diff --git a/AGENTS.md b/AGENTS.md index 7dd59404..cf6f3c45 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -33,9 +33,9 @@ ## 本地Git:用户已授权的开发方式 -- 1.12候选包含兼容Chat模型中心/池与已验证格式导入、只读巡检、来源复核项目记忆、Task检查点、本地Skills和受控stdio MCP。MCP未知副作用需核对原输入/工具账本后显式续接,无报告不补造结果,变化程序仍可停用。最终源码/发行/正式部署见docs/QA-1.12.md,真实模型工程按用户选择单独待验。 +- 1.12发行包含兼容Chat模型中心/池与已验证格式导入、只读巡检、来源复核项目记忆、Task检查点、本地Skills和受控stdio MCP。MCP未知副作用需核对原输入/工具账本后显式续接,无报告不补造结果,变化程序仍可停用。最终源码/发行/正式部署见docs/QA-1.12.md,真实模型工程按用户选择单独待验。 -- 本仓库已启用本地Git,main为当前开发分支,v1.0.0-baseline为已验证基线。 +- 本仓库已启用本地Git,v1.0.0-baseline为已验证基线;各切片使用具体开发分支,1.12交付位于feat/model-center-1.12。 - 用户授权后续按可审查小步本地提交。每个独立实现/修复/规划改动通过相关检查后,检查diff并提交,报告commit与结果;只读且无变化时不做空提交。 - 常规后续提交只暂存本次修改范围;保留其他人/用户的已有改动。 - 实验使用具体任务分支/worktree,合并前验证;不要用破坏性reset/clean丢弃工作。 diff --git a/README.md b/README.md index a71a9c83..e634c654 100644 --- a/README.md +++ b/README.md @@ -18,7 +18,7 @@ Agent Workbench 1.12.0 将 Claude Code 与 Cursor 的机制研究整合为独立 ## 后续产品与能力建设 -1.12候选包含模型中心/池路由、[项目记忆](docs/PROJECT-MEMORY.md)、[任务恢复检查点](docs/TASK-CHECKPOINTS.md)、[Skills](docs/SKILLS.md)和[项目MCP](docs/MCP.md)。记忆只在来源复核、脱敏且请求预算允许时使用;恢复检查点绑定完整要求和原结果,核对后显式续接同一任务。桌面壳、手机远程配对、多worker、更多模型协议及多模态按后续独立切片实现。 +1.12包含模型中心/池路由、[项目记忆](docs/PROJECT-MEMORY.md)、[任务恢复检查点](docs/TASK-CHECKPOINTS.md)、[Skills](docs/SKILLS.md)和[项目MCP](docs/MCP.md)。记忆只在来源复核、脱敏且请求预算允许时使用;恢复检查点绑定完整要求和原结果,核对后显式续接同一任务。桌面壳、手机远程配对、多worker、更多模型协议及多模态按后续独立切片实现。 当前Git项目可以先预览已提交版本,再创建独立目录和分支;来源已有暂存、未提交及未跟踪文件保留在原项目。子工作区有自己的项目、会话和实际执行目录,创建中断后显式核对。模型准备Git交付预览后停止请求,确认这份预览后由内核完成提交和报告。具体范围见[独立工作区](docs/WORKSPACES.md)及[1.6验收](docs/QA-1.6.md)。 diff --git a/docs/CAPABILITIES.md b/docs/CAPABILITIES.md index 6c226df2..51bc4cd6 100644 --- a/docs/CAPABILITIES.md +++ b/docs/CAPABILITIES.md @@ -4,9 +4,9 @@ 总体方案见 [PRODUCT-PLAN.md](PRODUCT-PLAN.md),研究问题与来源见 [RESEARCH-ROADMAP.md](RESEARCH-ROADMAP.md)。 -下一阶段[1.12执行方案](PLAN-1.12.md)按连接注册/专业界面、模型池、配置导入、运行巡检四个切片推进;兼容Chat协议的池路由已进入源码验证,跨协议、多模态及未知配置格式仍按各自边界实现与验收。 +[1.12执行方案](PLAN-1.12.md)的连接注册/专业界面、模型池、已验证格式导入、运行巡检及后续记忆、恢复、Skills/MCP切片已随1.12.0正式部署;独立源码357/357、完整界面150组及保留状态升级通过。跨协议、多模态及未知配置格式仍按各自边界实现与验收。 -2026-10-30源码进度:fb58a41已实现多连接、兼容Chat协议池路由、已确认格式导入与只读巡检;仍未作为新不可变发行部署。项目记忆管理f7292a9支持跨会话查看、来源/工程指纹、到期/归档与不完整扫描降级,7项专项和全量312/312通过。当前源码已实现有界模型上下文接入、脱敏及消费Task/Run原快照,新增10项专项与桌面/390px本地HTTP流程通过,最终全量322/322、199份输入和TAP已封存。真实模型池任务和WorkBuddy未知schema继续单独验收。 +2026-10-30交付进度:fb58a41实现多连接、兼容Chat协议池路由、已确认格式导入与只读巡检;1.12最终实现提交3f6797b,已由不可变发行20261030124454517部署至正式4318并保留原PID19084/Provider。项目记忆管理f7292a9支持跨会话查看、来源/工程指纹、到期/归档与不完整扫描降级,其阶段7项专项和全量312/312通过;有界模型上下文、脱敏及消费Task/Run原快照阶段新增10项专项与桌面/390px本地HTTP流程通过,阶段全量322/322、199份输入和TAP已封存。最终统一验收见[QA-1.12](QA-1.12.md),真实模型池任务和WorkBuddy未知schema继续单独验收。 ## 1. 能力的完成定义 @@ -16,10 +16,10 @@ ## 2. 能力矩阵 -### 1.12 完整候选(发行与部署见QA-1.12) +### 1.12 完整发行与正式升级(见QA-1.12) - C05:项目所属记忆、来源核对/过期/归档、有界脱敏模型上下文和原发送快照已通过17项专项、桌面/390px和322项全量,见[项目记忆](PROJECT-MEMORY.md)。 -- C04/C07/C11:新增可核验Task恢复包,保存完整要求、原工具/计划/证明及未知/待审查项;显式续接保留同Task和已完成结果。12项专项和桌面/390px三组通过,最终回归另行封存,见[任务检查点](TASK-CHECKPOINTS.md)。 +- C04/C07/C11:新增可核验Task恢复包,保存完整要求、原工具/计划/证明及未知/待审查项;显式续接保留同Task和已完成结果。12项专项和桌面/390px三组通过,已纳入1.12最终357项独立源码回归与正式升级,见[任务检查点](TASK-CHECKPOINTS.md)。 - C06/C07:项目所属[Skills](SKILLS.md)按版本启停/目录/读取,受控[stdio MCP](MCP.md)按实际schema、冻结请求目录与逐次审批调用;未知副作用需指纹核对后显式续接,宿主中断无报告也能查看原输入,不重放操作。 - C14/C15/C23:模型中心提供兼容Chat协议的多连接、轮询/权重、Run粘连、并发租约、故障冷却和请求账本;只导入已验证CCSwitch/工作台schema,凭据仅当前进程内存。运行中心只读检查不发送模型请求。 - 最终独立源码、全量界面、便携归档与正式升级见[1.12验收](QA-1.12.md)。新协议、多worker、远程MCP、桌面/手机配对、多模态和真实模型池任务继续独立开发与验收。 diff --git a/docs/MCP.md b/docs/MCP.md index 0b4748c8..31060be7 100644 --- a/docs/MCP.md +++ b/docs/MCP.md @@ -1,6 +1,6 @@ # 项目所属 MCP 工具 -1.12候选版可以按项目登记本地 stdio MCP 程序,探测真实工具目录,再让模型在明确审批后调用选定工具。探测通过、外部工具返回和工程交付分别判定。发行与部署状态见[1.12验收](QA-1.12.md)。 +1.12可以按项目登记本地 stdio MCP 程序,探测真实工具目录,再让模型在明确审批后调用选定工具。探测通过、外部工具返回和工程交付分别判定。发行与部署状态见[1.12验收](QA-1.12.md)。 ## 使用流程 diff --git a/docs/PLAN-1.12.md b/docs/PLAN-1.12.md index 22ec784a..05d8a951 100644 --- a/docs/PLAN-1.12.md +++ b/docs/PLAN-1.12.md @@ -1,6 +1,6 @@ # 1.12 专业工作台与模型池执行方案 -日期:2026-10-30。本文保留1.12的执行契约和实际进度;起点为1.11.0/PID19084和已封存的298项源码、126组界面及全部历史数据。当前进入1.12完整候选/独立发行验收,最终部署以[QA-1.12](QA-1.12.md)为准;真实模型续接仍按用户选择单独待验。 +日期:2026-10-30。本文保留1.12的执行契约和实际进度;起点为1.11.0/PID19084和已封存的298项源码、126组界面及全部历史数据。1.12完整发行与保留状态升级已完成,最终范围见[QA-1.12](QA-1.12.md);真实模型续接仍按用户选择单独待验。 ## 交付目标与顺序 @@ -12,15 +12,18 @@ | 1.12-B:模型池与故障切换 | 轮询/权重、任务内粘连、健康冷却、并发租约、排队、预算与逐次调用账本 | 实际HTTP故障样本覆盖429/503/401/超时/停止/部分返回;既有工具与审批无重放;归属、用量和选择原因可核对 | | 1.12-C:配置发现与导入 | WorkBuddy、CCSwitch等已验证格式的本地配置发现、导入差异和关闭同步 | 固定版本/配置schema及自有夹具先通过;实际安装只做授权范围的验证;无法转成模型API的登录态标明适用的引擎方式 | | 1.12-D:运行巡检与交付复验 | 宿主/依赖/数据/模型池健康页,故障导出、已知问题和修复复验 | 本地巡检与付费模型探针分开;无凭据时仍完成本地检查;状态不是固定绿灯;新包与原始记录可复核 | -| 后续独立发行 | 持久项目记忆、Skills/MCP/插件、更多模型协议与多模态、桌面/移动、多智能体、自我迭代 | 逐项接入已有Task/Run、权限、取消、工件和真实工程验收;不以占位入口作为完成 | +| 1.12-E:项目记忆 | 跨Task事实、来源与源码失效、有界模型上下文、原发送快照 | 来源/预算/脱敏边界、实际本地HTTP、桌面/390px与完整候选核对 | +| 1.12-F:恢复检查点 | 全部要求、原工具/计划/证明,核对后同Task新Run续接 | 真实进程提交前后中断、原工件损坏与不重放,代码/要求变化门控 | +| 1.12-G/H:Skills与MCP | 项目登记/修订/启停,Skills按需读取,本地stdio MCP实际探测/审批/调用 | 冻结目录与schema、进程归属、未知结果门控/人工核对、宿主中断无报告恢复 | +| 后续独立发行 | 隔离worker、更多模型协议与多模态、远程插件、桌面/手机、自我迭代评测 | 逐项接入已有Task/Run、权限、取消、工件和真实工程验收;不以占位入口作为完成 | A–D分别提交和验收。A先建立注册与归属,B依赖A,C使用A的连接契约,D贯穿每一切片;每次正式升级继续使用不可变发行目录和全量数据核对。新的真实模型验收在连接与用户安排就绪后执行。 -2026-10-30开发状态:A–D首个切片已本地提交fb58a41,支持兼容Chat协议连接注册、内存凭据、轮询/权重与故障切换、已验证CCSwitch/工作台JSON导入及只读运行巡检。WorkBuddy schema、更多协议、真实模型与正式发行仍待单独验收。 +2026-10-30交付状态:A–D首个切片提交fb58a41;记忆、检查点、Skills和MCP后续分段实现,1.12最终代码提交3f6797b。兼容Chat协议连接注册/池路由、内存凭据、已验证格式导入及巡检均随1.12正式升级。WorkBuddy schema、更多协议及真实模型工程继续单独验收。 项目记忆管理提交f7292a9,完成项目隔离、来源SHA256/工程指纹、显式到期/归档和扫描不完整时的unverified状态;管理专项7/7、桌面/390px和固定环境全量312/312通过。后续源码已接入模型请求:每轮复核、凭据脱敏、最多8条/12000字节、目标/代码优先和原发送快照封存;新增10项专项与桌面/390px本地HTTP流程通过,完整回归322/322通过、199份冻结输入和原TAP已封存。记忆不进入通用执行快照;源码核对不能证明用户记忆内容的业务结论正确,详见[项目记忆契约](PROJECT-MEMORY.md)。 -后续[任务恢复检查点](TASK-CHECKPOINTS.md)源码已实现保存完整要求/原工具工件/计划与证明、复核当前源码和Git/工作区、显式同Task续接。12项专项含真实进程提交前后退出及桌面/390px三组通过,最终源码/构建334/334回归及204份输入已独立封存;新包与真实模型长任务收益尚未验收。 +后续[任务恢复检查点](TASK-CHECKPOINTS.md)已实现保存完整要求/原工具工件/计划与证明、复核当前源码和Git/工作区、显式同Task续接。12项专项含真实进程提交前后退出及桌面/390px三组通过,阶段源码/构建334/334回归及204份输入已独立封存;新包已纳入1.12最终357项源码回归、便携运行及保留状态正式升级,真实模型长任务收益仍单独待验。 本地[Skills](SKILLS.md)已实现项目登记、来源SHA256、默认停用、显式启停/新修订、每轮目录与按需读取工件;10项专项和升级2项、桌面/390px四组通过。[项目MCP](MCP.md)已实现受控stdio登记/实际探测/启停、冻结schema、逐次审批、Task/Run原输入/报告和未知副作用门控;20项专项、6组管理和2组真实中断恢复界面通过。附带脚本不自动加载执行,远程MCP/自动安装仍待开发。 @@ -132,6 +135,6 @@ REA研究、Purge策略对照与外部引擎采用同一追溯要求:具体工 ## 下一次开发的明确起点 -连接注册/池路由、项目记忆管理/上下文、长任务恢复检查点和本地Skills/stdio MCP已分别通过本地专项。先收成1.12不可变候选,完成全量UI、独立源码/便携与保留状态升级,再推进隔离worker和桌面/移动宿主;两个worker必须绑定各自worktree和预算,父任务只归集实际结果与可审查改动。旧Provider内存连接、全部历史证据和正式4318在新候选验收前继续按现有方式运行。 +连接注册/池路由、项目记忆管理/上下文、长任务恢复检查点和本地Skills/stdio MCP已随1.12不可变发行20261030124454517交付。独立源码357/357、完整界面150组、最终源码/便携及保留状态升级均通过;正式4318保留原PID19084、Provider和全部历史证据。下一独立阶段按产品计划推进隔离worker、受控外部引擎及桌面/移动宿主;两个worker必须绑定各自worktree和预算,父任务只归集实际结果与可审查改动,真实模型工程继续按用户选择暂缓。 每个切片提交均包含最终行为说明、适当检查和真实限制。A–D最终发行还须独立源码/便携、数据迁移/升级及界面验证;真实模型工程样本的失败如实保留,不以通过数量替代工程交付能力。 diff --git a/docs/PRODUCT-PLAN.md b/docs/PRODUCT-PLAN.md index d34a9a62..6850f791 100644 --- a/docs/PRODUCT-PLAN.md +++ b/docs/PRODUCT-PLAN.md @@ -150,4 +150,12 @@ Purge的包声明Apache-2.0,另有商业许可联系说明;Harness声明MIT 4. 跨Task项目事实与来源、Codex/DeepSeek受控工具profile和Purge同模型/同题/同预算对照继续保留为后续核心切片。技术机制分别落入模块和契约检查,不将连接通过或提示名称当工程能力。 5. Electron桌面端、手机PWA及配对网关按M5复用同一执行宿主,单独验收安装、连接、审批去重和设备撤销。手机端不能直接使用电脑的127.0.0.1;实际设备连接与390px桌面模拟分别记录。 +2026-10-30接续:1.12模型中心/池、已验证配置导入和巡检、项目记忆/有界上下文、Task检查点、Skills与受控stdio MCP已进入产品实现并本地提交;最终发行验收与正式升级见[QA-1.12](QA-1.12.md)。后续按以下顺序独立开发,避免把未验收能力一起接入执行链路: + +1. 隔离worker:每个worker绑定独立Task/Run、worktree、父目标、模型选择与预算;父任务归集原证据并审查合并。先完成两个无重叠任务、重叠冲突拒绝、父停止传播和宿主中断不重放,再扩展角色与调度。 +2. 受控外部引擎/策略对照:从固定版本/profile开始真实工程样本;同题/模型/预算比较原Harness与Purge策略,保存失败和人工介入。连接握手和工具能力、业务任务完成分别核验。 +3. Windows桌面壳:复用已有宿主、模型中心、审查和工件;先验证窗口关闭/后台任务、重开、单实例、安装与保留数据升级,再扩到托盘通知及操作系统能力。 +4. 手机配对:设备身份和可撤销授权、同一审批去重、断线游标补发;先开发配对网关,再用真实手机完成同Task的观察、停止和审查。390px继续作为布局检查。 +5. 多协议/多模态与迭代评测:按每家真实协议分别适配图像/语音与缓存;开发者、审查者和评测者可使用不同模型,统一核对实际产物和用量。自我迭代先在隔离分支生成修复和报告,达到相同发行门槛后升级。 + 这些切片优先复用已验证的文件范围、基线备份、UTF-8、取消与诊断能力。研究结论每次至少绑定一个实现模块、一个契约检查和一个用户场景,按实际失败分类持续调整顺序。 diff --git a/docs/PROJECT-MEMORY.md b/docs/PROJECT-MEMORY.md index 9155a333..baf6a002 100644 --- a/docs/PROJECT-MEMORY.md +++ b/docs/PROJECT-MEMORY.md @@ -1,6 +1,6 @@ # 项目记忆与请求边界 -2026-10-30源码切片,正式4318仍为已验收的1.11发行。项目记忆管理提交f7292a9;上下文接入及最终验证以本轮记录为准。 +2026-10-30。1.12包含项目记忆管理及有界模型上下文;管理提交f7292a9,上下文提交af0a42b。完整发行和正式部署分别见[1.12验收](QA-1.12.md)。 记忆用于保存用户确认的项目约束、决策和事实。它属于项目数据,来源仍匹配只能说明依据版本未变,不能证明记忆内容正确、任务已完成,或授予额外权限。 diff --git a/docs/QA-1.12.md b/docs/QA-1.12.md index fbae491a..7972c6d1 100644 --- a/docs/QA-1.12.md +++ b/docs/QA-1.12.md @@ -1,6 +1,6 @@ # 1.12 模型中心与可扩展代理验收 -日期:2026-10-30。当前状态:候选验收中,正式4318仍保留原1.11进程/Provider和历史数据。通过完整候选检查后才按既有流程升级;本文随后登记原始结果与部署身份。 +日期:2026-10-30。最终不可变发行`20261030124454517`已部署到http://127.0.0.1:4318,版本1.12.0、原PID19084。完整源码、界面、便携、归档、正式升级与全部历史数据核对均通过;真实模型工程验收按用户选择单独暂缓。 ## 实现范围 @@ -11,11 +11,25 @@ ## 分段结果与最终验收 -记忆阶段322/322,检查点334/334,Skills相关专项与界面均有原始记录。MCP补强前353/353只是基线,见[mcp-baseline-regression.json](mcp-baseline-regression.json)。补强后stdio/注册20项、6组管理与2组实际宿主中断界面已通过,最终候选将单独封存全部源码与日志。 +记忆阶段322/322,检查点334/334,Skills相关专项与界面均有原始记录。MCP补强前353/353只是基线,见[mcp-baseline-regression.json](mcp-baseline-regression.json)。补强后stdio/注册20项、6组管理与2组实际宿主中断界面已通过,最终发行已独立封存全部源码输入与日志。 20类150组[完整界面](model-center-all-ui-validation.json)通过。最后修正模型中心标题栏实际组件选择器,桌面/390px的5组[专项复验](model-center-header-ui-validation.json)及截图核对通过;MCP长参数审批边界修复后20项专项、6组[管理](model-center-final-mcp-ui-validation.json)和2组[中断恢复](model-center-final-mcp-recovery-ui-validation.json)通过,原失败另存。 -独立源码/便携/ZIP、输入与构建散列、Git提交、原PID/Provider/历史数据保留及正式页面复验正在执行。正式交付完成前不将本段标记为通过。 +独立解压源码离线安装、213份输入前后核对、6份构建逐字节匹配,完整357/357通过,0失败/取消/跳过/todo。固定Node24.22.1、Python3.10.11/pytest8.4.2,6阶段原日志与TAP保留,见[源码报告](model-center-source-package-validation.json)和[完整TAP](model-center-final-package-tests.tap)。 + +源码与便携候选ZIP CRC/目录/清单/SHA256通过;便携实际启动/复用、4/4检查、REA三操作、DeepSeek六方法、Edge桌面/390px与正常停止通过。最终封包只整理验收文档,全部代码/测试/脚本/配置与这份独立源码逐字节核对;新ZIP与便携再次验收,分别见[最终归档](model-center-archives-validation.json)、[最终便携](model-center-release-validation.json)。 + +实现提交3f6797b;209份输入与Git原字节一致,4份原有文件仅CRLF/LF区别,规范化内容逐字节相同,见[输入/Git核对](model-center-git-inputs.json)。正式升级保留原Provider和完整历史,原PID/全部会话/数据库及部署后页面结果见[正式升级](model-center-upgrade-live-validation.json)、[部署界面](model-center-deployed-ui-validation.json)和[最终身份](model-center-release-identity.json)。 + +原始失败分别保留:[长参数审批边界](model-center-long-mcp-approval-failure.txt)、[隔离源码外部引擎目录缺失](model-center-source-environment-failure.json)。它们不计作通过,修复与最终复验各自登记。 + +## 正式升级与部署复验 + +正式服务保留同一Provider和原进程:15项目、26会话(19可见/7归档)、2,505条执行记录和4,476条事件逐行散列及全部会话导出一致,公开模型配置不变。对当前源码/最终源码包的213份输入及随包依赖完成8,796次文件比较;REA运行清单仅`builtAt`打包时间不同,其余字段、依赖文件和散列均相同。最终源码9,342文件、便携11,061文件的ZIP/目录/清单核对通过。 + +正式页面在1280px和390px各验证任务计划、模型中心、Skills与MCP,8个页面状态通过;0页面异常、请求失败、HTTP错误或写入请求。截图已目视核对,检查后数据库四类记录散列仍一致。调试端口关闭,6阶段原日志和13份报告散列已复核,见[发行身份](model-center-release-identity.json)。 + +部署前第一次逐字节比较在REA清单打包时间差处中止,没有安装新handler;核对全部依赖清单后,仅单独登记这项时间字段差异。部署后Python检查环境缺Playwright,在浏览器启动前退出;改用仓库已锁定的Node Playwright完成上述8个页面检查,没有改产品代码或调用真实模型。 ## 限制与后续 diff --git a/docs/SKILLS.md b/docs/SKILLS.md index c240bcc0..8a178367 100644 --- a/docs/SKILLS.md +++ b/docs/SKILLS.md @@ -1,6 +1,6 @@ # 项目所属本地技能 -2026-10-30源码切片,正式4318仍运行原1.11不可变发行。本切片接入本地SKILL.md的登记、来源核对、显式启停、版本记录和实际模型按需读取;完整外部插件、任意附件/脚本自动运行、动态MCP另行实现和验收。 +2026-10-30。1.12接入本地SKILL.md登记、来源核对、显式启停、版本记录和实际模型按需读取;完整发行和正式部署见[1.12验收](QA-1.12.md)。本地stdio MCP另见[项目MCP](MCP.md),远程插件与任意附件/脚本自动运行仍单独开发。 ## 使用与边界 diff --git a/docs/TASK-CHECKPOINTS.md b/docs/TASK-CHECKPOINTS.md index e971f6ab..68ce6214 100644 --- a/docs/TASK-CHECKPOINTS.md +++ b/docs/TASK-CHECKPOINTS.md @@ -1,6 +1,6 @@ # 任务恢复检查点 -2026-10-30源码切片。正式4318继续运行已验收的1.11发行;新恢复入口尚未发布为新的不可变安装包。 +2026-10-30。1.12任务恢复检查点的契约与使用范围如下;源码、不可变发行和正式部署分别见[1.12验收](QA-1.12.md)。 ## 用户可执行的流程 diff --git a/docs/VALIDATION.md b/docs/VALIDATION.md index 071f39f0..422eafe5 100644 --- a/docs/VALIDATION.md +++ b/docs/VALIDATION.md @@ -1,5 +1,9 @@ # Agent Workbench 验收记录 +## 1.12.0 · 模型中心、记忆、恢复与扩展工具 + +最终不可变发行20261030124454517完成357/357独立源码回归、213份输入/6份构建比对、20类150组完整界面和最终标题栏/MCP相关复验。源码/便携实际REA、DeepSeek六方法与Edge通过,最终ZIP/清单核对通过;正式4318保留PID19084和原Provider升级1.12.0,15项目、26会话、2,505记录和4,476事件逐行与全部导出一致。部署后桌面/390px的8个页面状态及数据库复核通过,真实模型0请求。见[1.12验收](QA-1.12.md)、[完整TAP](model-center-final-package-tests.tap)与[发行身份](model-center-release-identity.json)。 + ## 1.11.0 · 持久依赖计划、原证据核验与发行收尾 最终候选20261030064611655已完成298/298独立源码、180份冻结输入、6份构建比对、14类126组完整界面,以及源码/便携的实际REA、DeepSeek SDK和Edge验收。便携11,005文件、源码9,253文件归档通过;正式4318保留PID19084及原Provider升级1.11.0,15项目/26会话(含7归档)、2,499执行记录和4,463事件逐行散列及导出一致,部署后桌面/390px只读检查通过。真实模型续接按用户选择待验收,本轮0模型请求。原环境/超时/验证脚本失败分别保留,详见[1.11验收](QA-1.11.md)及[发行身份](task-plans-release-identity.json)。 diff --git a/docs/deployment.json b/docs/deployment.json index 258ebf06..dc446575 100644 --- a/docs/deployment.json +++ b/docs/deployment.json @@ -1,15 +1,15 @@ { "ready": true, "url": "http://127.0.0.1:4318", - "version": "1.11.0", + "version": "1.12.0", "mode": "compatible", "model": "gpt-6.1-sol", "hasKey": true, "pid": 19084, - "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.11.0-win-x64-20261030064611655", + "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", "originalAppRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64", "dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench", - "upgradedAt": "2026-10-30T07:17:46.025Z", + "upgradedAt": "2026-10-30T12:49:42.453Z", "storage": "sqlite", "realModelAcceptance": "deferred_by_user" } diff --git a/docs/model-center-archives-validation.json b/docs/model-center-archives-validation.json new file mode 100644 index 00000000..67794cdd --- /dev/null +++ b/docs/model-center-archives-validation.json @@ -0,0 +1,24 @@ +{ + "success": true, + "version": "1.12.0", + "testedAt": "2026-10-30T12:46:08.749552+00:00", + "archives": [ + { + "kind": "portable", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517.zip", + "files": 11061, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "3a00a375a3ee191e74b9a09d723b4c09ecce1b9f23b6466a4d6be9dcf17c5449" + }, + { + "kind": "source", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-source-20261030124454517.zip", + "files": 9342, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "853d3ef196d9df8db3c1ec35e3abb09469ad74cbae54176e6babf49e47c74c43" + } + ], + "extractionRoot": "D:\\awb\\source-check-8d6cb921eacb4fbbb6709553384b4140\\Agent-Workbench-1.12.0-source-20261030124454517" +} \ No newline at end of file diff --git a/docs/model-center-deployed-ui-validation.json b/docs/model-center-deployed-ui-validation.json new file mode 100644 index 00000000..280124e9 --- /dev/null +++ b/docs/model-center-deployed-ui-validation.json @@ -0,0 +1,79 @@ +{ + "success": true, + "version": "1.12.0", + "pid": 19084, + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606", + "results": [ + { + "width": 1280, + "height": 900, + "panel": "执行计划", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\plan-1280.png", + "screenshotSha256": "6018b5d1ac2aa5e0dd32a4670f08d45a5fd01f0803ffa60fd40561dc73cadca0" + }, + { + "width": 1280, + "height": 900, + "panel": "模型中心", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\model-center-1280.png", + "screenshotSha256": "ff017da4e5291ed4089290cf0b53da23eb110f51bb2a60b1cc7474609c4fdf9d" + }, + { + "width": 1280, + "height": 900, + "panel": "项目技能", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\skills-1280.png", + "screenshotSha256": "457e281af20de001c5eca3c6d73d81d2c7e62f3c6ab4b9ec5856e7ceb91c8542" + }, + { + "width": 1280, + "height": 900, + "panel": "项目 MCP 工具", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\mcp-1280.png", + "screenshotSha256": "5e83bf55ce2e27c769d7af8784dec97ae79c4e885bf3d3ae3e8e17c3e1f74a6b" + }, + { + "width": 390, + "height": 844, + "panel": "执行计划", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\plan-390.png", + "screenshotSha256": "1cd7dcacc10bed365ec2bde3e0b56e5fac4c3f0d3db5c0a3a3efdb4804302d97" + }, + { + "width": 390, + "height": 844, + "panel": "模型中心", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\model-center-390.png", + "screenshotSha256": "49e6f60567a8bbfe76cbaa843a2debba97c65d8c18bcb0e6fec386693c8aa9b5" + }, + { + "width": 390, + "height": 844, + "panel": "项目技能", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\skills-390.png", + "screenshotSha256": "71f9c2f2ba4f4adea8308574c9aab96d77c024a963095ec65b6d53fb65fec6fc" + }, + { + "width": 390, + "height": 844, + "panel": "项目 MCP 工具", + "readOnly": true, + "screenshot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployed-ui-8ac055ed-e6af-495b-8136-8317afae7606\\mcp-390.png", + "screenshotSha256": "81e08ad569c63d41c6b6e36ce161bde25056fc3fe294f270cc90ad8c6545b02a" + } + ], + "testedAt": "2026-10-30T12:51:27.546Z", + "pageErrors": [], + "requestFailures": [], + "httpErrors": [], + "blockedWrites": [], + "modelRequests": 0, + "scope": "Read-only smoke of deployed host in actual Edge desktop/390px; API mutations are blocked, no task/tool/model/configuration/project writes." +} diff --git a/docs/model-center-final-package-tests.tap b/docs/model-center-final-package-tests.tap new file mode 100644 index 00000000..0ae42793 --- /dev/null +++ b/docs/model-center-final-package-tests.tap @@ -0,0 +1,2159 @@ +TAP version 13 +# Subtest: the bundled local service enforces host, origin, token and JSON object contracts +ok 1 - the bundled local service enforces host, origin, token and JSON object contracts + --- + duration_ms: 1129.4444 + type: 'test' + ... +# Subtest: API review applies verified content, detects conflicts, exports sessions and keeps keys in memory +ok 2 - API review applies verified content, detects conflicts, exports sessions and keeps keys in memory + --- + duration_ms: 1599.2083 + type: 'test' + ... +# Subtest: a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume +ok 3 - a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume + --- + duration_ms: 7188.9869 + type: 'test' + ... +# Subtest: runtime diagnostics and model-response validation use actual records and preserve the saved connection +ok 4 - runtime diagnostics and model-response validation use actual records and preserve the saved connection + --- + duration_ms: 1058.1268 + type: 'test' + ... +# Subtest: persistent event replay is read-only and keeps run/artifact identity across reconnects +ok 5 - persistent event replay is read-only and keeps run/artifact identity across reconnects + --- + duration_ms: 6106.9458 + type: 'test' + ... +# Subtest: real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart +ok 6 - real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart + --- + duration_ms: 4706.565 + type: 'test' + ... +# Subtest: self harness browser tools require approval and feed verified actual page fields back to the original Task +ok 7 - self harness browser tools require approval and feed verified actual page fields back to the original Task + --- + duration_ms: 10251.7449 + type: 'test' + ... +# Subtest: browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement +ok 8 - browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement + --- + duration_ms: 4228.9547 + type: 'test' + ... +# Subtest: late HTTP stop of a finished browser job cannot interrupt a later job in the same Task +ok 9 - late HTTP stop of a finished browser job cannot interrupt a later job in the same Task + --- + duration_ms: 5718.3103 + type: 'test' + ... +# Subtest: actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records +ok 10 - actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records + --- + duration_ms: 15844.5567 + type: 'test' + ... +# Subtest: a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact +ok 11 - a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact + --- + duration_ms: 7764.4478 + type: 'test' + ... +# Subtest: actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels +ok 12 - actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels + --- + duration_ms: 6448.8713 + type: 'test' + ... +# Subtest: browser field coverage distinguishes sections and Run windows while retaining original source identity +ok 13 - browser field coverage distinguishes sections and Run windows while retaining original source identity + --- + duration_ms: 0.4349 + type: 'test' + ... +# Subtest: repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing +ok 14 - repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing + --- + duration_ms: 5284.1933 + type: 'test' + ... +# Subtest: browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution +ok 15 - browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution + --- + duration_ms: 0.8963 + type: 'test' + ... +# Subtest: real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen +ok 16 - real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen + --- + duration_ms: 3230.7777 + type: 'test' + ... +# Subtest: failed real page assertion preserves actual value and forbids silent retry of the original plan +ok 17 - failed real page assertion preserves actual value and forbids silent retry of the original plan + --- + duration_ms: 8405.661 + type: 'test' + ... +# Subtest: build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan +ok 18 - build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan + --- + duration_ms: 2483.7894 + type: 'test' + ... +# Subtest: outside network never reaches another local service, and original JavaScript/console failures remain failures +ok 19 - outside network never reaches another local service, and original JavaScript/console failures remain failures + --- + duration_ms: 3806.355 + type: 'test' + ... +# Subtest: stopping a real in-flight browser preserves finished steps, closes its owned root and never replays +ok 20 - stopping a real in-flight browser preserves finished steps, closes its owned root and never replays + --- + duration_ms: 3290.1584 + type: 'test' + ... +# Subtest: 原PNG损坏使原结果校验失败,不能以已有通过状态复用 +ok 21 - 原PNG损坏使原结果校验失败,不能以已有通过状态复用 + --- + duration_ms: 3107.4263 + type: 'test' + ... +# Subtest: batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart +ok 22 - batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart + --- + duration_ms: 3287.4128 + type: 'test' + ... +# Subtest: delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files +ok 23 - delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files + --- + duration_ms: 3298.0797 + type: 'test' + ... +# Subtest: a compatible model can seal proposals through the real HTTP loop while application stays behind user review +ok 24 - a compatible model can seal proposals through the real HTTP loop while application stays behind user review + --- + duration_ms: 8300.4748 + type: 'test' + ... +# Subtest: a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools +ok 25 - a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools + --- + duration_ms: 14450.4512 + type: 'test' + ... +# Subtest: applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation +ok 26 - applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation + --- + duration_ms: 3482.5997 + type: 'test' + ... +# Subtest: actual process exit at file-batch prepared preserves durable identity and never replays writes +ok 27 - actual process exit at file-batch prepared preserves durable identity and never replays writes + --- + duration_ms: 2490.7185 + type: 'test' + ... +# Subtest: actual process exit at file-batch application_started preserves durable identity and never replays writes +ok 28 - actual process exit at file-batch application_started preserves durable identity and never replays writes + --- + duration_ms: 2613.5956 + type: 'test' + ... +# Subtest: actual process exit at file-batch write_intent preserves durable identity and never replays writes +ok 29 - actual process exit at file-batch write_intent preserves durable identity and never replays writes + --- + duration_ms: 2641.7461 + type: 'test' + ... +# Subtest: actual process exit at file-batch staged preserves durable identity and never replays writes +ok 30 - actual process exit at file-batch staged preserves durable identity and never replays writes + --- + duration_ms: 2863.4421 + type: 'test' + ... +# Subtest: actual process exit at file-batch replaced preserves durable identity and never replays writes +ok 31 - actual process exit at file-batch replaced preserves durable identity and never replays writes + --- + duration_ms: 3569.7653 + type: 'test' + ... +# Subtest: actual process exit at file-batch file_recorded preserves durable identity and never replays writes +ok 32 - actual process exit at file-batch file_recorded preserves durable identity and never replays writes + --- + duration_ms: 3096.5923 + type: 'test' + ... +# Subtest: actual process exit at file-batch finished preserves durable identity and never replays writes +ok 33 - actual process exit at file-batch finished preserves durable identity and never replays writes + --- + duration_ms: 2369.0519 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_started preserves durable identity and never replays writes +ok 34 - actual process exit at file-batch rollback_started preserves durable identity and never replays writes + --- + duration_ms: 3875.4072 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_intent preserves durable identity and never replays writes +ok 35 - actual process exit at file-batch restore_intent preserves durable identity and never replays writes + --- + duration_ms: 3649.3972 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_staged preserves durable identity and never replays writes +ok 36 - actual process exit at file-batch restore_staged preserves durable identity and never replays writes + --- + duration_ms: 3618.5242 + type: 'test' + ... +# Subtest: actual process exit at file-batch restored preserves durable identity and never replays writes +ok 37 - actual process exit at file-batch restored preserves durable identity and never replays writes + --- + duration_ms: 3099.5538 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_recorded preserves durable identity and never replays writes +ok 38 - actual process exit at file-batch restore_recorded preserves durable identity and never replays writes + --- + duration_ms: 3441.1292 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_finished preserves durable identity and never replays writes +ok 39 - actual process exit at file-batch rollback_finished preserves durable identity and never replays writes + --- + duration_ms: 3220.0531 + type: 'test' + ... +# warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it +# warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files +ok 40 - sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files + --- + duration_ms: 3414.076 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: a conflict in the last file or Git branch prevents writing every file in the batch +ok 41 - a conflict in the last file or Git branch prevents writing every file in the batch + --- + duration_ms: 3520.0775 + type: 'test' + ... +# Subtest: duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch +ok 42 - duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch + --- + duration_ms: 1939.9084 + type: 'test' + ... +# Subtest: fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target +ok 43 - fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target + --- + duration_ms: 2601.671 + type: 'test' + ... +# Subtest: a failure after replacement restores only batch bytes and never retries an old application +ok 44 - a failure after replacement restores only batch bytes and never retries an old application + --- + duration_ms: 2139.3067 + type: 'test' + ... +# Subtest: rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery +ok 45 - rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery + --- + duration_ms: 2219.1393 + type: 'test' + ... +# Subtest: an unattempted owner-created file identical to a suggestion remains external and is never removed +ok 46 - an unattempted owner-created file identical to a suggestion remains external and is never removed + --- + duration_ms: 1777.5496 + type: 'test' + ... +# Subtest: active batch requests are serialized and cancellation leaves a verifiable ended batch +ok 47 - active batch requests are serialized and cancellation leaves a verifiable ended batch + --- + duration_ms: 1599.572 + type: 'test' + ... +# Subtest: batch application and rollback preserve unrelated Git index and worktree bytes +ok 48 - batch application and rollback preserve unrelated Git index and worktree bytes + --- + duration_ms: 3634.4337 + type: 'test' + ... +# Subtest: recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection +ok 49 - recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection + --- + duration_ms: 2949.8457 + type: 'test' + ... +# Subtest: one Task can seal pending proposals from earlier Runs while snapshots retain each source Run +ok 50 - one Task can seal pending proposals from earlier Runs while snapshots retain each source Run + --- + duration_ms: 2089.9998 + type: 'test' + ... +# Subtest: engineering inspection preserves a dirty Git baseline and treats project rules as data +ok 51 - engineering inspection preserves a dirty Git baseline and treats project rules as data + --- + duration_ms: 2377.9224 + type: 'test' + ... +# Subtest: real npm tests and build produce counted results, log artifacts and persistent verification +ok 52 - real npm tests and build produce counted results, log artifacts and persistent verification + --- + duration_ms: 2292.9293 + type: 'test' + ... +# Subtest: an actual failing test retains the nonzero exit code and failed count +ok 53 - an actual failing test retains the nonzero exit code and failed count + --- + duration_ms: 2009.6096 + type: 'test' + ... +# Subtest: zero tests, skipped tests and unrecognized stdout cannot become verification passes +ok 54 - zero tests, skipped tests and unrecognized stdout cannot become verification passes + --- + duration_ms: 6567.6205 + type: 'test' + ... +# Subtest: a successful build with no selected tests does not verify the task +ok 55 - a successful build with no selected tests does not verify the task + --- + duration_ms: 1244.798 + type: 'test' + ... +# Subtest: stale check plans and forged script names execute no project commands +ok 56 - stale check plans and forged script names execute no project commands + --- + duration_ms: 1282.3997 + type: 'test' + ... +# Subtest: applying a later proposal invalidates the prior passed engineering snapshot +ok 57 - applying a later proposal invalidates the prior passed engineering snapshot + --- + duration_ms: 2470.5337 + type: 'test' + ... +# Subtest: stopping an actual check terminates its child process and blocks concurrent jobs +ok 58 - stopping an actual check terminates its child process and blocks concurrent jobs + --- + duration_ms: 1725.5105 + type: 'test' + ... +# Subtest: check timeout records a failure with its actual termination result +ok 59 - check timeout records a failure with its actual termination result + --- + duration_ms: 1699.2967 + type: 'test' + ... +# Subtest: source edits during a successful check make the result stale +ok 60 - source edits during a successful check make the result stale + --- + duration_ms: 2587.3318 + type: 'test' + ... +# Subtest: bounded large logs retain the test footer and readable artifact instead of inventing counts +ok 61 - bounded large logs retain the test footer and readable artifact instead of inventing counts + --- + duration_ms: 1584.0887 + type: 'test' + ... +# Subtest: model-selected checks require a run-bound decision and denial creates no check job +ok 62 - model-selected checks require a run-bound decision and denial creates no check job + --- + duration_ms: 2574.1409 + type: 'test' + ... +# Subtest: check APIs expose owned plans and jobs and preserve the authoritative results across restart +ok 63 - check APIs expose owned plans and jobs and preserve the authoritative results across restart + --- + duration_ms: 3073.4049 + type: 'test' + ... +# Subtest: reviewed changes continue the original task without reopening a generic completed run +ok 64 - reviewed changes continue the original task without reopening a generic completed run + --- + duration_ms: 2211.0382 + type: 'test' + ... +# Subtest: concurrent review-continuation API requests accept one run and retain the goal after restart +ok 65 - concurrent review-continuation API requests accept one run and retain the goal after restart + --- + duration_ms: 5464.1209 + type: 'test' + ... +# Subtest: the model reads owned failure logs without running the check again +ok 66 - the model reads owned failure logs without running the check again + --- + duration_ms: 2747.621 + type: 'test' + ... +# Subtest: process exit at check queued preserves results and never replays commands +ok 67 - process exit at check queued preserves results and never replays commands + --- + duration_ms: 1457.2817 + type: 'test' + ... +# Subtest: process exit at check result_committed preserves results and never replays commands +ok 68 - process exit at check result_committed preserves results and never replays commands + --- + duration_ms: 2004.0542 + type: 'test' + ... +# Subtest: model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery +ok 69 - model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery + --- + duration_ms: 4619.0041 + type: 'test' + ... +# Subtest: bundled code APIs isolate project results, validate queries and create review-only patches with conflicts +ok 70 - bundled code APIs isolate project results, validate queries and create review-only patches with conflicts + --- + duration_ms: 1856.1195 + type: 'test' + ... +# Subtest: code tool arguments reject malformed ownership-independent inputs before side effects +ok 71 - code tool arguments reject malformed ownership-independent inputs before side effects + --- + duration_ms: 0.4847 + type: 'test' + ... +# Subtest: actual process exit at Git queued never replays a commit and can reconcile the durable result +ok 72 - actual process exit at Git queued never replays a commit and can reconcile the durable result + --- + duration_ms: 9318.1187 + type: 'test' + ... +# Subtest: actual process exit at Git preparing never replays a commit and can reconcile the durable result +ok 73 - actual process exit at Git preparing never replays a commit and can reconcile the durable result + --- + duration_ms: 8919.7283 + type: 'test' + ... +# Subtest: actual process exit at Git index_locked never replays a commit and can reconcile the durable result +ok 74 - actual process exit at Git index_locked never replays a commit and can reconcile the durable result + --- + duration_ms: 9355.5942 + type: 'test' + ... +# Subtest: actual process exit at Git prepared never replays a commit and can reconcile the durable result +ok 75 - actual process exit at Git prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 9912.8886 + type: 'test' + ... +# Subtest: actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result +ok 76 - actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 9911.1111 + type: 'test' + ... +# Subtest: actual process exit at Git publishing never replays a commit and can reconcile the durable result +ok 77 - actual process exit at Git publishing never replays a commit and can reconcile the durable result + --- + duration_ms: 9947.5187 + type: 'test' + ... +# Subtest: actual process exit at Git committed never replays a commit and can reconcile the durable result +ok 78 - actual process exit at Git committed never replays a commit and can reconcile the durable result + --- + duration_ms: 7182.3828 + type: 'test' + ... +# Subtest: actual process exit at Git index_published never replays a commit and can reconcile the durable result +ok 79 - actual process exit at Git index_published never replays a commit and can reconcile the durable result + --- + duration_ms: 8364.0029 + type: 'test' + ... +# Subtest: actual process exit at Git finished never replays a commit and can reconcile the durable result +ok 80 - actual process exit at Git finished never replays a commit and can reconcile the durable result + --- + duration_ms: 7237.9226 + type: 'test' + ... +# Subtest: an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock +ok 81 - an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock + --- + duration_ms: 6631.5893 + type: 'test' + ... +# Subtest: known publication with a later source edit retains the commit and marks the delivery for inspection +ok 82 - known publication with a later source edit retains the commit and marks the delivery for inspection + --- + duration_ms: 7660.8448 + type: 'test' + ... +# Subtest: CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership +ok 83 - CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership + --- + duration_ms: 8424.8807 + type: 'test' + ... +# Subtest: adding new durable record kinds to an existing hot Store preserves all existing Maps and records +ok 84 - adding new durable record kinds to an existing hot Store preserves all existing Maps and records + --- + duration_ms: 6497.659 + type: 'test' + ... +# Subtest: an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected +ok 85 - an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected + --- + duration_ms: 10386.3591 + type: 'test' + ... +# Subtest: actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files +ok 86 - actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files + --- + duration_ms: 9348.5619 + type: 'test' + ... +# Subtest: selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit +ok 87 - selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit + --- + duration_ms: 12240.3907 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD +ok 88 - source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD + --- + duration_ms: 14680.1565 + type: 'test' + ... +# Switched to a new branch 'delivery-branch' +# Subtest: a later Git metadata change keeps matching source evidence valid but a real source edit requires checks +ok 89 - a later Git metadata change keeps matching source evidence valid but a real source edit requires checks + --- + duration_ms: 6921.2629 + type: 'test' + ... +# Subtest: a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence +ok 90 - a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence + --- + duration_ms: 4274.7263 + type: 'test' + ... +# HEAD is now at 0bb927d Sealed delivery fixture baseline +# Subtest: Git filters, merge state, detached HEAD and old task ownership are explicitly rejected +ok 91 - Git filters, merge state, detached HEAD and old task ownership are explicitly rejected + --- + duration_ms: 17486.5295 + type: 'test' + ... +# Subtest: local snapshot commits disable repository hooks and signing and isolate the Git child environment +ok 92 - local snapshot commits disable repository hooks and signing and isolate the Git child environment + --- + duration_ms: 6794.7958 + type: 'test' + ... +# Subtest: stopping before publication cancels safely; stopping after publication preserves the actual completed commit +ok 93 - stopping before publication cancels safely; stopping after publication preserves the actual completed commit + --- + duration_ms: 11900.5397 + type: 'test' + ... +# Subtest: delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart +ok 94 - delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart + --- + duration_ms: 8310.612 + type: 'test' + ... +# Subtest: the model can prepare an owned Git review and evidence report while publishing remains a separate user action +ok 95 - the model can prepare an owned Git review and evidence report while publishing remains a separate user action + --- + duration_ms: 8201.3371 + type: 'test' + ... +# Subtest: HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved +ok 96 - HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved + --- + duration_ms: 9418.6892 + type: 'test' + ... +# Subtest: a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task +ok 97 - a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task + --- + duration_ms: 7266.25 + type: 'test' + ... +# Subtest: a question about the previous workbench error receives local error context and current change states +ok 98 - a question about the previous workbench error receives local error context and current change states + --- + duration_ms: 1852.9398 + type: 'test' + ... +# Subtest: a transient model failure after an approved command retries only the model request +ok 99 - a transient model failure after an approved command retries only the model request + --- + duration_ms: 2857.3004 + type: 'test' + ... +# Subtest: exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay +ok 100 - exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay + --- + duration_ms: 2381.72 + type: 'test' + ... +# Subtest: stopping during model backoff cancels further requests and clears the running request state +ok 101 - stopping during model backoff cancels further requests and clears the running request state + --- + duration_ms: 1191.6882 + type: 'test' + ... +# Subtest: HTTP authentication errors are classified, redacted and never automatically retried +ok 102 - HTTP authentication errors are classified, redacted and never automatically retried + --- + duration_ms: 21.5578 + type: 'test' + ... +# Subtest: temporary HTTP service errors retry and