证明。scripts/optimization-pipeline.js:
--data-pack 和 --video-pack 入口。history-data-template.csv 和 manual-review-template.csv。video-resource-template.csv。intake:readiness。video:resource-readiness。longrun:readiness 会接收 pipeline 生成的 intake-readiness-summary.json 和 video-resource-readiness-summary.json。scripts/optimization-pipeline-smoke.js:
--history-csv/--review-csv smoke。docs/tihao-experience-optimization-plan.md:
scripts/generate-optimization-handoff.js 和 scripts/generate-optimization-handoff-smoke.js:
optimization:pipeline --data-pack --video-pack 命令。node --check scripts\optimization-pipeline.js 通过。node --check scripts\optimization-pipeline-smoke.js 通过。npm.cmd run optimization:pipeline:smoke 通过:
steps=6npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run plan:consistency:smoke 通过:
hits=0npm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\evidence-index-latest 已刷新:
total=140realEvidence=5smokeOrLocal=25notProof=110npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsescripts/optimization-pipeline.js:
optimization-pipeline-summary.json 新增 nextActions。optimization-pipeline-report.md 新增“下一步动作”章节。--dry-run 执行真实 pipeline。cmd.exe /d /s /c 包装,避免 shell:true + args 的弃用提醒,同时保留 npm.cmd 兼容性。scripts/optimization-pipeline-smoke.js:
nextActions。scripts/evidence-index.js:
optimization-pipeline 证据摘要新增 nextActions=<数量>。node --check scripts\optimization-pipeline.js 通过。node --check scripts\optimization-pipeline-smoke.js 通过。npm.cmd run optimization:pipeline:smoke 通过:
steps=6npm.cmd run optimization:pipeline -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --current-manual-supplement-count 0 --output outputs\optimization-pipeline-latest 已刷新当前 pipeline:
pass=5fail=3readyForClaim=falsenextActionCount=3npm.cmd run evidence:index:smoke 通过:
total=25real_evidence=5smoke_or_local=11not_business_proof=9npm.cmd run evidence:index -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\evidence-index-latest 已刷新:
total=142realEvidence=5smokeOrLocal=24notProof=113npm.cmd run round:deposition -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run plan:consistency:smoke 通过:
hits=0readyForClaim=false,不能宣称客户效果完成;必须补齐真实历史数据、真实候选视频、客户最终选择和人工补号量证明后再跑 strict 审计。scripts/generate-optimization-handoff.js:
outputs/optimization-pipeline-latest/optimization-pipeline-summary.json。optimizationPipeline,包含 summary/report 路径、pass/fail 计数、readyForClaim 和 nextActions。scripts/generate-optimization-handoff-smoke.js:
nextActions 数组。readyForClaim。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\evidence-index-latest 已刷新:
total=144realEvidence=5smokeOrLocal=24notProof=115npm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0readyForClaim=false、pipeline fail=3、nextActions=3,长期目标仍不能标完成。scripts/business-proof-next-actions.js:
optimization-pipeline-summary.json。sourceState 新增 pipelineReadyForClaim、pipelineFailCount、pipelineNextActionCount。nextActions 合并进补证行动队列。history-audit 合并到 15 步的历史数据审计动作,并按 pipeline owner 改为商务。video-resource-readiness 合并到视频资源就绪审计动作,并按 pipeline owner 改为商务/投放。customer-effect-audit 合并到客户效果审计动作,并按 pipeline owner 改为商务。scripts/business-proof-next-actions-smoke.js:
pipeline.nextActionCount 和合并后的动作标题。node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=6topAction=填真实历史 Briefnpm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
actionCount=8ownerArtifacts=3topAction=填真实历史 Briefnpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\evidence-index-latest 已刷新:
total=145realEvidence=5smokeOrLocal=24notProof=116npm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run round:deposition -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=false填真实历史 Brief补齐历史数据审计字段人工复核标注补齐客户效果证明填真实视频资源补齐真实视频资源pipelineReadyForClaim=false、pipelineFailCount=3、pipelineNextActionCount=3,长期目标仍未完成。scripts/business-proof-next-actions.js:
history intake 仍未就绪时,pipeline 的 history-audit 动作合并到“填真实历史 Brief”,不再单独生成“补齐历史数据审计字段”。video intake 仍未就绪时,pipeline 的 video-resource-readiness 动作合并到“填真实视频资源”,不再单独生成“补齐真实视频资源”。review intake 仍未就绪时,pipeline 的 customer-effect-audit 动作合并到“人工复核标注”,不再单独生成“补齐客户效果证明”。scripts/business-proof-next-actions-smoke.js:
pipeline 当前动作 说明。node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=5topAction=填真实历史 Briefnpm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
actionCount=8ownerArtifacts=3topAction=填真实历史 Briefnpm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\evidence-index-latest 已刷新:
total=147realEvidence=5smokeOrLocal=24notProof=118npm.cmd run handoff:summary:smoke 通过:
readyCapabilities=27readyNotProven=2externalBlockers=2npm.cmd run round:deposition -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run hygiene:smoke 通过:
scannedFiles=113hitCount=0填真实历史 Brief人工复核标注填真实视频资源readyForClaim=false,真实历史数据、真实视频资源、客户最终选择和人工补号量证明仍需补齐。scripts/business-proof-next-actions.js:
填真实历史 Brief、填真实视频资源、人工复核标注 时,不再覆盖主动作的 执行命令、预期产物、通过标准。填写 outputs\data-intake-pack-latest\history-data-template.csv填写 outputs\video-intake-pack-latest\video-resource-template.csv填写 outputs\data-intake-pack-latest\manual-review-template.csv商务/投放,避免同时出现 商务/投放 和 投放/商务 两组重复负责人文件。outputs\business-proof-next-actions-latest\by-owner\media-business.mdoutputs\business-proof-next-actions-latest\by-owner\media-business.csvscripts/business-proof-next-actions-smoke.js:
商务/投放 只生成 by-owner/business-media.md,不再生成 by-owner/media-business.md。node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=5topAction=填真实历史 Briefnpm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
ownerArtifacts=3actionCount=8complete=falsebusiness.csv/mdbusiness-media.csv/mdtech-ai.csv/mdoptimization-status-report.md。npm run optimization:status -- --output outputs\optimization-status-latest 命令不会真正使用 --output,脚本只读取 TIHAO_STATUS_OUTPUT。outputs\optimization-status-latest,不利于每轮沉淀、交接摘要和 round deposition 查证。scripts/optimization-status-audit.js:
--output 参数解析。TIHAO_STATUS_OUTPUT 环境变量兼容。scripts/optimization-status-smoke.js:
optimization-status-audit.js --output <临时目录>。optimization-status-summary.json 和 optimization-status-report.md 都写入指定目录。node --check scripts\optimization-status-audit.js 通过。node --check scripts\optimization-status-smoke.js 通过。npm.cmd run optimization:status:smoke 通过。npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=150realEvidence=5smokeOrLocal=24notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。customer-effect:audit 仍未通过,不能宣称客户效果完成。proof-gap:closure 只用 video-hit-rate-summary.json.acceptance.passed=true 判断 video-ab-live-proof 是否 closed。proofContext,但仍可能被 latest 扫描命中,导致 video-ab-live-proof=closed。business-proof:progress 又依据 closure 行把第 11 步“视频 A/B 验收”标成 pass。optimization:status 中 video-ab-proof=ready_not_proven 发生冲突,并可能误导为“视频分析已经证明提升提号率”。scripts/video-hit-rate-audit.js:
acceptance:video-ab 产物新增 proofContext。mode=live、collectionMode=live、generatedBy=acceptance:video-ab、是否需要 runtime credential、VOC social provider、video analysis provider、视频分析模型等上下文。scripts/proof-gap-closure-audit.js:
video-ab-live-proof 只有同时满足以下条件才 closed:acceptance.passed=trueproofContext.mode=liveproofContext.collectionMode=liveproofContext.generatedBy=acceptance:video-abrequiresRuntimeCredential=truerequiresVocSocialProvider=truerequiresVideoAnalysisProvider=trueenhanced.provider.evidence.providerStatus=okscripts/business-proof-progress.js:
optimization-status 中 video-ab-proof=passed 且 closure 为 closed,才标记为 pass。video-ab-proof=ready_not_proven 时,第 11 步保持 pending。投放/商务 统一为 商务/投放,避免上游进度表再次制造负责人重复。proof-gap:closure:smoke 增加“passed 但没有 live proofContext 不得 closed”的断言。business-proof:progress:smoke 增加“status ready_not_proven 时视频 A/B 必须 pending”的断言。node --check scripts\video-hit-rate-audit.js 通过。node --check scripts\proof-gap-closure-audit.js 通过。node --check scripts\business-proof-progress.js 通过。node --check scripts\proof-gap-closure-smoke.js 通过。node --check scripts\business-proof-progress-smoke.js 通过。npm.cmd run proof-gap:closure:smoke 通过。npm.cmd run business-proof:progress:smoke 通过:
pass=3blocked_by_external_data=7fail=2pending=3npm.cmd run acceptance:video-ab:smoke 通过。npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest 已刷新:
complete=falseclosedCount=0openCount=5npm.cmd run business-proof:progress -- --output outputs\business-proof-progress-latest 已刷新:
complete=falsepass=3blocked=7pending=3fail=2npm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
complete=falseactionCount=8topAction=填真实历史 Briefnpm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
realEvidence=5smokeOrLocal=24notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。closedCount=0, openCount=5 是更准确的状态,不是倒退。proofContext,不能支撑真实视频提升结论。video-ab-live-proof,必须重新用真实 token/provider/真实视频资源运行 npm run acceptance:video-ab,生成带 proofContext 的新 summary。outputs\proof-gap-request-latest 仍是较早生成的请求包,里面的 status/evidence 计数和最新 closure/progress 不一致。技术/投放、商务/客户 等负责人标签,与行动队列中的 商务、商务/投放、技术/AI 三类口径不一致。proof-gap:closure 的 openCount,商务或下一轮 AI 需要额外打开 closure 文件才能确认当前真实证明缺口是否已关闭。scripts/generate-proof-gap-request.js:
--closure 输入,默认读取 latest proof-gap-closure-summary.json。observed 和报告中展示:closure.completeclosure.openCountvideo-ab-live-proof:技术/AIlive-provider-overnight-proof:技术/AImanual-review-and-customer-effect:商务scripts/generate-proof-gap-request-smoke.js:
proofGapClosureOpenCount=5。技术/投放、商务/客户、投放/商务 旧负责人标签。closure.openCount:5。node --check scripts\generate-proof-gap-request.js 通过。node --check scripts\generate-proof-gap-request-smoke.js 通过。npm.cmd run proof-gap:request:smoke 通过:
gapCount=5unresolvedCount=5npm.cmd run proof-gap:request -- --output outputs\proof-gap-request-latest 已刷新:
gapCount=5unresolvedCount=5npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
realEvidence=5smokeOrLocal=24notProof=121npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。unresolvedCount=5,closure.openCount=5,长期目标仍未完成。optimization:pipeline 原本只用“所有步骤 pass + 存在 reviewCsv”判断 readyForClaim。history/review/customer-effect 都通过时,可能过早出现 readyForClaim=true。scripts/optimization-pipeline.js:
proof-gap:closure 步骤。historical-dataset-audit.jsonintake-readiness-summary.jsonvideo-resource-readiness-summary.jsoncustomer-effect-summary.jsonreadyForClaim 改为必须同时满足:status=passreviewCsvproof-gap:closure complete=trueproofGapClosure:completeopenCountclosedCountproofGapClosure.completeproofGapClosure.openCountnextActions 会输出“关闭真实证明缺口”。scripts/optimization-pipeline-smoke.js:
proof-gap:closure。readyForClaim 必须为 false。<输出目录>/proof-gap-closure/proof-gap-closure-summary.json。node --check scripts\optimization-pipeline.js 通过。node --check scripts\optimization-pipeline-smoke.js 通过。npm.cmd run optimization:pipeline:smoke 通过:
steps=7npm.cmd run optimization:pipeline -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --current-manual-supplement-count 0 --output outputs\optimization-pipeline-latest 已刷新:
pass=6fail=3readyForClaim=falseproofGapClosure.complete=falseproofGapClosure.openCount=5proofGapClosure.closedCount=0npm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
actionCount=8topAction=填真实历史 Briefnpm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest 已刷新:
closedCount=0openCount=5npm.cmd run proof-gap:request -- --output E:\workspace\tihao-ai\claude-code-tihao-sourcing\outputs\proof-gap-request-latest 已刷新:
gapCount=5unresolvedCount=5npm.cmd run optimization:status -- --output outputs\optimization-status-latest 已刷新:
passed=27ready_not_proven=2blocked_by_external_data=2complete=falsenpm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
realEvidence=5smokeOrLocal=24notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。proofGapClosure.openCount=5,因此 readyForClaim=false 是正确状态。optimization:pipeline 已经把 proof-gap:closure complete=true 纳入 readyForClaim 门禁。evidence:index 里的 pipeline 分类仍是旧说明:
readyForClaim=true 时写“客户效果仍以 customer-effect 产物单独判定”。proofGapClosure.complete/openCount。scripts/evidence-index.js:
classifyPipeline 读取 pipeline.proofGapClosure。closureCompleteclosureOpenreadyForClaim 展示值改为必须同时满足:pipeline.readyForClaim=trueproofGapClosure.complete=truescripts/evidence-index-smoke.js:
proofGapClosure.complete=true。pipeline-claim-with-open-closure fixture:即使原始 readyForClaim=true,只要 closure open,证据台账 summary 必须显示 readyForClaim=false。closureOpen=1。node --check scripts\evidence-index.js 通过。node --check scripts\evidence-index-smoke.js 通过。npm.cmd run evidence:index:smoke 通过:
total=26smoke_or_local=12not_business_proof=9real_evidence=5npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=150realEvidence=5smokeOrLocal=24notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。readyForClaim=falseproofGapClosure.complete=falseproofGapClosure.openCount=5proof-gap:request 只能说明当前请求包里还有哪些缺口,不能证明缺口已真实关闭。longrun:readiness 只看 request 的 unresolved 数,可能出现“请求表同步了,但 closure 仍有 open 项”的误判。scripts/long-run-readiness-audit.js:
