docs: seal Agent Workbench 1.20 release and milestone review

This commit is contained in:
Agent Workbench Dev
2026-11-01 12:31:20 +08:00
parent 49314764f5
commit 3f4784ea97
1228 changed files with 1909859 additions and 48 deletions
+2 -2
View File
@@ -1,6 +1,6 @@
# Agent Workbench项目执行规范
1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 不可变Agent-Workbench-1.19.0-win-x64-20261031184556353,来源c685546f9acfb496977d9744700d62ab1f5c2865。原件见docs/project-cache-f-release-evidence/manifest.json及docs/project-cache-release-identity.json;下一PLAN-1.20仅方案。
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。 不可变Agent-Workbench-1.20.0-win-x64-20261101024825846,代码来源49314764f571ad48b7cef38d62c32b0bb66a8e9f;原件见docs/engineering-evals-f-release-evidence/manifest.json及docs/engineering-evals-release-identity.json,下一PLAN-1.21仅方案。
## 范围与目标
@@ -60,7 +60,7 @@
## 当前本地服务与Windows
- 正式服务入口http://127.0.0.1:4318,当前1.19.0,沿用用户手动启动的PID36552与原Provider;当前运行目录及数据身份以docs/project-cache-release-identity.json为准,完整F及原生回看已通过。1.15期间旧内存Key丢失是历史记录;本轮原连接配置和当前Provider均保持。普通源码/规划/Git工作不重启服务、不读取或复制Key。
- 正式服务入口http://127.0.0.1:4318,当前1.20.0,沿用用户手动启动的PID36552与原Provider;当前身份以docs/engineering-evals-release-identity.json为准,完整F及原生回看已通过。本轮原连接、全部表/会话/工件均保持;普通源码/规划/Git工作不重启服务、不读取或复制Key。
- 浏览器/fixture验证使用独立端口与数据目录;用户项目与研究对象的登录/会话配置不用于测试凭据。
- Windows执行环境以实测shell为准。现有工具使用PowerShell 5.1和UTF-8;不用&&/||拼接命令,使用换行和$LASTEXITCODE核对结果。
- 桌面与移动共用执行宿主。手机127.0.0.1指手机,远程接入通过未来经验证的配对网关。
+1 -1
View File
@@ -6,7 +6,7 @@
- 原版只执行原检查,候选复用原模型连接/池、提案审查、命令审批与停止恢复;测试、脚本和运行声明保持原输入,执行前后核对来源。
- 桌面/窄屏展示原版与候选的全部检查尝试、失败/停止/未知、日志SHA、人工审批/应用、用时和上游实际用量;缺失费用显示未报告,固定响应标签持续可见。
- 全部样本封存后可采纳一项候选,必须经过父工程变更集审查、新检查及精确范围本地Git交付,保留父原暂存/未提交内容。
- Node8/8、React9/9、Python10/10及来源绑定自身模块9/9的14节点试点通过。自身汇总修复已执行未封存状态误算未执行的问题;不据固定响应宣称模型推理收益或全仓自主升级。完整发行结果见QA-1.20。
- Node8/8、React9/9、Python10/10及来源绑定自身模块9/9的14节点试点通过。自身汇总修复已执行未封存状态误算未执行的问题;不据固定响应宣称模型推理收益或全仓自主升级。完整发行604/604独立源码、28类210组界面、随包新评测5组、同载荷安装7组、正式26页及原生回看通过;原PID/Provider、全部表/会话/工件保持。原版本遗漏失败及重验分别封存,真实模型请求0,详见QA-1.20。
## 1.19.0 · 来源核对的项目解析缓存
+4 -4
View File
@@ -1,8 +1,8 @@
# 本地 Agent 工作台
1.20.0候选正在进行完整发行验收。「工程评测」可固定需求和原测试、准备同源工作区、对照原版/候选真实结果,再经过父审查/检查/Git采纳。四类工程14节点与桌面/390px7组已通过;正式入口暂时保持1.19。见[使用说明](docs/ENGINEERING-EVALUATIONS.md)、[当前验收](docs/QA-1.20.md)与[回顾](docs/RETROSPECTIVE-1.20.md)。
1.20.0已完成本地正式升级和验收。「工程评测」可固定需求、来源和原检查,准备同源原版/候选,核对真实失败、改动与人工操作,再经父审查/检查/Git采纳。独立604项、210组历史界面、四类工程14节点及安装/升级/原生回看通过;原连接和全部历史保持。见[工作台](http://127.0.0.1:4318/?release=1.20.0)、[使用说明](docs/ENGINEERING-EVALUATIONS.md)、[验收](docs/QA-1.20.md)、[身份](docs/engineering-evals-release-identity.json)和[下一阶段](docs/PLAN-1.21.md)。固定响应验证执行链,真实模型自主完成率仍单独验收。
1.19.0已完成本地正式升级和验收。工程「索引 → 解析缓存」可查看当前来源核对、真实复用/失效和容量,管理本机开关或仅清除本项目派生材料。独立590项、203组历史UI、三类实际工程、安装/升级、正式24页及原生回看通过;原连接和全部历史保持。跨实例Node/React有局部收益,冷/热/失效仍有来源核对开销,Python未得稳定收益。见[工作台](http://127.0.0.1:4318/?release=1.19.0)、[缓存](docs/PROJECT-CACHE.md)、[验收](docs/QA-1.19.md)、[身份](docs/project-cache-release-identity.json)和[后续方案](docs/PLAN-1.20.md)。
1.19.0历史交付项目解析缓存。工程「索引 → 解析缓存」可查看当前来源核对、真实复用/失效和容量,管理本机开关或仅清除本项目派生材料。独立590项、203组历史UI、三类实际工程、安装/升级、正式24页及原生回看通过;原连接和全部历史保持。跨实例Node/React有局部收益,冷/热/失效仍有来源核对开销,Python未得稳定收益。见[工作台](http://127.0.0.1:4318/?release=1.19.0)、[缓存](docs/PROJECT-CACHE.md)、[验收](docs/QA-1.19.md)、[身份](docs/project-cache-release-identity.json)和[后续方案](docs/PLAN-1.20.md)。
1.18.0历史交付工程截图、视觉选路与预算续接。可为工程任务添加PNG/JPEG截图,核对实际视觉选路及原图/发送副本;预算暂停会显示具体分解,预览确认后继续同一Task。独立源码576项、196组历史UI及截图Node/React/Python工程通过,原项目、会话和模型连接保持。见[工作台](http://127.0.0.1:4318/?release=1.18.0)、[截图与续接](docs/INPUT-ATTACHMENTS.md)、[验收](docs/QA-1.18.md)、[发行身份](docs/vision-inputs-release-identity.json)和[下一阶段](docs/PLAN-1.19.md)。