recover with recorded attempt counts +ok 103 - temporary HTTP service errors retry and recover with recorded attempt counts + --- + duration_ms: 17.9982 + type: 'test' + ... +# Subtest: invalid and oversized protocol responses fail once with a useful response-format diagnosis +ok 104 - invalid and oversized protocol responses fail once with a useful response-format diagnosis + --- + duration_ms: 4.2086 + type: 'test' + ... +# Subtest: HTTP rate limits expose their source and obey the service retry interval before recovery +ok 105 - HTTP rate limits expose their source and obey the service retry interval before recovery + --- + duration_ms: 1013.6013 + type: 'test' + ... +# Subtest: Windows commands preserve Chinese through a PowerShell pipeline into Node +ok 106 - Windows commands preserve Chinese through a PowerShell pipeline into Node + --- + duration_ms: 816.9417 + type: 'test' + ... +# Subtest: Windows shell syntax errors stay readable and native command exit codes are retained +ok 107 - Windows shell syntax errors stay readable and native command exit codes are retained + --- + duration_ms: 1123.0441 + type: 'test' + ... +# Subtest: review and completed states do not turn a generic continue click into a new model request +ok 108 - review and completed states do not turn a generic continue click into a new model request + --- + duration_ms: 808.8791 + type: 'test' + ... +# Subtest: old session data receives a truthful historical connection diagnosis without rewriting history +ok 109 - old session data receives a truthful historical connection diagnosis without rewriting history + --- + duration_ms: 958.0702 + type: 'test' + ... +# Subtest: engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart +ok 110 - engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart + --- + duration_ms: 2846.1393 + type: 'test' + ... +# Subtest: HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session +ok 111 - HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session + --- + duration_ms: 3448.5621 + type: 'test' + ... +# Subtest: engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch +ok 112 - engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch + --- + duration_ms: 1029.3926 + type: 'test' + ... +# Subtest: owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence +ok 113 - owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence + --- + duration_ms: 1502.1841 + type: 'test' + ... +# Subtest: an invalid startup nonce is rejected before initialize and preserves the process close and partial report +ok 114 - an invalid startup nonce is rejected before initialize and preserves the process close and partial report + --- + duration_ms: 1560.604 + type: 'test' + ... +# Subtest: SDK identity and session directory mismatches retain raw responses and never become verified +ok 115 - SDK identity and session directory mismatches retain raw responses and never become verified + --- + duration_ms: 4486.0493 + type: 'test' + ... +# Subtest: cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation +ok 116 - cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation + --- + duration_ms: 2048.9289 + type: 'test' + ... +# Subtest: cancel before readiness sends no protocol request and a user retry creates a different process and record +ok 117 - cancel before readiness sends no protocol request and a user retry creates a different process and record + --- + duration_ms: 1806.423 + type: 'test' + ... +# Subtest: source or scratch changes and unexpected model traffic fail after preserving the actual observed result +ok 118 - source or scratch changes and unexpected model traffic fail after preserving the actual observed result + --- + duration_ms: 4453.9718 + type: 'test' + ... +# Subtest: unowned idle notifications stay quarantined and server requests receive a rejection without granting operations +ok 119 - unowned idle notifications stay quarantined and server requests receive a rejection without granting operations + --- + duration_ms: 3521.0046 + type: 'test' + ... +# Subtest: engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths +ok 120 - engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths + --- + duration_ms: 1933.2999 + type: 'test' + ... +# Subtest: foreign sessions and altered reports or task bindings cannot reuse verified engine evidence +ok 121 - foreign sessions and altered reports or task bindings cannot reuse verified engine evidence + --- + duration_ms: 1913.4713 + type: 'test' + ... +# Subtest: restart never replays an active engine check or stops a historical PID, and keeps prior task state +ok 122 - restart never replays an active engine check or stops a historical PID, and keeps prior task state + --- + duration_ms: 2151.4475 + type: 'test' + ... +# Subtest: model argument validation and runtime activity do not grant external engine prompt or project execution +ok 123 - model argument validation and runtime activity do not grant external engine prompt or project execution + --- + duration_ms: 1036.7542 + type: 'test' + ... +# Subtest: a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged +ok 124 - a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged + --- + duration_ms: 3193.5925 + type: 'test' + ... +# Subtest: JSON migration survives process exit before commit and retains exact legacy backups +ok 125 - JSON migration survives process exit before commit and retains exact legacy backups + --- + duration_ms: 2823.7554 + type: 'test' + ... +# Subtest: process exit after_state rolls back state, event and outbox together +ok 126 - process exit after_state rolls back state, event and outbox together + --- + duration_ms: 2433.9904 + type: 'test' + ... +# Subtest: process exit after_event rolls back state, event and outbox together +ok 127 - process exit after_event rolls back state, event and outbox together + --- + duration_ms: 2425.1771 + type: 'test' + ... +# Subtest: crash recovery at accepted retains execution identity and never replays side effects +ok 128 - crash recovery at accepted retains execution identity and never replays side effects + --- + duration_ms: 2593.2924 + type: 'test' + ... +# Subtest: crash recovery at queued retains execution identity and never replays side effects +ok 129 - crash recovery at queued retains execution identity and never replays side effects + --- + duration_ms: 3146.3457 + type: 'test' + ... +# Subtest: crash recovery at approval_wait retains execution identity and never replays side effects +ok 130 - crash recovery at approval_wait retains execution identity and never replays side effects + --- + duration_ms: 3887.9457 + type: 'test' + ... +# Subtest: crash recovery at approved retains execution identity and never replays side effects +ok 131 - crash recovery at approved retains execution identity and never replays side effects + --- + duration_ms: 3991.2741 + type: 'test' + ... +# Subtest: crash recovery at effect_unrecorded retains execution identity and never replays side effects +ok 132 - crash recovery at effect_unrecorded retains execution identity and never replays side effects + --- + duration_ms: 3783.9341 + type: 'test' + ... +# Subtest: crash recovery at result_committed retains execution identity and never replays side effects +ok 133 - crash recovery at result_committed retains execution identity and never replays side effects + --- + duration_ms: 3964.1654 + type: 'test' + ... +# Subtest: crash recovery at before_next_model retains execution identity and never replays side effects +ok 134 - crash recovery at before_next_model retains execution identity and never replays side effects + --- + duration_ms: 4626.4758 + type: 'test' + ... +# Subtest: state and event failures publish no success and preserve the last committed memory snapshot +ok 135 - state and event failures publish no success and preserve the last committed memory snapshot + --- + duration_ms: 1037.7136 + type: 'test' + ... +# Subtest: tool result artifacts and event cursors retain project ownership across restart +ok 136 - tool result artifacts and event cursors retain project ownership across restart + --- + duration_ms: 2575.4713 + type: 'test' + ... +# Subtest: token budgets pause before tools execute and continuation keeps original task and accumulated usage +ok 137 - token budgets pause before tools execute and continuation keeps original task and accumulated usage + --- + duration_ms: 2108.1698 + type: 'test' + ... +# Subtest: a time budget interrupts an unresponsive model and persists a resumable run +ok 138 - a time budget interrupts an unresponsive model and persists a resumable run + --- + duration_ms: 1157.9874 + type: 'test' + ... +# Subtest: a corrupted large result artifact cannot become a recovered success +ok 139 - a corrupted large result artifact cannot become a recovered success + --- + duration_ms: 1321.7012 + type: 'test' + ... +# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes +ok 140 - proposals preserve project bytes until review; apply backs up the exact original bytes + --- + duration_ms: 1163.3262 + type: 'test' + ... +# Subtest: new nested files are created only on apply and unchanged content creates no proposal +ok 141 - new nested files are created only on apply and unchanged content creates no proposal + --- + duration_ms: 972.5127 + type: 'test' + ... +# Subtest: stale reads and changed baselines are rejected without overwriting external edits +ok 142 - stale reads and changed baselines are rejected without overwriting external edits + --- + duration_ms: 1015.4412 + type: 'test' + ... +# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions +ok 143 - file paths reject traversal, absolute paths, credentials and outside junctions + --- + duration_ms: 877.1294 + type: 'test' + ... +# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files +ok 144 - read and search expose bounded text scopes and reject non UTF-8 / oversized files + --- + duration_ms: 889.1468 + type: 'test' + ... +# Subtest: MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup +ok 145 - MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup + --- + duration_ms: 2527.0841 + type: 'test' + ... +# Subtest: MCP probe holds the project operation lock until its owned process and report are settled +ok 146 - MCP probe holds the project operation lock until its owned process and report are settled + --- + duration_ms: 2016.6271 + type: 'test' + ... +# Subtest: MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch +ok 147 - MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch + --- + duration_ms: 1.3858 + type: 'test' + ... +# Subtest: actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets +ok 148 - actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets + --- + duration_ms: 5685.7763 + type: 'test' + ... +# Subtest: denying an MCP call never starts another process or executes the external tool +ok 149 - denying an MCP call never starts another process or executes the external tool + --- + duration_ms: 4507.0708 + type: 'test' + ... +# Subtest: actual handshake drift rejects tools/call even if program entry hash is unchanged +ok 150 - actual handshake drift rejects tools/call even if program entry hash is unchanged + --- + duration_ms: 5915.0005 + type: 'test' + ... +# Subtest: cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen +ok 151 - cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen + --- + duration_ms: 5064.2658 + type: 'test' + ... +# Subtest: changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch +ok 152 - changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch + --- + duration_ms: 2397.6137 + type: 'test' + ... +# Subtest: registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests +ok 153 - registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests + --- + duration_ms: 3014.9055 + type: 'test' + ... +# Subtest: unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay +ok 154 - unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay + --- + duration_ms: 7025.1129 + type: 'test' + ... +# Subtest: MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged +ok 155 - MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged + --- + duration_ms: 5242.2681 + type: 'test' + ... +# Subtest: actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call +ok 156 - actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call + --- + duration_ms: 4771.0292 + type: 'test' + ... +# Subtest: changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source +ok 157 - changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source + --- + duration_ms: 2721.4448 + type: 'test' + ... +# Subtest: stdio preserves split UTF-8 frames and final replies drained after process exit +ok 158 - stdio preserves split UTF-8 frames and final replies drained after process exit + --- + duration_ms: 1976.8604 + type: 'test' + ... +# Subtest: server-initiated model requests are refused instead of inheriting provider privileges +ok 159 - server-initiated model requests are refused instead of inheriting provider privileges + --- + duration_ms: 908.0262 + type: 'test' + ... +# Subtest: invalid or over-budget protocol invalid closes only its owned process and is not retried +ok 160 - invalid or over-budget protocol invalid closes only its owned process and is not retried + --- + duration_ms: 1079.3881 + type: 'test' + ... +# Subtest: invalid or over-budget protocol oversized closes only its owned process and is not retried +ok 161 - invalid or over-budget protocol oversized closes only its owned process and is not retried + --- + duration_ms: 857.2919 + type: 'test' + ... +# Subtest: cancel and timeout do not resend a dispatched request and pre-cancel has no request trace +ok 162 - cancel and timeout do not resend a dispatched request and pre-cancel has no request trace + --- + duration_ms: 984.1487 + type: 'test' + ... +# Subtest: startup failure remains undispatched and has no process PID to terminate +ok 163 - startup failure remains undispatched and has no process PID to terminate + --- + duration_ms: 874.0582 + type: 'test' + ... +# Subtest: REA launch filters a fixture credential canary and rejects changed entry identity before a new connection +ok 164 - REA launch filters a fixture credential canary and rejects changed entry identity before a new connection + --- + duration_ms: 865.423 + type: 'test' + ... +# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart +ok 165 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart + --- + duration_ms: 1583.8855 + type: 'test' + ... +# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts +ok 166 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts + --- + duration_ms: 963.6403 + type: 'test' + ... +# Subtest: real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity +ok 167 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity + --- + duration_ms: 3145.975 + type: 'test' + ... +# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests +ok 168 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests + --- + duration_ms: 4369.1945 + type: 'test' + ... +# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes +ok 169 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes + --- + duration_ms: 1502.6165 + type: 'test' + ... +# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request +ok 170 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request + --- + duration_ms: 1271.8164 + type: 'test' + ... +# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model +ok 171 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model + --- + duration_ms: 1445.0624 + type: 'test' + ... +# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply +ok 172 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply + --- + duration_ms: 873.7945 + type: 'test' + ... +# Subtest: several patches are matched against one original snapshot in any input order and keep LF +ok 173 - several patches are matched against one original snapshot in any input order and keep LF + --- + duration_ms: 1001.8047 + type: 'test' + ... +# Subtest: mixed line endings require exact anchors and preserve untouched formatting +ok 174 - mixed line endings require exact anchors and preserve untouched formatting + --- + duration_ms: 1116.6708 + type: 'test' + ... +# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write +ok 175 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write + --- + duration_ms: 1004.0475 + type: 'test' + ... +# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts +ok 176 - stale original hashes and changes before apply preserve owner edits and mark conflicts + --- + duration_ms: 803.5248 + type: 'test' + ... +# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes +ok 177 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes + --- + duration_ms: 1048.4788 + type: 'test' + ... +# Subtest: JS/TS/React AST indexes actual declarations, exports, imports and verified source lines +ok 178 - JS/TS/React AST indexes actual declarations, exports, imports and verified source lines + --- + duration_ms: 1131.9805 + type: 'test' + ... +# Subtest: default expressions, named default exports and declared functions retain their AST evidence +ok 179 - default expressions, named default exports and declared functions retain their AST evidence + --- + duration_ms: 979.0017 + type: 'test' + ... +# Subtest: incremental refresh invalidates changed/deleted symbols and recalculates reused import targets +ok 180 - incremental refresh invalidates changed/deleted symbols and recalculates reused import targets + --- + duration_ms: 963.0226 + type: 'test' + ... +# Subtest: Python candidates exclude comments and multiline strings and declare limited evidence +ok 181 - Python candidates exclude comments and multiline strings and declare limited evidence + --- + duration_ms: 907.1343 + type: 'test' + ... +# Subtest: indexes isolate project identity and root and evict bounded caches without sharing results +ok 182 - indexes isolate project identity and root and evict bounded caches without sharing results + --- + duration_ms: 1046.0998 + type: 'test' + ... +# Subtest: Git ignore, credential paths and links stay outside the index and no project files are executed +ok 183 - Git ignore, credential paths and links stay outside the index and no project files are executed + --- + duration_ms: 1568.6568 + type: 'test' + ... +# Subtest: malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable +ok 184 - malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable + --- + duration_ms: 772.9148 + type: 'test' + ... +# Subtest: index query rejects invalid limits/types and does not imply reference or alias resolution +ok 185 - index query rejects invalid limits/types and does not imply reference or alias resolution + --- + duration_ms: 1023.5806 + type: 'test' + ... +# Subtest: read-only engineering inspection disables configured Git clean filters and preserves index bytes +ok 186 - read-only engineering inspection disables configured Git clean filters and preserves index bytes + --- + duration_ms: 1889.7713 + type: 'test' + ... +# Subtest: Python multiline declarations retain candidate scope without interpreting expressions as declarations +ok 187 - Python multiline declarations retain candidate scope without interpreting expressions as declarations + --- + duration_ms: 1000.754 + type: 'test' + ... +# Subtest: TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit +ok 188 - TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit + --- + duration_ms: 817.1741 + type: 'test' + ... +# Subtest: actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart +ok 189 - actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart + --- + duration_ms: 2591.095 + type: 'test' + ... +# Subtest: actual HTTP request excludes archived, timed-out and foreign-project memories +ok 190 - actual HTTP request excludes archived, timed-out and foreign-project memories + --- + duration_ms: 3710.6073 + type: 'test' + ... +# Subtest: actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool +ok 191 - actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool + --- + duration_ms: 3061.3762 + type: 'test' + ... +# Subtest: incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots +ok 192 - incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots + --- + duration_ms: 2992.7698 + type: 'test' + ... +# Subtest: corrupt original artifact expires its memory and cannot reach an HTTP model request +ok 193 - corrupt original artifact expires its memory and cannot reach an HTTP model request + --- + duration_ms: 2167.9194 + type: 'test' + ... +# Subtest: memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values +ok 194 - memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values + --- + duration_ms: 3475.9379 + type: 'test' + ... +# Subtest: optional memory yields to the complete goal and original code evidence under the whole-request budget +ok 195 - optional memory yields to the complete goal and original code evidence under the whole-request budget + --- + duration_ms: 1346.2872 + type: 'test' + ... +# Subtest: changed sealed memory artifacts or binding fields fail verification while the original request remains immutable +ok 196 - changed sealed memory artifacts or binding fields fail verification while the original request remains immutable + --- + duration_ms: 1894.5469 + type: 'test' + ... +# Subtest: a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service +ok 197 - a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service + --- + duration_ms: 2104.9727 + type: 'test' + ... +# Subtest: an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure +ok 198 - an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure + --- + duration_ms: 1399.5365 + type: 'test' + ... +# Subtest: project memories persist across restart, keep source provenance, and are visible across tasks +ok 199 - project memories persist across restart, keep source provenance, and are visible across tasks + --- + duration_ms: 1395.2533 + type: 'test' + ... +# Subtest: source changes expire current project memories and keep the original evidence +ok 200 - source changes expire current project memories and keep the original evidence + --- + duration_ms: 1153.0528 + type: 'test' + ... +# Subtest: incomplete source scans mark current memories unverified without expiring or reusing them +ok 201 - incomplete source scans mark current memories unverified without expiring or reusing them + --- + duration_ms: 909.4686 + type: 'test' + ... +# Subtest: explicit file provenance is rechecked even when the inventory excludes that path +ok 202 - explicit file provenance is rechecked even when the inventory excludes that path + --- + duration_ms: 1063.0498 + type: 'test' + ... +# Subtest: execution snapshots do not expose project memories before their source scope is validated +ok 203 - execution snapshots do not expose project memories before their source scope is validated + --- + duration_ms: 1081.1017 + type: 'test' + ... +# Subtest: project memory records stay isolated and archive requires the owning session +ok 204 - project memory records stay isolated and archive requires the owning session + --- + duration_ms: 1153.76 + type: 'test' + ... +# Subtest: project memory HTTP API exposes read-only source status and explicit writes +ok 205 - project memory HTTP API exposes read-only source status and explicit writes + --- + duration_ms: 2047.7728 + type: 'test' + ... +# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart +ok 206 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart + --- + duration_ms: 7884.6894 + type: 'test' + ... +# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls +ok 207 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls + --- + duration_ms: 34604.0346 + type: 'test' + ... +# Subtest: Python static inspection does not import project code or probe a project interpreter before approval +ok 208 - Python static inspection does not import project code or probe a project interpreter before approval + --- + duration_ms: 1122.7629 + type: 'test' + ... +# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence +ok 209 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence + --- + duration_ms: 4346.6385 + type: 'test' + ... +# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names +ok 210 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names + --- + duration_ms: 2562.1242 + type: 'test' + ... +# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task +ok 211 - unittest empty, skipped, expected failure and class initialization errors never verify a task + --- + duration_ms: 6975.1512 + type: 'test' + ... +# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector +ok 212 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector + --- + duration_ms: 2931.5233 + type: 'test' + ... +# Subtest: compilation reads actual Python source bytes without executing top-level project code +ok 213 - compilation reads actual Python source bytes without executing top-level project code + --- + duration_ms: 2915.3915 + type: 'test' + ... +# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection +ok 214 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection + --- + duration_ms: 2410.8565 + type: 'test' + ... +# Subtest: changed project interpreters and forged Python plan bindings execute no check +ok 215 - changed project interpreters and forged Python plan bindings execute no check + --- + duration_ms: 1810.2653 + type: 'test' + ... +# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope +ok 216 - malformed TOML and invalid Python test paths are reported without expanding npm check scope + --- + duration_ms: 1214.2891 + type: 'test' + ... +# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled +ok 217 - stopping a real Python check terminates its child and keeps the completed result as cancelled + --- + duration_ms: 2051.3883 + type: 'test' + ... +# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes +ok 218 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes + --- + duration_ms: 13547.1838 + type: 'test' + ... +# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check +ok 219 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check + --- + duration_ms: 12019.0038 + type: 'test' + ... +# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass +ok 220 - a missing interpreter and repeated pytest item objects cannot create a false verification pass + --- + duration_ms: 2445.3409 + type: 'test' + ... +# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause +ok 221 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause + --- + duration_ms: 1.9016 + type: 'test' + ... +# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget +ok 222 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget + --- + duration_ms: 0.6641 + type: 'test' + ... +# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters +ok 223 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters + --- + duration_ms: 9.2997 + type: 'test' + ... +# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress +ok 224 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress + --- + duration_ms: 0.3519 + type: 'test' + ... +# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools +ok 225 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools + --- + duration_ms: 3789.6903 + type: 'test' + ... +# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly +ok 226 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly + --- + duration_ms: 4162.974 + type: 'test' + ... +# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay +ok 227 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay + --- + duration_ms: 4225.037 + type: 'test' + ... +# Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs +ok 228 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs + --- + duration_ms: 1898.0269 + type: 'test' + ... +# Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification +ok 229 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification + --- + duration_ms: 2240.8854 + type: 'test' + ... +# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget +ok 230 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget + --- + duration_ms: 1479.902 + type: 'test' + ... +# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments +ok 231 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments + --- + duration_ms: 4698.5437 + type: 'test' + ... +# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests +ok 232 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests + --- + duration_ms: 1156.0222 + type: 'test' + ... +# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window +ok 233 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window + --- + duration_ms: 2376.1239 + type: 'test' + ... +# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix +ok 234 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix + --- + duration_ms: 1849.5189 + type: 'test' + ... +# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived +ok 235 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived + --- + duration_ms: 1224.2783 + type: 'test' + ... +# Subtest: invalid orphan result is rejected before archive or network preparation +ok 236 - invalid orphan result is rejected before archive or network preparation + --- + duration_ms: 1055.2872 + type: 'test' + ... +# Subtest: invalid missing result is rejected before archive or network preparation +ok 237 - invalid missing result is rejected before archive or network preparation + --- + duration_ms: 900.3764 + type: 'test' + ... +# Subtest: invalid wrong result is rejected before archive or network preparation +ok 238 - invalid wrong result is rejected before archive or network preparation + --- + duration_ms: 922.0294 + type: 'test' + ... +# Subtest: invalid duplicate call is rejected before archive or network preparation +ok 239 - invalid duplicate call is rejected before archive or network preparation + --- + duration_ms: 1081.7648 + type: 'test' + ... +# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON +ok 240 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON + --- + duration_ms: 2536.5365 + type: 'test' + ... +# Subtest: changed or missing archived evidence stops reuse and is never silently recreated +ok 241 - changed or missing archived evidence stops reuse and is never silently recreated + --- + duration_ms: 1123.4314 + type: 'test' + ... +# Subtest: transaction failure prevents publishing a plan and any corresponding model request +ok 242 - transaction failure prevents publishing a plan and any corresponding model request + --- + duration_ms: 895.6091 + type: 'test' + ... +# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP +ok 243 - the Provider rejects body mutation after a sealed plan before calling HTTP + --- + duration_ms: 954.1491 + type: 'test' + ... +# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command +ok 244 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command + --- + duration_ms: 8610.1201 + type: 'test' + ... +# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request +ok 245 - a real process exit after plan persistence marks interruption and never issues an automatic model request + --- + duration_ms: 1680.4125 + type: 'test' + ... +# Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence +ok 246 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence + --- + duration_ms: 2659.7548 + type: 'test' + ... +# Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity +ok 247 - user research registration creates an owned Task without model requests and seals the exact artifact identity + --- + duration_ms: 1242.3846 + type: 'test' + ... +# Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload +ok 248 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload + --- + duration_ms: 2804.4875 + type: 'test' + ... +# Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses +ok 249 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses + --- + duration_ms: 3819.666 + type: 'test' + ... +# Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history +ok 250 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history + --- + duration_ms: 2813.5713 + type: 'test' + ... +# Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID +ok 251 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID + --- + duration_ms: 2325.0409 + type: 'test' + ... +# Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed +ok 252 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed + --- + duration_ms: 2383.0482 + type: 'test' + ... +# Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts +ok 253 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts + --- + duration_ms: 1199.9785 + type: 'test' + ... +# Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay +ok 254 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay + --- + duration_ms: 4533.1597 + type: 'test' + ... +# Subtest: file identity rejects directory and invalid formats without running a target +ok 255 - file identity rejects directory and invalid formats without running a target + --- + duration_ms: 902.9142 + type: 'test' + ... +# Subtest: a stop from the event loop interrupts immediate model replies before later tools +ok 256 - a stop from the event loop interrupts immediate model replies before later tools + --- + duration_ms: 2023.8874 + type: 'test' + ... +# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group +ok 257 - a stop after the first tool preserves a complete interrupted multi-call protocol group + --- + duration_ms: 2334.1241 + type: 'test' + ... +# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands +ok 258 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands + --- + duration_ms: 5901.164 + type: 'test' + ... +# Subtest: denial prevents command execution and produces a paired denied result +ok 259 - denial prevents command execution and produces a paired denied result + --- + duration_ms: 2429.9762 + type: 'test' + ... +# Subtest: stopping during approval interrupts pending calls without executing or replaying them +ok 260 - stopping during approval interrupts pending calls without executing or replaying them + --- + duration_ms: 2205.4401 + type: 'test' + ... +# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state +ok 261 - stopping a running fixture command terminates its own process tree and retains uncertain state + --- + duration_ms: 2814.1159 + type: 'test' + ... +# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment +ok 262 - command output decodes split UTF-8 and excludes the workbench key from child environment + --- + duration_ms: 1329.826 + type: 'test' + ... +# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors +ok 263 - model-list testing uses a tentative key without changing the saved connection and redacts service errors + --- + duration_ms: 6.7914 + type: 'test' + ... +# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities +ok 264 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities + --- + duration_ms: 3288.9875 + type: 'test' + ... +# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history +ok 265 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history + --- + duration_ms: 1712.2124 + type: 'test' + ... +# Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project +ok 266 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project + --- + duration_ms: 1220.9198 + type: 'test' + ... +# Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code +ok 267 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code + --- + duration_ms: 826.2571 + type: 'test' + ... +# Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing +ok 268 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing + --- + duration_ms: 2843.6098 + type: 'test' + ... +# Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay +ok 269 - source edits after a catalog request prevent the read and appear as changed on the next request without replay + --- + duration_ms: 3186.8899 + type: 'test' + ... +# Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project +ok 270 - disabled and foreign skills cannot be read by guessing their IDs from another project + --- + duration_ms: 3140.3719 + type: 'test' + ... +# Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code +ok 271 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code + --- + duration_ms: 1605.3174 + type: 'test' + ... +# Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact +ok 272 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact + --- + duration_ms: 4370.1667 + type: 'test' + ... +# Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network +ok 273 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network + --- + duration_ms: 1332.6559 + type: 'test' + ... +# Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs +ok 274 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs + --- + duration_ms: 2448.957 + type: 'test' + ... +# Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls +ok 275 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls + --- + duration_ms: 2462.4264 + type: 'test' + ... +# Subtest: JSON state keeps an atomic backup and preserves corrupt primary files +ok 276 - JSON state keeps an atomic backup and preserves corrupt primary files + --- + duration_ms: 1050.7705 + type: 'test' + ... +# Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results +ok 277 - tool-pair recovery fills missing results and drops orphan or duplicate results + --- + duration_ms: 0.4458 + type: 'test' + ... +# Subtest: restart pauses unfinished work, retains proposals and never replays a command +ok 278 - restart pauses unfinished work, retains proposals and never replays a command + --- + duration_ms: 1275.7811 + type: 'test' + ... +# Subtest: public snapshots carry increasing revisions without the private provider transcript or config key +ok 279 - public snapshots carry increasing revisions without the private provider transcript or config key + --- + duration_ms: 1069.5055 + type: 'test' + ... +# Subtest: a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay +ok 280 - a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay + --- + duration_ms: 4101.3868 + type: 'test' + ... +# Subtest: checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact +ok 281 - checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact + --- + duration_ms: 3361.5175 + type: 'test' + ... +# Subtest: unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work +ok 282 - unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work + --- + duration_ms: 3420.9435 + type: 'test' + ... +# Subtest: checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt +ok 283 - checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt + --- + duration_ms: 3256.5644 + type: 'test' + ... +# Subtest: checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes +ok 284 - checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes + --- + duration_ms: 3134.9762 + type: 'test' + ... +# Subtest: Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state +ok 285 - Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state + --- + duration_ms: 3112.6985 + type: 'test' + ... +# Subtest: checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay +ok 286 - checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay + --- + duration_ms: 2605.3433 + type: 'test' + ... +# Subtest: incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements +ok 287 - incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements + --- + duration_ms: 2709.7417 + type: 'test' + ... +# Subtest: oversized recovery evidence is refused before reading or publishing the checkpoint +ok 288 - oversized recovery evidence is refused before reading or publishing the checkpoint + --- + duration_ms: 2013.3852 + type: 'test' + ... +# Subtest: compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation +ok 289 - compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation + --- + duration_ms: 4890.5566 + type: 'test' + ... +# Subtest: actual process exit before checkpoint commit retains only durable records without replay +ok 290 - actual process exit before checkpoint commit retains only durable records without replay + --- + duration_ms: 2104.4812 + type: 'test' + ... +# Subtest: actual process exit after checkpoint commit retains only durable records without replay +ok 291 - actual process exit after checkpoint commit retains only durable records without replay + --- + duration_ms: 2520.1109 + type: 'test' + ... +# Subtest: task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart +ok 292 - task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart + --- + duration_ms: 2934.1421 + type: 'test' + ... +# Subtest: concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan +ok 293 - concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan + --- + duration_ms: 2580.145 + type: 'test' + ... +# Subtest: a real escaped long-file tool message keeps its proof identity within a tight request budget +ok 294 - a real escaped long-file tool message keeps its proof identity within a tight request budget + --- + duration_ms: 1546.8953 + type: 'test' + ... +# Subtest: task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies +ok 295 - task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies + --- + duration_ms: 