--proof-gap-closure 参数和 TIHAO_PROOF_GAP_CLOSURE_SUMMARY 环境变量。full-matrix 和 customer-effect 模式会检查 proofGapClosure.complete=true 且 openCount=0。nextCommands 增加 npm run proof-gap:closure -- --output outputs\proof-gap-closure-latest。proof-gap:closure 仍有 open 项时,不能宣称长期优化目标完成。scripts/long-run-readiness-smoke.js:
ready=false。proof-gap:closure。docs/ai-optimization-proof-gap-software-table.mdnode --check scripts\long-run-readiness-audit.js 通过。node --check scripts\long-run-readiness-smoke.js 通过。npm.cmd run longrun:readiness:smoke 通过。npm.cmd run longrun:readiness -- --mode full-matrix --intake-readiness outputs\intake-readiness-latest\intake-readiness-summary.json --proof-gap outputs\proof-gap-request-latest\proof-gap-request-summary.json --proof-gap-closure outputs\proof-gap-closure-latest\proof-gap-closure-summary.json --history outputs\optimization-pipeline-latest\history-audit\historical-dataset-audit.json --output outputs\long-run-readiness-latest 已刷新:
ready=falsefailCount=7warnCount=0npm.cmd run business-proof:progress -- --output outputs\business-proof-progress-latest 已刷新:
complete=falsepass=3blocked=7pending=3fail=2npm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
complete=falseactionCount=8ownerArtifacts=3topAction=填真实历史 Briefnpm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=150realEvidence=5smokeOrLocal=24notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。longrun:readiness 已经受 proof-gap:closure 约束,不能绕过真实关闭证据。proofGapClosure.complete=false 且 openCount=5,长期优化目标仍未完成。docs/ai-optimization-proof-gap-software-table.md 已经按软件端格式收敛为 5 个唯一补证任务。business-proof:next-actions 的真实 latest 仍输出 8 条行动:
scripts/business-proof-next-actions.js:
compactBusinessGapActions,把技术验证动作合并到对应业务缺口。填真实历史 Brief,保留 intake、history:from-csv、history:audit 的验证说明和预期产物。填真实视频资源,保留 video:resource-readiness 的验证说明。人工复核标注,保留 review:metrics 和 customer-effect:audit 的验证说明。真实视频 A/B 验收。真实 live/provider 长跑证明,保留 longrun readiness 和 optimization:pipeline 的前置说明。longrun:readiness 推荐命令同步增加 --proof-gap-closure outputs\proof-gap-closure-latest\proof-gap-closure-summary.json。live proof 等半英文标题。scripts/business-proof-next-actions-smoke.js:
node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过:
actionCount=3topAction=填真实历史 Briefnpm.cmd run business-proof:next-actions -- --output outputs\business-proof-next-actions-latest 已刷新:
complete=falseactionCount=5ownerArtifacts=3topAction=填真实历史 Brief填真实历史 Brief填真实视频资源人工复核标注真实视频 A/B 验收真实 live/provider 长跑证明npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=150realEvidence=5smokeOrLocal=24notProof=121npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=44failCount=0warnCount=0npm.cmd run acceptance 通过。proofGap.openCount=5intake.failureCount=9video.failureCount=1pipeline.readyForClaim=falsebusiness-proof:next-actions 真实 latest 从 8 条压成 5 条。round:deposition 只记录 businessProofNextActionsCount=5,没有把“必须按业务缺口去重”作为硬性检查。scripts/round-deposition-audit.js:
business-proof-next-actions-deduped 检查项。proofGap.unresolvedCount 对齐。填真实历史 Brief填真实视频资源人工复核标注真实视频 A/B 验收真实 live/provider 长跑证明真实材料预审历史数据导入历史数据审计视频资源就绪审计长跑前门禁运行策略矩阵视频 A/B 验收商务复核指标客户效果审计商务、商务/投放、技术/AI 三类负责人。scripts/round-deposition-smoke.js:
business-proof-next-actions-deduped。businessProofNextActionsCount=5。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过:
passCount=45failCount=0proofGapUnresolvedCount=5npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=45failCount=0warnCount=0businessProofNextActionsCount=5npm.cmd run acceptance 通过。proofGapUnresolvedCount=5proofGapClosure.openCount=5intakeReadinessFailureCount=9longRunReadinessReady=falsedocs/ai-optimization-proof-gap-software-table.md 是给软件端和商务看的 5 条补证表。outputs/business-proof-next-actions-latest/business-proof-next-actions-summary.json 是自动生成的下一步行动队列。scripts/plan-consistency-smoke.js:
docs/ai-optimization-proof-gap-software-table.md。GAP-001 到 GAP-005 行,且 ID 不重复。真实历史 Brief 数据集真实视频资源表真实视频证据 A/B真实 live/provider 长跑证明商务复核和客户效果填真实历史 Brief填真实视频资源人工复核标注真实视频 A/B 验收真实 live/provider 长跑证明真实材料预审历史数据导入历史数据审计视频资源就绪审计长跑前门禁运行策略矩阵视频 A/B 验收商务复核指标客户效果审计docs/ai-optimization-proof-gap-software-table.md:
真实 provider 长跑 调整为 真实 live/provider 长跑证明,与 next-actions 保持一致。node --check scripts\plan-consistency-smoke.js 通过。npm.cmd run plan:consistency:smoke 通过:
scannedFiles=7hits=[]npm.cmd run acceptance 通过。npm.cmd run round:deposition -- --output outputs\round-deposition-latest 通过:
passed=truepassCount=45failCount=0warnCount=0proofGapUnresolvedCount=5proofGapClosure.openCount=5intakeReadinessFailureCount=9longRunReadinessReady=falsedocs/ai-optimization-proof-gap-software-table.md。outputs/business-proof-next-actions-latest/business-proof-next-actions.csv。scripts/export-proof-gap-software-form.js:
docs/ai-optimization-proof-gap-software-table.md 读取软件端格式补证表。outputs/tihao-proof-gap-software-form-latest。rowCount、duplicateIdCount、headerMatches、rowWidthOk 和 passed。scripts/export-proof-gap-software-form-smoke.js:
proof-gap:software-formproof-gap:software-form:smokescripts/acceptance.js 增加 proof-gap:software-form:smoke。scripts/plan-consistency-smoke.js 增加 latest 表单 summary 检查:
outputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form-summary.jsonpassed=true、headerMatches=true、rowWidthOk=true、rowCount=5、duplicateIdCount=0。outputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form.csvoutputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form.mdoutputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form-summary.jsonnode --check scripts\export-proof-gap-software-form.js 通过。node --check scripts\export-proof-gap-software-form-smoke.js 通过。npm.cmd run proof-gap:software-form -- --output outputs\tihao-proof-gap-software-form-latest --strict 已生成最新表单:
rowCount=5duplicateIdCount=0headerMatches=truenpm.cmd run proof-gap:software-form:smoke 通过:
rowCount=5duplicateIdCount=0npm.cmd run plan:consistency:smoke 通过:
scannedFiles=7hits=[]npm.cmd run acceptance 通过。npm.cmd run round:deposition -- --output outputs\round-deposition-latest 通过:
passed=truepassCount=45failCount=0warnCount=0outputs/tihao-proof-gap-software-form-latest。round:deposition 的来源、当前观测和检查项里还没有记录该表单,交接报告无法直接看到表单是否通过、行数和重复 ID 数。scripts/round-deposition-audit.js:
--proof-gap-software-form 参数。tihao-proof-gap-software-form-summary.json。sources 增加 proofGapSoftwareFormSummary。observed 增加:proofGapSoftwareFormPassedproofGapSoftwareFormRowCountproofGapSoftwareFormDuplicateIdCountproofGapSoftwareFormHeaderMatchesproofGapSoftwareFormRowWidthOkproof-gap-software-form-summaryproof-gap-software-form-passedpassed=trueheaderMatches=truerowWidthOk=truerowCount 与 proofGap.unresolvedCount 对齐duplicateIdCount=0scripts/round-deposition-smoke.js:
outputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form-summary.json。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过:
passCount=47failCount=0proofGapUnresolvedCount=5npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=47failCount=0warnCount=0npm.cmd run acceptance 通过。round:deposition 记录。handoff:summary 仍只列出数据模板、补证进度表、下一步行动队列和负责人文件。passed、rowCount 和 duplicateIdCount。scripts/generate-optimization-handoff.js:
outputs/tihao-proof-gap-software-form-latest。tihao-proof-gap-software-form-summary.json。proofGapSoftwareForm:csvmarkdownsummarypassedrowCountduplicateIdCountheaderMatchesrowWidthOk## 最新提号补证表单 区块。nextCommands 新增:npm run proof-gap:software-form -- --output outputs\tihao-proof-gap-software-form-latest --strictscripts/generate-optimization-handoff-smoke.js:
passed=true、rowCount=5、duplicateIdCount=0。## 最新提号补证表单、CSV 路径和表单状态。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2outputs/tihao-proof-gap-software-form-latest/tihao-proof-gap-software-form.csvpassed=truerowCount=5duplicateIdCount=0npm.cmd run acceptance 通过。npm.cmd run round:deposition -- --output outputs\round-deposition-latest 通过:
passed=truepassCount=47failCount=0warnCount=0evidence:index 仍只识别 proof-gap request/closure、handoff、round deposition 等产物。scripts/evidence-index.js:
tihao-proof-gap-software-form-summary.json。proof-gap-software-form。passed=true 时只归类为 smoke_or_local,不归类为 real_evidence。rows、duplicateId、header、rowWidth。scripts/evidence-index-smoke.js:
smoke_or_local 从 12 增至 13。proof-gap-software-form=1。node --check scripts\evidence-index.js 通过。node --check scripts\evidence-index-smoke.js 通过。npm.cmd run evidence:index:smoke 通过:
total=27smoke_or_local=13not_business_proof=9real_evidence=5npm.cmd run evidence:index -- --output outputs\evidence-index-latest 已刷新:
total=151realEvidence=5smokeOrLocal=25notProof=121npm.cmd run handoff:summary -- --output outputs\optimization-handoff-latest 已刷新:
complete=falsereadyCapabilities=27externalBlockers=2npm.cmd run round:deposition -- --output outputs\round-deposition-latest 已刷新:
passed=truepassCount=47failCount=0warnCount=0npm.cmd run acceptance 通过。outputs/optimization-status-latest/optimization-status-report.mdoutputs/evidence-index-latest/evidence-index-report.mdoutputs/optimization-handoff-latest/optimization-handoff-report.mdoutputs/round-deposition-latest/round-deposition-report.mdscripts/refresh-round-artifacts.js:
proof-gap:software-formoptimization:statusevidence:indexhandoff:summaryround:deposition --strictoutputs/round-refresh-summary.json,记录每个步骤是否通过。--output-root,可用于真实 latest 或临时 smoke 目录。scripts/refresh-round-artifacts-smoke.js:
real_evidence、smoke_or_local、not_business_proof。package.json:
round:refreshround:refresh:smokescripts/acceptance.js:
round:refresh:smoke。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。npm.cmd run round:refresh:smoke 通过:
steps=proof-gap-software-form:pass, optimization-status:pass, evidence-index:pass, optimization-handoff:pass, round-deposition:passroundPassCount=47npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
optimization-status-latest: passed=27、ready_not_proven=2、blocked_by_external_data=2、complete=falseevidence-index-latest: total=151、realEvidence=5、smokeOrLocal=25、notProof=121optimization-handoff-latest: complete=false、readyCapabilities=27、externalBlockers=2round-deposition-latest: passed=true、passCount=47、failCount=0npm.cmd run acceptance 通过。complete=false,ready_not_proven=2,blocked_by_external_data=2。round:refresh 已经能按固定顺序刷新每轮 latest 产物。handoff:summary 的 nextCommands 仍提示分开跑 evidence:index 和 handoff:summary。docs/business-proof-action-order.md 第 15 步仍按旧方式列多个分散命令。docs/tihao-experience-optimization-plan.md 的每轮沉淀章节也没有明确优先使用 round:refresh。scripts/generate-optimization-handoff.js:
nextCommands 新增“每轮沉淀一键刷新”:npm run round:refresh -- --output-root outputs --strictevidence:index 和 handoff:summary 命令改为排查/单独刷新时使用。scripts/generate-optimization-handoff-smoke.js:
round:refresh 且包含 --strict。docs/business-proof-action-order.md:
round:refresh。round-refresh-summary.json 5 步全部通过,且 round:deposition 通过。docs/tihao-experience-optimization-plan.md:
npm run round:refresh -- --output-root outputs --strictnode --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run plan:consistency:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
round-refresh-summary.json: 5 步全部 passoptimization-status-latest: complete=falseevidence-index-latest: total=151、realEvidence=5、smokeOrLocal=25、notProof=121optimization-handoff-latest: readyCapabilities=27、externalBlockers=2round-deposition-latest: passed=true、passCount=47、failCount=0proofGapClosureOpenCount=5,仍需真实业务材料关闭缺口。nextCommands 已经优先暴露 round:refresh。optimization-status 的 readyCapabilities 里仍有旧 next 文案:
optimization-handoff 仍提示单独跑 handoff:summary。round-deposition 仍提示先跑 round:deposition,再刷新 evidence:index 和 handoff:summary。evidence-index 仍提示单独跑 evidence:index。scripts/optimization-status-audit.js:
optimization-handoff.next 改为常规每轮优先 round:refresh,只在单独刷新交接摘要时跑 handoff:summary。round-deposition.next 改为常规每轮优先 round:refresh,确保状态、证据台账、交接摘要和沉淀审计按顺序刷新。evidence-index.next 改为长跑或复核后优先 round:refresh,只在单独刷新证明等级时跑 evidence:index。scripts/optimization-status-smoke.js:
optimization-handoff.next 必须包含 round:refresh。round-deposition.next 必须包含 round:refresh,且不得再包含旧的“再刷新 evidence:index”口径。evidence-index.next 必须包含 round:refresh。node --check scripts\optimization-status-audit.js 通过。node --check scripts\optimization-status-smoke.js 通过。npm.cmd run optimization:status:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
round-refresh-summary.json: 5 步全部 passoptimization-status-latest: 三个 next 文案均指向 round:refreshoptimization-handoff-latest: readyCapabilities 和 nextCommands 均指向 round:refreshround-deposition-latest: passed=true、failCount=0round:refresh。proofGapClosureOpenCount=5,仍需真实历史 Brief、真实视频资源、真实 A/B、真实 live/provider 长跑和客户复核效果数据。round:refresh 只刷新提号补证表单、状态、证据台账、交接摘要和 round deposition。proof-gap:request、proof-gap:closure、business-proof:progress、business-proof:next-actions 仍依赖旧 latest。business-proof:next-actions 暴露出一个真实回归:模板生成步骤、视频资源收集包生成步骤和“刷新证据和交接”步骤混入了下一步业务补证队列,导致行动数从 5 条膨胀到 8 条。scripts/refresh-round-artifacts.js:
proof-gap-software-form、proof-gap-request、proof-gap-closure、business-proof-progress、business-proof-next-actions、optimization-status、evidence-index、optimization-handoff、round-deposition。round-refresh-summary.json 现在记录 proof-gap 和 business-proof 两类产物路径。scripts/refresh-round-artifacts-smoke.js:
scripts/business-proof-next-actions.js:
step-01、step-02、step-15 作为准备/沉淀动作过滤,不再进入业务补证行动队列。npm run round:refresh -- --output-root outputs --strict。scripts/business-proof-next-actions-smoke.js:
round:refresh。docs/business-proof-action-order.md:
round-refresh-summary.json 5 步通过改为 9 步通过。scripts/generate-optimization-handoff.js:
node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过。npm.cmd run round:refresh:smoke 通过:
steps=proof-gap-software-form:pass, proof-gap-request:pass, proof-gap-closure:pass, business-proof-progress:pass, business-proof-next-actions:pass, optimization-status:pass, evidence-index:pass, optimization-handoff:pass, round-deposition:passbusiness-proof-next-actions.actionCount=5roundPassCount=47npm.cmd run plan:consistency:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
proof-gap-request-latest: unresolvedCount=5proof-gap-closure-latest: openCount=5business-proof-progress-latest: pass=3、blocked=7、pending=3、fail=2business-proof-next-actions-latest: actionCount=5evidence-index-latest: total=151、realEvidence=5、smokeOrLocal=25、notProof=121round-deposition-latest: passed=true、failCount=0proofGapClosureOpenCount=5,真实业务证明仍未关闭,不能宣称客户效果或命中率提升已达标。scripts/latest-form-index.js:
outputs/latest-form-index-latest/latest-form-index.md 和 latest-form-index-summary.json。directCustomerProof=false,避免把补证表单或候选名单误当成客户效果证明。scripts/latest-form-index-smoke.js:
tihao-proof-gap-software-form.csv 和 software-client-list.final.csv。round:refresh:
latest-form-index。round-refresh-summary.json 新增 latestFormIndex 产物路径。docs/business-proof-action-order.md 和 docs/tihao-experience-optimization-plan.md:
round-refresh-summary.json 10 步通过。node --check scripts\latest-form-index.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run round:refresh:smoke 通过:
steps=proof-gap-software-form:pass, proof-gap-request:pass, proof-gap-closure:pass, business-proof-progress:pass, business-proof-next-actions:pass, optimization-status:pass, evidence-index:pass, optimization-handoff:pass, latest-form-index:pass, round-deposition:passoutputs/latest-form-index-latest/latest-form-index.md,但 handoff 和 round deposition 还没有把它当成必须检查的一等产物。scripts/generate-optimization-handoff.js:
latestFormIndex 汇总字段。npm run latest-form:index -- --output outputs\latest-form-index-latest --strict。scripts/refresh-round-artifacts.js:
latest-form-index,再生成 optimization-handoff,最后跑 round-deposition。scripts/round-deposition-audit.js:
latest-form-index-summary、latest-form-index-passed、handoff-latest-form-index 三个检查项。scripts/evidence-index.js:
latest-form-index 证据分类,标记为 smoke_or_local,明确不证明客户效果或命中率提升。handoff:summary:smoke 断言 handoff 包含最新表单索引。round:deposition:smoke 断言沉淀审计检查最新表单索引。evidence:index:smoke 断言证据台账识别 latest-form-index。optimization:status:smoke 断言状态审计暴露稳定 ID latest-form-index。round:refresh:smoke 在临时环境中种入 software-client-latest,保证索引必须指向候选名单。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。node --check scripts\evidence-index.js 通过。node --check scripts\optimization-status-audit.js 通过。npm.cmd run handoff:summary:smoke 通过:readyCapabilities=28。npm.cmd run round:deposition:smoke 通过:passCount=50、failCount=0。npm.cmd run evidence:index:smoke 通过:total=28、smoke_or_local=14。npm.cmd run optimization:status:smoke 通过。npm.cmd run round:refresh:smoke 通过:
steps=proof-gap-software-form:pass, proof-gap-request:pass, proof-gap-closure:pass, business-proof-progress:pass, business-proof-next-actions:pass, optimization-status:pass, evidence-index:pass, latest-form-index:pass, optimization-handoff:pass, round-deposition:passroundPassCount=50intake:readiness 才整批退回。scripts/create-data-intake-pack.js:
brief编号、客户原始Brief、历史人工补号量基线、参考账号或视频、博主名称/主页链接、客户选择、拒绝原因 的必填规则和常见退回原因。人工复核标签、归因类型、反馈原因、客户选择、本轮人工补号量 的验收规则。npm run intake:readiness 的预审命令。scripts/create-video-intake-pack.js:
资源角色、博主名称/主页链接、视频链接、封面链接、字幕或ASR文本、帧图链接、内容摘要/风格调性标签/画面人设场景信号、是否真实资源 的必填规则和常见退回原因。npm run video:resource-readiness 的预审命令。data:intake-template:smoke 断言 README 包含字段验收表、常见退回原因、intake readiness 预审命令和客户拒绝原因要求。video:intake-template:smoke 断言 README 包含字段验收表、常见退回原因、video resource readiness 预审命令和防止占位行标成真实资源的提醒。outputs/data-intake-pack-latest/README.mdoutputs/video-intake-pack-latest/README.mdnode --check scripts\create-data-intake-pack.js 通过。node --check scripts\create-video-intake-pack.js 通过。npm.cmd run data:intake-template:smoke 通过。npm.cmd run video:intake-template:smoke 通过。npm.cmd run data:intake-template -- --output outputs\data-intake-pack-latest 已刷新数据收集包。npm.cmd run video:intake-template -- --output outputs\video-intake-pack-latest 已刷新视频收集包。npm.cmd run intake:readiness -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-readiness-latest 通过执行,当前模板数据正确被拦截:
overallReady=falsefailureCount=9npm.cmd run video:resource-readiness -- --input outputs\video-intake-pack-latest\video-resource-template.csv --output outputs\video-resource-readiness-latest 通过执行,当前模板数据正确被拦截:
readyForVideoAbPreflight=falsefailureCount=1intake:readiness 和 video:resource-readiness 之前能告诉用户有哪些问题,但商务/投放还需要人工把问题翻译成“改哪张表、哪一列、由谁改、通过标准是什么”。scripts/intake-readiness-audit.js:
repairActions。intake-readiness-repair-actions.csv,列包含优先级、负责人、区域、问题类型、文件、字段、修复动作和通过标准。scripts/video-resource-readiness-audit.js:
repairActions。video-resource-repair-actions.csv,列包含优先级、负责人、问题类型、行号、文件、字段、修复动作和通过标准。intake:readiness:smoke 断言模板审计为每个 issue 输出一条 repair action,并生成 CSV。video:resource-readiness:smoke 断言失败样本输出 repair actions 和 CSV,成功样本 repair actions 为 0。node --check scripts\intake-readiness-audit.js 通过。node --check scripts\video-resource-readiness-audit.js 通过。npm.cmd run intake:readiness:smoke 通过。npm.cmd run video:resource-readiness:smoke 通过。npm.cmd run intake:readiness -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-readiness-latest 已刷新:
failureCount=9repairActionCount=9outputs/intake-readiness-latest/intake-readiness-repair-actions.csvnpm.cmd run video:resource-readiness -- --input outputs\video-intake-pack-latest\video-resource-template.csv --output outputs\video-resource-readiness-latest 已刷新:
failureCount=1repairActionCount=1outputs/video-resource-readiness-latest/video-resource-repair-actions.csvintake-readiness 和 video-resource-readiness 生成的修复清单。scripts/latest-form-index.js:
repairActions.dataIntake 和 repairActions.videoResource。outputs/intake-readiness-latest/intake-readiness-repair-actions.csvoutputs/video-resource-readiness-latest/video-resource-repair-actions.csvscripts/generate-optimization-handoff.js:
latestFormIndex 汇总中同步携带 repairActions。latest-form:index:smoke 断言修复清单 CSV 和动作数存在。handoff:summary:smoke 断言交接摘要记录并展示修复清单入口。node --check scripts/latest-form-index.js 通过。node --check scripts/latest-form-index-smoke.js 通过。node --check scripts/generate-optimization-handoff.js 通过。node --check scripts/generate-optimization-handoff-smoke.js 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:refresh:smoke 通过:
roundPassCount=50failCount=0npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
proof-gap-closure.openCount=5business-proof-next-actions.actionCount=5optimization-status.passed=28optimization-status.ready_not_proven=2optimization-status.blocked_by_external_data=2evidence-index.total=152evidence-index.realEvidence=5evidence-index.smokeOrLocal=26evidence-index.notProof=121round-deposition.passed=trueround-deposition.passCount=50round-deposition.failCount=0outputs/latest-form-index-latest/latest-form-index.md 包含“修复清单入口”、两份 repair action CSV。outputs/optimization-handoff-latest/optimization-handoff-report.md 包含“修复清单入口”、两份 repair action CSV。outputs/latest-form-index-latest/latest-form-index-summary.json 和 outputs/optimization-handoff-latest/optimization-handoff-summary.json 均记录:failureCount=9,repairActionCount=9failureCount=1,repairActionCount=1proof-gap-closure.openCount > 0 或状态中仍有 ready_not_proven / blocked_by_external_data,就不能宣称长期优化目标完成。round-deposition 仍只检查索引是否指向补证表、候选名单和负责人行动文件。intake-readiness-repair-actions.csv 或 video-resource-repair-actions.csv 的入口,沉淀审计不会报警,商务又会回到“知道有缺口,但不知道改哪张表”的状态。scripts/round-deposition-audit.js:
latest-form-index-repair-actions。handoff-latest-form-repair-actions。observed 新增:latestFormIndexDataRepairCsvlatestFormIndexDataRepairActionCountlatestFormIndexVideoRepairCsvlatestFormIndexVideoRepairActionCountscripts/round-deposition-smoke.js:
repairActions。scripts/refresh-round-artifacts-smoke.js:
video-resource-readiness-latest 种子目录。node --check scripts/round-deposition-audit.js 通过。node --check scripts/round-deposition-smoke.js 通过。node --check scripts/refresh-round-artifacts-smoke.js 通过。npm.cmd run round:deposition:smoke 通过:
passCount=52failCount=0npm.cmd run round:refresh:smoke 通过:
roundPassCount=52failCount=0npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
passround-deposition.passed=trueround-deposition.passCount=52round-deposition.failCount=0passlatestFormIndexDataRepairCsv=outputs/intake-readiness-latest/intake-readiness-repair-actions.csvlatestFormIndexDataRepairActionCount=9latestFormIndexVideoRepairCsv=outputs/video-resource-readiness-latest/video-resource-repair-actions.csvlatestFormIndexVideoRepairActionCount=1proof-gap-closure.openCount=5,真实历史 Brief、真实视频资源、人工复核标注、真实视频 A/B 和真实 live/provider 长跑仍未关闭。intake-readiness-repair-actions.csv 或 video-resource-repair-actions.csv,商务还需要回到索引里再找一次具体修复字段,执行链路仍不够短。scripts/business-proof-next-actions.js:
intake-readiness-summary.json 和 video-resource-readiness-summary.json 读取 repairActions。ownerRepairArtifacts,按 owner 聚合修复清单附件。ownerArtifacts 中同步写入对应负责人的 repairArtifacts。node --check scripts/business-proof-next-actions.js 通过。node --check scripts/business-proof-next-actions-smoke.js 通过。npm.cmd run business-proof:next-actions:smoke 通过。npm.cmd run round:refresh:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
passbusiness-proof-next-actions.actionCount=5round-deposition.passed=trueround-deposition.passCount=52round-deposition.failCount=0outputs/business-proof-next-actions-latest/by-owner/business.md 包含“修复清单附件”和 intake-readiness-repair-actions.csv。outputs/business-proof-next-actions-latest/by-owner/business-media.md 包含“修复清单附件”、video-resource-repair-actions.csv 和归属投放的视频字段修复项。outputs/business-proof-next-actions-latest/business-proof-next-actions-report.md 包含两份 repair CSV。npm.cmd run acceptance 通过,npm pack / workspace install smoke / MCP smoke 均正常。ownerRepairArtifacts 仍基于模板/占位数据的预审失败项生成;真实通过需要商务/投放替换为真实历史 Brief、真实视频资源、人工复核和客户选择后重跑。optimization-status.complete=false。business-proof-next-actions-summary.json 已经有 owner 级 repairArtifacts,负责人 Markdown 也能直接展示修复清单附件。latest-form-index 和 optimization-handoff 在重新归一化负责人文件时只保留 Markdown/CSV,丢掉了 repairArtifacts。scripts/latest-form-index.js:
normalizeOwnerArtifacts 优先读取 business-proof-next-actions-summary.json 的 ownerArtifacts。repairArtifacts。scripts/generate-optimization-handoff.js:
normalizeOwnerArtifacts 保留每个 owner 的 repairArtifacts。latest-form:index:smoke 断言商务和商务/投放 owner repair artifacts 不丢失。handoff:summary:smoke 断言 handoff 中商务和商务/投放 owner repair artifacts 不丢失。node --check scripts/latest-form-index.js 通过。node --check scripts/generate-optimization-handoff.js 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:refresh:smoke 通过。npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
passround-deposition.passed=trueround-deposition.passCount=52round-deposition.failCount=0outputs/latest-form-index-latest/latest-form-index-summary.json 中 nextActions.ownerArtifacts 已保留 owner 级 repairArtifacts。outputs/optimization-handoff-latest/optimization-handoff-summary.json 中 businessProofNextActions.ownerArtifacts 已保留 owner 级 repairArtifacts。outputs/latest-form-index-latest/latest-form-index.md 和 outputs/optimization-handoff-latest/optimization-handoff-report.md 都包含“修复附件”、intake-readiness-repair-actions.csv 和 video-resource-repair-actions.csv。npm.cmd run acceptance 通过,npm pack / workspace install smoke / MCP smoke 均正常。optimization-status.complete=false,不能宣称命中率或客户效果已达标。repairArtifacts,但 round-deposition 之前只检查全局 repairActions。scripts/round-deposition-audit.js:
latest-form-index-owner-repair-actions。handoff-owner-repair-actions。observed 新增 latestFormIndexOwnerRepairSummary 和 handoffOwnerRepairSummary。scripts/round-deposition-smoke.js:
node --check scripts/round-deposition-audit.js 通过。node --check scripts/round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过:
passCount=54failCount=0npm.cmd run round:refresh:smoke 通过:
roundPassCount=54failCount=0npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
passround-deposition.passed=trueround-deposition.passCount=54round-deposition.failCount=0latest-form-index-owner-repair-actions=passhandoff-owner-repair-actions=passlatestFormIndexOwnerRepairSummary 和 handoffOwnerRepairSummary 均记录商务、商务/投放 owner repair 附件。npm.cmd run acceptance 通过,npm pack / workspace install smoke / MCP smoke 均正常。optimization-status.complete=false。intake-readiness-repair-actions.csv 与 video-resource-repair-actions.csv。evidence-index 之前只把这些修复清单折叠在 latest-form-index 或 readiness 产物里,没有独立证据条目。scripts/evidence-index.js:
intake-repair-actions 分类。video-resource-repair-actions 分类。smoke_or_local,只表示补证执行清单存在,不升级为真实业务证明。scripts/evidence-index-smoke.js:
node --check scripts/evidence-index.js 通过。node --check scripts/evidence-index-smoke.js 通过。npm.cmd run evidence:index:smoke 通过:
total=30smoke_or_local=16not_business_proof=9real_evidence=5npm.cmd run round:refresh:smoke 通过。npm.cmd run hygiene:smoke 通过:
hitCount=0npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
passevidence-index.total=154evidence-index.smoke_or_local=28evidence-index.not_business_proof=121evidence-index.real_evidence=5intake-repair-actions=1video-resource-repair-actions=1round-deposition.passed=trueround-deposition.passCount=54round-deposition.failCount=0npm.cmd run acceptance 通过,npm pack / workspace install smoke / MCP smoke / provider mock 均正常。proof-gap-closure.openCount=5,真实历史 Brief、真实视频资源、人工复核标注、真实视频 A/B、真实 live/provider 长跑证明仍未关闭。optimization-status.complete=false。scripts/business-execution-index.js:
business-execution-index-summary.json、business-execution-index.md、business-execution-index.csv。directCustomerProof=false,证明等级固定为 smoke_or_local。scripts/business-execution-index-smoke.js,覆盖负责人行动、修复清单和关键文件行。package.json:新增 business-execution:index 和 business-execution:index:smoke。scripts/refresh-round-artifacts.js:round:refresh 增加 business-execution-index 步骤。scripts/evidence-index.js 和 smoke:新增 business-execution-index 证据分类。scripts/generate-optimization-handoff.js 和 smoke:handoff 新增“商务执行总表”入口。scripts/acceptance.js:发布前验收纳入 business-execution:index:smoke。node --check scripts/business-execution-index.js 通过。node --check scripts/business-execution-index-smoke.js 通过。node --check scripts/refresh-round-artifacts.js 通过。node --check scripts/generate-optimization-handoff.js 通过。node --check scripts/evidence-index.js 通过。npm.cmd run business-execution:index:smoke 通过:rowCount=8,repairRowCount=2。npm.cmd run evidence:index:smoke 通过:total=31,smoke_or_local=17。npm.cmd run round:refresh:smoke 通过,新增 business-execution-index:pass。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
business-execution-index.passed=truebusiness-execution-index.rowCount=11business-execution-index.actionRowCount=5business-execution-index.repairRowCount=3business-execution-index.proofOpenCount=5business-execution-index.directCustomerProof=falseevidence-index.total=155evidence-index.smoke_or_local=29evidence-index.not_business_proof=121evidence-index.real_evidence=5npm.cmd run handoff:summary:smoke 通过。npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run acceptance 通过,npm pack / workspace install smoke / MCP smoke / provider mock 均正常。proof-gap-closure.openCount=5,真实历史 Brief、真实视频资源、人工复核标注、真实视频 A/B、真实 live/provider 长跑证明仍未关闭。当前 optimization-status.complete=false。
business-execution-index 已经能把负责人行动、修复清单、关键文件和证明边界汇总成商务可执行总表,但上一版 round-deposition 还没有把它作为每轮沉淀的硬门槛。directCustomerProof=false、proofOpenCount、负责人行动/修复清单/关键文件三类行,旧审计不会拦截。generate-optimization-handoff 在临时 outputsDir 场景下仍可能读取根目录 outputs 的旧产物,导致 smoke 刷新和真实刷新看到的执行总表不一致。scripts/round-deposition-audit.js:新增 businessExecutionIndexPath 输入,并新增 business-execution-index-summary、business-execution-index-passed、handoff-business-execution-index 三个检查项。scripts/round-deposition-audit.js:observed 增加 businessExecutionIndexPassed、businessExecutionIndexRowCount、businessExecutionIndexActionRowCount、businessExecutionIndexRepairRowCount、businessExecutionIndexProofOpenCount、businessExecutionIndexDirectCustomerProof。scripts/round-deposition-smoke.js:新增 business-execution-index-latest 夹具,覆盖负责人行动、修复清单、关键文件三类行,并断言报告展示 businessExecutionIndex.rowCount 和 businessExecutionIndex.directCustomerProof。scripts/generate-optimization-handoff.js:latestOutputDir 改为尊重传入的 outputsDir,并新增 artifactPath、artifactRef,保证根目录相对产物和临时绝对路径产物读取一致。node --check scripts/round-deposition-audit.js 通过。node --check scripts/round-deposition-smoke.js 通过。node --check scripts/generate-optimization-handoff.js 通过。npm.cmd run round:deposition:smoke 通过:passCount=57,failCount=0,proofGapUnresolvedCount=5。npm.cmd run round:refresh:smoke 通过:11 个刷新步骤全部 pass,roundPassCount=57。npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:business-execution-index.passed=true,rowCount=11,actionRowCount=5,repairRowCount=3,proofOpenCount=5,directCustomerProof=false,round-deposition.passCount=57,round-deposition.failCount=0。npm.cmd run acceptance 通过,包含 package smoke、workspace install smoke、MCP smoke、provider mock、round refresh smoke 和 round deposition smoke。当前 optimization-status.complete=false,proof-gap-closure.openCount=5,不能宣布长期优化目标完成。
intake-readiness-repair-actions.csv 能给出“问题类型级”的修复动作,但商务实际补数时还需要逐行、逐字段知道该填哪里、当前值是什么、通过标准是什么。scripts/intake-field-checklist.js:
data-intake-pack-latest/history-data-template.csv、data-intake-pack-latest/manual-review-template.csv 和 video-intake-pack-latest/video-resource-template.csv。intake-field-checklist-summary.json、intake-field-checklist.md、intake-field-checklist.csv。proofLevel=smoke_or_local、directCustomerProof=false,明确不证明客户效果。scripts/intake-field-checklist-smoke.js:
package.json:
intake:field-checklist 和 intake:field-checklist:smoke。scripts/refresh-round-artifacts.js:
round:refresh 新增 intake-field-checklist 步骤,且显式使用本轮 outputRoot 下的 data/video pack。scripts/refresh-round-artifacts-smoke.js:
intake-field-checklist 产物存在,并进入证据台账。scripts/evidence-index.js:
intake-field-checklist 证据分类,等级为 smoke_or_local。scripts/business-execution-index.js:
scripts/acceptance.js:
intake:field-checklist:smoke。node --check scripts/intake-field-checklist.js 通过。node --check scripts/intake-field-checklist-smoke.js 通过。node --check scripts/refresh-round-artifacts.js 通过。node --check scripts/evidence-index.js 通过。node --check scripts/business-execution-index.js 通过。npm.cmd run intake:field-checklist:smoke 通过:itemCount=21,missingRequiredCount=8,placeholderCount=13。npm.cmd run round:refresh:smoke 通过:12 个刷新步骤全部 pass,字段级核对表被证据台账识别。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
intake-field-checklist.passed=trueintake-field-checklist.itemCount=25intake-field-checklist.missingRequiredCount=8intake-field-checklist.placeholderCount=17business-execution-index.rowCount=12evidence-index.total=156evidence-index.smoke_or_local=30round-deposition.passCount=57round-deposition.failCount=0npm.cmd run acceptance 通过,包含新增字段级核对表 smoke、round refresh smoke、workspace install smoke、MCP smoke 和 provider mock。optimization-status.complete=false,proof-gap-closure.openCount=5。intake-field-checklist,但 handoff 和 round deposition 还需要把它作为硬性交接与沉淀项。scripts/generate-optimization-handoff.js:
intake-field-checklist-summary.json。intakeFieldChecklist。npm run intake:field-checklist -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-field-checklist-latest。scripts/generate-optimization-handoff-smoke.js:
directCustomerProof=false。intake-field-checklist.csv。scripts/round-deposition-audit.js:
intakeFieldChecklistPath 输入。intake-field-checklist-summary、intake-field-checklist-passed、handoff-intake-field-checklist 三个检查项。observed 新增 intakeFieldChecklistPassed、intakeFieldChecklistItemCount、intakeFieldChecklistMissingRequiredCount、intakeFieldChecklistPlaceholderCount、intakeFieldChecklistDirectCustomerProof。scripts/round-deposition-smoke.js:
directCustomerProof=false。node --check scripts/generate-optimization-handoff.js 通过。node --check scripts/round-deposition-audit.js 通过。node --check scripts/round-deposition-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:deposition:smoke 通过:passCount=60,failCount=0。npm.cmd run round:refresh:smoke 通过:12 个刷新步骤全部 pass,roundPassCount=60。npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 已刷新真实 latest:
intake-field-checklist.passed=trueintake-field-checklist.itemCount=25intake-field-checklist.missingRequiredCount=8intake-field-checklist.placeholderCount=17business-execution-index.rowCount=12evidence-index.total=156evidence-index.smoke_or_local=30round-deposition.passCount=60round-deposition.failCount=0optimization-status.complete=falseproof-gap-closure.openCount=5npm.cmd run acceptance 通过,包含字段级核对表 smoke、handoff、round refresh、round deposition、MCP、workspace install、npm pack 和 provider mock。optimization-status.complete=false,长期优化目标还不能标记完成。proof-gap-closure.openCount=5,仍需外部真实历史 Brief、真实视频资源、人工复核标注、真实视频 A/B 和真实 live/provider 长跑证明。proof-gap-closure 已经能阻止 sample、smoke 或缺少 proofContext 的视频 A/B 产物关闭真实证明缺口。mode=unknown、generatedBy=unknown 等信息,商务或下一轮 AI 需要自己推断到底缺了哪些证明字段。scripts/proof-gap-closure-audit.js 的用户可见文案存在历史编码显示问题,虽然产物可读,但维护时容易误改。scripts/proof-gap-closure-audit.js 的用户可见文案为可读中文。getVideoAbMissingRequirements(videoAb):
acceptance.passed=true。proofContext.mode=live。proofContext.collectionMode=live。proofContext.generatedBy=acceptance:video-ab。proofContext.requiresRuntimeCredential=true。proofContext.requiresVocSocialProvider=true。proofContext.requiresVideoAnalysisProvider=true。enhanced.provider.evidence.providerStatus=ok。proof-gap-closure-summary.json 的 video-ab-live-proof 行新增 missingProofRequirements。proof-gap-closure-report.md 新增“缺失证明”列,让视频 A/B 为什么仍为 open 可以直接读出来。scripts/proof-gap-closure-smoke.js:
proofContext 的视频 A/B 即使 acceptance.passed=true,也必须保持 open。node --check scripts\proof-gap-closure-audit.js 通过。node --check scripts\proof-gap-closure-smoke.js 通过。npm.cmd run proof-gap:closure:smoke 通过:openCount=5,closedCount=5。npm.cmd run round:refresh -- --output-root outputs --strict 通过:
proof-gap-closure.complete=falseproof-gap-closure.openCount=5video-ab-live-proof.status=openvideo-ab-live-proof.missingProofRequirements 包含 proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab、proofContext.requiresRuntimeCredential=true、proofContext.requiresVocSocialProvider=true、proofContext.requiresVideoAnalysisProvider=trueround-deposition.passCount=60round-deposition.failCount=0npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run acceptance 通过,包含 proof-gap closure smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。video-ab-live-proof。optimization-status.complete=false,proof-gap-closure.openCount=5。proof-gap-closure 已经结构化输出 video-ab-live-proof.missingProofRequirements。mode=unknown、generatedBy=unknown 等当前证据,技术/AI 打开负责人文件时还需要回到 closure 报告推断缺什么。scripts/business-proof-next-actions.js:
actionFromClosureRow 保留 missingProofRequirements。next 字段自动追加“缺失证明:...”。mergeList 保留缺失证明列表,避免技术动作合并后丢失。scripts/business-proof-next-actions-missing-proof-smoke.js:
video-ab-live-proof 的 proof-gap closure fixture。missingProofRequirements。proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab。package.json:
business-proof:next-actions:missing-proof:smoke。scripts/acceptance.js:
node --check scripts\business-proof-next-actions.js 通过。node --check scripts\business-proof-next-actions-missing-proof-smoke.js 通过。npm.cmd run business-proof:next-actions:missing-proof:smoke 通过:missingCount=3。npm.cmd run business-proof:next-actions:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过:
business-proof-next-actions.actionCount=5gap-video-ab-live-proof.missingProofRequirements 包含 6 个缺失证明项。business-proof-next-actions-report.md、by-owner/tech-ai.md、business-proof-next-actions.csv 均展示 proofContext.mode=live、proofContext.generatedBy=acceptance:video-ab 等缺失证明。round-deposition.passCount=60round-deposition.failCount=0npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run acceptance 通过,包含新增 missing-proof smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。acceptance:video-ab 产物带完整 live proofContext 并通过 closure 审计,才能关闭 video-ab-live-proof。optimization-status.complete=false,proof-gap-closure.openCount=5。video-ab-live-proof.missingProofRequirements 透传到下一步行动队列、技术/AI 负责人文件和 CSV。proofContext.mode=live、proofContext.generatedBy=acceptance:video-ab 等缺失证明。scripts/business-execution-index.js:
missingProofRequirements。appendMissingProofRequirements 把缺失证明追加进总表验收标准。scripts/business-execution-index-smoke.js:
missingProofRequirements。proofContext.mode=live。node --check scripts\business-execution-index.js 通过。node --check scripts\business-execution-index-smoke.js 通过。npm.cmd run business-execution:index:smoke 通过:rowCount=8,repairRowCount=2。npm.cmd run round:refresh -- --output-root outputs --strict 通过:
business-execution-index.passed=truebusiness-execution-index.rowCount=12proofOpenCount=5business-execution-index.md 和 business-execution-index.csv 的“真实视频 A/B 验收”行均展示 proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab、proofContext.requiresRuntimeCredential=true、proofContext.requiresVocSocialProvider=true、proofContext.requiresVideoAnalysisProvider=true。round-deposition.passCount=60round-deposition.failCount=0npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run acceptance 通过,包含 business execution smoke、missing-proof smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。acceptance:video-ab 产物并通过 closure 审计后才能关闭。optimization-status.complete=false,proof-gap-closure.openCount=5。proof-gap-closure、下一步行动队列、负责人文件和商务执行总表已经能展示视频 A/B 缺失证明。optimization-handoff 之前没有直接记录 closure 明细,只提供了相关入口链接。video-ab-live-proof 为什么是 open,以及还缺哪些 live proof 字段。scripts/generate-optimization-handoff.js:
proof-gap-closure-summary.json。proofGapClosure 字段,包含 summary、report、complete、openCount、closedCount、intakeReady 和标准化 rows。scripts/generate-optimization-handoff-smoke.js:
openCount。video-ab-live-proof 必须展示 proofContext.mode=live。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:refresh -- --output-root outputs --strict 通过:
optimization-handoff.proofGapClosure.openCount=5optimization-handoff.proofGapClosure.rows=6video-ab-live-proof.missingProofRequirements 包含 6 个 live proof 缺失项。optimization-handoff-report.md 开头新增“真实证明缺口关闭状态”,直接展示 proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab 等缺失证明。round-deposition.passCount=60round-deposition.failCount=0npm.cmd run hygiene:smoke 通过:hitCount=0。npm.cmd run acceptance 通过,包含 handoff smoke、business execution smoke、missing-proof smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。optimization-status.complete=false,proof-gap-closure.openCount=5。proofGapClosure 写入 optimization-handoff-summary.json 和 handoff 正文。round-deposition 只审 standalone 的 proof-gap-closure-summary.json,没有独立校验 handoff 内部的 proofGapClosure 是否完整。video-ab-live-proof 仍缺哪些 live proof 字段,进而误把接口 200、sample 或 smoke 当作业务证明。scripts/round-deposition-audit.js:
handoff-proof-gap-closure 检查项。hasHandoffProofGapClosure(handoff, closure),校验 handoff 中的 proofGapClosure.complete=false、openCount、closedCount、intakeReady、summary/report 路径和 rows 与 closure summary 对齐。video-ab-live-proof.missingProofRequirements 必须包含 6 个 live proof 缺失项:proofContext.mode=live、proofContext.collectionMode=live、proofContext.generatedBy=acceptance:video-ab、proofContext.requiresRuntimeCredential=true、proofContext.requiresVocSocialProvider=true、proofContext.requiresVideoAnalysisProvider=true。handoffProofGapClosureOpenCount、handoffProofGapClosureRows、handoffVideoAbMissingProofCount。scripts/round-deposition-smoke.js:
proofGapClosure。video-ab-live-proof 和 missingProofRequirements。handoff-proof-gap-closure 检查项,且 report/summary 必须展示 handoff closure openCount、rows 和视频 A/B 缺失证明数。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run round:deposition:smoke 通过:
passCount=61failCount=0proofGapUnresolvedCount=5npm.cmd run round:refresh -- --output-root outputs --strict 通过:
round-deposition.passCount=61round-deposition.failCount=0round-deposition.warnCount=0proof-gap-closure.openCount=5optimization-handoff.complete=falseoptimization-status.complete=falsenpm.cmd run acceptance 通过,包含 round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。npm.cmd run hygiene:smoke 通过:
hitCount=0handoff.proofGapClosure.openCount=5,video-ab-live-proof 仍缺 6 个真实 live proof 字段。optimization-status.complete=false,长期优化目标仍不能标记完成。feedback:roundtrip 能证明 sample 工作流里记忆会影响第二轮名单,但没有独立沉淀“负反馈账号是否泄漏进第二轮可发客户名单”的审计产物。scripts/feedback-loop-closure-audit.js:
--feedback <反馈CSV>、--memory <记忆JSON>、--result <第二轮tihao-sourcing-result.json>。feedback-loop-closure-summary.json、feedback-loop-closure-report.md、feedback-loop-closure.csv。passed=false、complete=false、directCustomerProof=false 和缺失输入清单。proofLevel=smoke_or_local,不作为客户效果证明。scripts/feedback-loop-closure-smoke.js:
leakedCount=0。directCustomerProof=false。package.json:
feedback:closure。feedback:closure:smoke。scripts/acceptance.js:
feedback:closure:smoke。scripts/refresh-round-artifacts.js 和 scripts/refresh-round-artifacts-smoke.js:
feedback-loop-closure 步骤。scripts/evidence-index.js:
feedback-loop-closure 分类。directCustomerProof、passed 区分 real_evidence、smoke_or_local、not_business_proof。scripts/generate-optimization-handoff.js 和 smoke:
feedbackLoopClosure。feedback:closure 命令。directCustomerProof=false。scripts/round-deposition-audit.js 和 smoke:
feedback-loop-closure-summary、feedback-loop-closure-boundary、handoff-feedback-loop-closure 三个检查项。scripts/optimization-status-audit.js:
feedback-roundtrip 能力判断纳入 feedback:closure、feedback:closure:smoke、directCustomerProof 和 leakedCount 口径。node --check scripts\feedback-loop-closure-audit.js 通过。node --check scripts\feedback-loop-closure-smoke.js 通过。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\round-deposition-audit.js 通过。npm.cmd run feedback:closure:smoke 通过:
negativeFeedbackCount=4leakedCount=0directCustomerProof=falsenpm.cmd run optimization:status:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:refresh:smoke 通过:
steps=13feedback-loop-closure.directCustomerProof=falseroundPassCount=64npm.cmd run round:refresh -- --output-root outputs --strict 通过:
feedback-loop-closure-latest.passed=falsefeedback-loop-closure-latest.complete=falsefeedback-loop-closure-latest.directCustomerProof=falsefeedback-loop-closure-latest.negativeFeedbackCount=0feedback-loop-closure-latest.leakedCount=0evidence-index.total=158evidence-index.smoke_or_local=31evidence-index.not_business_proof=122round-deposition.passCount=64round-deposition.failCount=0npm.cmd run acceptance 通过,包含 feedback closure smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。npm.cmd run hygiene:smoke 通过:
hitCount=0tihao-sourcing-result.json,所以 feedback-loop-closure-latest.passed=false 且 directCustomerProof=false 是正确状态。当前 optimization-status.complete=false,proof-gap-closure.openCount=5,长期优化目标仍不能标记完成。
homepage-evidence-provider.js 和 homepage:smoke,可以验证 provider 请求契约、成功挂载和鉴权失败 fallback。scripts/homepage-evidence-readiness-audit.js:
tihao-sourcing-result.json、主页证据 JSON 或 CSV。homepage-evidence-readiness-summary.json、homepage-evidence-readiness-report.md、homepage-evidence-repair-actions.csv。--strict 下证据不足会返回非零。directCustomerProof=false,避免把主页证据 ready 误报为客户效果证明。scripts/homepage-evidence-readiness-smoke.js,覆盖 ready、weak 和 strict weak 三种场景。package.json 新增 homepage:readiness 和 homepage:readiness:smoke。acceptance、round:refresh、evidence:index、handoff:summary、optimization:status、round:deposition 均已纳入该审计。node --check scripts\homepage-evidence-readiness-audit.js 通过。node --check scripts\homepage-evidence-readiness-smoke.js 通过。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\round-deposition-audit.js 通过。npm.cmd run homepage:readiness:smoke 通过。npm.cmd run evidence:index:smoke 通过:total=34,smoke_or_local=19,not_business_proof=10,real_evidence=5。npm.cmd run handoff:summary:smoke 通过:readyCapabilities=29,readyNotProven=2,externalBlockers=2。npm.cmd run optimization:status:smoke 通过。npm.cmd run round:refresh:smoke 通过:steps=14,roundPassCount=69。npm.cmd run round:refresh -- --output-root outputs --strict 通过:
homepage-evidence-readiness-latest.ready=falsehomepage-evidence-readiness-latest.proofLevel=not_business_proofhomepage-evidence-readiness-latest.failureCount=9homepage-evidence-readiness-latest.repairActionCount=9optimization-status.complete=falseproof-gap-closure.openCount=5evidence-index.total=161round-deposition.passCount=69round-deposition.failCount=0npm.cmd run acceptance 通过,包含 homepage readiness smoke、round refresh smoke、round deposition smoke、MCP、workspace install、npm pack 和 provider mock。npm.cmd run hygiene:smoke 通过:hitCount=0。homepage-evidence-readiness-latest.ready=false 是正确状态。optimization-status.complete=false,proof-gap-closure.openCount=5,长期优化目标仍不能标记完成。docs/tihao-experience-implementation-log-20260608-business-execution-field-recheck-rows.md。business-execution-index 不再只展示字段核对表入口,而是把 intake-field-checklist 中的 ownerGroups 展开为 字段补齐负责人 行。business-execution-index 已把 recheckCommands 展开为 补齐后复验命令 行,商务补完材料后可以直接看到复验命令。round-deposition 守卫新增对 fieldOwnerRowCount 和 recheckCommandRowCount 的观察与校验,防止后续刷新丢失这两类行。npm.cmd run business-execution:index:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=74,failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过。proof-gap-closure.openCount=5,optimization-status.complete=false。docs/tihao-experience-implementation-log-20260608-latest-form-business-execution-entry.md。latest-form:index 新增 businessExecutionIndex,指向 business-execution-index.md/csv/summary。round-deposition 新增检查项 latest-form-index-business-execution-index,确保最新索引不会丢失商务执行总表入口。npm.cmd run latest-form:index:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=75,failCount=0。latest-form:index 新增 businessFillGuide,把字段补齐负责人分组转换为商务可直接使用的填表执行视图。latest-form-index:smoke 新增对 businessFillGuide 的结构、复验命令和“不证明客户效果”边界校验。round-deposition 新增检查项 latest-form-index-business-fill-guide,防止最新提号表单索引退化为只给文件路径、不告诉商务如何填和如何复验。npm.cmd run latest-form:index:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=76,failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 的 round-deposition.passCount=76,failCount=0。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run acceptance 通过。proof-gap-closure.openCount=5,optimization-status.complete=false。docs/tihao-experience-implementation-log-20260608-business-fill-guide.md。handoff:summary 已从最新提号表单索引读取 businessFillGuide,并写入 optimization-handoff-summary.json 的 latestFormIndex.businessFillGuide。optimization-handoff-report.md 的“最新提号表单索引”段落新增“商务填表执行视图”,展示 history、video、review 三类填表任务的文件、优先 FIELD、复验命令、验收标准和证明边界。handoff:summary:smoke 新增对 businessFillGuide 的结构、真实模板文件、视频资源复验命令和证明边界断言。round-deposition 新增检查项 handoff-latest-form-business-fill-guide,确保下一轮 AI 从交接摘要即可看到商务填表顺序。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=77,failCount=0。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 的 round-deposition.passCount=77,failCount=0。npm.cmd run acceptance 通过。proof-gap-closure.openCount=5,optimization-status.complete=false。docs/tihao-experience-implementation-log-20260608-handoff-business-fill-guide.md。manual-review:label-guide,生成 outputs/manual-review-label-guide-latest/manual-review-label-guide.md/csv/summary.json。latest-form:index 新增 manualReviewLabelGuide,商务打开最新提号表单索引即可看到复核标签指南入口。handoff:summary 承接 latestFormIndex.manualReviewLabelGuide,下一轮 AI 能从交接摘要拿到复核标签和归因口径。round:refresh 新增 manual-review-label-guide 步骤,round-deposition 新增指南本体、最新表单索引和交接摘要三类守卫。npm.cmd run manual-review:label-guide:smoke 通过。npm.cmd run latest-form:index:smoke 通过。npm.cmd run handoff:summary:smoke 通过。npm.cmd run round:deposition:smoke 通过,passCount=81,failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 的 round-deposition.passCount=81,failCount=0。proof-gap-closure.openCount=5,optimization-status.complete=false。skills/tihao-creator-sourcing/references/user-workflow.md,把提号 SOP、参考视频补证、豆包视频分析、人工复核标签、归因类型和验收命令整理为中文可读流程。skills/tihao-creator-sourcing/references/output-format.md,把软件端交付表固定表头、人工复核字段、去重规则、JSON/MCP 保留字段和效果证明边界沉淀为中文。docs/manual-review-handoff.md,让商务能直接看到复核表位置、标签口径、归因类型、复核顺序、质量指标和客户效果审计命令。skill:refs:smoke 与 scripts/skill-reference-readability-smoke.js,检查三份关键文档必须包含人工复核标签、归因类型、客户效果边界,并阻止常见乱码回退。acceptance 已纳入 skill:refs:smoke,发布前会自动校验技能参考文档和人工复核交接文档。npm.cmd run skill:refs:smoke 通过,3 份关键文档 hasCommonMojibake=false。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run acceptance 通过,包含 workspace install smoke 与 npm pack --dry-run。docs/tihao-experience-optimization-plan.md 从乱码版替换为中文可读执行版。customer-effect:audit 通过。npm.cmd run plan:consistency:smoke 通过。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,15 个刷新步骤全部 pass。round-deposition.passCount=81,failCount=0,warnCount=0。proof-gap-closure.openCount=5,optimization-status.complete=false。plan:execution-status,生成 outputs/plan-execution-status-latest/plan-execution-status.md/csv/summary.json。plan:execution-status:smoke,校验 8 个章节、中文报告、proofOpenCount、防误报边界、无 token 泄露和无常见乱码。round:refresh 从 15 步扩展为 16 步,最后一步自动刷新计划执行状态面板。npm.cmd run plan:execution-status:smoke 通过,rowCount=8,proofOpenCount=5。npm.cmd run round:refresh:smoke 通过,16 个步骤顺序稳定。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 已生成 outputs/plan-execution-status-latest/*。