@@ -34,7 +34,7 @@ Agent Workbench 将 Claude Code 与 Cursor 的机制研究整合为独立的本
## 后续产品与能力建设
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。1.13两个受限worker与1.14受控引擎/提示实验均已完成发行;1.15桌面和本机加密完整发行已验收,具体结果以[QA-1.15](docs/QA-1.15.md)为准;1.16手机伴随端及1.17两协议/流式/能力路由均已交付;1.18工程截图、视觉选路与预算续接已完整本地交付;1.19来源核对的项目解析缓存已完整交付;下一[1.20工程质量评测与受控自我迭代](docs/PLAN-1.20.md)仅方案。
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。1.13两个受限worker与1.14受控引擎/提示实验均已完成发行;1.15桌面和本机加密完整发行已验收,具体结果以[QA-1.15](docs/QA-1.15.md)为准;1.16手机伴随端及1.17两协议/流式/能力路由均已交付;1.18工程截图、视觉选路与预算续接已完整本地交付;1.19来源核对的项目解析缓存已完整交付;1.20固定工程评测与受控候选采纳已完整交付;下一[1.21工程依赖与可复现环境](docs/PLAN-1.21.md)仅方案。
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)。
@@ -51,7 +51,7 @@ Agent Workbench 将 Claude Code 与 Cursor 的机制研究整合为独立的本
## 直接运行
Windows x64 1.19桌面/便携包自带Node.js 24.22.1、npm、Electron 45.2.0、REA 6.8.0、Playwright 1.64.1及锁定生产依赖。页面验收使用本机Microsoft Edge。安装版双击安装目录的AgentWorkbench.exe,便携版双击Start-Desktop.cmd打开桌面;Start-Workbench.cmd仍可打开浏览器入口http://127.0.0.1:4318。当前安装/发行状态见[QA-1.19](docs/QA-1.19.md)。
Windows x64 1.20桌面/便携包自带Node.js 24.22.1、npm、Electron 45.2.0、REA 6.8.0、Playwright 1.64.1及锁定生产依赖。页面验收使用本机Microsoft Edge。安装版双击安装目录的AgentWorkbench.exe,便携版双击Start-Desktop.cmd打开桌面;Start-Workbench.cmd仍可打开浏览器入口http://127.0.0.1:4318。当前安装/发行状态见[QA-1.20](docs/QA-1.20.md)。
启动不需要安装 npm 依赖或管理员权限。窗口关闭后本地服务仍运行,任务与会话继续保存。再次打开相同地址即可查看记录。
+9 -1
View File
@@ -1,5 +1,13 @@
# Agent Workbench 能力目标与验收矩阵
## 当前1.20交付
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。
见[使用说明](ENGINEERING-EVALUATIONS.md)、[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[发行身份](engineering-evals-release-identity.json)。下一[1.21方案](PLAN-1.21.md)聚焦工程依赖与可复现环境,尚未实现。
C01/C02/C07/C09/C11/C13/C15/C24:每批1–3固定样本、原测试保护、两个同源工作区、原版0模型请求、候选审批/检查、失败与未知保留、JSON/Markdown原报告和单个候选受控采纳。工作台自身试点绑定原提交模块;非OS沙箱,不直接更改运行发行。
1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 见[1.19验收](QA-1.19.md)、[回顾](RETROSPECTIVE-1.19.md)、[缓存契约](PROJECT-CACHE.md)和[发行身份](project-cache-release-identity.json)。
1.18.0完整本地交付:PNG/JPEG工程截图、原图/发送副本SHA、Chat/Responses实际视觉输入、按任务能力选池、独立视觉检测和具体预算诊断已实现;冻结预览确认后在同Task新建Run续接,原完成/未知工具不重放。独立源码576/576、26类196组历史UI、随包原生窗口7项/原生流程9组/桌面三工程16节点、Responses三工程13节点、新截图三工程7节点及Node8/8、React9/9、Python10/10通过;源码/便携各7组伴随端、5组协议和5组视觉流程,同载荷隔离安装/重启/卸载7组、正式20页及原生回看通过。正式PID36552/Provider保持,17项目/30全部会话/2614记录/4701事件,全部表每行/会话导出/模型中心/工件原字节保持;1466条工件和1376个去重文件核对通过,9229关闭。手机新增截图只读观察/SHA/下载,正式网关保持关闭、无QA设备或证书迁入。本轮验收发起真实模型请求0;安装期间工作台新增的原1.17调用单独保留,不计为1.18视觉验收。真实模型视觉工程/Purge收益及新增iPhone流程实机仍分别待验。 见[1.18验收](QA-1.18.md)、[回顾](RETROSPECTIVE-1.18.md)与[发行身份](vision-inputs-release-identity.json)。
@@ -152,7 +160,7 @@
| C21 桌面产品 | 1.15真实Electron窗口/后台宿主拆分、单实例、原生入口、安装/更新/回退/卸载完整发行和正式保留状态部署已交付 | Electron Windows安装/升级、后台执行宿主、工程/终端/diff/成果区和任务通知 | 产品方案 / desktop、gateway / M5 | 关闭窗口后可再查看任务;安装/升级保留数据;宿主进程生命周期明确 |
| C22 手机伴随端 | 1.16默认关闭HTTPS、一次性配对、项目/操作授权、原Task/Run审批/停止及SHA报告、PWA壳和断线恢复已实现;真实iPhone核心与完整独立发行通过。iPhone 14 Pro Max/iOS 27.2为用户提供,原生操作由用户确认、原审计/进程/文件另验 | PWA任务/进度/审查入口;配对网关与设备撤销;共用Run与事件游标 | 产品方案 / mobile、gateway / M5 | 实际手机连电脑并审查同一任务;断线补发不重复执行;失效设备不能授权 |
| C23 数据、配置与发布迁移 | 临时Key默认内存;1.15新增显式DPAPI保存/关闭/删除、同事务回退和安装根入口/指针回退已实际验收;正式发行已通过,1.16设备配对/撤销已验收 | 用户主动配置凭据、系统凭据存储、数据库迁移/回退、版本兼容和日志导出 | CX-2、DS-1 / storage、gateway、desktop / M1、M5–M6 | 升级副本与回退可验证;导出无Key;任务和来源不丢失 |