0.6449 + type: 'test' + ... +# Subtest: sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools +ok 296 - sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools + --- + duration_ms: 1223.8935 + type: 'test' + ... +# Subtest: proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes +ok 297 - proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes + --- + duration_ms: 2070.5398 + type: 'test' + ... +# Subtest: new user requirements invalidate current proofs and reseal the same original operations in a new revision +ok 298 - new user requirements invalidate current proofs and reseal the same original operations in a new revision + --- + duration_ms: 2249.0466 + type: 'test' + ... +# Subtest: applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits +ok 299 - applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits + --- + duration_ms: 2435.5224 + type: 'test' + ... +# Subtest: actual npm checks are verified by original counted logs and current source, with failure history retained +ok 300 - actual npm checks are verified by original counted logs and current source, with failure history retained + --- + duration_ms: 7309.9074 + type: 'test' + ... +# Subtest: real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds +ok 301 - real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds + --- + duration_ms: 12313.9133 + type: 'test' + ... +# Subtest: Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit +ok 302 - Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit + --- + duration_ms: 11099.7095 + type: 'test' + ... +# Subtest: the runtime supplies owned read IDs and completes a plan only after original step evidence verification +ok 303 - the runtime supplies owned read IDs and completes a plan only after original step evidence verification + --- + duration_ms: 3423.7768 + type: 'test' + ... +# Subtest: premature model completion pauses the original Task and resume preserves the existing plan without replay +ok 304 - premature model completion pauses the original Task and resume preserves the existing plan without replay + --- + duration_ms: 4238.3437 + type: 'test' + ... +# Subtest: plan operations participate in project activity and orderly shutdown +ok 305 - plan operations participate in project activity and orderly shutdown + --- + duration_ms: 1527.9206 + type: 'test' + ... +# Subtest: actual process exit before plan save restores only committed plan evidence without replay +ok 306 - actual process exit before plan save restores only committed plan evidence without replay + --- + duration_ms: 1649.5483 + type: 'test' + ... +# Subtest: actual process exit after plan save restores only committed plan evidence without replay +ok 307 - actual process exit after plan save restores only committed plan evidence without replay + --- + duration_ms: 1406.5664 + type: 'test' + ... +# Subtest: actual process exit before proof save restores only committed plan evidence without replay +ok 308 - actual process exit before proof save restores only committed plan evidence without replay + --- + duration_ms: 1290.2134 + type: 'test' + ... +# Subtest: actual process exit after proof save restores only committed plan evidence without replay +ok 309 - actual process exit after proof save restores only committed plan evidence without replay + --- + duration_ms: 2078.6066 + type: 'test' + ... +# Subtest: the latest oversized session result reaches the next request together with already read source modules +ok 310 - the latest oversized session result reaches the next request together with already read source modules + --- + duration_ms: 2564.7421 + type: 'test' + ... +# Subtest: every call in a large latest group keeps its actual outcome, including denied and unknown results +ok 311 - every call in a large latest group keeps its actual outcome, including denied and unknown results + --- + duration_ms: 1526.5355 + type: 'test' + ... +# Subtest: a small complete latest tool group is sent once and needs no duplicate feedback view +ok 312 - a small complete latest tool group is sent once and needs no duplicate feedback view + --- + duration_ms: 1076.5473 + type: 'test' + ... +# Subtest: real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing +ok 313 - real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing + --- + duration_ms: 2689.2308 + type: 'test' + ... +# Subtest: a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes +ok 314 - a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes + --- + duration_ms: 4315.4548 + type: 'test' + ... +# Subtest: failed upgrade restores the original artifact object, provider and request handler +ok 315 - failed upgrade restores the original artifact object, provider and request handler + --- + duration_ms: 1107.0775 + type: 'test' + ... +# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider +ok 316 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider + --- + duration_ms: 2777.7699 + type: 'test' + ... +# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection +ok 317 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection + --- + duration_ms: 12714.7487 + type: 'test' + ... +# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit +ok 318 - small code and actual failed command stay visible when their original multi-tool group cannot fit + --- + duration_ms: 1770.9447 + type: 'test' + ... +# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes +ok 319 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes + --- + duration_ms: 2567.3317 + type: 'test' + ... +# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence +ok 320 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence + --- + duration_ms: 2180.4681 + type: 'test' + ... +# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence +ok 321 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence + --- + duration_ms: 1360.8079 + type: 'test' + ... +# Subtest: a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid +ok 322 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid + --- + duration_ms: 5213.1712 + type: 'test' + ... +# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries +ok 323 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries + --- + duration_ms: 4.3615 + type: 'test' + ... +# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening +ok 324 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening + --- + duration_ms: 12644.3205 + type: 'test' + ... +# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request +ok 325 - actual HTTP file pagination advances over a long file with each returned page visible in the next request + --- + duration_ms: 3721.7562 + type: 'test' + ... +# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements +ok 326 - later mixed history pages cannot displace the actual module sources and complete requirements + --- + duration_ms: 7888.0405 + type: 'test' + ... +# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation +ok 327 - a later narrow page of the same file revision cannot evict the wider actual observation + --- + duration_ms: 3859.7826 + type: 'test' + ... +# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper +ok 328 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper + --- + duration_ms: 1599.5233 + type: 'test' + ... +# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view +ok 329 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view + --- + duration_ms: 1584.47 + type: 'test' + ... +# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes +ok 330 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes + --- + duration_ms: 12216.5066 + type: 'test' + ... +# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files +ok 331 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files + --- + duration_ms: 6812.085 + type: 'test' + ... +# Subtest: isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report +ok 332 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report + --- + duration_ms: 32133.4553 + type: 'test' + ... +# warning: in the working copy of 'src/空 格.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion +ok 333 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion + --- + duration_ms: 5602.1928 + type: 'test' + ... +# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation +ok 334 - an ignored external file at checkout is observed and never accepted as pristine creation + --- + duration_ms: 4859.6059 + type: 'test' + ... +# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution +ok 335 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution + --- + duration_ms: 4684.1835 + type: 'test' + ... +# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions +ok 336 - workspace preparation refuses known shared-repository activity and preserves archived child sessions + --- + duration_ms: 4723.1375 + type: 'test' + ... +# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name +ok 337 - compact checkout identities create in deep Unicode source directories while retaining the human branch name + --- + duration_ms: 5123.6799 + type: 'test' + ... +# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes +ok 338 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes + --- + duration_ms: 2825.3259 + type: 'test' + ... +# Subtest: a pending source snapshot participates in shutdown and completes before storage can close +ok 339 - a pending source snapshot participates in shutdown and completes before storage can close + --- + duration_ms: 1816.4677 + type: 'test' + ... +# Subtest: source configuration values stay private and a configuration change invalidates a saved review +ok 340 - source configuration values stay private and a configuration change invalidates a saved review + --- + duration_ms: 2390.9579 + type: 'test' + ... +# Subtest: workspace review rejects excluded dependency before any checkout +ok 341 - workspace review rejects excluded dependency before any checkout + --- + duration_ms: 2386.4117 + type: 'test' + ... +# Subtest: workspace review rejects large committed blob before any checkout +ok 342 - workspace review rejects large committed blob before any checkout + --- + duration_ms: 2196.2944 + type: 'test' + ... +# Subtest: workspace review rejects case collision before any checkout +ok 343 - workspace review rejects case collision before any checkout + --- + duration_ms: 2602.1515 + type: 'test' + ... +# Subtest: workspace review rejects committed symbolic link before any checkout +ok 344 - workspace review rejects committed symbolic link before any checkout + --- + duration_ms: 2400.4305 + type: 'test' + ... +# Subtest: workspace review rejects external config include before any checkout +ok 345 - workspace review rejects external config include before any checkout + --- + duration_ms: 2251.0089 + type: 'test' + ... +# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay +ok 346 - actual process exit at workspace intent preserves source and reconciles without creation replay + --- + duration_ms: 4623.3182 + type: 'test' + ... +# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay +ok 347 - actual process exit at workspace git_started preserves source and reconciles without creation replay + --- + duration_ms: 5633.4309 + type: 'test' + ... +# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay +ok 348 - actual process exit at workspace git_finished preserves source and reconciles without creation replay + --- + duration_ms: 5880.8224 + type: 'test' + ... +# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay +ok 349 - actual process exit at workspace verifying preserves source and reconciles without creation replay + --- + duration_ms: 5337.9598 + type: 'test' + ... +# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay +ok 350 - actual process exit at workspace registering preserves source and reconciles without creation replay + --- + duration_ms: 6118.0963 + type: 'test' + ... +# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay +ok 351 - actual process exit at workspace project_registered preserves source and reconciles without creation replay + --- + duration_ms: 7072.9183 + type: 'test' + ... +# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay +ok 352 - actual process exit at workspace session_registered preserves source and reconciles without creation replay + --- + duration_ms: 6898.8993 + type: 'test' + ... +# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay +ok 353 - actual process exit at workspace ready preserves source and reconciles without creation replay + --- + duration_ms: 4608.4723 + type: 'test' + ... +# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity +ok 354 - outside changes at project registration remain unknown and preserve the already registered child identity + --- + duration_ms: 4614.0137 + type: 'test' + ... +# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity +ok 355 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity + --- + duration_ms: 5017.6439 + type: 'test' + ... +# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation +ok 356 - stale review, branch/path collisions and forged ownership do not run worktree creation + --- + duration_ms: 3524.2307 + type: 'test' + ... +# Subtest: workspace project verification is read-only and rejects physical Git identity changes +ok 357 - workspace project verification is read-only and rejects physical Git identity changes + --- + duration_ms: 4154.872 + type: 'test' + ... +1..357 +# tests 357 +# suites 0 +# pass 357 +# fail 0 +# cancelled 0 +# skipped 0 +# todo 0 +# duration_ms 640666.0334 diff --git a/docs/model-center-git-inputs.json b/docs/model-center-git-inputs.json new file mode 100644 index 00000000..b09e8580 --- /dev/null +++ b/docs/model-center-git-inputs.json @@ -0,0 +1,33 @@ +{ + "success": true, + "at": "2026-10-30T12:37:00.398Z", + "commit": "3f6797b8eeef261193fe1c781cb184f20a478629", + "inputFiles": 213, + "exactBytes": 209, + "normalized": [ + { + "path": "scripts/verify-ui.mjs", + "sourceSha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6", + "gitBlobSha256": "cd57dd67aada66f667a4e62b7a8f76a79d3c09acd7ba7c658b89e6d38dc6be9f", + "difference": "CRLF to LF only" + }, + { + "path": "src/client/SkillCenter.tsx", + "sourceSha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10", + "gitBlobSha256": "de7a4426aef468a73a9522da9883592ab0cc29a1f2b3786b764cd51a304347b2", + "difference": "CRLF to LF only" + }, + { + "path": "src/client/styles.css", + "sourceSha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218", + "gitBlobSha256": "734193e1a166024f1418c021bbd56255412d49268386c2c688e5766ef118e438", + "difference": "CRLF to LF only" + }, + { + "path": "tests/skills.test.mjs", + "sourceSha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6", + "gitBlobSha256": "977e987ccdeab5bf07fd3dd1788d8ba866a3dc3715c9dd947982a9abfbab7e06", + "difference": "CRLF to LF only" + } + ] +} diff --git a/docs/model-center-release-identity.json b/docs/model-center-release-identity.json new file mode 100644 index 00000000..496734bb --- /dev/null +++ b/docs/model-center-release-identity.json @@ -0,0 +1,190 @@ +{ + "success": true, + "version": "1.12.0", + "releaseId": "20261030124454517", + "sealedAt": "2026-10-30T12:52:04.679Z", + "codeCommit": "3f6797b8eeef261193fe1c781cb184f20a478629", + "evidenceCommitBase": "3f6797b8eeef261193fe1c781cb184f20a478629", + "release": { + "portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-source-20261030124454517", + "portable": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517.zip", + "bytes": 90583674, + "sha256": "3a00a375a3ee191e74b9a09d723b4c09ecce1b9f23b6466a4d6be9dcf17c5449" + }, + "source": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-source-20261030124454517.zip", + "bytes": 51066998, + "sha256": "853d3ef196d9df8db3c1ec35e3abb09469ad74cbae54176e6babf49e47c74c43" + }, + "nodeVersion": "v24.22.1", + "reaRuntime": { + "version": "6.8.0", + "protocolVersion": "2025-03-26", + "packages": 149, + "files": 8413, + "bytes": 142395402, + "lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e" + }, + "portableFiles": 11061, + "licenseTexts": 76, + "browserRuntime": { + "playwrightVersion": "1.64.1", + "packages": [ + { + "name": "playwright", + "version": "1.64.1", + "files": 60 + }, + { + "name": "playwright-core", + "version": "1.64.1", + "files": 115 + } + ] + } + }, + "sourceInputs": 213, + "gitExactInputBytes": 209, + "gitLfOnlyInputs": [ + { + "path": "scripts/verify-ui.mjs", + "sourceSha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6", + "gitBlobSha256": "cd57dd67aada66f667a4e62b7a8f76a79d3c09acd7ba7c658b89e6d38dc6be9f", + "difference": "CRLF to LF only" + }, + { + "path": "src/client/SkillCenter.tsx", + "sourceSha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10", + "gitBlobSha256": "de7a4426aef468a73a9522da9883592ab0cc29a1f2b3786b764cd51a304347b2", + "difference": "CRLF to LF only" + }, + { + "path": "src/client/styles.css", + "sourceSha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218", + "gitBlobSha256": "734193e1a166024f1418c021bbd56255412d49268386c2c688e5766ef118e438", + "difference": "CRLF to LF only" + }, + { + "path": "tests/skills.test.mjs", + "sourceSha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6", + "gitBlobSha256": "977e987ccdeab5bf07fd3dd1788d8ba866a3dc3715c9dd947982a9abfbab7e06", + "difference": "CRLF to LF only" + } + ], + "buildMatchedFiles": 6, + "testStatistics": { + "tests": 357, + "pass": 357, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "logsVerified": 6, + "postSmokeDatabaseUnchanged": true, + "originals": [ + { + "path": ".qa/archives-validation.json", + "bytes": 928, + "sha256": "5d5702e40a89090c983aac993e6ab8872eaac13f28ff523aa7254869f5cf666a" + }, + { + "path": ".qa/source-package-validation.json", + "bytes": 41468, + "sha256": "b984831f5e7120a08c4955a82339987baa3a810a015d70d5927ce4d13a33de61" + }, + { + "path": ".qa/release-validation.json", + "bytes": 5053, + "sha256": "c7a427d69f54f2ddbdec75b6af0d3f2af012690c9b21ea35e076009a1cc2f45e" + }, + { + "path": ".qa/model-center-deployed-ui-validation.json", + "bytes": 3350, + "sha256": "61e815fb34a7a671fb688a6cfb433f81c7e4cfd5a3d94915cc0f846dd7ddd5e5" + }, + { + "path": ".qa/model-center-git-inputs.json", + "bytes": 1267, + "sha256": "6fbb0f13eda2a32d582f53fdcd0bf7e307c51dd712887ed9a0568cecbb0c2720" + }, + { + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\tests.tap", + "bytes": 96809, + "sha256": "662bf1708cb8b3f7781de47f1fda62f6879a8f12967184ee5213adcd8f849d86" + } + ], + "reports": [ + { + "path": "docs/model-center-archives-validation.json", + "bytes": 905, + "sha256": "8182adcae4c03fee845017a3e0726262a968c5a08720e22b782d2b2ce111ecb4" + }, + { + "path": "docs/model-center-source-package-validation.json", + "bytes": 41468, + "sha256": "b984831f5e7120a08c4955a82339987baa3a810a015d70d5927ce4d13a33de61" + }, + { + "path": "docs/model-center-release-validation.json", + "bytes": 5053, + "sha256": "c7a427d69f54f2ddbdec75b6af0d3f2af012690c9b21ea35e076009a1cc2f45e" + }, + { + "path": "docs/model-center-deployed-ui-validation.json", + "bytes": 3350, + "sha256": "61e815fb34a7a671fb688a6cfb433f81c7e4cfd5a3d94915cc0f846dd7ddd5e5" + }, + { + "path": "docs/model-center-git-inputs.json", + "bytes": 1267, + "sha256": "6fbb0f13eda2a32d582f53fdcd0bf7e307c51dd712887ed9a0568cecbb0c2720" + }, + { + "path": "docs/model-center-final-package-tests.tap", + "bytes": 96809, + "sha256": "662bf1708cb8b3f7781de47f1fda62f6879a8f12967184ee5213adcd8f849d86" + }, + { + "path": "docs/model-center-upgrade-live-validation.json", + "bytes": 12102, + "sha256": "6e3eed65976c16e34bd5d3be56c97f89ec0eae53edaac7c47c2c94bb8dcac410" + }, + { + "path": "docs/model-center-all-ui-validation.json", + "bytes": 5289, + "sha256": "6fa5a3fe8af8172a29368760a24f40ea6816e6d4f8dd90201d55fcd18eab79bf" + }, + { + "path": "docs/model-center-header-ui-validation.json", + "bytes": 780, + "sha256": "85a95f8246666d75111f3f50283b932e21d966e9accd50f3aab431f8160c2470" + }, + { + "path": "docs/model-center-final-mcp-ui-validation.json", + "bytes": 952, + "sha256": "b4c3509d8f47dbfa51882a2f3f8ed75f1b29086590f85cb1f0cd8fd2b47ee946" + }, + { + "path": "docs/model-center-final-mcp-recovery-ui-validation.json", + "bytes": 482, + "sha256": "ef83aff35909d50a22dd6f28bf80e26621ef961a23a7deea45fda51877522972" + }, + { + "path": "docs/model-center-source-environment-failure.json", + "bytes": 37949, + "sha256": "e9f4b65c8d1b5730b5fae4d9e5e602b9071c5b9fa025657172b8e91c151502d1" + }, + { + "path": "docs/model-center-mcp-specialists.tap", + "bytes": 5738, + "sha256": "8a82b954d17fa5fb45d2431955f5416cf74ae8160c284218b0b2228f7ad2b738" + } + ], + "realModelAcceptance": { + "status": "deferred_by_user", + "requests": 