outputs/plan-execution-status-latest/plan-execution-status-summary.json 显示 complete=false、proofOpenCount=5。plan-execution-status 纳入 latest-form:index,最新提号表单索引现在直接展示 plan-execution-status.md/csv/summary.json、rowCount=8、complete=false 和 proofOpenCount。plan-execution-status 纳入 handoff:summary,交接摘要同时在顶层和 latest-form-index 子节点展示计划执行状态面板,方便下一轮 AI 与商务从一个入口看到当前完成度。plan-execution-status 纳入 round:deposition 审计,新增 4 个守卫:面板存在、8 个章节与未完成边界、最新表单索引可见、交接摘要可见。round:refresh 顺序:先生成 plan-execution-status,再生成 latest-form-index、optimization-handoff 和 round-deposition,确保三类入口引用同一轮状态面板。open,不再误报为 missing。npm.cmd run plan:execution-status:smoke 通过,rowCount=8,proofOpenCount=5。npm.cmd run latest-form:index:smoke 通过,最新表单索引已校验 plan-execution-status.md/csv/summary.json。npm.cmd run handoff:summary:smoke 通过,交接摘要已校验顶层和 latest-form-index 内的计划状态入口。npm.cmd run round:deposition:smoke 通过,passCount=85,failCount=0。npm.cmd run round:refresh:smoke 通过,16 步顺序为 ... evidence-index, plan-execution-status, latest-form-index, optimization-handoff, round-deposition。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 已刷新。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run acceptance 通过,包含 workspace install smoke 与 npm pack --dry-run。proof-gap-closure.openCount=5,plan-execution-status.complete=false,optimization-status.complete=false。proof-gap:operator-pack,生成 outputs/proof-gap-operator-pack-latest/proof-gap-operator-pack.md/csv/summary.json。directCustomerProof=false、proofLevel=not_business_proof;sample、接口 200、长跑稳定或补齐材料都不能单独证明客户效果。round:refresh,刷新链路从 16 步扩展为 17 步:先刷新计划执行状态,再生成补证操作包,再刷新 evidence index、latest form、handoff 和 round deposition。evidence:index、latest-form:index 和 handoff:summary,商务和下一轮 AI 可以从最新表单索引或交接摘要直接找到补证操作表。npm.cmd run proof-gap:operator-pack:smoke 通过,rowCount=5,openCount=5。npm.cmd run latest-form:index:smoke 通过,最新表单索引可读取新增操作包入口。npm.cmd run handoff:summary:smoke 通过,交接摘要可读取顶层和 latest-form-index 内的操作包入口。npm.cmd run evidence:index:smoke 通过,证据索引支持 proof-gap-operator-pack 类型。npm.cmd run round:refresh:smoke 通过,17 步顺序稳定,且 evidence index 已收录操作包。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 已刷新。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run acceptance 通过,包含 workspace install smoke 与 npm pack --dry-run。outputs/proof-gap-operator-pack-latest/proof-gap-operator-pack-summary.json 显示 passed=true、complete=false、openCount=5、rowCount=5。docs/tihao-experience-optimization-plan.md 替换为中文可读执行版,不再依赖 .zh-CN.md 作为备用入口。plan:consistency:smoke:对主计划改为检查中文关键短语,包括“全局博主唯一”“平台 + 规范化主页链接”“平台 + 规范化博主名称”“不得宣称客户效果完成”。npm.cmd run plan:consistency:smoke 通过,hits=[]。npm.cmd run plan:execution-status:smoke 通过,rowCount=8,proofOpenCount=5。npm.cmd run round:refresh -- --output-root outputs --strict 通过,17 步全部 pass。npm.cmd run hygiene:smoke 通过,hitCount=0。npm.cmd run acceptance 通过,包含 workspace install smoke 与 npm pack --dry-run。proof-gap-closure.openCount=5,plan-execution-status.complete=false,optimization-status.complete=false。outputs/long-run-readiness-latest/long-run-readiness-report.md 和 long-run-readiness-summary.json 作为一等入口纳入 latest-form:index。latest-form-index-summary.json 新增 longRunReadiness,暴露 mode、ready、passCount、failCount、warnCount、directCustomerProof=false 和 proofLevel=not_business_proof。handoff:summary 顶层新增“长跑前置门禁”段落,同时在 latestFormIndex.longRunReadiness 中透传同一入口,避免下一轮 AI 只能从 round-refresh-summary.json 间接定位长跑门禁。handoff:summary 的下一轮命令新增 longrun:readiness,明确启动 full-matrix/live 长跑或客户效果审计前必须先跑前置门禁。latest-form:index:smoke 和 handoff:summary:smoke,要求报告包含 long-run-readiness-report.md、ready=false 和“不证明客户效果”的边界。node --check scripts\latest-form-index.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。npm.cmd run latest-form:index:smoke 通过,longRunReadiness.ready=false、failCount>=1、proofLevel=not_business_proof。npm.cmd run handoff:summary:smoke 通过,handoff 顶层和 latestFormIndex 嵌套节点都能看到长跑前置门禁。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实输出已刷新;当前 long-run-readiness.ready=false、failCount=6。npm.cmd run round:refresh:smoke 通过,临时 22 步刷新链路同样保留长跑前置门禁入口。npm.cmd run task:handoff-index:smoke 通过,任务交接入口继续保留 openCount=5、readyForClaim=false 边界。npm.cmd run hygiene:smoke 通过,扫描 166 个文件,hitCount=0。npm.cmd run acceptance 通过,总验收保持通过,且 latest-form:index:smoke、handoff:summary:smoke、round:refresh:smoke 均在 acceptance 中通过。proof-gap-closure.openCount=5,optimization-completion.readyForClaim=false,不得宣称提号率提升、客户效果达标或人工补号量下降。longrun:readiness.ready=false 是真实卡点,不是交付失败;它说明 full-matrix/live 长跑和客户效果审计还不能启动或宣称完成。intake:readiness、video:resource-readiness 和 longrun:readiness 纳入 round:refresh,刷新链路从 19 步扩展为 22 步。round:refresh --strict 中不使用 strict 失败退出,而是如实刷新当前状态:overallReady=false、readyForVideoAbPreflight=false、longrun.ready=false。round-refresh-summary.json 的 artifacts 新增 intakeReadiness、videoResourceReadiness、longRunReadiness,让完成度审计不再依赖旧的前置门禁 summary。round:refresh:smoke,要求 22 步顺序稳定,并断言 intake/video/longrun 三个前置门禁产物被刷新。docs/tihao-handoff-index.md 和 task:handoff-index:smoke,当前交接入口明确显示 round-refresh-summary.json 为 22 步全部 pass。node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\refresh-round-artifacts-smoke.js 通过。npm.cmd run round:refresh:smoke 通过,22 步顺序稳定。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 已刷新为 22 步;当前 intake-readiness.failureCount=9、video-resource-readiness.failureCount=1、long-run-readiness.failCount=6。npm.cmd run task:handoff-index:smoke 通过,交接入口已同步 22 步口径。proof-gap-closure.openCount=5,optimization-completion.readyForClaim=false,不得宣称提号率提升、客户效果达标或人工补号量下降。round:refresh 22 步全部 pass 只代表审计/索引/交接产物成功刷新,不代表 22 个业务门槛都通过。scripts/optimization-completion-audit.js 和 scripts/optimization-completion-smoke.js。optimization:completion、optimization:completion:smoke。complete=false、readyForClaim=false、proofGapOpenCount=5,并把 canClaim.tihaoRateImproved、canClaim.customerEffectAchieved、canClaim.manualSupplementReduced 全部保持为 false。acceptance,将完成度审计产物纳入 round:refresh,刷新链路从 18 步扩展为 19 步。evidence:index 新增 optimization-completion 类型:只有 complete=true、readyForClaim=true 且 proofGapOpenCount=0 时才可归为 real_evidence;当前 incomplete 时归为 not_business_proof。docs/tihao-handoff-index.md,把 outputs/optimization-completion-latest/optimization-completion-report.md 作为长期优化完成判断入口,并明确它本身不是业务证明。docs/business-proof-action-order.zh-CN.md 的长期完成判定,要求 optimization:completion 同时满足 complete=true、readyForClaim=true、proofGapOpenCount=0。round-deposition 的补证操作顺序守卫现在检查 optimization:completion 和 readyForClaim=true,避免后续只看 proof-gap:closure 就误判长期目标完成。latest-form:index 现在把 optimization-completion-report.md/summary.json 作为一等入口,summary 暴露 complete、readyForClaim、proofGapOpenCount、blockingReasonCount 和三个 canClaim=false 开关。real-proof-intake-bundle 现在在“打开顺序”中加入优化完成度审计报告,在 sourceState 暴露 optimizationCompletionComplete=false、optimizationCompletionReadyForClaim=false,并新增 optimization:completion 复验命令。real-proof-intake-bundle.complete 现在同时要求 proof-gap:closure.complete=true、plan-execution-status.complete=true、optimization-completion.complete=true、readyForClaim=true 和 proofOpenCount=0,避免真实证明缺口未关时误判长期目标完成。npm.cmd run optimization:completion:smoke 通过。npm.cmd run optimization:completion -- --output outputs\optimization-completion-latest 通过,输出 complete=false、readyForClaim=false、proofGapOpenCount=5、blockingReasonCount=10。npm.cmd run round:refresh -- --output-root outputs --strict 通过,19 步全部 pass;optimization-completion 已纳入刷新链路,round-deposition 通过项为 85、failCount=0。npm.cmd run evidence:index:smoke 通过,已识别 optimization-completion 类型。npm.cmd run optimization:status:smoke 通过,状态面板已识别 optimization-completion 稳定项。npm.cmd run round:refresh:smoke 通过,19 步顺序稳定。npm.cmd run round:deposition:smoke 通过,补证操作顺序守卫已覆盖 optimization:completion。npm.cmd run round:deposition -- --outputs outputs --output outputs\round-deposition-latest --strict 通过,passCount=85、failCount=0。npm.cmd run task:handoff-index:smoke 通过,交接入口已记录 optimization-completion.readyForClaim=false。npm.cmd run handoff:summary:smoke 通过,交接摘要仍保持 complete=false。npm.cmd run latest-form:index:smoke 通过,最新表单入口仍保持补证/收集材料边界。node --check scripts\latest-form-index.js、node --check scripts\real-proof-intake-bundle.js、node --check scripts\latest-form-index-smoke.js、node --check scripts\real-proof-intake-bundle-smoke.js 均通过。npm.cmd run proof-gap:intake-bundle:smoke 通过,新增完成度审计入口后仍为 complete=false、proofOpenCount=5、exportRowCount=32。npm.cmd run latest-form:index:smoke 通过,最新表单索引已校验 optimization-completion-report.md、readyForClaim=false、proofGapOpenCount>=1 和三个禁用宣称开关。npm.cmd run round:refresh -- --output-root outputs --strict 重新通过,19 步全部 pass;latest-form index、real-proof intake bundle 和 optimization-completion latest 产物已刷新。npm.cmd run round:refresh:smoke、npm.cmd run task:handoff-index:smoke、npm.cmd run hygiene:smoke、npm.cmd run round:deposition:smoke 均通过。npm.cmd run acceptance 在完成度审计和补证顺序守卫更新后通过;包内容门禁显示 entryCount=167,workspace install smoke 通过。proof-gap-closure.openCount=5,optimization-completion.readyForClaim=false,不得宣称提号率提升、客户效果达标或人工补号量下降。real-proof-intake-bundle、proof-gap-request、proof-gap-operator-pack、最新索引、执行总表和完成度审计都不是客户效果证明。proof-gap:intake-bundle,生成 outputs/real-proof-intake-bundle-latest/real-proof-intake-bundle.md/csv/summary.json。directCustomerProof=false、proofLevel=not_business_proof;总包通过只代表补证入口完整,不证明客户效果。round:refresh,刷新链路从 17 步扩展为 18 步,并在 evidence:index、latest-form:index 和 handoff:summary 中暴露入口。npm.cmd run proof-gap:intake-bundle:smoke 通过,proofOpenCount=5,exportRowCount=30。npm.cmd run latest-form:index:smoke 通过,最新表单索引可读取 real-proof-intake-bundle.md/csv/summary.json。npm.cmd run handoff:summary:smoke 通过,交接摘要可读取顶层真实验收材料收集总包入口。npm.cmd run round:refresh:smoke 通过,18 步顺序稳定,且 evidence index 已收录 real-proof-intake-bundle 类型。proofOpenCount=5,长期优化目标仍未完成。proof-gap-request-latest 作为一等入口纳入 latest-form:index,最新表单索引现在展示 proof-gap-request-report.md/csv/summary.json、unresolvedCount、rowCount 和证明边界。handoff:summary 顶层,并在 latestFormIndex 嵌套节点中同步展示;即使 latest-form 索引尚未刷新,handoff 也会回退到独立的 proof-gap-request-latest 产物路径。round:refresh:smoke,确认 18 步刷新后 latest-form 和 handoff 都能看到请求包入口。npm.cmd run latest-form:index:smoke 通过,请求包入口已进入最新表单索引。npm.cmd run handoff:summary:smoke 通过,请求包入口已进入交接摘要顶层和 latest-form 嵌套节点。npm.cmd run round:refresh:smoke 通过,18 步顺序稳定,且整轮交接仍为 passed=true。proofOpenCount/openCount 仍为 5 时,不得宣称提号率提升、客户效果达标或人工补号量下降。hygiene:smoke 默认扫描范围,除 docs、scripts、mcp/src、skills、fixtures 外,新增覆盖 package.json、install.js、bin、skill-package-manifest.json、.mcp.json、.claude-plugin 和 memory-templates。npm.cmd run hygiene:smoke 通过,默认扫描文件数从 154 扩展到 161,hitCount=0。npm.cmd run skill:refs:smoke 通过,技能引用文档仍无常见乱码。proofOpenCount/openCount=5,仍需真实历史 Brief、真实候选视频、真实 live/provider 和客户效果材料后才能进入完成判断。package:contents:smoke,基于 npm pack --dry-run --json 解析真实 npm 包文件清单。outputs/、output/、node_modules/、.git/、.codex-run/、.npm-cache、.claude/、.vscode/、dist/、tmp/、coverage/、.env、.npmrc、package-lock.json、日志、tgz 或 zip 打入 npm 包。package:contents:smoke 接入 acceptance,放在原有 npm pack --dry-run 前面,先机器断言,再保留 dry-run 清单给人工查看。npm.cmd run package:contents:smoke 通过,entryCount=163,必需文件 17 项全部存在。npm.cmd run hygiene:smoke 通过,默认扫描文件数扩展到 162,hitCount=0。docs/tihao-handoff-index.md,作为下一轮 AI、商务或投放接手长期优化任务时的第一入口。latest-form:index 和 handoff:summary 的 supportDocs,避免入口只存在于 docs/ 目录而没有出现在最新交接产物中。task:handoff-index:smoke,校验入口文档、README、最新表单索引、交接摘要和 acceptance 门禁都能看到该入口。docs/tihao-handoff-index.md 加入 npm 包内容门禁必需文件。proofOpenCount/openCount=5,仍不能宣称提号率提升、客户效果达标或人工补号量下降。docs/tihao-handoff-index.md 的复验顺序执行 intake:readiness、video:resource-readiness --strict、proof-gap:closure 和 round:refresh --strict。docs/tihao-handoff-index.md 的“最近一次复验结果”章节,方便下一轮 AI、商务和投放直接看到当前卡点。task:handoff-index:smoke,要求任务入口保留 overallReady=false、failureCount=9、readyForVideoAbPreflight=false、realCandidateRows=0、openCount=5 和“不能用 0 或示例值代替”的边界。npm.cmd run intake:readiness -- --data-pack outputs\data-intake-pack-latest --video-pack outputs\video-intake-pack-latest --output outputs\intake-readiness-latest 通过执行,结果为 overallReady=false、failureCount=9。npm.cmd run video:resource-readiness -- --input outputs\video-intake-pack-latest\video-resource-template.csv --output outputs\video-resource-readiness-latest --strict 按预期失败,结果为 readyForVideoAbPreflight=false、failureCount=1、realCandidateRows=0。npm.cmd run proof-gap:closure -- --output outputs\proof-gap-closure-latest 通过执行,结果为 complete=false、openCount=5、closedCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,18 步全部 pass。optimization:pipeline 未运行,因为缺真实 <本轮人工补号量> 和可通过 intake readiness 的真实材料;不能用 0、示例值或模板值替代。proof-gap-operator-pack 强化为可机器审计的执行件,summary 稳定输出 gapIds、fillFileCount、recheckCommandCount 和 ownerGroupCount。historical-dataset、video-real-candidate、video-ab-live-proof、live-provider-overnight-proof、manual-review-and-customer-effect。