| C24 工程能力评测 | 固定40原基准、实际Node/React/Python检查/构建/页面/Git;1.19新增缓存9节点与108次旧/新比较,保留原失败及开销;质量比较/隔离自身候选产品流程见PLAN-1.20,尚未实现 | 固定样本、重复评测、原分母/失败/未知、人工介入及实际用量 | 全部目标 / evaluation、artifacts / M1–M6 | 固定回答只证明协议和执行链;自主成功率及视觉/Purge真实收益单独评测 |
| C24 工程能力评测 | 1.20固定样本/同源原版与候选/全部尝试/原报告/受控采纳已完整交付;Node8/8、React9/9、Python10/10及自身模块9/9,四类工程14节点通过;固定HTTP与真实模型收益分开 | 固定样本、重复评测、原分母/失败/未知、人工介入及实际用量 | 全部目标 / evaluation、artifacts / M1–M6 | 固定回答只证明协议和执行链;自主成功率及视觉/Purge真实收益单独评测 |
### 1.6.1 M2实际工作依据切片
+9 -1
View File
@@ -1,6 +1,14 @@
# 里程碑回顾与修复审查
## 当前节点:1.19完整本地交付
## 当前节点:1.20完整本地交付
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。
见[使用说明](ENGINEERING-EVALUATIONS.md)、[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[发行身份](engineering-evals-release-identity.json)。下一[1.21方案](PLAN-1.21.md)聚焦工程依赖与可复现环境,尚未实现。
回顾发现并修复:同批样本迟到报告归属、已执行未封存状态误算未执行、发行包/实际服务版本标识不一致,以及旧界面验收版本白名单遗漏。原失败及前两次冻结保持,最终代码4931476重新独立验收;未放宽现有快照边界或直接替换运行目录。
## 1.19历史节点:完整本地交付
1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 见[1.19验收](QA-1.19.md)、[回顾](RETROSPECTIVE-1.19.md)、[缓存契约](PROJECT-CACHE.md)和[发行身份](project-cache-release-identity.json)。 原Esc中断及中间封存保持;本轮重新观察1.19正式原生窗口后完成F,独立ACCEPTANCE绑定交付Git。
+5 -5
View File
@@ -1,10 +1,10 @@
# 后续执行计划
更新:2026-10-31。1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 见[1.19验收](QA-1.19.md)、[回顾](RETROSPECTIVE-1.19.md)、[缓存契约](PROJECT-CACHE.md)和[发行身份](project-cache-release-identity.json)。
更新:2026-10-31。1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。 见[使用说明](ENGINEERING-EVALUATIONS.md)、[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[发行身份](engineering-evals-release-identity.json)。下一[1.21方案](PLAN-1.21.md)聚焦工程依赖与可复现环境,尚未实现。
产品目标是让用户给出需求后,工作台能保留项目基线,完成定位、计划、修改、检查、必要修复、审查和Git交付,并在停止、故障、断线后明确保留已完成结果。桌面与手机共享同一执行宿主、任务和证据。
当前接续:1.19 A–F、保留状态正式升级、原生回看及回顾已完成。下一[PLAN-1.20](PLAN-1.20.md)推进固定工程评测、原版/候选对照和隔离自我迭代。原用户Esc中断及867份中间封存保持,后续原生观察和完整F使用新原证据;每切片验收、回顾并本地Git。
当前接续:1.20 A–F、独立发行、保留状态正式升级及原生回看已完成。下一[PLAN-1.21](PLAN-1.21.md)优先补齐工程依赖诊断、固定准备计划、审批/停止与可复现环境,解决本轮React仍需QA显式安装依赖的真实缺口;每切片验收、回顾并本地Git。
## 执行顺序与完成门槛
@@ -17,7 +17,7 @@
| 3:Windows桌面(1.15完成) | 单实例、后台宿主、项目/终端/审查入口、安装包与保留数据更新 | 宿主与客户端生命周期拆分;本机凭据加密;稳定迁移契约 | 关闭/重开窗口不丢任务;重复启动复用宿主;安装/升级/卸载的数据行为可核验;崩溃后显式恢复;旧版本可回退 |
| 4:手机伴随端(1.16完成) | PWA、一次性配对、设备身份、撤销、同Run观察/审批、断线游标补发 | 设备认证、加密传输、审批身份/幂等、速率限制;阶段3宿主 | 在真实手机完成配对和撤销;断线后按seq恢复;旧Run/过期/重复审批拒绝;手机和桌面显示同一结果;手机不直接执行宿主文件与命令 |
| 5:模型、多模态与上下文 | 1.17协议/流式、1.18PNG/JPEG视觉/预算续接已交付;1.19缓存独立发行、正式升级及原生回看通过;语音后续独立实现 | 实际协议/用量/取消和所属附件/缓存边界 | 原失败保持,缓存可关闭/清除并核对当前来源;局部收益与复核开销并列,真实推理另验 |
| 6:自我迭代与专业交付 | 隔离分支生成候选、固定评测集、多模型复核、质量/成本对照、升级候选和回滚 | 可复现工程基准、完整质量门槛、阶段1隔离和阶段3更新 | 工作台可提出并验证自身改进;候选不直接改运行中的发行;回归或独立验收失败不能发布;保存原差异、指标和回退点;采纳须经用户已有权限规则 |
| 6:自我迭代与专业交付 | 1.20固定评测、同源原版/候选和受控自身模块采纳已交付;多模型复核、更多样本及全仓升级后续分别验收 | 固定来源/原检查、同源环境、现有审批/审查/检查/Git及完整独立发行 | 候选不直接改运行中的发行;回归失败不能发布;保留原失败、人工介入及实际用量,不从固定回答推断模型收益 |
阶段间可并行完成只读研究和文档,涉及项目写入、权限、发行的实现按依赖推进。每个切片提交真实功能、失败分类、验收证据和本地Git提交;不自动推送远端。
@@ -37,7 +37,7 @@
按[PLAN-1.14](PLAN-1.14.md)已固定DeepSeek Harness的prompt/事件/审批/停止契约并通过受限桥完成所属工程、父审查和Git;实际SDK仍缺少session/cancel,停止单位为所属进程树,旧SDK会话不自动恢复,逐token流未实现。Codex等其它适配按具体版本独立推进,不能从连接成功推断能力。
DSH-purge两版本的来源锁定和同题本地HTTP夹具对照已完成,独立提示实验默认关闭;真实推理收益继续待验。当前[1.15桌面阶段](PLAN-1.15.md)A–F完整交付;下一[1.16](PLAN-1.16.md)按实际HTTPS和一次性配对开始。手机、跨协议多模态和自我迭代依照上表前置推进,每个切片继续回顾并本地Git。
DSH-purge两版本的来源锁定和同题本地HTTP夹具对照已完成,独立提示实验默认关闭;真实推理收益继续待验。1.15桌面、1.16手机、1.17协议、1.18视觉、1.19缓存和1.20固定评测均已交付;工程依赖、更多引擎与其它多模态依照最新方案前置推进,每个切片继续回顾并本地Git。
## 跨阶段必须保持的能力
@@ -59,7 +59,7 @@ REA用于发行工件或运行证据,完整公开源码直接分析。研究
DSH-purge源码位于`D:\Ai-project\REA逆向\dsh-purge-1.1.78-windows`;DeepSeek工程位于`D:\Ai-project\DeepSeek-Harness-Desktop`。它们与ModelProvider分层管理。原六方法SDK探针仍只证明连接,1.14新增受限桥的真实prompt、工具、独立工程和停止验收另有原报告;Purge本地夹具提示生效/开销对照已完成,真实模型工程收益未测。