0 + } +} diff --git a/docs/model-center-release-validation.json b/docs/model-center-release-validation.json new file mode 100644 index 00000000..ebb8a13a --- /dev/null +++ b/docs/model-center-release-validation.json @@ -0,0 +1,139 @@ +{ + "success": true, + "date": "2026-10-30T12:46:23.011Z", + "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "version": "1.12.0", + "nodeVersion": "v24.22.1", + "verifiedFiles": 11061, + "url": "http://127.0.0.1:56114", + "reusedPid": 49532, + "checks": { + "jobId": "62e520f1-a38d-4f1b-a52e-a19c185d873f", + "status": "passed", + "tests": { + "total": 4, + "passed": 4, + "failed": 0, + "cancelled": 0, + "skipped": 0 + } + }, + "actualRea": [ + { + "operation": "javascript", + "jobId": "62c37ddb-079b-4cfd-bf3e-409698e7137f", + "evidenceId": "ev_a3eac1990720fba4f4deba604ad0b52a59a8651ba9bcbda1ad9ae2435d4c1bc0", + "targetSha256": "ea3344eef6dee240680a079188f1222f37bc73452902a3915d93be509c2f40e7", + "bundleSha256": "8fc7eb41278aeebbb2fea075aa3dd672a7ccfbee6e324a773a3fdce04667964a", + "rootExited": true, + "reusedJobId": "9eb7461d-b66d-4f89-978d-00edfd7979e5" + }, + { + "operation": "pe-imports", + "jobId": "39104f6b-d8b8-4311-a91f-08b29a5724b1", + "evidenceId": "ev_481e1f135b2147a88675944ccfab5432e50643b5669834af2b873e3094d11293", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "bundleSha256": "16d765c42e84aabfbe2859b6dc4c3762ef6215c3504242809d10cda94a279ff1", + "rootExited": true, + "reusedJobId": "939c3bcc-8553-49cc-b4d8-632739207a7f" + }, + { + "operation": "pe-resources", + "jobId": "92861d38-1813-431f-ae1a-ed01671eb56e", + "evidenceId": "ev_33384172dae6ff6aa7ae0d769197cb03a5aa5adcfc8e4b1e920093c6ce7ee4dc", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "bundleSha256": "cc2eec5f9143584eb6ddc4bfc41cff443f5630e33e795487b7be769eb41eb39f", + "rootExited": true, + "reusedJobId": "c8b2ceb9-02e9-46b9-8d1e-2eafe8742d28" + } + ], + "actualEngine": { + "packageVersion": "0.2.1-rc.2", + "profile": "sdk-minimal", + "installationSha256": "31882d45884b2dba4e19c2aa301d1d5a74e8254be6888946c244bcaeb6664308", + "reportSha256": "3583e2b5f90c5007cffbcc7b701fc41d468931e1a247a77d581e34b3571c7190", + "rootExited": true, + "modelRequests": 0, + "nativeMethods": [ + "initialize", + "session/working-directory/get", + "session/wait", + "session/resume", + "session/cancel", + "shutdown" + ], + "node": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517\\runtime\\node.exe", + "bytes": 93915464, + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5", + "version": "24.22.1" + } + }, + "actualBrowser": { + "success": true, + "installation": { + "status": "available", + "engine": "Microsoft Edge", + "playwrightVersion": "1.64.1" + }, + "results": [ + { + "jobId": "a0d36a9b-50e2-42db-955b-50e2b8a7a7ee", + "taskId": "33ab1d5c-1b37-45c0-a0ec-c126e53f5b61", + "viewport": { + "width": 1280, + "height": 900 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "93ed42477263dd274095760cc5f3008dbd4a61afa09f958a07e5d409bb801906", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54", + "browserExited": true, + "reusedOriginalJob": true + }, + { + "jobId": "49536414-7cd7-4404-af45-b78254085b8b", + "taskId": "33ab1d5c-1b37-45c0-a0ec-c126e53f5b61", + "viewport": { + "width": 390, + "height": 844 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "ed41889d3df7e3edae1b5a1d8eb383ef24a7b12b87da157b25bae5a59386e28c", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f", + "browserExited": true, + "reusedOriginalJob": true + } + ], + "modelRequests": 0, + "scope": "Actual API, locked browser runtime, two isolated Edge processes, CSS interactions, original DOM and PNG bytes. The task is created through the offline demonstration; no remote model is used." + }, + "steps": [ + "manifest hashes", + "bundled Node launch", + "same-service reuse", + "packaged example and static page", + "explicit command consent", + "actual bundled Node version", + "actual bundled npm check without system Node/npm", + "check log artifact", + "contained REA installation and Node identity", + "actual ASAR/imports/resources", + "original Bundle and target hash binding", + "verified reuse without producer replay", + "report availability", + "graceful stop" + ], + "realModel": false +} \ No newline at end of file diff --git a/docs/model-center-source-package-validation.json b/docs/model-center-source-package-validation.json new file mode 100644 index 00000000..1deff574 --- /dev/null +++ b/docs/model-center-source-package-validation.json @@ -0,0 +1,1221 @@ +{ + "success": true, + "version": "1.12.0", + "testedAt": "2026-10-30T12:44:20.852Z", + "sourceRoot": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626", + "directory": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2", + "nodeVersion": "v24.22.1", + "python": { + "version": "3.10.11", + "pytest": "8.4.2", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\dev-task-plans\\.qa\\python-3.10\\Scripts\\python.exe" + }, + "offlineInstall": true, + "inputs": [ + { + "path": "index.html", + "bytes": 411, + "sha256": "893c264c5c1293d6af54a6ca65280cf637b5afffee3cd2156ff88e4a44c370c5" + }, + { + "path": "package-lock.json", + "bytes": 79507, + "sha256": "33afcdd6146d79178fd6b05e2d251e2d0ee5e25453f5d8b8c5a17fecbf45f065" + }, + { + "path": "package.json", + "bytes": 2005, + "sha256": "e815399e52b9b7b80a8681027d6501deccd2cd5b6b392698b98e6b75feb3cbe9" + }, + { + "path": "scripts/Start-Workbench.ps1", + "bytes": 3211, + "sha256": "36d8ab194974369afa47ff717e60cad763432ee1f1abb6ccc4e6b1b6b11da253" + }, + { + "path": "scripts/Stop-Workbench.ps1", + "bytes": 980, + "sha256": "f6d12d32006c17fcb20192a73b762592f900ddfcda0cabda6f202e37405d1331" + }, + { + "path": "scripts/build-server.mjs", + "bytes": 553, + "sha256": "67e4ae3f5bd9214bfbf2596e3fb9c2af465ec7364293d37da07c7810c789d15e" + }, + { + "path": "scripts/bundle-browser.mjs", + "bytes": 2629, + "sha256": "c9bd500e469d5aa60a69a35d5863a5f2d56b336cbd8f2d5268b5e05f0687d23b" + }, + { + "path": "scripts/bundle-rea.mjs", + "bytes": 5700, + "sha256": "90fbc4af57eb2e92d4d92de5be5ac26eb8c99f132efdafe8f3e133ec1db7ffbe" + }, + { + "path": "scripts/engine-fixtures.mjs", + "bytes": 5241, + "sha256": "8ca536f1a6f4edb6a03b0508e6f175879eeb39a835149f4f6c8ba806e07266e8" + }, + { + "path": "scripts/inspect-ui.mjs", + "bytes": 1187, + "sha256": "81a6e6f96aae44b60c9f382e53d54f673868b3705a4c3eb1d0107c11ff790b88" + }, + { + "path": "scripts/live-react-client.mjs", + "bytes": 4278, + "sha256": "6c01ae7b2be7e2b82831c718e72bebe353bab864f97373ed95c5d478ac28b32b" + }, + { + "path": "scripts/package.mjs", + "bytes": 9925, + "sha256": "22ffb0a5dc23d654ac4bf6e9d261fc6dd034d4f17a402b5a5356bc08f24365b2" + }, + { + "path": "scripts/python-check-runner.py", + "bytes": 9553, + "sha256": "17bd6fd64ad93b8f806e0f5d325e75fd4534c065f4fcb597ad45fb9152caf657" + }, + { + "path": "scripts/qa-evidence.mjs", + "bytes": 648, + "sha256": "e4f16e7d70260b2d07a9e518f00df064b916d4670b85ced04097d0b7921d087f" + }, + { + "path": "scripts/qa-python-requirements.txt", + "bytes": 14, + "sha256": "bf4dc0555928a3facf67b3370001388d4b65e69a071c339f8b201310bde4486a" + }, + { + "path": "scripts/research-fixtures.mjs", + "bytes": 3712, + "sha256": "ba1f5644045ddba894a787cc4d9fa85c9a7e00730e3ea2e9b18d594a43498a8c" + }, + { + "path": "scripts/tune-styles.mjs", + "bytes": 1369, + "sha256": "8909eaaff060753745d7d6945377689ca531d784390cdd7d84acf97551d7b1c0" + }, + { + "path": "scripts/upgrade-running.mjs", + "bytes": 12294, + "sha256": "a60d3783d1bcdd29f8e6857626888c96dc8c5280b38eb3a79d8a6ff3bb683dc1" + }, + { + "path": "scripts/verify-all-ui.mjs", + "bytes": 8282, + "sha256": "f123d8816e4f0040206a124fd0cf71ae2603a812e1d52b0d2cada4898a0c0e0d" + }, + { + "path": "scripts/verify-archives.py", + "bytes": 4206, + "sha256": "05bbe3f23d422f6a1e0f90076209bf36dfbe8adb27c405290f391822f3441b5c" + }, + { + "path": "scripts/verify-browser-ui.mjs", + "bytes": 14638, + "sha256": "c4a99fcf45fc0e1d39024937d481119965349c486422a14b3084264539c4157a" + }, + { + "path": "scripts/verify-browser.mjs", + "bytes": 10768, + "sha256": "8ccbe961ce26363079fc8ea30559e57ee78f88926b438e1004d5b3528beacb76" + }, + { + "path": "scripts/verify-change-sets-ui.mjs", + "bytes": 15962, + "sha256": "c6236c0d337a81a34ae27f8171a6b782658d814d5766a2a04ab1a3e2114ea113" + }, + { + "path": "scripts/verify-context-ui.mjs", + "bytes": 18435, + "sha256": "790f75f42c32432439eccd0311d9dcf3d521735afff36ffc1c9c3b204295fe9b" + }, + { + "path": "scripts/verify-delivery-ui.mjs", + "bytes": 22757, + "sha256": "eae0e07b901f0a3da4d595bbc8e214e032d7da45d7d8ea033c034ad45dc34c3d" + }, + { + "path": "scripts/verify-diagnostics-ui.mjs", + "bytes": 15521, + "sha256": "476d284fc1b8c086f8d7f44013a44d200ec5b5df2d8b58e52caaedd46e569ab0" + }, + { + "path": "scripts/verify-engines-ui.mjs", + "bytes": 15763, + "sha256": "b1ae2b6274d2584ba190faa1818f53f1bc775430f9140cb68ca77d9952756f2e" + }, + { + "path": "scripts/verify-engines.mjs", + "bytes": 4748, + "sha256": "c1f0d9949230527cc4933a90e64a68053ef8bc040b14384119998a5a2f223b4d" + }, + { + "path": "scripts/verify-execution-ui.mjs", + "bytes": 15157, + "sha256": "f78149dda36baea05cd1f7c36dab0301e3c1c94df70cefb1bb12f51313d383be" + }, + { + "path": "scripts/verify-index-ui.mjs", + "bytes": 13822, + "sha256": "04f1b925aff59f06583325d18e69a6160bfae98e87254b3ee2e6fd0dabccdbfb" + }, + { + "path": "scripts/verify-live-browser.mjs", + "bytes": 11765, + "sha256": "b1bb7e3ac8ac6c1abec0c90b996bbde0a335e87acb956a05918fc31245ee0b33" + }, + { + "path": "scripts/verify-live-delivery.mjs", + "bytes": 24628, + "sha256": "4c45acd05841ddf2a6e0a04ee1d0a9f4c003e34d794318bfe3892a29d474117e" + }, + { + "path": "scripts/verify-live-engineering.mjs", + "bytes": 18301, + "sha256": "2e42a1347069c56beb4022627f760a2088751d4f0829606b49d2edd0833d934c" + }, + { + "path": "scripts/verify-live-model.mjs", + "bytes": 5607, + "sha256": "848495e2488125eb5e79c9d8b121025f9f740551535dc8529b415b4246da455b" + }, + { + "path": "scripts/verify-live-session.mjs", + "bytes": 6727, + "sha256": "f71f22f2355d499afa501f9ba37a04f8b8cf5d404fdfe95b65cc1d324775ac9b" + }, + { + "path": "scripts/verify-live-task-plans.mjs", + "bytes": 13181, + "sha256": "577fc325a6b13f7cd21fb8b1ab96f8940afe94e65bffa74046b47af572b1c510" + }, + { + "path": "scripts/verify-mcp-recovery-ui.mjs", + "bytes": 6336, + "sha256": "b11e321e0d92efb57d8e76b612c053e6a0229f0f3641721c606a28a61fe12a18" + }, + { + "path": "scripts/verify-mcp-ui.mjs", + "bytes": 9714, + "sha256": "c3c93d4ea8109dce1bfb4c91bf3a8b11dc2c7bbee3986c55ed2a4fcde0446d34" + }, + { + "path": "scripts/verify-model-center-ui.mjs", + "bytes": 8760, + "sha256": "d4c13f9e328172f973143f7333cdc4f5627c7d33f188f59a6588c1cbd1f8745a" + }, + { + "path": "scripts/verify-project-memory-ui.mjs", + "bytes": 8405, + "sha256": "b197345800d805ca3e52094ea660f8eb8d4d90defde2c49dc1a17a4b97270bdb" + }, + { + "path": "scripts/verify-python-ui.mjs", + "bytes": 11489, + "sha256": "676e4222a25ca68ed5bbb6661b9f7ec5eac4abaa9de70d9a5eb07a3429ba2457" + }, + { + "path": "scripts/verify-rea.mjs", + "bytes": 5166, + "sha256": "cdca5f73ee9f5b2b1fc4cd58ce98a7c0fcd551164879ae3192d67edd8e69491d" + }, + { + "path": "scripts/verify-react-delivery.mjs", + "bytes": 13013, + "sha256": "51a6c000d6ff148204d500b8505e2f7589f55a68947b9eabd4097ed0e477d118" + }, + { + "path": "scripts/verify-release.mjs", + "bytes": 14262, + "sha256": "0601615dd3c08443e0e0fad46914a1cace99de5c21ee21f9be241cedbbdbd8ef" + }, + { + "path": "scripts/verify-research-ui.mjs", + "bytes": 18573, + "sha256": "0844a6d22e843123afc0d133302096a08c35b9cb7d9dd3bafacf85a2a50b260d" + }, + { + "path": "scripts/verify-skills-ui.mjs", + "bytes": 7956, + "sha256": "2139b2caa764c17752edb13f8cc43e0d4643e9c0d4d47c34e6c95b0374efd974" + }, + { + "path": "scripts/verify-source-package.mjs", + "bytes": 9758, + "sha256": "0fac0ebf633b25e0e9409653d1b696b9ad195a9a5d207b61f4d1400c1dd33887" + }, + { + "path": "scripts/verify-task-checkpoints-ui.mjs", + "bytes": 6176, + "sha256": "2af7d9abf21b2a13a618ed080e324f61c21a42a386d09c5bd62c7bdf70ec5de2" + }, + { + "path": "scripts/verify-task-plans-ui.mjs", + "bytes": 16078, + "sha256": "7a0d5a0c5c59040bd203c65453a0ff9c6282e9bd46c14b573a67a59a8920a5fa" + }, + { + "path": "scripts/verify-tests.mjs", + "bytes": 5124, + "sha256": "3e9140831477df004d39187e240ce8e27e8680d051a9353dc6b9b17de81994f4" + }, + { + "path": "scripts/verify-ui.mjs", + "bytes": 18880, + "sha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6" + }, + { + "path": "scripts/verify-workspaces-ui.mjs", + "bytes": 15427, + "sha256": "fdf5900e0936b681d030f18a7a5245beacf8ab091b79a495ca823df65e8bb4a7" + }, + { + "path": "src/client/App.tsx", + "bytes": 61296, + "sha256": "678223d317c091e2dceef71dfb326eba47ceb57551375371e70d84cbef74882b" + }, + { + "path": "src/client/BrowserPanel.css", + "bytes": 5050, + "sha256": "3032abddc1cfeea3100cb4b34bb2e9e25e965f470c4fd38c73d564dfc80f3450" + }, + { + "path": "src/client/BrowserPanel.tsx", + "bytes": 16962, + "sha256": "24a7479a2740ac72de22dadb556565904fb4525117cddc2a08ab1b766437ce30" + }, + { + "path": "src/client/ChangeSetPanel.css", + "bytes": 4477, + "sha256": "c1ac9307b78e4e42159398e499074d85da395faf7c88f2f485c6b7901d142459" + }, + { + "path": "src/client/ChangeSetPanel.tsx", + "bytes": 11104, + "sha256": "b3a3b3e73bf74a23c08f74d124fe98c6b45e0c048d3fabb745fd488140d58f61" + }, + { + "path": "src/client/ChangesInspector.tsx", + "bytes": 3324, + "sha256": "5799507f52e1414ec573eb1d0452bb3c173728836d3c1644c760b31cab4a3ee4" + }, + { + "path": "src/client/CodeIndexPanel.css", + "bytes": 5796, + "sha256": "76f6f2b32e25df3b3f4c8761273de4963b7b25dff01cbe97b2f5171ec8358286" + }, + { + "path": "src/client/CodeIndexPanel.tsx", + "bytes": 7715, + "sha256": "2574080bbb0aa9ff05571ef406dadd3c008f792cf2443ff1f779f0975a6d97d4" + }, + { + "path": "src/client/DeliveryPanel.css", + "bytes": 5070, + "sha256": "8c12813290c171b616ffb36c002395fc40ff2c7d5b63cd2f13613be435a2d3c6" + }, + { + "path": "src/client/DeliveryPanel.tsx", + "bytes": 14267, + "sha256": "23a9c1519c6b94508f2cabaedd47ccf43f0cdae26d5f956d81b3c26f37f6d531" + }, + { + "path": "src/client/DiagnosticsPanel.tsx", + "bytes": 3823, + "sha256": "a5746d019da37c99af60c69f556b007ea307e2f3a02fcde504b547ed468dd07f" + }, + { + "path": "src/client/EnginePanel.css", + "bytes": 6275, + "sha256": "5a0fc3b6fab7038751f346cdd40e6b4540e8886c0f0c54478c09c18eeaeec1d3" + }, + { + "path": "src/client/EnginePanel.tsx", + "bytes": 12950, + "sha256": "d36f3058ab8e0a5d327f68f6894d34fc4b1f721949c873e1356dcb28907a4e07" + }, + { + "path": "src/client/McpJobHistory.tsx", + "bytes": 7508, + "sha256": "207ba78dce96c85dedf7ff34f7678dff1e925118fb93dd1d5a144f38c7aaf618" + }, + { + "path": "src/client/McpPanel.css", + "bytes": 9547, + "sha256": "e1c89f3229acb0bb739fcf91e605d09f7d8f38f4f367da1f11835b2b9452538d" + }, + { + "path": "src/client/McpPanel.tsx", + "bytes": 15591, + "sha256": "f1ea14216c4340f6cd76b267763a468bf0d311dd6f8b273afe3ee9cf6768a260" + }, + { + "path": "src/client/ModelCenter.css", + "bytes": 9222, + "sha256": "99f81bc87f634fa77bedd00247500b99314412db36574a58e6e382cca19f903f" + }, + { + "path": "src/client/ModelCenter.tsx", + "bytes": 22142, + "sha256": "bde2746b5e2d3595a5459dff3f6154c44d67853cc57bd8aa3c744428bac3823a" + }, + { + "path": "src/client/ProjectMemory.css", + "bytes": 4322, + "sha256": "0d6c9a23afafa77e7230edd9294299a3d233aa7b49c191d522ee9c106839a1f1" + }, + { + "path": "src/client/ProjectMemoryPanel.tsx", + "bytes": 7381, + "sha256": "b7c140f126bc2d48df00fe4111517e3ea2f43926d52797d26733e1f2522f6a03" + }, + { + "path": "src/client/RequestContextPanel.tsx", + "bytes": 9245, + "sha256": "9b7bd92ff4afc6a8e4c1fd129dea053acb8b135330582643beef62608b737e79" + }, + { + "path": "src/client/ResearchPanel.css", + "bytes": 7271, + "sha256": "f24f8eb283c0b419037adcd680bc1bbe84002abf661bfda94891dcea5fc92682" + }, + { + "path": "src/client/ResearchPanel.tsx", + "bytes": 16684, + "sha256": "cae237fc267a491db18f24f88e0b6926a635225886bfa58683a37f6d4586c8e1" + }, + { + "path": "src/client/SkillCenter.css", + "bytes": 6453, + "sha256": "d9f79bba3be7369a0231434aa29fe061e0c5d1f792aeb7e15e3f2a7744165242" + }, + { + "path": "src/client/SkillCenter.tsx", + "bytes": 9303, + "sha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10" + }, + { + "path": "src/client/TaskCheckpointPanel.tsx", + "bytes": 5367, + "sha256": "77b552924379531eff51c81c5bf4e2512c1201f39641245c781a468e6a7e397a" + }, + { + "path": "src/client/TaskPanel.css", + "bytes": 8906, + "sha256": "6dc737d84406fafd2f1b36ba1eaf02c8b0f59594b30a1fadcf2d3451ada285db" + }, + { + "path": "src/client/TaskPanel.tsx", + "bytes": 18980, + "sha256": "cb781e0c81f4f24b822b4b7472bd4d14cc6591f78a96558f259bc0bd587cb3ec" + }, + { + "path": "src/client/TaskPlanPanel.css", + "bytes": 4257, + "sha256": "e47eb1195a61400d60817de793893d9e4924f334bdf452ffb744ed69741c43fc" + }, + { + "path": "src/client/TaskPlanPanel.tsx", + "bytes": 16038, + "sha256": "3ead0b021ae550b0bc3891b8e852c297f05f895ce3516f693a91d23456ebc1f1" + }, + { + "path": "src/client/WorkspacePanel.css", + "bytes": 3743, + "sha256": "d8c4558f6c559ff8b4bbc7723aca08e4e37f8fef8f5b8d5619faec8332314ba3" + }, + { + "path": "src/client/WorkspacePanel.tsx", + "bytes": 10026, + "sha256": "c91d097edd5e044f72583bdccd39848f35a5b82c4d9abf7c09648e21ecfdb8c2" + }, + { + "path": "src/client/api.ts", + "bytes": 3058, + "sha256": "6e706020502cc3e079ddc46f4f843571cfb883852fb7ea21bd2c3c9ff463d56c" + }, + { + "path": "src/client/components.tsx", + "bytes": 13189, + "sha256": "7b735a151ceb1889702f3127a15a8a2918f6fba7140304c3b81b5662f1b43741" + }, + { + "path": "src/client/control-console.css", + "bytes": 4836, + "sha256": "bbb0f00ff90ea4c8d0f969b4fa95df4e95413b97ab28a204a893a99671a10bc7" + }, + { + "path": "src/client/main.tsx", + "bytes": 256, + "sha256": "6dec6d76306f0e47b1a9e77004377daa5312270d519a685f169c025a9e071792" + }, + { + "path": "src/client/styles.css", + "bytes": 38537, + "sha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218" + }, + { + "path": "src/client/types.ts", + "bytes": 24332, + "sha256": "ffc135242245843efe42b8df2614afafe7b8c8c98731dfc3fa6b10e1b9d8cfd8" + }, + { + "path": "src/core/browser/browser-driver.mjs", + "bytes": 18254, + "sha256": "d63e3ae49bdec13f2f86923c21d4af4d7f1ea1b07c768be3cc85b4833836bdd2" + }, + { + "path": "src/core/browser/browser-manager.mjs", + "bytes": 24633, + "sha256": "0efc0e30f19a8649c964e1193c455d6cc6f32bfd4a4a5e18fc6ff8014d67b820" + }, + { + "path": "src/core/browser/build-snapshot.mjs", + "bytes": 4309, + "sha256": "2424f37847e72621327b5c0157f9fc03c1e7dd266ca71292b4b70571f17170a9" + }, + { + "path": "src/core/check-runner.mjs", + "bytes": 21065, + "sha256": "03cb18e181013092febcc2a69cb1977dfe8db04dcb7496e7842a38f5a73f4c7d" + }, + { + "path": "src/core/context/project-index.mjs", + "bytes": 18380, + "sha256": "acaa896eca725bcce13a6d34a46267ce70a8a824eac8ca2ffccb91c4d18bd304" + }, + { + "path": "src/core/context/read-budget.mjs", + "bytes": 10437, + "sha256": "7544a22f8a0f2aeb9f06cd3d43f9eae77cc3141503930571a8c170b1ff4bb0cd" + }, + { + "path": "src/core/context/request-plan.mjs", + "bytes": 36015, + "sha256": "3d8c158f8b0d7e696a311f642a95f184cf69d38db9859498dbb8d2db6ab85108" + }, + { + "path": "src/core/context/tool-feedback.mjs", + "bytes": 9598, + "sha256": "7523f2ef18d9fea975d15e665c8c122293fdf52f3c7093ad08e16b8a83b6c95f" + }, + { + "path": "src/core/context/working-set.mjs", + "bytes": 10948, + "sha256": "61220be2142fff4194b633cf85e39f87c0a71ddf0745ce1406a5bc54977bdb0a" + }, + { + "path": "src/core/delivery-report.mjs", + "bytes": 22037, + "sha256": "a0bb895459be2805684b881f80674f5592c2d55c285adcc30a0657c3a9c7bb5d" + }, + { + "path": "src/core/engine-manager.mjs", + "bytes": 12455, + "sha256": "ec29a945c84ee79a41d30ac3a70296281bdd7d7898cc727a85bb6d78af62f015" + }, + { + "path": "src/core/engines/deepseek-adapter.mjs", + "bytes": 10977, + "sha256": "b5d3e3f1ba74b8d15b002594f13652bbc98761226a3e5e3fb408071762958fa9" + }, + { + "path": "src/core/engines/deepseek-installation.mjs", + "bytes": 5979, + "sha256": "5bca6da6d1fd972405762b81a4be7936ac597337e310aec2a7d88aa9e5cce7a9" + }, + { + "path": "src/core/git-delivery.mjs", + "bytes": 40952, + "sha256": "4c53fcb82813a559b1e61615fb879dd7afe48686832d2ffd992f81dc56579bad" + }, + { + "path": "src/core/git-process.mjs", + "bytes": 2655, + "sha256": "80547ec8928610ac4df5a05c5aef12d1aab0dca9e7b1def2773fc745f5adf5f5" + }, + { + "path": "src/core/memory/project-memory.mjs", + "bytes": 13871, + "sha256": "9c7da0ef9c7f36b431015fd4414f55304f8d5e25a61bc527fb7e3be0b7971e51" + }, + { + "path": "src/core/models/config-import.mjs", + "bytes": 