fillFileCount=3、recheckCommandCount=9、ownerGroupCount=3,每行同时暴露主填写文件和首个复验命令,方便商务、投放和技术按缺口派工。latest-form:index 和 handoff:summary 已透传操作包的 markdown、csv、summary、5 个 gapId、填写文件数、复验命令数和负责人组数。round-deposition 新增 4 个检查:proof-gap-operator-pack-summary、proof-gap-operator-pack-actionable、latest-form-index-proof-gap-operator-pack、handoff-proof-gap-operator-pack,本轮真实 passCount=101、failCount=0。docs/tihao-handoff-index.md 已补充操作包阅读入口、最近复验结果和可说/不可说边界,并由 task:handoff-index:smoke 守住关键字段。npm.cmd run proof-gap:operator-pack:smoke 通过,openCount=5、rowCount=5。npm.cmd run proof-gap:operator-pack -- --outputs outputs --output outputs\proof-gap-operator-pack-latest --strict 通过,真实输出已刷新。npm.cmd run latest-form:index:smoke 通过,最新表单索引可读取 proof-gap-operator-pack.md/csv/summary.json。npm.cmd run handoff:summary:smoke 通过,交接摘要可读取顶层和 latest-form 嵌套的操作包入口。npm.cmd run round:deposition:smoke 通过,passCount=101、failCount=0。npm.cmd run round:refresh:smoke 通过,22 步顺序稳定。npm.cmd run round:refresh -- --output-root outputs --strict 通过,真实 outputs 已刷新,round-deposition.passCount=101。proof-gap-closure.openCount=5,optimization-completion.readyForClaim=false,longrun:readiness.ready=false。proof-gap-operator-pack summary 中新增 evidenceRowCount、nextActionCount 和 missingProofRequirementCount,当前真实输出为 evidenceRowCount=5、nextActionCount=5。video-ab-live-proof 这类缺口把 proofContext.* 重复列出。latest-form:index、handoff:summary 和 round-deposition 已透传并审计 evidenceRowCount、nextActionCount,防止操作包退化成只有文件链接和命令清单。docs/tihao-handoff-index.md 已同步记录 5 条当前证据和 5 条下一步动作,task:handoff-index:smoke 会守住这些字段。node --check scripts\proof-gap-operator-pack.js、node --check scripts\latest-form-index.js、node --check scripts\generate-optimization-handoff.js、node --check scripts\round-deposition-audit.js 均通过。npm.cmd run proof-gap:operator-pack:smoke 通过,操作包报告/CSV 已包含“当前证据”和“下一步”列。npm.cmd run latest-form:index:smoke 通过,最新表单索引已透传 evidenceRowCount=5、nextActionCount=5。npm.cmd run handoff:summary:smoke 通过,交接摘要已透传操作包证据行和下一步动作数。npm.cmd run round:deposition:smoke 通过,每轮沉淀审计继续 passCount=101、failCount=0。optimization-completion.readyForClaim=false 时仍不得宣称提号率提升、客户效果达标或人工补号量下降。proof-gap-operator-pack 的当前证据和下一步动作透传进 real-proof-intake-bundle,summary 新增 operatorPackEvidenceRowCount=5、operatorPackNextActionCount=5、operatorPackMissingProofRequirementCount=6。real-proof-intake-bundle.md 的“证明缺口闭环”表新增“当前证据”和“下一步”列,CSV 同步新增 当前证据、下一步 两列,商务打开总包时可直接看到每个真实证明缺口当前卡点和补齐动作。latest-form:index 和 handoff:summary 已透传真实验收材料总包的操作包证据/下一步计数,round-deposition 已把这些字段作为观测项输出。task:handoff-index:smoke 已补充对 realProofIntakeBundle 顶层、latest-form 和 handoff 嵌套入口的字段校验。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果和可说/不可说边界。node --check scripts\real-proof-intake-bundle.js、node --check scripts\latest-form-index.js、node --check scripts\generate-optimization-handoff.js、node --check scripts\round-deposition-audit.js、node --check scripts\task-handoff-index-smoke.js 均通过。npm.cmd run proof-gap:intake-bundle:smoke 通过,真实验收材料总包输出 operatorPackEvidenceRowCount=5、operatorPackNextActionCount=5。npm.cmd run latest-form:index:smoke 通过,最新表单索引已展示真实验收材料总包的操作包证据/下一步计数。npm.cmd run handoff:summary:smoke 通过,交接摘要顶层和 latest-form 嵌套入口均可读取真实验收材料总包字段。npm.cmd run round:deposition:smoke 通过,round deposition 继续 passCount=101、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,任务交接入口已守住 operatorPackEvidenceRowCount=5、operatorPackNextActionCount=5。npm.cmd run acceptance 通过,发布前总门禁、包内容门禁、安全审计和任务交接入口均保持通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false,仍不得宣称提号率提升、客户效果达标或人工补号量下降。proof-gap-operator-pack 新增按负责人拆分的 by-owner 附件,当前输出 ownerArtifactCount=3。outputs/proof-gap-operator-pack-latest/by-owner/business.md/csv、outputs/proof-gap-operator-pack-latest/by-owner/business-media.md/csv、outputs/proof-gap-operator-pack-latest/by-owner/tech-ai.md/csv。gapIds、topPriority、actionCount、evidenceRowCount、nextActionCount,让商务、商务/投放、技术/AI 能直接打开自己的补证清单,不必在总表里手动筛选。latest-form:index、handoff:summary 和 round-deposition 已透传并审计 ownerArtifactCount=3 与三份 by-owner 文件路径,防止后续刷新丢失角色附件。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、接手角色分工、最近复验结果和可说/不可说边界,明确这些负责人附件仍只是补证派工材料。node --check scripts\latest-form-index.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run proof-gap:operator-pack:smoke 通过,操作包 smoke 已检查 by-owner 附件。npm.cmd run latest-form:index:smoke 通过,最新表单索引已透传 ownerArtifactCount=3。npm.cmd run handoff:summary:smoke 通过,交接摘要已透传顶层和 latest-form 嵌套的负责人附件。npm.cmd run round:deposition:smoke 通过,passCount=101、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,任务交接入口已守住负责人附件字段。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。proofGapOperatorPack.ownerArtifactCount=3、latestFormIndex.proofGapOperatorPackOwnerArtifactCount=3、handoff.proofGapOperatorPackOwnerArtifactCount=3。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。real-proof-intake-bundle、proof-gap-request、proof-gap-operator-pack、by-owner 附件、最新索引和执行总表仍都是协调/执行材料,不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。real-proof-intake-bundle 新增 operatorPackOwnerArtifactCount=3 和 operatorPackOwnerArtifacts,直接透传 proof-gap-operator-pack 的三份 by-owner 派工文件。evidenceRowCount 和 nextActionCount。负责人附件,因此当前真实输出 exportRowCount=37;商务只打开总包 CSV 时,也能看到 by-owner/business.csv、by-owner/business-media.csv、by-owner/tech-ai.csv。latest-form:index 和 handoff:summary 已透传真实总包内的 operatorPackOwnerArtifactCount=3 和三份附件路径。round-deposition 新增 real-proof-intake-bundle-operator-owner-artifacts 防回退检查,当前真实 passCount=102、failCount=0。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果和可说/不可说边界,明确这些负责人附件仍只是补证派工材料。node --check scripts\real-proof-intake-bundle.js 通过。node --check scripts\real-proof-intake-bundle-smoke.js 通过。node --check scripts\latest-form-index.js 通过。node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff.js 通过。node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\round-deposition-audit.js 通过。node --check scripts\round-deposition-smoke.js 通过。npm.cmd run proof-gap:intake-bundle:smoke 通过,真实验收材料总包输出 exportRowCount=37、operatorPackOwnerArtifactCount=3。npm.cmd run latest-form:index:smoke 通过,最新表单索引已展示真实总包的操作包负责人附件字段。npm.cmd run handoff:summary:smoke 通过,交接摘要顶层和 latest-form 嵌套入口均可读取真实总包负责人附件字段。npm.cmd run round:deposition:smoke 通过,passCount=102、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,任务交接入口已守住 operatorPackOwnerArtifactCount=3。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。real-proof-intake-bundle、by-owner 附件、最新索引、交接摘要和 22 步 refresh 仍都不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。business-execution-index 新增读取 proof-gap-operator-pack-summary.json,并把三份 by-owner 派工文件写成 3 行 操作包负责人附件。operatorPackOwnerArtifactCount=3、operatorPackOwnerArtifactRowCount=3 和 operatorPackOwnerArtifacts,当前真实输出 rowCount=27、proofOpenCount=5。outputs/proof-gap-operator-pack-latest/by-owner/business.md/csv、business-media.md/csv、tech-ai.md/csv,并保留 gapIds、evidenceRowCount、nextActionCount 和“不证明客户效果”边界。latest-form:index、handoff:summary 和 round-deposition 已透传并审计商务执行总表里的操作包负责人附件;round:refresh 顺序已调整为先刷新 proof-gap-operator-pack,再刷新 business-execution-index。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果、接手角色分工和可说/不可说边界,明确商务执行总表里的负责人附件仍只是补证派工材料。node --check scripts\business-execution-index.js、node --check scripts\business-execution-index-smoke.js 通过。node --check scripts\latest-form-index.js、node --check scripts\generate-optimization-handoff.js、node --check scripts\round-deposition-audit.js、node --check scripts\refresh-round-artifacts.js 通过。node --check scripts\generate-optimization-handoff-smoke.js、node --check scripts\round-deposition-smoke.js、node --check scripts\task-handoff-index-smoke.js、node --check scripts\refresh-round-artifacts-smoke.js 通过。npm.cmd run business-execution:index:smoke 通过,fixture 输出包含 3 行操作包负责人附件。npm.cmd run latest-form:index:smoke 通过,最新表单索引已展示商务执行总表的 operatorPackOwnerArtifactCount=3。npm.cmd run handoff:summary:smoke 通过,交接摘要已透传商务执行总表里的操作包负责人附件。npm.cmd run round:deposition:smoke 通过,passCount=104、failCount=0。npm.cmd run round:refresh:smoke 通过,22 步顺序已改为 proof-gap-operator-pack 先于 business-execution-index。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,任务交接入口已守住商务执行总表的 operatorPackOwnerArtifactCount=3。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。操作包负责人附件、真实验收材料总包、最新索引、交接摘要和 22 步 refresh 仍都不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。business-proof-progress 新增读取 proof-gap-operator-pack-summary.json 和 business-execution-index-summary.json,summary 透传 operatorPackOwnerArtifactCount=3 与三份 operatorPackOwnerArtifacts。business-proof-progress-report.md 新增 proof-gap 操作包负责人附件 区块,让商务查看进度表时也能直接定位 by-owner/business.md/csv、business-media.md/csv、tech-ai.md/csv。plan-execution-status 新增透传 operatorPackOwnerArtifactCount=3、operatorPackOwnerArtifacts、businessExecutionOperatorPackOwnerArtifactCount=3 和 businessExecutionOperatorPackOwnerArtifactRowCount=3。plan-execution-status.md 新增 proof-gap 操作包负责人附件 表,并在计划第 3、4 行证据中显示操作包负责人附件计数和商务执行总表附件行数。latest-form:index 和 handoff:summary 已把计划执行状态面板里的负责人附件字段继续透传到最新索引和交接摘要。round-deposition 新增 business-proof-progress-operator-owner-artifacts、plan-execution-status-operator-owner-artifacts 两个防回退检查,真实 outputs 当前 passCount=106、failCount=0。latest-form:index:smoke 和 handoff:summary:smoke 的 fixture 准备顺序已和 round:refresh 对齐,先刷新 plan-execution-status-latest 再生成 latest/handoff,避免单脚本 smoke 读到旧面板。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果和可说/不可说边界,明确这些字段仍只是执行/审计入口,不是业务证明。node --check scripts\business-proof-progress.js、node --check scripts\business-proof-progress-smoke.js 通过。node --check scripts\plan-execution-status.js、node --check scripts\plan-execution-status-smoke.js 通过。node --check scripts\latest-form-index.js、node --check scripts\latest-form-index-smoke.js 通过。node --check scripts\generate-optimization-handoff.js、node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\refresh-round-artifacts.js、node --check scripts\refresh-round-artifacts-smoke.js 通过。node --check scripts\round-deposition-audit.js、node --check scripts\round-deposition-smoke.js 通过。npm.cmd run business-proof:progress:smoke 通过,fixture 输出 operatorPackOwnerArtifactCount=3 且 complete=false。npm.cmd run plan:execution-status:smoke 通过,fixture 输出 rowCount=8、proofOpenCount=5、operatorPackOwnerArtifactCount=3。npm.cmd run latest-form:index:smoke 通过,最新表单索引已透传计划执行状态面板的 operatorPackOwnerArtifactCount=3 和 businessExecutionOperatorPackOwnerArtifactRowCount=3。npm.cmd run handoff:summary:smoke 通过,交接摘要顶层和 latest-form 嵌套入口均可读取计划执行状态面板负责人附件字段。npm.cmd run round:refresh:smoke 和 npm.cmd run round:deposition:smoke 通过,沉淀审计 passCount=106、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,任务交接入口仍记录 openCount=5、businessExecutionOperatorPackOwnerArtifactCount=3、readyForClaim=false。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。businessProofProgress.operatorPackOwnerArtifactCount=3、planExecutionStatus.operatorPackOwnerArtifactCount=3、latestFormIndex.planExecutionStatus.operatorPackOwnerArtifactCount=3、handoff.planExecutionStatus.operatorPackOwnerArtifactCount=3。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。business-proof-progress、plan-execution-status、商务执行总表、真实验收材料总包、最新索引、交接摘要和 22 步 refresh 仍都不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。generate-optimization-handoff 现在读取 business-proof-progress-summary.json,不再只在交接摘要里放补证进度表路径。businessProofProgress 新增 complete、counts、operatorPackOwnerArtifactCount=3、operatorPackOwnerArtifacts、businessExecutionOperatorPackOwnerArtifactRowCount=3 等字段。optimization-handoff-report.md 的“补证进度表”区块新增 pass/pending/fail/blocked 统计、负责人附件计数和三份 by-owner 文件表,便于下一轮 AI 只读交接摘要也能定位补证进度派工文件。handoff:summary:smoke 已先刷新 business-proof-progress-latest,再生成交接摘要,避免读取旧的进度表。task-handoff-index-smoke 新增读取真实 business-proof-progress-summary.json 和 plan-execution-status-summary.json,并校验 handoff/latest 中的负责人附件传播字段。round-deposition 新增 handoff-business-proof-progress-operator-owner-artifacts 防回退检查,真实 outputs 当前 passCount=107、failCount=0。docs/tihao-handoff-index.md 已同步当前结论、阅读顺序、最近复验结果和可说/不可说边界,明确交接摘要里的进度表负责人附件仍只是补证派工入口。node --check scripts\generate-optimization-handoff.js、node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\task-handoff-index-smoke.js 通过。node --check scripts\round-deposition-audit.js、node --check scripts\round-deposition-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过,交接摘要已透传 businessProofProgress.operatorPackOwnerArtifactCount=3。npm.cmd run round:deposition:smoke 通过,passCount=107、failCount=0。npm.cmd run task:handoff-index:smoke 通过,输出已记录 businessProofProgressOperatorPackOwnerArtifactCount=3、planExecutionStatusOperatorPackOwnerArtifactCount=3、planExecutionStatusBusinessExecutionOperatorPackOwnerArtifactRowCount=3。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。