当前Windows安装、可选本机加密、1.16用户确认的iPhone流程、1.17两协议/流式及1.18截图/视觉已交付;1.19解析缓存已完整交付。未交付OS沙箱、固定DeepSeek桥以外的工程引擎接入、未知WorkBuddy格式自动导入、语音、通用电脑操作及受控自我迭代;稳定自主工程成功率继续真实模型评测。
当前Windows安装、本机可选加密、1.16用户确认iPhone流程、两协议/流式、工程截图/视觉、来源缓存及1.20固定工程评测和受控候选采纳已交付。未交付工程依赖准备、OS沙箱、固定DeepSeek桥以外的工程引擎、未知WorkBuddy格式自动导入、语音、通用电脑操作与全仓自主升级;稳定自主工程成功率继续真实模型评测。
1.15交付回顾保留的体验改进:在不减少完整性核对的前提下研究安装/激活校验耗时和进度反馈,并补超长自定义安装路径的提前拒绝。当前正式安装与原数据核对已通过,以上优化尚未实现,不与1.16真实手机验收混计。
+2 -2
View File
@@ -1,6 +1,6 @@
# 1.20 后续方案:工程质量评测与受控自我迭代
# 1.20 实施方案与交付范围:工程质量评测与受控自我迭代
1.19已完成原生续验、完整F封存及独立ACCEPTANCE,最终Git790350e。本阶段在feat/engineering-evals-1.20实施,优先把已有工程工具、模型池和隔离工作区组织成可核对的质量循环;语音、通用电脑操作和更多外部引擎仍分别排期。各切片实际结果见[验收记录](QA-1.20.md)和[回顾](RETROSPECTIVE-1.20.md)。
1.20 A–F已完成,来源790350e,分支feat/engineering-evals-1.20。固定工程评测、同源原版/候选、原报告和受控采纳已进入产品;独立发行、保留状态升级和原生回看通过。结果见[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[身份](engineering-evals-release-identity.json)。下一[PLAN-1.21](PLAN-1.21.md)仅方案;语音、通用电脑操作、更多引擎和真实推理收益分别排期。
## 用户能完成的任务
+4
View File
@@ -22,3 +22,7 @@
优先npm固定lockfile和已有受支持Python检查,不同时加入所有包管理器。依赖生命周期脚本按实际风险和来源展示、按既有权限审批,不能把模型选择等同授权。下载与本地缓存分开记账;缓存只作派生材料,不保存密钥。网络或可信源缺失时保留明确失败,不静默切换注册源或降低校验。
后续真实多模型复核、其它引擎、语音和更大工程范围,仍按实际问题、契约与可复现实测分别排期;不因一项接入成功宣称全部能力完成。
1.20发行回顾还记录正式stage总计约870.6秒及安装进度不够可见。作为后续独立维护项,先分段测量安装预检、载荷读取、完整性和数据快照,再安排进度显示与最小运行载荷/历史证据分发分离;不跳过原字节检查、不覆盖原证据,也不将此问题宣称已在1.21实现。
正式指针激活另耗时约726.6秒并通过原门槛;后续性能验收须分别记录stage、升级、activate及最后验证,避免用一个总时长推断瓶颈。
+2 -2
View File
@@ -1,6 +1,6 @@
# Agent Workbench 后续产品与执行开发方案
更新:2026-10-31。当前正式基线1.19.0,F及原生回看已完成。1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 见[1.19验收](QA-1.19.md)、[回顾](RETROSPECTIVE-1.19.md)、[缓存契约](PROJECT-CACHE.md)和[发行身份](project-cache-release-identity.json)。 下一[1.20](PLAN-1.20.md)仅方案。
更新:2026-10-31。当前正式基线1.20.0,A–F及原生回看已完成。1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。 见[使用说明](ENGINEERING-EVALUATIONS.md)、[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[发行身份](engineering-evals-release-identity.json)。下一[1.21方案](PLAN-1.21.md)聚焦工程依赖与可复现环境,尚未实现。
## 1. 产品目标
@@ -31,7 +31,7 @@ Purge的源码机制不证明模型权重或工程成功率已经提升。增强
现有基础:React工作台、兼容模型连接、Task/Run/Tool及预算、SQLite/工件恢复、工程索引与精确补丁、npm实际检查、单文件/整批审核、Git和报告。1.4.0增加原/新字节快照和逐文件执行账本、整批预检及显式恢复;各版本实测证据单独登记。
当前已实现Task所属计划/原证明、原请求与预算、来源记忆/检查点、模型中心/池、Skills/stdio MCP、两个隔离worker及父审查、固定DeepSeek受控桥、Windows桌面/可选DPAPI、真实iPhone伴随端、Chat/Responses有界SSE、PNG/JPEG视觉与预算续接,以及1.19来源核对的持久解析缓存。各阶段实际验收见对应QA;1.19独立发行、正式升级及原生回看已通过。动态引擎/更大调度、OS沙箱、语音、通用电脑操作、未知客户端导入及受控自我迭代待开发;真实模型自主完成率和视觉/Purge收益待单独评测。现有文本批次不提供跨文件原子事务。
当前已实现Task所属计划/原证明、请求预算、来源记忆/检查点、模型中心/池、Skills/stdio MCP、受限worker与父审查、固定DeepSeek受控桥、Windows桌面/可选DPAPI、真实iPhone伴随端、Chat/Responses有界SSE、PNG/JPEG视觉与预算续接、来源核对的持久解析缓存,以及1.20固定工程评测/受控自身模块候选采纳。各阶段证据见对应QA;工程依赖准备、更多引擎、OS沙箱、语音、通用电脑操作及未知客户端格式仍待开发。真实模型自主完成率和视觉/Purge收益单独评测;现有文本批次不提供跨文件原子事务。
工作台源码已建立本地Git,基线提交为`bac87da`,标签`v1.0.0-baseline`,继续按可审查小步提交。用户工程已有内置审查提交/证据报告、独立工作区及1.13父子文本成果审查合并;任意自动合并、归档和总体自主工程完成率继续实施与验收。
+16 -2
View File
@@ -1,6 +1,8 @@
# 1.20 工程评测验收记录
来源790350e,分支feat/engineering-evals-1.20。当前实施中,正式仍为已验收1.19,不宣称1.20发行完成。
来源790350e,分支feat/engineering-evals-1.20。A–F完整本地交付,正式1.20.0;代码与QA输入冻结于49314764f571ad48b7cef38d62c32b0bb66a8e9f,完整原件见[证据清单](engineering-evals-f-release-evidence/manifest.json)和[发行身份](engineering-evals-release-identity.json)。
正式收尾:stage、单次升级、指针激活及身份验证均成功。首次正式只读UI在9页后因QA查找“工程评测”弹窗、而冻结产品的实际标题是“工程质量评测”失败;页面/请求/HTTP/拦截写入错误均为0,原日志、9页截图、原脚本和收据保持。只复制新QA脚本并精确修正这一处标题后,完整26页在新收据下通过;未拼接局部结果、未修改冻结产品,也未重跑安装/升级/激活。原管线失败与只读续验管线分别封存;随后原生回看及证据封存均已完成,最终Git身份由独立ACCEPTANCE绑定。