8132, + "sha256": "aa2e4fd4b154e7ab97da5da2e73af8c20655f3de52214bde34a69723eaa3fef0" + }, + { + "path": "src/core/models/model-hub.mjs", + "bytes": 16526, + "sha256": "e7e94292cc4e163a0b691a4c2553ea440c78c1a01a5ae600e3f4e30ef32e0ec9" + }, + { + "path": "src/core/project-inspector.mjs", + "bytes": 10892, + "sha256": "9e81ed2928fc5dcdb20915a406a8cdc69068deb04fd9d36d0792a86598405782" + }, + { + "path": "src/core/python-project.mjs", + "bytes": 4721, + "sha256": "74e09a96f2e1970b155d37af176379807add0d5a05f72ccd9491d4d494d58707" + }, + { + "path": "src/core/python-runtime.mjs", + "bytes": 12726, + "sha256": "a72634712ef10decc7291971fb83c1ee6f2254641bb7d77894c97fa760eda887" + }, + { + "path": "src/core/research-manager.mjs", + "bytes": 19987, + "sha256": "15981370de1f02db4acec2c3e1450d068236e1f6ab70f677ec8617aa968fc2dc" + }, + { + "path": "src/core/skills/skill-registry.mjs", + "bytes": 15494, + "sha256": "63e435d65e3dfe7dff1b1711590b5a4a5ca2efddaa67822087de06facdadf3bb" + }, + { + "path": "src/core/storage/artifact-store.mjs", + "bytes": 2918, + "sha256": "2934d31a28da215f7ea73a3b5e56d106b723b34539ea8605d523b121762e488a" + }, + { + "path": "src/core/storage/legacy-import.mjs", + "bytes": 4825, + "sha256": "aa6a6b95d4049c5091d39e8c65ee301a0d6e533e081da59c87f2733bfb5a15ed" + }, + { + "path": "src/core/storage/state-database.mjs", + "bytes": 8565, + "sha256": "2a38f7564df44c4ee5183d850064be1d46fba7e072e2b87f73afb8e1a85a1517" + }, + { + "path": "src/core/tasks/task-checkpoint-manager.mjs", + "bytes": 13524, + "sha256": "2f50f9de2e6b8c90376028ed2814eb795633e1ea917ab944a977299220ad820f" + }, + { + "path": "src/core/tasks/task-plan-manager.mjs", + "bytes": 22026, + "sha256": "4feafa9462ab57f694854c79c846a9ba58fe9313b343341f2ca2a334255eec24" + }, + { + "path": "src/core/tools/mcp-contract.mjs", + "bytes": 8366, + "sha256": "4860792132e2d18caa075ddca8c24687b3692c005a1c6c4c81933e6dc9e0a6bc" + }, + { + "path": "src/core/tools/mcp-registry.mjs", + "bytes": 26252, + "sha256": "8f52b11ba37d1c350aa279e4890a0c5b00fff3b77fc4f2211a4ea1c07bbadebc" + }, + { + "path": "src/core/tools/mcp-stdio.mjs", + "bytes": 8109, + "sha256": "1c1081b9356855db5c8964ac5b9f5fb2c79fef5323ff1f933447a06f77cac447" + }, + { + "path": "src/core/tools/rea-adapter.mjs", + "bytes": 9010, + "sha256": "36f7d2a095fcaef4e1ca056a1f2475e0b15fe1fc48d0179589b41abadf39c6c4" + }, + { + "path": "src/core/tools/research-output.mjs", + "bytes": 1750, + "sha256": "b9d53487192f12b0d2b0f0922c918b5b3d88a276777cd64903395800ff07c1c0" + }, + { + "path": "src/core/workspaces/change-sets.mjs", + "bytes": 25967, + "sha256": "759315b541c127b9eabb411f9b61975dff88daac063af63520cac81f7f8a18c0" + }, + { + "path": "src/core/workspaces/git-workspaces.mjs", + "bytes": 36568, + "sha256": "2b123a1e92e7f07fbfdd650ccbf44908d6b2e1d7504f893034e12a0cd0f32839" + }, + { + "path": "src/server/app.mjs", + "bytes": 49724, + "sha256": "3a8a11203d44e66e13280d5cce32e0c604875569b45731c1772e7b161d1b46c9" + }, + { + "path": "src/server/diagnostics.mjs", + "bytes": 7965, + "sha256": "a62eba2444edae318043c3bd30e9b879066402af0c63ca409ac4a798fa0374c5" + }, + { + "path": "src/server/files.mjs", + "bytes": 14427, + "sha256": "6d7e298d74453f102941baf422a686e4550b46067d8e9ad693d9c9915de2b019" + }, + { + "path": "src/server/hot-upgrade.mjs", + "bytes": 5441, + "sha256": "bae94aace2a785333ec5532408f63c68301c2b97736e6a55d52bad63dee88574" + }, + { + "path": "src/server/index.mjs", + "bytes": 2668, + "sha256": "16b9d751870188d185ca6b03429376f19b5e7b94fd91a6ce401a096fae74ef64" + }, + { + "path": "src/server/provider.mjs", + "bytes": 28524, + "sha256": "c55d060f833c81be376a9c3ed5703079968b6676b9a57bc715e280ada7fb6074" + }, + { + "path": "src/server/runtime.mjs", + "bytes": 55604, + "sha256": "2fc182251f8061951e54dbd73f62e61d165309445f2107cd351ee9013b9b80fb" + }, + { + "path": "src/server/store.mjs", + "bytes": 41653, + "sha256": "d027b8adccd0df0470ad4bd6b7e3c6e3dc2baec1ca7fe7e0872c841cf325f65b" + }, + { + "path": "src/shared/contracts/browser.mjs", + "bytes": 4775, + "sha256": "af8f71616097dbbb08bde31bf1cc42c90708802f17ad89b4ba220351fb30f439" + }, + { + "path": "src/shared/contracts/change-sets.mjs", + "bytes": 1189, + "sha256": "01586cdcffe00129c2b61e4cbf4a622b22306cd5a893620f4a7db441f978f1da" + }, + { + "path": "src/shared/contracts/delivery-review.mjs", + "bytes": 1368, + "sha256": "1b17efdfa2549801db72eabe439907419a4d85ea07e4d010563db2d483d565f9" + }, + { + "path": "src/shared/contracts/engines.mjs", + "bytes": 2234, + "sha256": "8d52facab1b7c1941637ae86756e73a7050467be04a0e036259bff6aad42c42b" + }, + { + "path": "src/shared/contracts/execution.mjs", + "bytes": 5035, + "sha256": "2ceb700eaa3f8f2adf01b348575f7deb381f970e30eabe553e3ee30840d699a5" + }, + { + "path": "src/shared/contracts/model-request.mjs", + "bytes": 901, + "sha256": "3744dfa7302dde72d1c24c54e7c00672ff063b45786add2fb19d46233b759e78" + }, + { + "path": "src/shared/contracts/research.mjs", + "bytes": 6860, + "sha256": "eb970b52f923d7dbfd8e7da49381ce135b8a2ae9d04c0d4321958a2e93d12003" + }, + { + "path": "src/shared/contracts/task-plan-tools.mjs", + "bytes": 3029, + "sha256": "b14392919e1b551751a6c311004d9d200bc494a7873987c8c0f34a8c4bec1ec1" + }, + { + "path": "src/shared/contracts/task-plans.mjs", + "bytes": 7290, + "sha256": "c312f4511f495b90ec8983e5c8ecc357e85f67d97b8deda2d052651c3f491adb" + }, + { + "path": "src/shared/contracts/workspaces.mjs", + "bytes": 3975, + "sha256": "4cd6873ca73de9dac5e73f3aaabe062674c5ca1d50c28a2e2b6eb9e138c32be9" + }, + { + "path": "tests/api.test.mjs", + "bytes": 10732, + "sha256": "c216d1d2153e84e2d447a05eea86f6d7ca91409728ecf63aa0377b535a3ba62c" + }, + { + "path": "tests/browser-api.test.mjs", + "bytes": 9597, + "sha256": "30c8f5adb89bd60277c48e9f4e1e9f5c3a0fc8652cda447a4d6c273210e2576b" + }, + { + "path": "tests/browser-delivery.test.mjs", + "bytes": 4085, + "sha256": "21c1280d95f070504840c94c4bdf556559653636332f8e38d355144fc080dc2e" + }, + { + "path": "tests/browser-locators.test.mjs", + "bytes": 4926, + "sha256": "cad3236d3ac1e17524ad304e159659d4009ce3ae265ccb9047a36df00dbd31f3" + }, + { + "path": "tests/browser.test.mjs", + "bytes": 8150, + "sha256": "2e4a0d1d5136a9729b015b977af9344a9802a2015583d7e2cf5825d606888242" + }, + { + "path": "tests/change-set-api.test.mjs", + "bytes": 12753, + "sha256": "44170084aea8e31cfd4c59e4c96006413f0f66151e6241d27b7a0aacf5d1a328" + }, + { + "path": "tests/change-set-recovery.test.mjs", + "bytes": 3435, + "sha256": "8cfa9ae1526975111f6ec7fa60afb79e40a994c5fdbf86abcf1edd2cc69077e0" + }, + { + "path": "tests/change-sets.test.mjs", + "bytes": 14054, + "sha256": "b5a72b65da8f6ee239c8d6bd51e3dcbc901f1e43b16708548f2f082eccaeaa20" + }, + { + "path": "tests/checks.test.mjs", + "bytes": 21968, + "sha256": "d7936ef6fa5c0421976cdb30e435a910e7a0c461829e991091b4c6ee00e924ab" + }, + { + "path": "tests/code-tools.test.mjs", + "bytes": 7518, + "sha256": "f6c120892e86ec21c67b010e256e359b2f1ba7196b48937961f4e8c62deeef93" + }, + { + "path": "tests/delivery-recovery.test.mjs", + "bytes": 10733, + "sha256": "bec27e3d4bdd8777d7a08e146019e79436cbb463131cd2b07f6f819e002652b1" + }, + { + "path": "tests/delivery.test.mjs", + "bytes": 22944, + "sha256": "d6e05886de2d27395cc6f2d0cd8581e87150ac95a7b017337fd59d1ce388c489" + }, + { + "path": "tests/diagnostics.test.mjs", + "bytes": 13318, + "sha256": "88a3b333ddc9da6c65eaafc1e73b16e28c79e617d9a8348d1a7b925b1cf99615" + }, + { + "path": "tests/engine-api.test.mjs", + "bytes": 5089, + "sha256": "da7dd728a5a30039cda74e5b67a451908384527d7946600fc2170335cc2e64cd" + }, + { + "path": "tests/engine.test.mjs", + "bytes": 14173, + "sha256": "77a917ae867a4b7e509c10e10f36b75f5755e18066b44f6ebd73552cf9355e03" + }, + { + "path": "tests/execution.test.mjs", + "bytes": 14144, + "sha256": "f3004d5cc4fcf5ac65eea0c24c864fa63227d9d1127f32b41621e6c3b7bc52ba" + }, + { + "path": "tests/files.test.mjs", + "bytes": 5022, + "sha256": "2d2dcd77a2956a7da6028b4a2ccee536d1a0c4ed7147d48aa8849863deb62ec3" + }, + { + "path": "tests/fixtures/browser-project.mjs", + "bytes": 1972, + "sha256": "cb682a64f65953bfcdb577768b82b1f7a7e86e530379ea8580ecdbf864132ff2" + }, + { + "path": "tests/fixtures/change-set-crash-worker.mjs", + "bytes": 909, + "sha256": "0f564eea935f576de9ef6db7a09cc95db2f95a38b654d476de67e3b5eb166c96" + }, + { + "path": "tests/fixtures/change-set-project.mjs", + "bytes": 1688, + "sha256": "b597f7ec0d32975673fdc36284d6688af401040b06e6fe8370a3e565a98016c2" + }, + { + "path": "tests/fixtures/check-crash-worker.mjs", + "bytes": 654, + "sha256": "3de4749fb0b016e44c16029a71366231acd021c2196b075029d55d767e0c4c84" + }, + { + "path": "tests/fixtures/context-plan-crash-worker.mjs", + "bytes": 558, + "sha256": "9ebc5980e78d39a3d382d6336eb021e2088baeff4ff670f427617c01c4e509d8" + }, + { + "path": "tests/fixtures/core-crash-worker.mjs", + "bytes": 2852, + "sha256": "ff6a92e7600844f47a49eecdf800a3e7219ee193547cb0008568a578854303ed" + }, + { + "path": "tests/fixtures/delivery-crash-worker.mjs", + "bytes": 744, + "sha256": "a2f5e2ba4382e6ef0a614a9d07928a06a07a74a748441b1404570dd714428492" + }, + { + "path": "tests/fixtures/delivery-project.mjs", + "bytes": 4095, + "sha256": "578fa6074b9d4d375a31f94d02b34acada63e85df1dce22ac7dfbd259c5d55cb" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/README.md", + "bytes": 346, + "sha256": "ec995a6accae2d5bdd4e43b1a698ea5a3b13241cfb70d57dc103650d665c3d1b" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/artifact-store.mjs", + "bytes": 2655, + "sha256": "b5e7d5dba4614c9e93aa118e1765266be22b7871c0751aa1b902c5ad358ab10f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/README.md", + "bytes": 524, + "sha256": "e5d044b72eea8ad836196a8e86abab366453b14addd9f206f9a2da75511da52f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/dist-server/hot-upgrade.mjs", + "bytes": 95288, + "sha256": "0a701a6cb3063bf8459bdaf2adb6e93af33682592ab67f3c69e96a32c8b92148" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/README.md", + "bytes": 536, + "sha256": "ebee2fdec8207c66d172604f7fa28d10be1c7f2a01e26f92c6e4c41da0d6aabd" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/dist-server/server.mjs", + "bytes": 73087, + "sha256": "00770b85ea3372259b5a481616616aa1dc1bdefac00c210b5b307898f63ad934" + }, + { + "path": "tests/fixtures/mcp-host-crash.mjs", + "bytes": 1238, + "sha256": "a7ceecb6419270bb918e72704d0cf124623afd037da433b7b4c9af6f769aafa7" + }, + { + "path": "tests/fixtures/python-project.mjs", + "bytes": 3277, + "sha256": "4b20f285de410302839782d544257483c666609ae519c1a6facea5a8dbcaecc2" + }, + { + "path": "tests/fixtures/registered-mcp-server.mjs", + "bytes": 2200, + "sha256": "e6479755be0d7d0e08a7f98cbc59cf4ea494c8092bdab40e5dff752d5b8840c1" + }, + { + "path": "tests/fixtures/research-mcp.cjs", + "bytes": 1744, + "sha256": "8fe82e55327f6e32ab2bafc66d9374b4b542959656d5a341c50779d1ae579458" + }, + { + "path": "tests/fixtures/task-checkpoint-crash-worker.mjs", + "bytes": 884, + "sha256": "835b95c4baf1f4a69228f88e7da99092dfc77238d2cbea6b08600bdafc18017b" + }, + { + "path": "tests/fixtures/task-plan-crash-worker.mjs", + "bytes": 1089, + "sha256": "a3f0b614dfdc2c14906fe0435a7b8fb07d3267cd0732f63e174c44c59909cd6c" + }, + { + "path": "tests/fixtures/task-plan-fixture.mjs", + "bytes": 1698, + "sha256": "036fa5f0e1dc3a55a2adba55700d4f597396fbf5cf216fc2404ec101df2544d9" + }, + { + "path": "tests/fixtures/workspace-crash-worker.mjs", + "bytes": 1006, + "sha256": "c12bc83f501fc2eb522c6f30235d2e089ab6129a96c44e0d4edb4fb135d9215c" + }, + { + "path": "tests/fixtures/workspace-project.mjs", + "bytes": 995, + "sha256": "69002bf2e6940f314aec3e8d7f758e53d6376f0814e6b4e1b16505abbe46a699" + }, + { + "path": "tests/helpers.mjs", + "bytes": 6248, + "sha256": "71ac890f4278cb664bbc313dfe1df2cd063e77544a65f528c6428a822da2425b" + }, + { + "path": "tests/mcp-registry.test.mjs", + "bytes": 22599, + "sha256": "b6059a9c3966ded29450e85e5a43ad088a181049d218eb5ecb7c76782db93d05" + }, + { + "path": "tests/mcp-stdio.test.mjs", + "bytes": 5402, + "sha256": "58510c241450d5300f1ca4a4f7ad4adecf6a7abdae295197c311934883c5b23b" + }, + { + "path": "tests/model-center.test.mjs", + "bytes": 11687, + "sha256": "d665c081ed00f516d3a9428a0ce35755be24900247e86bef862059aeeb2b4cb1" + }, + { + "path": "tests/patch.test.mjs", + "bytes": 6579, + "sha256": "d90404327527e820e3195d04edbf1a7349a450564d80e7dbc4e0c582559e6102" + }, + { + "path": "tests/project-index.test.mjs", + "bytes": 15256, + "sha256": "83fbc65f713e68e29395ad1053bcbf7272922fb932c6e17f62f4ea402878519d" + }, + { + "path": "tests/project-memory-context.test.mjs", + "bytes": 13430, + "sha256": "bf2996b50e26a69eba737d09de1e5273f5332d695c93f708e508269a29e8bfaf" + }, + { + "path": "tests/project-memory.test.mjs", + "bytes": 7438, + "sha256": "811da36aeffaeddfc496809f00f81ec2cfd722c7411614c6f6b282de2e5d3764" + }, + { + "path": "tests/python-api.test.mjs", + "bytes": 9733, + "sha256": "7694d82dc70d458371d347dbd54886cfa3fb1118c37f59fc4773dd1921fca173" + }, + { + "path": "tests/python-checks.test.mjs", + "bytes": 18057, + "sha256": "b60bde10ac220570a6fc59555b287061d1325783be7532a613885d834ee58078" + }, + { + "path": "tests/read-budget.test.mjs", + "bytes": 13724, + "sha256": "106ddd1eae179c03a01d4952aa3f72d68057badf572e093156f6cc3b37e8edbf" + }, + { + "path": "tests/request-plan-api.test.mjs", + "bytes": 4837, + "sha256": "f3d9a63ee319d44a2ae74d293eb229a8b2cd77bdd29119abcdc23040496d1b57" + }, + { + "path": "tests/request-plan.test.mjs", + "bytes": 18997, + "sha256": "d9e816d4258f9ad4fc35b72d12071e8cb529c7ce708f77a22292760f97c5302b" + }, + { + "path": "tests/research.test.mjs", + "bytes": 16967, + "sha256": "76c8f486bb1fdc4bbef25246ff219bcaa8b8242fb8b7add89c831f9de8ede219" + }, + { + "path": "tests/runtime.test.mjs", + "bytes": 15006, + "sha256": "cf4ce1675cd5f5ab7f81ebd9cd9c949eed1a8121db15cd5349d3c45a732a2b1e" + }, + { + "path": "tests/skills.test.mjs", + "bytes": 17628, + "sha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6" + }, + { + "path": "tests/store.test.mjs", + "bytes": 3880, + "sha256": "e932cdf3a682a3c10309e04d4373f2180f0466443eda2b7d29865ca5eb5f9437" + }, + { + "path": "tests/task-checkpoints.test.mjs", + "bytes": 16172, + "sha256": "bca05de242d6ca7705e7f07e03744b831748e7e6569e00ad540d95cb0fc6ce19" + }, + { + "path": "tests/task-plans-api.test.mjs", + "bytes": 3657, + "sha256": "e0f067eed3e748a39b864e26f8d844a28cc45709aac305a04230cbb19ccd7684" + }, + { + "path": "tests/task-plans.test.mjs", + "bytes": 21545, + "sha256": "99e9b5ba17818bdd8bd8b035868beec4bb2d6bb520b5e1592b02bb3008054461" + }, + { + "path": "tests/tool-feedback.test.mjs", + "bytes": 8409, + "sha256": "61cb597fcd7f8ec32c072f70e0937086535fe50eaa0997479ca06968425bcee3" + }, + { + "path": "tests/upgrade-artifacts.test.mjs", + "bytes": 6267, + "sha256": "6cfb50727f8601f03300de605a4021f7b3e388cba597814a2089438b8a0eb957" + }, + { + "path": "tests/upgrade.test.mjs", + "bytes": 9711, + "sha256": "1a6ded4be5e89ac7a41c9a60c4b37569723ad7d5f80f48c9406940ad727455d3" + }, + { + "path": "tests/working-set.test.mjs", + "bytes": 23492, + "sha256": "b5a163c4d441c49b68a906508156f1e0792d2f0a5a6fe76ebe4429970c432d76" + }, + { + "path": "tests/workspace-api.test.mjs", + "bytes": 9444, + "sha256": "b1dd1ed7a2b14cdd8851a6ff6e15b8f5f9dce85a4e70f1314dcfce98e66d8dd8" + }, + { + "path": "tests/workspace-policy.test.mjs", + "bytes": 12247, + "sha256": "ff8cc7ea014bb630951ae61e7fdda80d5333155823a91986f52f998d011d010c" + }, + { + "path": "tests/workspace-recovery.test.mjs", + "bytes": 5382, + "sha256": "7aeaf03ae89a7de7641d260704aafca4a330b532e46d2d0468a64932c1ab057c" + }, + { + "path": "tests/workspaces.test.mjs", + "bytes": 5490, + "sha256": "4118e9208fed31b3ea2ab55276ed1477291c2daf83809753764a5f17dee7bc60" + }, + { + "path": "tsconfig.json", + "bytes": 398, + "sha256": "aca51bc97061d8ee755197b432ce24f70eb37e02cf8c60445edcfe35305d0510" + }, + { + "path": "vite.config.ts", + "bytes": 247, + "sha256": "6ad3b1bd9d5390876535ba189200fa08e46e5fb481f3f57581376859998e63f4" + } + ], + "inputFiles": 213, + "logs": [ + { + "stage": "install", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\install.log", + "sha256": "d004705f9743512ff45730927b3cc7f185b3c61eb38e5412e95df8d0843125a2", + "bytes": 401 + }, + { + "stage": "build", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\build.log", + "sha256": "9d717220d1e08ef2b584d6ea4690a1b13e255fe761a02e34c68ef00c9cfb5d1f", + "bytes": 685 + }, + { + "stage": "contained REA", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\rea.log", + "sha256": "bf3270ef60219ca9e4248171f58b75fb4ab3218c6670ad74144f2bf0bd93933b", + "bytes": 923 + }, + { + "stage": "native DeepSeek SDK", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\engines.log", + "sha256": "3af034b5f401c3424d776bb35b08ee98b4ecfb5f56a09fadc8f970488624eb02", + "bytes": 396 + }, + { + "stage": "contained browser runtime", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\browser.log", + "sha256": "b8f6ffc5ba074d2fb1127c9a0b7465df614601266eb23c1dc0231a9aa23ca272", + "bytes": 1251 + }, + { + "stage": "tests", + "path": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2\\tests.tap", + "sha256": "662bf1708cb8b3f7781de47f1fda62f6879a8f12967184ee5213adcd8f849d86", + "bytes": 96809 + } + ], + "buildMatchedFiles": 6, + "tests": { + "tests": 357, + "pass": 357, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "actualRea": { + "success": true, + "version": "1.12.0", + "directory": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\rea-integration-5575c387-87d5-4678-9180-f04ab5cecc58", + "results": [ + { + "operation": "javascript", + "evidenceId": "ev_b8d9b502f62bfbfdaeff22c0f38f67bc38735c1fccdf09ec62523a11375a86e1", + "targetSha256": "12749e2a95135a5d0fbd39fee9f25347d0356ce70937e01a6efe2a3f72f41d28", + "advertisedTools": 229, + "rootExited": true + }, + { + "operation": "pe-imports", + "evidenceId": "ev_49e797493853defa639b7ec0cae1eba6af792e596ca92329050ca730082327be", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "advertisedTools": 229, + "rootExited": true + }, + { + "operation": "pe-resources", + "evidenceId": "ev_79a4bb67103e362cf411a88aefe842ec34958dd645b840da85447131539c1703", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "advertisedTools": 229, + "rootExited": true + } + ] + }, + "actualEngine": { + "success": true, + "version": "1.12.0", + "directory": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\native-engine-40a77613-e15a-401e-9edc-77c9df1fde96", + "sdkVersion": "0.2.1-rc.2", + "nativeMethods": [ + "initialize", + "session/working-directory/get", + "session/wait", + "session/resume", + "session/cancel", + "shutdown" + ], + "modelRequests": 0, + "rootExited": true + }, + "actualBrowser": { + "success": true, + "version": "1.12.0", + "directory": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626\\.qa\\browser-native-7371497b-5acf-473e-b3f5-0c1593ece1bf", + "results": [ + { + "jobId": "209cc3e9-e76c-4325-9309-f47b4ead6ab6", + "taskId": "4ab10193-114b-40d5-a4cd-0ef5c39f82f0", + "viewport": { + "width": 1280, + "height": 900 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "6878d6ef328cc8beb92900170be3d3600ffa2852b0b0eed1e74fa13d80f79078", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54", + "browserExited": true, + "reusedOriginalJob": true + }, + { + "jobId": "309fc9e0-6b3a-4d9c-a727-328ea283d0cf", + "taskId": "4ab10193-114b-40d5-a4cd-0ef5c39f82f0", + "viewport": { + "width": 390, + "height": 844 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "92de94a5b8b0451a12ad1b6b2f0adbb384f5d423b9d0743a773292f9ba171e90", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f", + "browserExited": true, + "reusedOriginalJob": true + } + ], + "modelRequests": 0, + "rootExited": true + }, + "credentialsHandling": "Only build/runtime environment paths are inherited; no model configuration or credentials are used." +} \ No newline at end of file diff --git a/docs/model-center-tested-candidate-archives-validation.json b/docs/model-center-tested-candidate-archives-validation.json new file mode 100644 index 00000000..32f25ac3 --- /dev/null +++ b/docs/model-center-tested-candidate-archives-validation.json @@ -0,0 +1,24 @@ +{ + "success": true, + "version": "1.12.0", + "testedAt": "2026-10-30T12:31:27.122945+00:00", + "archives": [ + { + "kind": "portable", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030123032626.zip", + "files": 11053, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "1f6e2ea1380ca630074971774c52520031bca081e75d7ef4629195db5bc488a6" + }, + { + "kind": "source", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-source-20261030123032626.zip", + "files": 