businessProofProgress、optimization-handoff、round-deposition 和 task-handoff-index 仍是协调/审计入口,不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。generate-optimization-handoff 现在把 business-proof-next-actions-summary.json 的 complete、actionCount=5、ownerGroupCount=3、ownerArtifactCount=3、sourceState.proofGapOpenCount=5 和前 5 个高优先级 topActions 写入交接摘要。optimization-handoff-report.md 的“下一步行动队列”区块现在展示 actionCount、proofGapOpenCount、intake/video/pipeline 状态和 top action 表,下一轮 AI 只读交接摘要也能看到首批补证动作。handoff:summary:smoke 会先刷新 business-proof-next-actions-latest,再校验 handoff 中的 step-03 历史数据补齐动作和 gap-video-ab-live-proof 视频 A/B live proof 动作。round-deposition 新增 handoff-business-proof-next-actions-top-actions 防回退检查,并把 handoff.businessProofNextActions.count/topActionCount/proofGapOpenCount 写入 observed 和报告;真实 outputs 当前 passCount=108、failCount=0。task-handoff-index-smoke 新增读取真实 business-proof-next-actions-summary.json,校验当前 handoff 和临时生成 handoff 都透传 actionCount=5、proofGapOpenCount=5 与 topActions。docs/tihao-handoff-index.md 已同步当前结论、最近复验结果和可说/不可说边界,明确下一步行动队列仍只是补证派工入口。node --check scripts\generate-optimization-handoff.js、node --check scripts\generate-optimization-handoff-smoke.js 通过。node --check scripts\round-deposition-audit.js、node --check scripts\round-deposition-smoke.js 通过。node --check scripts\task-handoff-index-smoke.js 通过。npm.cmd run handoff:summary:smoke 通过,交接摘要已透传 businessProofNextActions.actionCount=5 和 topActions。npm.cmd run round:deposition:smoke 通过,passCount=108、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,22 步全部 pass,真实 outputs 已刷新。npm.cmd run task:handoff-index:smoke 通过,输出已记录 businessProofNextActionCount=5、handoffBusinessProofNextActionCount=5。npm.cmd run round:refresh:smoke 通过,临时刷新链路的 roundPassCount=108。npm.cmd run hygiene:smoke 通过,scannedFiles=166、hitCount=0。npm.cmd run acceptance 通过,包内容门禁、任务交接入口 smoke、安全审计和 workspace install smoke 均保持通过。proof-gap-closure.openCount=5、optimization-completion.readyForClaim=false、longrun:readiness.ready=false。businessProofNextActions、optimization-handoff、round-deposition、task-handoff-index 和 22 步 refresh 仍是协调/审计入口,不是业务证明;不得宣称提号率提升、客户效果达标或人工补号量下降。
evidence:index 的 historical-dataset 分类已复用完整历史证明门槛;historical-dataset-audit.json 只写 acceptance.readyForCustomerEffectProof=true、readyForLongRun=true 或 briefCount>=5 不再能进入 real_evidence。
business-proof-progress 的第 7 步“历史数据审计”已改为输出 missing=<count>,薄历史审计只能保持 blocked_by_external_data,不能因为有审计文件或顶层 ready 字段而误判为 pass。
历史证据现在必须同时具备完整 acceptance 子门槛、5 条以上可审计 items、客户选中/拒绝记录、拒绝原因覆盖、人工最终名单覆盖和历史人工补号量基线覆盖,才能支撑客户效果证明。
business-proof:progress:smoke 新增薄历史审计 fixture:历史导入因文件存在为 pass,但历史审计继续 blocked,锁住“有文件不等于有业务证明”的边界。
node --check scripts\evidence-index.jsnode --check scripts\business-proof-progress.jsnode --check scripts\evidence-index-smoke.jsnode --check scripts\business-proof-progress-smoke.jsnpm.cmd run evidence:index:smokenpm.cmd run business-proof:progress:smokenpm.cmd run round:refresh -- --output-root outputs --strictnpm.cmd run hygiene:smokenpm.cmd run task:handoff-index:smokenpm.cmd run acceptanceproof-gap-closure.complete=false、proof-gap-closure.openCount=3、proof-gap-closure.closedCount=2。optimization-completion 仍是 complete=false、readyForClaim=false、proofGapOpenCount=3,且 canClaim.*=false。business-proof:next-actions 现在读取最新 optimization-completion-summary.json,根据 completion 对 optimization-pipeline 的阻塞原因判断旧 pipeline 是否 stale。optimizationPipeline.stale=true 或 completion 显示 pipeline 不能作为当前证明时,旧 optimization-pipeline-summary.json.nextActions 不再进入当前业务派工队列,只在 sourceState 中保留原始数量、压制数量和 stale 原因。businessProofNextActions.actionCount=3,只保留 step-03 真实历史 Brief、step-12 人工复核标注和 gap-video-ab-live-proof 真实视频 A/B 验收;旧 pipeline 的 3 条 nextActions 已全部被压制。latest-form:index 与 handoff:summary 已透传 pipelineStale=true、pipelineRawNextActionCount=3、pipelineSuppressedNextActionCount=3 和 pipelineStaleReason,下一轮接手时能看到旧 pipeline 为什么不能继续派工。round-deposition 新增 business-proof-next-actions-stale-pipeline-suppression 防回退检查,避免 stale pipeline 动作再次混入当前行动队列。latest-form:index:smoke 与 handoff:summary:smoke 已新增直接断言,校验 pipelineStale=true、pipelineNextActionCount=0、pipelineRawNextActionCount>=1、pipelineSuppressedNextActionCount=raw、stale reason 和缺失证明要求,并确认 topActions 不含 optimization-pipeline 来源。optimization-handoff-summary.json 新增顶层 pipelineStaleSummary,把 pipelineStale、pipelineReadyForClaim、raw/suppressed/current pipeline 动作数量、缺失证明要求数量和不可派工边界直接放到交接摘要顶层,避免只扫顶层 JSON 的接手方漏读 businessProofNextActions.sourceState。node --check scripts\business-proof-next-actions.jsnode --check scripts\business-proof-next-actions-missing-proof-smoke.jsnode --check scripts\latest-form-index.jsnode --check scripts\generate-optimization-handoff.jsnode --check scripts\round-deposition-audit.jsnode --check scripts\task-handoff-index-smoke.jsnpm.cmd run business-proof:next-actions:smokenpm.cmd run business-proof:next-actions:missing-proof:smokenpm.cmd run round:deposition:smoke,当前 passCount=128、failCount=0。npm.cmd run task:handoff-index:smokenpm.cmd run round:refresh -- --output-root outputs --strictnpm.cmd run latest-form:index:smokenpm.cmd run handoff:summary:smokenode --check scripts\generate-optimization-handoff.jsnode --check scripts\generate-optimization-handoff-smoke.jsproof-gap-closure.complete=false、proof-gap-closure.openCount=3、proof-gap-closure.closedCount=2。optimization-completion 仍是 complete=false、readyForClaim=false、proofGapOpenCount=3,且 canClaim.*=false。proof-gap:closure summary 新增 businessOpenCount、businessClosedCount、precheckRowCount、precheckOpenCount、precheckClosedCount 和 countSemantics,明确 openCount/closedCount 只是业务证明缺口兼容别名,不包含 intake-readiness 预审行。proof-gap-closure-report.md 现在同时展示业务证明缺口计数和预审行计数,避免看到 rows.length=6 与 openCount=3 时误以为计数不一致。handoff:summary 已透传 proof-gap closure 的 business/precheck 计数字段,optimization-handoff-report.md 也会显示 businessOpenCount、businessClosedCount、precheckOpenCount 和 countSemantics.openCount。latest-form:index 新增 proofGapClosure 区块,索引页可直接定位 proof-gap-closure-summary.json/report.md,并显示 openCount/businessOpenCount/precheckOpenCount/totalRows。proof-gap:closure:smoke、handoff:summary:smoke、latest-form:index:smoke 均新增断言,防止后续把 intake 预审误算进业务 openCount,或在交接层丢失计数语义。node --check scripts\proof-gap-closure-audit.jsnode --check scripts\proof-gap-closure-smoke.jsnode --check scripts\generate-optimization-handoff.jsnode --check scripts\generate-optimization-handoff-smoke.jsnode --check scripts\latest-form-index.jsnode --check scripts\latest-form-index-smoke.jsnpm.cmd run proof-gap:closure:smokenpm.cmd run handoff:summary:smokenpm.cmd run latest-form:index:smokenpm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,round-deposition.passCount=129、failCount=0。npm.cmd run hygiene:smoke,hitCount=0。npm.cmd run task:handoff-index:smokenpm.cmd run acceptancebusinessOpenCount/openCount=3 判断剩余真实业务证明缺口;precheckOpenCount 只表示 intake 预审是否仍有未就绪行。round-deposition 中新增 proof-gap-closure-count-semantics 防回退守卫,要求 proof-gap-closure-summary.json 的 openCount/businessOpenCount 只统计业务证明缺口,precheckOpenCount/precheckRowCount 单独统计 intake 预审行。round-deposition observed/report 已新增 standalone 与 handoff 两套计数字段:businessOpenCount、businessClosedCount、businessGapCount、precheckOpenCount 和 countSemantics.openCount,避免只看沉淀报告或交接摘要时误读计数口径。handoff-proof-gap-closure 校验也同步检查 business/precheck 计数和 countSemantics 是否与 standalone closure 一致,防止 handoff 丢字段或旧口径回流。round-deposition:smoke fixture 与断言已补齐,覆盖新守卫、observed 字段和报告展示字段。node --check scripts\round-deposition-audit.jsnode --check scripts\round-deposition-smoke.jsnpm.cmd run round:deposition:smoke,当前 passCount=129、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict,28 步全部 pass,最新真实 round-deposition.passCount=129、failCount=0。proof-gap-closure.complete=false、businessOpenCount/openCount=3、precheckOpenCount=1、optimization-completion.readyForClaim=false。business-proof:next-actions summary 顶层新增 actionCount、ownerGroupCount、ownerRepairArtifactCount 和 topActions;负责人附件写入后同步补 ownerArtifactCount,避免下游只能从 actions.length、ownerGroups.length 或文件存在性反推行动队列状态。latest-form:index 和 handoff:summary 已优先读取 next-actions 顶层 actionCount/topActions/ownerGroupCount/ownerArtifactCount,没有顶层字段时才兼容回退到旧 actions 数组。round-deposition 的 business-proof-next-actions-open 守卫已收紧:要求顶层 actionCount 与 actions.length 一致,topActions 至少覆盖前 5 个高优先级动作,并且每个 top action 带 owner、title、command 和 acceptance。business-proof:next-actions:smoke、business-proof:next-actions:missing-proof:smoke 和 round:deposition:smoke 已补断言,防止后续 summary 退化为只剩 actions 数组。node --check scripts\business-proof-next-actions.jsnode --check scripts\latest-form-index.jsnode --check scripts\generate-optimization-handoff.jsnode --check scripts\round-deposition-audit.jsnode --check scripts\round-deposition-smoke.jsnpm.cmd run business-proof:next-actions:smokenpm.cmd run business-proof:next-actions:missing-proof:smokenpm.cmd run latest-form:index:smokenpm.cmd run handoff:summary:smokenpm.cmd run round:deposition:smoke,当前 passCount=129、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,28 步全部 pass,最新真实 round-deposition.counts.pass=129、counts.fail=0。npm.cmd run hygiene:smoke 通过,scannedFiles=175、hitCount=0。npm.cmd run task:handoff-index:smoke 通过,交接入口仍记录 openCount=3、businessProofNextActionCount=3、readyForClaim=false。npm.cmd run acceptance 通过,包级 smoke、任务交接入口 smoke、安全审计、包内容门禁和 workspace install smoke 均保持通过。actionCount=3、topActions.length=3、ownerGroupCount=2、ownerArtifactCount=2,对应真实历史 Brief、人工复核标注和真实视频 A/B 验收。proof-gap-closure.complete=false、businessOpenCount/openCount=3、optimization-completion.readyForClaim=false,不能宣称提号率提升、客户效果达标或人工补号量下降。acceptance:video-ab 现在会在缺运行凭证、company、VOC social provider 或视频分析 provider 时先输出 video-hit-rate-preflight-summary.json 和 video-hit-rate-preflight-report.md,退出码仍为失败,但不再把缺凭证场景表现为一段 stack trace。materialType=video_ab_runtime_preflight、proofLevel=not_business_proof、canCloseProofGap=false、proofContext.generatedBy=acceptance:video-ab-preflight,并只记录 token 是否存在,不写入 token 明文。evidence:index 已新增 video-ab-runtime-preflight 分类;即使 readyForVideoAb=true,该类型也固定为 not_business_proof,必须生成 live video-hit-rate-summary.json 才能进入 proof-gap closure。round-deposition 新增 evidence-index-video-ab-runtime-preflight-boundary 守卫,要求证据台账中的 video A/B runtime preflight 不能替代 acceptance:video-ab live proof。node --check scripts\video-hit-rate-audit.jsnode --check scripts\video-hit-rate-audit-smoke.jsnpm.cmd run acceptance:video-ab:smokenpm.cmd run acceptance:video-ab 会生成 outputs\video-hit-rate-preflight-latest\video-hit-rate-preflight-summary.json,并以失败退出;本轮用退出码 2 作为预期失败验证通过。node --check scripts\evidence-index.jsnode --check scripts\evidence-index-smoke.jsnpm.cmd run evidence:index:smoke,当前 fixture total=43、not_business_proof=18。node --check scripts\round-deposition-audit.jsnode --check scripts\round-deposition-smoke.jsnpm.cmd run round:deposition:smoke,当前 passCount=130、failCount=0。npm.cmd run round:refresh -- --output-root outputs --strict 通过,28 步全部 pass,最新真实 round-deposition.passCount=130、failCount=0。outputs/video-hit-rate-preflight-latest/video-hit-rate-preflight-summary.json 不能关闭 video-ab-live-proof,也不能证明视频分析提升提号结果。当前仍是 proof-gap-closure.complete=false、businessOpenCount/openCount=3、optimization-completion.readyForClaim=false,不能宣称提号率提升、客户效果达标或人工补号量下降。
real-gap:materials 三缺口材料审计脚本,统一读取 DHA PoC 原始工作簿、local-seed-to-intake-worklist、真实视频资源 readiness、acceptance:video-ab preflight、经验逐字稿索引和最新 proof-gap:closure。real-gap:materials:smoke 并纳入 npm run acceptance,固定断言三个缺口都能找到项目材料,同时 canCloseNow=false,防止把候选名单、逐字稿经验、preflight 或 readiness 误升格为业务证明。outputs/real-gap-material-audit-latest/,当前 gapCount=3、materialFoundCount=3、openGapCount=3、canCloseProofGap=false。briefCount=1;video A/B 有真实候选视频资源和 15 条候选视频 note 线索但缺 live proofContext;客户效果有 12 行人工复核草稿和经验规则但缺真实客户选择、反馈原因、本轮人工补号量和通过的 history audit。package.json、package-lock.json、.claude-plugin/plugin.json、skill-package-manifest.json 和 MCP server 版本同步到 1.0.1,准备作为 1.0 后的补丁发布。docs/release-notes.md 与 docs/tihao-handoff-index.md 已补 1.0.1 交接说明,要求后续先读三缺口材料审计再继续补证。npm.cmd run real-gap:materials:smokenpm.cmd run real-gap:materialsnpm.cmd run acceptancenpm.cmd publish --dry-run --access public --registry https://registry.npmjs.org/npm.cmd publish --access public --registry https://registry.npmjs.org/,返回 + @vocmarket/tihao-sop@1.0.1npm.cmd view @vocmarket/tihao-sop@1.0.1 version --registry https://registry.npmjs.org/,返回 1.0.1npm.cmd view @vocmarket/tihao-sop dist-tags.latest version --registry https://registry.npmjs.org/,返回 latest=1.0.1npx.cmd --yes @vocmarket/tihao-sop@latest workspace --smokeproof-gap-closure.complete=false、businessOpenCount/openCount=3、optimization-completion.readyForClaim=false。