| 切片 | 状态 | 证据 |
| --- | --- | --- |
@@ -9,7 +11,7 @@
| C 比较 | 专项通过 | 原失败/全部尝试/日志SHA、原用量缺失及人工审批/应用、不可变报告和父审查/Git门控 |
| D 产品流程 | 7组通过 | 桌面/390px准备、审查、比较、导出、刷新、采纳、停止和来源变化;两视口实际截图回看 |
| E 实际工程 | 14节点通过 | Node8/8、React9/9、Python10/10、自身原模块9/9;React两视口各12步,原版失败/候选/父交付保持 |
| F 完整发行 | 待验 | 完整源码/历史UI/独立源码/便携/安装/升级/原生回看 |
| F 完整发行 | 已完成 | 独立604/604、28类210组界面、源码/便携新评测5组、四类工程14节点、安装7组、保留全部状态升级、正式26页/原生回看 |
开发夹具只证明执行链、边界和真实工具结果。用户实际配置模型的自主完成率、视觉/Purge收益继续单列,不从固定响应推断。
@@ -46,3 +48,15 @@ D/E原失败、实际报告、原HTTP请求、检查日志、工程源码与必
候选版本1.20.0已构建。版本准备脚本因假定旧controlled-ui含1.19枚举而在只读断言中止;已按实际文件补齐余下版本门控,没有重复执行已完成的版本写入。首轮编译服务验收前3组通过,之后QA将Git preparing当作终态,提前断言completed;原收据`.qa/engineering-evals-release-aff1830d-8827-4832-a496-18c06ea37027`保持,改为等待明确Git终态后独立整轮复验。正式1.19未改。
修正后的编译流程5组通过,但随后完整UI版本核对拒绝了缓存页报告:服务APP_VERSION遗漏升级,仍报1.19。自动打包在失败门槛处停止,未生成/升级正式发行。已修复服务常量并补编译服务与所选包版本一致性断言;97bf5ed第一次冻结及UI失败原件单独保持,最终代码重新提交/冻结并完整重验。此前5组只说明新代码执行链走通,不能充作最终1.20发行通过。仍在运行的第一轮开发测试也保留原轮;最终验收以新冻结独立源码整轮为准。
## F 最终发行
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。
冻结415输入/22构建/40基准,代码来源49314764f571ad48b7cef38d62c32b0bb66a8e9f。独立源码从新归档提取并移至同卷短路径后逐字节核对;离线依赖/构建及22份构建完全一致。源码和便携均运行实际新评测5组、伴随端7组、协议5组、视觉5组、缓存7组;源码另验四类评测工程14节点、原生窗口7项/流程9组/桌面工程16节点、Responses13节点、截图7节点和缓存9节点,原父Node8/8、React9/9、Python10/10保持。
安装验收采用相同产品载荷、隔离登记的7组实际安装/原生启动/加密连接/工程检查/窗口崩溃/宿主重启/卸载保留数据,再以正式产品安装器stage、单次保留Provider升级、独立activate和只读验证。实际升级前重新快照全部会话和每表每行,未套用旧计数;私有SQLite备份不提交。正式手机网关保持关闭且无QA设备/证书。升级后原生窗口和只读26页均通过,未启动用户任务或修改连接。
原完整UI首轮因APP_VERSION遗漏拒绝,原编译验证等待Git中间态导致失败,全部失败原件保留。修复后新冻结重验;没有把局部成功记为最终通过。原日志追加只接受明确核对的固定卸载收尾,保留原前缀和最终字节。
自身试点只覆盖来源绑定模块;React依赖由QA显式按lockfile准备,不计模型自主安装。真实模型、视觉/Purge收益、多模型复核、全仓自升级和新iPhone流程仍分别未验证。下一阶段见[PLAN-1.21](PLAN-1.21.md)。
+14
View File
@@ -37,3 +37,17 @@
升级前原生1.19实际窗口已回看并封存,原项目/历史预算提示及空输入保留。只关闭客户端窗口后,后台PID36552、hasKey=true及17项目仍在,活动为空;未运行用户模型或变更任务。正式数据计数仍需在实际升级前重新做完整快照,不沿用屏幕可见会话数或历史数字。
第二次全UI整轮在多文件变更集旧脚本处拒绝:服务实际1.20.0正确,但脚本白名单仅到1.19。原15类120组已通过结果及原失败日志按原字节保存,未计为完整成功;改为直接核对随脚本的package版本,同时对上下文验收采用相同检查,防止继续手工追加版本。原89f4748冻结单独保留,最终QA输入重新提交/冻结/整轮复验。归档后尝试核对所属旧QA宿主时进程已退出,原脚本因此拒绝;随后复核确已不在,不向旧PID发信号,未触碰正式宿主。
下一整轮在Python界面遇到一次Edge CSS请求ERR_NO_BUFFER_SPACE,7项操作完成但页面原截图确实缺少样式,严格网络检查因此拒绝;原日志/DOM/截图及全部已通过部分独立封存。故障后仅观察到269条TCP连接,未证明持续耗尽,原因保持未知;没有改系统设置或结束用户浏览器。相同冻结代码和原断言单独复验7组通过、无网络错误,随后完整串行整轮使用新收据,不拼接局部结果。本次开发整轮604/604也已完成,最终仍以独立源码包整轮为准。
正式stage成功用时约870.6秒,含新产品安装器的原安装预检/全载荷写入/安装后登记,以及外层独立目录/原数据再次核对;不能把总时长误算成单次散列成本。当前产品安装等待缺少足够可见进度,完整发行包含累计证据使载荷增大;后续应分别测量路径/散列/数据快照阶段,改善明确进度,并研究将历史验收原件与最小运行载荷分发分离。原研究/源码证据与完整性门槛均须保持,不以删减核对换取速度。此为已观察问题和后续待办,本轮未实现。
正式formal-activate原阶段收据成功,总计约726.6秒;安装指针已指向1.20,原PID/Provider与全部数据保持,调试端口关闭、手机网关关闭且无设备/证书迁入。此时最后只读与原生回看仍待完成。该耗时包含多次新旧目录与来源复核,尚无分段测量,不能归因于某一个函数或单次散列。
最后正式只读UI首轮9页后发现QA弹窗名少了“质量”两字,实际产品标题为“工程质量评测”。原9页不是完整成功,原失败脚本、日志、截图及收据不动;新脚本只精确替换该标题,保留全部布局/网络/禁止写入断言,独立完整26页通过。封存同时要求原失败、单处QA差异SHA和完整续验收据,避免以局部通过掩盖失败;成功安装、升级和激活没有重放。
## F 完成回顾
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。
包/服务版本对照成功拦截一次真实发行遗漏,最终冻结重验后才交付;完整回归与归档验证不能由开发工作区局部通过替代。自身试点发现汇总状态问题并完成原版失败/候选通过/父交付,但全仓超过快照边界,未扩大权限或上限。下一1.21解决依赖环境需人工准备的缺口;模型自主能力、多模型复核与Purge收益继续用实际工程评测,不从固定HTTP推断。
+6
View File
@@ -1,5 +1,11 @@
# Agent Workbench 验收记录
## 1.20 · 固定工程评测完整本地交付
1.20.0完整本地交付:固定工程评测、同源原版/候选、全部尝试与原日志对照、显式采纳及父审查/检查/Git。独立源码604/604、28类210组界面、四类工程14节点、随包与同载荷安装7组、正式26页及原生回看通过。原PID36552/Provider、17项目/30全部会话/3144记录/5986事件、全部表每行/导出/模型中心及1824工件记录/1721去重文件原字节保持,9229关闭。本轮真实模型请求0;固定HTTP不代表自主推理收益或全仓自升级。