9334, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "f5e5796fc648e172253645cefcdb5ede0f0e5e5ddcce195bc20457681294aa7c" + } + ], + "extractionRoot": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626" +} \ No newline at end of file diff --git a/docs/model-center-tested-candidate-release-validation.json b/docs/model-center-tested-candidate-release-validation.json new file mode 100644 index 00000000..780735cd --- /dev/null +++ b/docs/model-center-tested-candidate-release-validation.json @@ -0,0 +1,139 @@ +{ + "success": true, + "date": "2026-10-30T12:35:03.092Z", + "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030123032626", + "version": "1.12.0", + "nodeVersion": "v24.22.1", + "verifiedFiles": 11053, + "url": "http://127.0.0.1:50212", + "reusedPid": 45724, + "checks": { + "jobId": "3dbac3c1-610b-4888-a763-739ed9f49d49", + "status": "passed", + "tests": { + "total": 4, + "passed": 4, + "failed": 0, + "cancelled": 0, + "skipped": 0 + } + }, + "actualRea": [ + { + "operation": "javascript", + "jobId": "e28cd4ad-aab5-46e4-8edb-6fa8393c904d", + "evidenceId": "ev_0a60d91068cab7128f795a2d6eb7537a3bd661850a7d8bf8ad2a79816ec2a353", + "targetSha256": "57414a63fa4822243c1625a4fae6a59a3feedc42fd9be5245a927a20f394ff08", + "bundleSha256": "c710d6141d216dbdb49a4cb4c16640c735af6021ec7714c521499eb99fc4c909", + "rootExited": true, + "reusedJobId": "127aa6d9-cb4e-4be5-9a7a-a55a10eb0fdc" + }, + { + "operation": "pe-imports", + "jobId": "db3f81f6-fc2d-4da5-8f1a-ac558a8543b2", + "evidenceId": "ev_44042ec636aaf93a793f697cb1a2286db6c35c5d39b577b95064cd438a2ef9ad", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "bundleSha256": "0993f4f12a4f7051baf62100c9baadfa47ba89afaedc095bb20239523a3ac1cc", + "rootExited": true, + "reusedJobId": "80fcbb88-028c-48be-8a5a-a261c2b4796a" + }, + { + "operation": "pe-resources", + "jobId": "b0c0cdff-31f0-4941-b412-6fd1a29fd26d", + "evidenceId": "ev_6058921f9a518b4099125fc822a1551ecd03fcdfedb038f5cfcfa7129125653d", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "bundleSha256": "b73f949f6286cdef97f691e150f1ad9f573c8bcbf045aac67c71d781372df61f", + "rootExited": true, + "reusedJobId": "46873081-bd94-459a-b3bf-c9572eb948d1" + } + ], + "actualEngine": { + "packageVersion": "0.2.1-rc.2", + "profile": "sdk-minimal", + "installationSha256": "2cec254a71163612bcd11c82a56eb5b1fbd742e352953b192bef310a8fb32b53", + "reportSha256": "fce7fd737f346f6b78981e544ac416fa2ac011c98faa3fe0daed0b35a0ffecf9", + "rootExited": true, + "modelRequests": 0, + "nativeMethods": [ + "initialize", + "session/working-directory/get", + "session/wait", + "session/resume", + "session/cancel", + "shutdown" + ], + "node": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030123032626\\runtime\\node.exe", + "bytes": 93915464, + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5", + "version": "24.22.1" + } + }, + "actualBrowser": { + "success": true, + "installation": { + "status": "available", + "engine": "Microsoft Edge", + "playwrightVersion": "1.64.1" + }, + "results": [ + { + "jobId": "cc6fda8e-5eeb-4f00-8f99-2820cb9a54af", + "taskId": "129cd7d0-806a-4497-85df-eb47d93e21aa", + "viewport": { + "width": 1280, + "height": 900 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "bd23a1ec5296655a890d10c57368922d07b6a3385d886781fd6e7f37c32e9d9e", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54", + "browserExited": true, + "reusedOriginalJob": true + }, + { + "jobId": "d2e4afd6-bf68-42d8-8e56-4d72ee82358c", + "taskId": "129cd7d0-806a-4497-85df-eb47d93e21aa", + "viewport": { + "width": 390, + "height": 844 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "0754d597427f2a80ab137f63dcfbf05d0060645ef6697b9c56fda4b5d4096678", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f", + "browserExited": true, + "reusedOriginalJob": true + } + ], + "modelRequests": 0, + "scope": "Actual API, locked browser runtime, two isolated Edge processes, CSS interactions, original DOM and PNG bytes. The task is created through the offline demonstration; no remote model is used." + }, + "steps": [ + "manifest hashes", + "bundled Node launch", + "same-service reuse", + "packaged example and static page", + "explicit command consent", + "actual bundled Node version", + "actual bundled npm check without system Node/npm", + "check log artifact", + "contained REA installation and Node identity", + "actual ASAR/imports/resources", + "original Bundle and target hash binding", + "verified reuse without producer replay", + "report availability", + "graceful stop" + ], + "realModel": false +} \ No newline at end of file diff --git a/docs/model-center-upgrade-live-validation.json b/docs/model-center-upgrade-live-validation.json new file mode 100644 index 00000000..2aa43b5f --- /dev/null +++ b/docs/model-center-upgrade-live-validation.json @@ -0,0 +1,291 @@ +{ + "success": true, + "testedAt": "2026-10-30T12:49:42.453Z", + "version": "1.12.0", + "pid": 19084, + "hasKey": true, + "projects": 15, + "sessions": 26, + "appDirectory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "verified": true, + "connectionPreserved": true, + "url": "http://127.0.0.1:4318", + "previousVersion": "1.11.0", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-center-deployment-2c6fe44f-0faa-4c24-add2-4a4f3ab2b1bb", + "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench", + "model": "gpt-6.1-sol", + "allSessionCount": 26, + "visibleSessionCount": 19, + "archivedSessionCount": 7, + "database": { + "projects": { + "count": 15, + "sha256": "b97d06f11ad99082d6641c5563ba0abf4edf714aa5cfc524edae4d2f5d7ce73f" + }, + "sessions": { + "count": 26, + "sha256": "4f8060276e735c54de6ecdf2bf9b309831157e9c0e9ef0bb705a6d4ded229370" + }, + "records": { + "count": 2505, + "sha256": "516b048d39d4026742fe34cfa90860ffa4a8f3ad33353c9981a80ce4ce233387" + }, + "events": { + "count": 4476, + "sha256": "d8dcd7ee88144e4adaba52763572058873963d40fdf75d088a05fb5505a31ad7" + } + }, + "recordKinds": [ + { + "kind": "artifact", + "count": 1415 + }, + { + "kind": "browser_job", + "count": 5 + }, + { + "kind": "browser_plan", + "count": 5 + }, + { + "kind": "change_set", + "count": 5 + }, + { + "kind": "check_job", + "count": 16 + }, + { + "kind": "check_plan", + "count": 17 + }, + { + "kind": "context_plan", + "count": 201 + }, + { + "kind": "delivery_job", + "count": 7 + }, + { + "kind": "delivery_plan", + "count": 7 + }, + { + "kind": "engine_job", + "count": 1 + }, + { + "kind": "run", + "count": 43 + }, + { + "kind": "step", + "count": 260 + }, + { + "kind": "task", + "count": 21 + }, + { + "kind": "tool", + "count": 499 + }, + { + "kind": "workspace", + "count": 3 + } + ], + "preservedSessionSnapshots": [ + { + "id": "03d6acd3-01ee-46fb-aa1c-90483307737e", + "session": "ce12fab8fa32c200b16851a66d7af6eea99ddb4783aa5c2ebd2211f7fbbfcb4b", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "0c9601a4-cc20-476c-aa28-ea010c222f70", + "session": "915912a528aa7578b56b5b1329518201102b4229a28a457a6916695cbd7eb287", + "project": "8de47871c83677c90f046ab4ef11b10f2bf6602e4e7683a68034f91665f18ae7", + "execution": "e826073aa1f1535941fe334dfc660aef9b3d888b192730d03dd314bd1a8c050d" + }, + { + "id": "0f3ace68-4988-4370-bf22-aac01f33a8ab", + "session": "462ab9235f6132141aab9b6fc9c03966d256970c8e19b98a17a38d1a0812b4b4", + "project": "b62f016403188e605f211acf90e6435af951fa772e339f5a967078dc49341dc9", + "execution": "ee93daaa7a1318ab0f98df6378d0afdbf8df5ead6d7e8a48b38c5ea5223fbd5c" + }, + { + "id": "1102be26-9799-4f0f-9a28-7a4ce552f3a9", + "session": "3303bc0113392be74ba3091f133a247b86acf7fdd935a9d3d7692a12a555f928", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "1cf22a27-ac13-4c95-a878-9b4356ccb5b3", + "session": "519eea1e103fd081279a82d4b4e72d17857a18b027eb0b156972855c90349552", + "project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1", + "execution": "1fdf39f6d6876e362cc130d621ddf22ae0887395fdaa21be822742e9d2c3367d" + }, + { + "id": "4442eee6-8b68-4bb5-a39c-9cafbaeb9eb8", + "session": "7c45225f6ace5f5397584a92e5303db762acdb2bfa311cc3d16e8fd6aaeb5253", + "project": "5ec499d561c29586cc0f4d4237d361d144bcbee14c1fc262479172a77d93b1a1", + "execution": "d1a01e32fbb6295a6aba6b788057eaa2354fd208610d9fbda1465ab96531fa71" + }, + { + "id": "4abc4201-549e-46e0-947c-3d3f5b53ffae", + "session": "2868af7181ce7ecbc903932c9f25fcaba421100317017dd9e3c94b5aebd5ebe5", + "project": "91f80e1c4cec343d0b632ad7e0b9eb8f732ca39c8290e40a8dc085f113339ffd", + "execution": "4e3ca3e707c618ae28d4ff8c6738c80a8b8dbbc6e272b9203a79219ed5c5f702" + }, + { + "id": "50c279be-66ad-48b8-a483-4e11c814db47", + "session": "9abdcf0865de6578dbfda995836e7e913f4f65ee38c0f40af90f7bb8a9f0ae87", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "569c9457-d399-46e6-b53e-4b1fdbb02109", + "session": "4daa494a90d4ed6d5161e4ea2cfe7ae60703b7c7722cb31621859d66bbb32677", + "project": "91f80e1c4cec343d0b632ad7e0b9eb8f732ca39c8290e40a8dc085f113339ffd", + "execution": "16b8c268db9de78d3f44461496f022371d0bd8345e124e27e20a08618c9cb0c3" + }, + { + "id": "57aee35b-7e64-46cf-a685-4867de8f4e0b", + "session": "61d32b2fdf93e5c4eec42d9f4cab28f3c24e7c7b0cf308e21f7ff3884870daec", + "project": "76532f9c3e309accdb4e46a50552ed347d089d63096efedf1372444527ae1ea3", + "execution": "cf40e7826c922323a84e7a5260000992527eb8956bbc8c6f1632bab358aa408c" + }, + { + "id": "596df050-d490-44da-be1c-bcaf58c88dc0", + "session": "870300930ed9b8791b2d3381df7bd9c6ae7578aa39ba0fed72b606c9af548adb", + "project": "3b83f6c68b0af564e8732559ff71514f738252a0fd2d097db61c9a023f179d79", + "execution": "68fc0ee38d3101de7d2d75a8d821ec71ec97fbaf996fa5924b413bac20adb4b9" + }, + { + "id": "72d3d22f-14d9-4bca-bb6a-ab686bc96b26", + "session": "707ebc4a9c4dd210eacb5f3c2b119fe999085e6b157df50dd89180706df812e0", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "339307371999d6e01c107c102d0b0e17609f263aed6eb05cd48eb63dd17df7e5" + }, + { + "id": "776d488f-18a7-41aa-96a4-91dd1f19d374", + "session": "dc9824b3cd6e7203e6e805ab7291bd6c4b514c7524637a937e487c32853aab1d", + "project": "bcaad9ff6ce07b52fbe8f23009bc72f8928c2f2a4859099bfbd3121d52d0bca3", + "execution": "9e11585ede5558f130e22f01deb51d7d1f1f35582ab390fcd1a749378fa221a5" + }, + { + "id": "77f7237d-b7b4-4725-b82b-0781a669740b", + "session": "27f35a1b6db0905f20b758abc68c79286a703c6557eeef7bcb95bc17c13eafa0", + "project": "d881bf752b0e14b37c0325d077a459b08be741605aef0db775195d2de66c4595", + "execution": "66dcd67380219986a70e663e87a38d6d511dab82b4873beb1628ff4f193d6581" + }, + { + "id": "87a48440-804e-4ac4-8a9f-5ba38a55c082", + "session": "b4e9c835232835730d601c1a327795602c5bc21bf330d30b67acd0f5b57720fa", + "project": "3b83f6c68b0af564e8732559ff71514f738252a0fd2d097db61c9a023f179d79", + "execution": "a2748e42a4fd85c61e5f9ad9c604c33996592039f5268fdaec4529e60fc17377" + }, + { + "id": "997213e9-ccd7-485e-a099-ad348b626610", + "session": "7edddb9135e4c0694e9e375d00d0db38f889b47c3cd8ce9c118873e3ab17c9a8", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "af2827eb-b31c-456e-b9ab-6f34ab8f600e", + "session": "8b5fcd43f63f2dcb5a2bf65c9503b02147f3e0a76ca5da6c84cb588b53b1714c", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "b045829c-377b-4f69-ad0b-513fe797b421", + "session": "44040c046fd23053228a203745112b277acfcb191ae5a5ce957dd7090c983a2f", + "project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1", + "execution": "e441f4dbf00fbe867072c0cf89134eb81e33bce2ad87848bc573d6fb577a491f" + }, + { + "id": "c25669d5-9c3b-4548-80d5-51c58a3c5e73", + "session": "e662f26079c573528662fe5a144142fc938f8a316a74afea9a4eaffd4fa25e69", + "project": "e5048b792e2681faf68f83b4cd35a7e321dce4ac0dafd07d8b6007d430db66bf", + "execution": "b3c9912482a56bda774344e7da9db4b7e05a661896f15554c1f95d9f56075f5d" + }, + { + "id": "c32c9c87-8239-4606-a4c0-783529603bc7", + "session": "5a9d028a1054136e85c2037d4151709c3d835d9edb2e67476e3dd9becb493e83", + "project": "6b00a6786f0a47fc81edbcdb39300b0d486deea338d1c4c327395da64238f331", + "execution": "989ea006d275a3a8127409ac55d2efffb0990a11c9b825ae970a2e2f3fe8392a" + }, + { + "id": "c52d620a-dbaa-4bbd-9039-0eabe53ba03d", + "session": "019799045a657a75bf74f2cb659ca00aa31e55a8c1609df64ac007ee4b1a9c61", + "project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa", + "execution": "fc07423c0785459b1860eca780a5f50d0d8da5237062fc9c77dfcfeac348f6aa" + }, + { + "id": "dccf608f-44c9-4031-a58c-5ba87fe3b3f8", + "session": "00018e8b18ba8311b139cce9ab5c5414c26b8893b3234efd8f54804711978ed1", + "project": "844f1c9a520e159edb9e76a169d674484386ca30a141e47de720a8c2ec4d4acd", + "execution": "d1c4dc43bbcfec94500e51d23ba4f995c55f798fd27a53fa2d3d63172a7e4b1c" + }, + { + "id": "e8846c6e-1ba2-497e-b0db-ca5778181eb0", + "session": "81477eeefcdf965fdd9091e05670df99e3817f7cbc6ab56605c215262ec3cd5c", + "project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1", + "execution": "7a000c717f543db70875d9f163766606a1bc9ec8747881e5d91a9fafa7d2a084" + }, + { + "id": "ea5ec3cb-b074-41ac-989c-34c6515bd742", + "session": "983e92750affa53234ea805de39889e58c5a2a1b4e016e8a84d1ff15d83bb918", + "project": "3b83f6c68b0af564e8732559ff71514f738252a0fd2d097db61c9a023f179d79", + "execution": "3d6af5dd21d62fa98fd36ce353111b08bb48194985d16262d7bd9a7ca036e0a6" + }, + { + "id": "f8a5a714-183d-4d6c-af27-ed56c60225b2", + "session": "cff80cd569d20f8294703ad3fce75555a21b911e07339220a5bb2a31c01eb78d", + "project": "d3025c877b071c0815d63323d883f68be4e778ba4392ab2bae91cf24cd34e29f", + "execution": "daab52abf10ac06e6a0e1b2b13cd4bd0f9de620e9b6404392041212d63df8808" + }, + { + "id": "fc87c3f6-a108-4095-ae41-4ef56bc789c3", + "session": "49dbf09c02b74d867df47a65185c60f5fac173ed114ccd6e7adf261a93e71b1f", + "project": "72cc4e0235d860965503c3b4f7d0a59f5f8a8720592e10578c4da7ab36bf1af1", + "execution": "4dce8aa90154d21f6f34e2a562cc567cc37f0eb06dd600094b1b47278b97b5df" + } + ], + "allRowsAndExportsPreserved": true, + "inspectorClosed": true, + "comparedFiles": 8796, + "repackedMetadata": [ + { + "path": "runtime/REA-RUNTIME.json", + "currentBuiltAt": "2026-10-30T12:44:54.516Z", + "testedBuiltAt": "2026-10-30T12:30:32.624Z", + "currentSha256": "8616c96d919dae8f47feaf640906baf274f3eca0687622dcdc48d89d4efd410e", + "testedSha256": "31e7027e4e89cc0dddcca0139941ca27cf3485160c54213be43c1abfd518b820", + "difference": "builtAt only; all other JSON fields equal" + } + ], + "frozenInputs": 213, + "frozenInputsSha256": "083a71f9b2b6d508fe348097b4d07e94be44196872c9e99663eb06e778a509a1", + "independentSourceRoot": "D:\\awb\\source-check-052aaa95cdf244ca87aa37f9048aeb0b\\Agent-Workbench-1.12.0-source-20261030123032626", + "independentSourceTests": { + "tests": 357, + "pass": 357, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "uiGroups": 150, + "realModel": { + "status": "deferred", + "reason": "User chose local validation first and model configuration later.", + "requests": 0 + }, + "comparison": "Exact canonical hashes for every persisted project/session/record/event and every exported project/session/execution; only an absent mcpJobs field is projected to an empty array.", + "credentialsHandling": "Only public hasKey/model/config hashes are inspected. The existing Provider retains any connection in memory. No model key is read, copied, printed or saved; no model request is sent." +} diff --git a/findings.md b/findings.md index 2d4ae3d9..c0b18976 100644 --- a/findings.md +++ b/findings.md @@ -397,3 +397,10 @@ Claude Code 报告已验证工具输入校验、权限决定、队列并发屏 - 最后MCP参数边界已用13200字符原审批与真实stdio结果复验,20项专项和6+2组界面全部通过。终端6000字符限制保持,MCP审批单独24000字符但实际参数仍限16000字节。 - 独立源码首轮原生DeepSeek核验未给安装目录,隔离到D:/awb后无法按父目录自动发现;原环境失败保存docs/model-center-source-environment-failure.json。显式指定现有deepseek-harness目录后,REA/原生SDK/浏览器通过,完整回归已开始;不改产品源码。 + +## 2026-10-30 1.12最终验收与正式服务 + +- 最终独立源码357/357、213份输入、6份构建与6阶段日志均通过;最终发行ID20261030124454517,便携11061文件、源码9342文件,归档和实际便携运行分别验证。完整界面20类150组及最后标题栏/MCP专项复验有独立原证据,不能用此前353项基线代替最终结果。 +- 正式服务已是1.12.0/PID19084,原Provider和公开hasKey=true状态保持;15项目/26全部会话/2505执行记录/4476事件逐行散列与导出一致。部署后8个桌面/390px页面状态只读复验通过,四类数据库仍不变。物理service-info.appRoot保留最初启动目录,实际runtimeRoot和健康版本才标识已升级运行代码。 +- 最终包与测试输入逐份核对,REA-RUNTIME.json仅builtAt不同,其余JSON字段及全部依赖散列严格一致;未广泛忽略清单。209份输入与Git原字节一致,4份旧文件仅CRLF/LF差异且规范化后逐字节相同,未为凑散列改写原文件。 +- 6阶段原日志与13份报告散列封存在docs/model-center-release-identity.json;真实模型请求为0,既有用户选择继续有效。桌面壳、手机配对、隔离worker、多协议/多模态和真实工程成功率均为后续独立开发或验收范围。 diff --git a/progress.md b/progress.md index 50482239..2d11310f 100644 --- a/progress.md +++ b/progress.md @@ -441,3 +441,20 @@ - 审查发现MCP允许16000字节参数,但requestCommand复用终端6000字符限制,长参数在审批前失败;已以13200字符真实stdio/模型夹具复现,失败保留.qa/mcp-long-approval-initial-failure.log。MCP审批上限单独为24000字符,原终端限制不变,参数仍按16000字节/schema核对。 - 修复后20/20 stdio与注册专项通过,含长参数完整审批/实际结果/目录核验;最终构建与MCP6组管理+2组实际崩溃恢复界面通过。原20类150组功能UI与最后标题栏5组复验分别封存,不覆写旧结果。 - 已变更源码统一LF后重新封存候选,确保Git字节身份可核对。前两次候选仅完成ZIP/目录清单验证,不作为最终源码验收;以下最终候选将从独立解压源码完成全量回归。 + +## 1.12最终源码与发行回归进行中 + +- 代码实现已本地提交3f6797b;候选20261030123032626的源码/便携ZIP及目录清单通过,便携启动/复用、4/4实际检查、REA三操作、DeepSeek六方法与Edge两视口通过并正常停止。 +- 固定Node24.22.1、Python3.10.11/pytest8.4.2并显式指定D:/Ai-project/DeepSeek-Harness-Desktop/deepseek-harness;独立源码离线安装/构建、六份构建匹配、REA/DeepSeek/浏览器通过,完整回归进行中。原目录D:/awb/source-check-052aaa95cdf244ca87aa37f9048aeb0b/Agent-Workbench-1.12.0-source-20261030123032626/.qa/package-validation-d444505e-0fc9-4d6e-9a36-f75524c658d2,原输出tests.tap;会话8482。 +- 213份实际冻结输入与Git HEAD对比:209份完全相同,4份原有未修改文件仅CRLF/LF区别,已逐字节验证规范化后等于Git blob,详见.qa/model-center-git-inputs.json。第一次严格原字节比较失败不代表代码差异;未改写旧原文件以凑散列。 +- 正式4318仍1.11.0/PID19084、Provider保留,真实模型0请求。待完整回归通过后,整理验收文档的最终不可变包(仅文档更新,代码逐份与测试输入一致),重新验证最终ZIP与便携,再按.qa/finish-model-center-deployment.mjs及只读页面smoke升级,原4类数据库与全部26会话导出需保持。 +- .qa/seal-model-center-evidence.mjs用于部署后核验原日志、冻结输入/Git、所有报告和smoke后数据库,再封存发行身份。全量回归未完成前不得宣称最终通过。 + +## 2026-10-30 1.12正式交付与证据封存 + +- 独立源码完整357/357通过,0失败/取消/跳过/todo,耗时640666.0334ms;213份冻结输入前后一致,6份构建逐字节匹配,6阶段原日志散列核对通过。最终TAP SHA256为662bf1708cb8b3f7781de47f1fda62f6879a8f12967184ee5213adcd8f849d86,原目录与失败记录均保留。 +- 最终不可变发行20261030124454517完成源码9342文件/便携11061文件的ZIP CRC、目录、清单与SHA256核对;便携启动/复用、4/4实际检查、REA三操作、DeepSeek六方法、Edge桌面/390px和正常停止均通过。最终封包仅整理文档,代码/测试/脚本/配置与独立测试输入一致;完整界面20类150组、标题栏5组及最终MCP6+2组复验分别封存。 +- 已保留原PID19084和Provider升级正式4318至1.12.0。15项目、26会话(19可见/7归档)、2505执行记录和4476事件的逐行散列及全部会话导出一致,公开模型配置不变。213份输入与随包文件完成8796次比较;REA运行清单仅builtAt打包时间不同,其他字段和依赖散列严格匹配,差异单独登记。 +- 部署后1280px/390px各检查执行计划、模型中心、Skills和MCP,8个实际页面状态通过,0页面异常/请求失败/HTTP错误/写入请求;四类数据库散列仍一致。6阶段日志和13份报告已封存docs/model-center-release-identity.json,调试端口9229关闭,本轮真实模型请求0。 +- 升级前首次REA清单时间差使流程在新handler安装前停止;部署后Python环境缺Playwright使检查在浏览器启动前退出,随后使用锁定Node Playwright完成8组只读复验。两次均保留原记录,不修改产品代码、不重放工具或调用模型。 +- 本轮收尾仅修正文档中的旧候选/未发布状态,补充最终验收和后续开发顺序。代码已由3f6797b封存;最终报告和规划另作本地文档提交,不推送。下一独立阶段为隔离worker及受控外部引擎,再推进桌面、真实手机配对、多协议/多模态与迭代评测;真实模型验收继续按用户选择暂缓。 diff --git a/task_plan.md b/task_plan.md index 0db53e9e..63289fbf 100644 --- a/task_plan.md +++ b/task_plan.md @@ -1,12 +1,12 @@ # Agent Workbench:核心代理能力研究与产品计划 -## 2026-10-30 当前接续:1.12 完整候选与本地交付 +## 2026-10-30 当前接续:1.12 完整发行与本地交付 1. [complete] 模型中心/池、来源核对记忆、检查点、Skills已本地实现并分段提交;MCP实际stdio、未知结果门控、人工核对与无报告恢复已补强。 2. [complete] MCP补强后20项专项、6组管理与2组真实中断界面通过;353项旧全量仅作为补强前基线,不替代最终源码结果。 3. [complete] 统一1.12版本/文档/验收脚本;20类150组界面通过,标题栏5组复验及最终MCP6+2组复验通过。修复并实际复验长MCP参数审批上限,20项stdio/注册专项全通过。 -4. [in_progress] 最终不可变便携/源码/ZIP与独立源码完整回归,核对输入与构建/日志散列;本地Git提交。 -5. [pending] 按已有流程保留原PID/Provider/全部历史升级正式4318;只读桌面/390px复验,模型请求为0。 +4. [complete] 最终不可变发行20261030124454517:357/357独立源码、213份输入/6份构建、6阶段日志与150组UI通过;新源码/便携ZIP与运行验收通过,代码提交3f6797b。 +5. [complete] 正式4318保留PID19084/Provider升级1.12.0,15项目/26会话/2505记录/4476事件逐行与全部导出一致;部署后桌面/390px共8个页面通过、数据库不变、调试端口关闭,真实模型0请求。 6. [pending] 下一独立阶段开发隔离worker与桌面/手机网关;真实模型工程验收继续按用户选择暂缓。 ## 前序:项目记忆与上下文 @@ -15,7 +15,7 @@ 2. [complete] f7292a9封存记忆管理和验证文档;正式4318保持不可变1.11,不重启、不读取凭据、不发真实模型请求。 3. [complete] 已核对current记忆接入有界请求,10项新边界+原7项管理、桌面/390px原快照和最终322/322全量通过;199份输入与原TAP封存,真实模型0请求。 4. [complete] af0a42b封存记忆上下文。Task恢复检查点内核/API/界面、12项专项和桌面/390px三组通过;最终334/334全量、204份源码/构建输入一致和原TAP封存,真实模型0请求。 -5. [in_progress] 按依赖先开发版本可追溯、可启停的Skills/MCP注册与调用契约,复用Task/Run、权限、预算和取消;之后推进隔离worker和桌面/移动。计划或夹具结果不登记为真实模型交付。 +5. [complete] 版本可追溯、可启停的Skills/MCP注册与调用契约已随1.12本地交付;隔离worker和桌面/移动按下一独立阶段推进。计划或夹具结果不登记为真实模型交付。 ## 当前切片:版本化本地Skills @@ -29,9 +29,9 @@ 1. [complete] 登记绝对可执行文件/可选Node入口、固定参数、文件SHA和配置修订;默认停用。探测/调用均明确确认,固定2025-03-26协议,实际tools/list+schema冻结,不从annotations推断权限。 2. [complete] 完成独立所属进程、凭据隔离、Task/Run原报告、预算/取消/unknown不重放;未知结果阻止新任务与副作用,核对同步工具/恢复账本,持久化失败恢复内存。 3. [complete] MCP管理/权限/报告/无报告原输入核对、变更程序停用与390px换行已验收;20项stdio/注册专项和6+2组实际界面通过。 -4. [in_progress] 纳入1.12完整候选与独立源码冻结验收,通过后本地提交和正式服务保留状态升级;真实模型单独待验。 +4. [complete] 已纳入1.12完整发行:357项独立源码、相关界面、最终包与保留状态正式升级通过;真实模型单独待验。 -## 当前执行:1.11本地交付完成,1.12-A/B/C/D进入实现与验收 +## 前序执行:1.11本地交付完成,1.12-A/B/C/D进入实现与验收 最新接续:main已封存1.11交付2bd7d48及报告散列修复0442c48;正式4318为1.11.0/PID19084,15项目/26全部会话(19可见/7归档)。原PID23080在断线期间退出,PID19084沿用原数据。验收期间公开hasKey由false变为true,升级保留原Provider和当前公开配置;本轮0模型请求,真实模型续接按用户选择暂缓。