见[使用说明](ENGINEERING-EVALUATIONS.md)、[验收](QA-1.20.md)、[回顾](RETROSPECTIVE-1.20.md)及[发行身份](engineering-evals-release-identity.json)。下一[1.21方案](PLAN-1.21.md)聚焦工程依赖与可复现环境,尚未实现。
## 1.19 · 项目解析缓存完整本地交付
1.19.0完整本地交付:有界持久解析缓存、逐次两轮来源SHA核对、严格失效、开关/清除及索引/诊断入口。独立源码590/590、27类203组历史UI、新缓存7组及9节点工程、原生窗口7项/受控流程9组/桌面工程16节点、Responses13节点、截图7节点及Node8/8、React9/9、Python10/10通过。随包缓存/伴随端/协议/视觉、同载荷安装7组、正式24页和升级后原生回看通过。原PID36552/Provider、17项目/30全部会话/2614记录/4701事件、全部表每行/导出/模型中心/工件原字节保持,1466工件记录/1376去重文件核对,9229关闭。本轮真实模型请求0;真实视觉工程/Purge收益及新增iPhone实机继续单列待验。 见[1.19验收](QA-1.19.md)、[回顾](RETROSPECTIVE-1.19.md)、[缓存契约](PROJECT-CACHE.md)和[发行身份](project-cache-release-identity.json)。
@@ -0,0 +1,233 @@
{
"success": true,
"version": "1.20.0",
"at": "2026-11-01T02:48:23.918Z",
"groups": 210,
"results": [
{
"script": "verify-evaluations-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 89515,
"evidence": "docs/engineering-evals-evaluations-ui-validation.json",
"log": ".qa/engineering-evals-verify-evaluations-ui.log"
},
{
"script": "verify-project-cache-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 5144,
"evidence": "docs/engineering-evals-project-cache-ui-validation.json",
"log": ".qa/engineering-evals-verify-project-cache-ui.log"
},
{
"script": "verify-vision-ui.mjs",
"success": true,
"groups": 5,
"durationMs": 13531,
"evidence": "docs/engineering-evals-vision-ui-validation.json",
"log": ".qa/engineering-evals-verify-vision-ui.log"
},
{
"script": "verify-model-protocols-ui.mjs",
"success": true,
"groups": 5,
"durationMs": 12000,
"evidence": "docs/engineering-evals-model-protocols-ui-validation.json",
"log": ".qa/engineering-evals-verify-model-protocols-ui.log"
},
{
"script": "verify-companion-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 14796,
"evidence": "docs/engineering-evals-companion-ui-validation.json",
"log": ".qa/engineering-evals-verify-companion-ui.log"
},
{
"script": "verify-controlled-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 57195,
"evidence": "docs/engineering-evals-controlled-final-ui-validation.json",
"log": ".qa/engineering-evals-verify-controlled-ui.log"
},
{
"script": "verify-purge-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 20707,
"evidence": "docs/engineering-evals-purge-final-ui-validation.json",
"log": ".qa/engineering-evals-verify-purge-ui.log"
},
{
"script": "verify-workers-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 118630,
"evidence": "docs/engineering-evals-workers-ui-validation.json",
"log": ".qa/engineering-evals-verify-workers-ui.log"
},
{
"script": "verify-task-plans-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 13486,
"evidence": "docs/engineering-evals-task-ui-validation.json",
"log": ".qa/engineering-evals-verify-task-plans-ui.log"
},
{
"script": "verify-browser-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 23298,
"evidence": "docs/engineering-evals-browser-ui-validation.json",
"log": ".qa/engineering-evals-verify-browser-ui.log"
},
{
"script": "verify-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 20636,
"evidence": "docs/engineering-evals-basic-ui-validation.json",
"log": ".qa/engineering-evals-verify-ui.log"
},
{
"script": "verify-diagnostics-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 19350,
"evidence": "docs/engineering-evals-diagnostics-ui-validation.json",
"log": ".qa/engineering-evals-verify-diagnostics-ui.log"
},
{
"script": "verify-execution-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 24911,
"evidence": "docs/engineering-evals-execution-ui-validation.json",
"log": ".qa/engineering-evals-verify-execution-ui.log"
},
{
"script": "verify-delivery-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 43178,
"evidence": "docs/engineering-evals-delivery-ui-validation.json",
"log": ".qa/engineering-evals-verify-delivery-ui.log"
},
{
"script": "verify-index-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 7202,
"evidence": "docs/engineering-evals-index-ui-validation.json",
"log": ".qa/engineering-evals-verify-index-ui.log"
},
{
"script": "verify-change-sets-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 10906,
"evidence": "docs/engineering-evals-change-sets-ui-validation.json",
"log": ".qa/engineering-evals-verify-change-sets-ui.log"
},
{
"script": "verify-context-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 16096,
"evidence": "docs/engineering-evals-context-ui-validation.json",
"log": ".qa/engineering-evals-verify-context-ui.log"
},
{
"script": "verify-workspaces-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 26946,
"evidence": "docs/engineering-evals-workspaces-ui-validation.json",
"log": ".qa/engineering-evals-verify-workspaces-ui.log"
},
{
"script": "verify-python-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 19179,
"evidence": "docs/engineering-evals-python-ui-validation.json",
"log": ".qa/engineering-evals-verify-python-ui.log"
},
{
"script": "verify-react-delivery.mjs",
"success": true,
"groups": 6,
"durationMs": 23473,
"evidence": "docs/engineering-evals-react-delivery-validation.json",
"log": ".qa/engineering-evals-verify-react-delivery.log"
},
{
"script": "verify-research-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 23490,
"evidence": "docs/engineering-evals-research-ui-validation.json",
"log": ".qa/engineering-evals-verify-research-ui.log"
},
{
"script": "verify-engines-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 11574,
"evidence": "docs/engineering-evals-engines-ui-validation.json",
"log": ".qa/engineering-evals-verify-engines-ui.log"
},
{
"script": "verify-model-center-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 7405,
"evidence": "docs/engineering-evals-model-center-ui-validation.json",
"log": ".qa/engineering-evals-verify-model-center-ui.log"
},
{
"script": "verify-project-memory-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 6291,
"evidence": "docs/engineering-evals-project-memory-ui-validation.json",
"log": ".qa/engineering-evals-verify-project-memory-ui.log"
},
{
"script": "verify-task-checkpoints-ui.mjs",
"success": true,
"groups": 3,
"durationMs": 6414,
"evidence": "docs/engineering-evals-task-checkpoints-ui-validation.json",
"log": ".qa/engineering-evals-verify-task-checkpoints-ui.log"
},
{
"script": "verify-skills-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 8465,
"evidence": "docs/engineering-evals-skills-ui-validation.json",
"log": ".qa/engineering-evals-verify-skills-ui.log"
},
{
"script": "verify-mcp-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 9923,
"evidence": "docs/engineering-evals-mcp-ui-validation.json",
"log": ".qa/engineering-evals-verify-mcp-ui.log"
},
{
"script": "verify-mcp-recovery-ui.mjs",
"success": true,
"groups": 2,
"durationMs": 6446,
"evidence": "docs/engineering-evals-mcp-recovery-ui-validation.json",
"log": ".qa/engineering-evals-verify-mcp-recovery-ui.log"
}
],
"scope": "Every verifier owns an independent port and synthetic data directory. Synthetic provider fixtures verify protocols; configured-model acceptance is separate. No production service or real key read/copied."
}
@@ -0,0 +1,27 @@
{
"success": true,
"url": "http://127.0.0.1:51791",
"browser": "Microsoft Edge 156.0.4314.50",
"date": "2026-11-01T02:43:51.519Z",
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\ui-4ec29e73-f604-4521-ae99-ca646e8e3a0b\\ui-project",
"viewports": [
1440,
780,
390
],
"passed": [
"project selection and real file preview",
"real command consent, execution and stale snapshot rejection",
"diff review and verified file application",
"manual editor creates a reviewable proposal",
"file responses stay with the current selection",
"denial, session selection, reload, stale response rejection and export",
"project inventory responses cannot replace another project",
"780 and 390 px: project drawer, file, diff and trace controls, no page overflow",
"unified and detailed research reports render",
"model list, ephemeral key, compatible fixture tool loop and return to offline mode"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; no real model"
}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:37.798Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-batch-desktop-review.png",
".qa/screenshots/engineering-evals-batch-desktop-conflict.png",
".qa/screenshots/engineering-evals-batch-desktop-recovery.png",
".qa/screenshots/engineering-evals-batch-mobile-review.png",
".qa/screenshots/engineering-evals-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-c242d13f-8948-469e-8fad-ac64c9a4faa0",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,175 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:43:30.703Z",
"directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee",
"passed": [
"actual step editor seals the chosen build, viewport and three CSS interactions without opening the page",
"review shows exact build identity and planned assertions; cancelling executes no browser work",
"real inner Edge clicks the intended element and the two counted assertions display with original Task/Run/build identity",
"original large JSON is paged in the UI and downloads the complete hash-identical result",
"the original screenshot renders at its actual resolution and downloads identical PNG bytes",
"a real failed assertion retains actual count one and requires a newly reviewed plan instead of replaying",
"390px forms and result records remain usable and the inner browser captures its real 390px layout",
"stopping an actual in-flight assertion closes its owned browser and preserves prior successful and failed jobs",
"a delayed original-record failure stays with its source and does not appear in a newly selected task",
"actual host restart preserves the four original browser jobs and PNGs without model requests or execution replay"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee\\browser-desktop-results.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee\\browser-desktop-original-image.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee\\browser-mobile-results.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee\\browser-mobile-original-image.png"
],
"taskId": "39aae8cb-6bc5-4fe6-8469-7ee27437c87b",
"sessionId": "3594f051-4ac9-4b51-af9a-f7bc30bbc7ad",
"jobs": [
{
"id": "6579a816-2620-443b-acbf-f69cc96127e4",
"status": "passed",
"planId": "fc9beee5-03fd-401e-bece-3760c66813d8",
"assertions": {
"total": 2,
"passed": 2,
"failed": 0
},
"resultSha256": "489435e109849fd14ff0934a3ec69132b13e5ff17651eea82b2a1208a92bd471",
"cleanup": {
"pid": 11312,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-11-01T02:43:13.701Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "5abbae63-fce2-4378-93e8-e5b2925ffe35",
"sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef",
"bytes": 101061,
"width": 1280,
"height": 900,
"label": "initial"
},
{
"artifactId": "746c93b4-6008-44df-b19d-3a66280438cf",
"sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7",
"bytes": 85261,
"width": 1280,
"height": 900,
"label": "final"
}
]
},
{
"id": "c98960fa-84ad-4d7d-80af-64c14a6eaffc",
"status": "failed",
"planId": "03fe1bd6-2ab3-4230-8c10-5defd68da507",
"assertions": {
"total": 2,
"passed": 1,
"failed": 1
},
"resultSha256": "804e309ded6253b0eb3188c9edbda440f888e23134eee5ed24f8f224ac8bba9a",
"cleanup": {
"pid": 51736,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-11-01T02:43:20.843Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "bd1b3a3d-bfac-426c-94a1-7befb37abbef",
"sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef",
"bytes": 101061,
"width": 1280,
"height": 900,
"label": "initial"
},
{
"artifactId": "cc3ad122-bfc1-42d9-9a2c-9b572fc79f84",
"sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7",
"bytes": 85261,
"width": 1280,
"height": 900,
"label": "failure"
}
]
},
{
"id": "1039d8a1-e504-47b1-8301-4a4a731594bc",
"status": "passed",
"planId": "65b7e027-d837-4a81-8222-ac68979e5cc6",
"assertions": {
"total": 2,
"passed": 2,
"failed": 0
},
"resultSha256": "fcb45934ec3a1597178f4dc42233f4dbac637237b814de740e67d8ba5fb45f4c",
"cleanup": {
"pid": 12072,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-11-01T02:43:24.177Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "4cb771b9-f4f2-4706-9bb0-09d1caebe6b7",
"sha256": "93969f1954eec1f7fa4736d7a3035631c6066b6727132ff1179180eadb745602",
"bytes": 11011,
"width": 390,
"height": 844,
"label": "initial"
},
{
"artifactId": "0b015ecd-f57e-4784-9eb0-8458550a305d",
"sha256": "a6908ecfcfd239721ec6bbb916a5054d2f61183b6dea3f014db89216d371d0e3",
"bytes": 18832,
"width": 390,
"height": 844,
"label": "final"
}
]
},
{
"id": "568a41c8-9087-43a3-a151-1ead944b0607",
"status": "interrupted",
"planId": "4ab67cd8-af45-43c0-8930-03884efc713e",
"assertions": {
"total": 3,
"passed": 2,
"failed": 1
},
"resultSha256": "6cf6a19d4faa3bef1b2bce898194ba9520767e8a2e1205755e56c284346ccba0",
"cleanup": {
"pid": 40776,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-11-01T02:43:27.430Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "262ed0d6-7185-48b7-a1a1-547bb660c6f9",
"sha256": "93969f1954eec1f7fa4736d7a3035631c6066b6727132ff1179180eadb745602",
"bytes": 11011,
"width": 390,
"height": 844,
"label": "initial"
}
]
}
],
"scope": "Actual independent Workbench UI plus real Edge static-build executions. The configured production Provider, other projects and keys are not accessed."
}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:37.798Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-batch-desktop-review.png",
".qa/screenshots/engineering-evals-batch-desktop-conflict.png",
".qa/screenshots/engineering-evals-batch-desktop-recovery.png",
".qa/screenshots/engineering-evals-batch-mobile-review.png",
".qa/screenshots/engineering-evals-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-c242d13f-8948-469e-8fad-ac64c9a4faa0",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,42 @@
{
"success": true,
"version": "1.20.0",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench",
"nodePath": "D:\\Ai-project\\REA逆向\\tools\\node-v24.22.1-win-x64\\node.exe",
"nodeSha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
"containedRuntime": false,
"passed": [
"desktop explicitly enables HTTPS and downloads the actual public CA without changing OS trust",
"390px real gateway pairing clears fragment, displays scoped task list and registers the same device in desktop",
"phone UI confirms original Task/Run approval and the existing Runtime executes one command",
"original paginated diff and counted check/report display verified content from the same Task",
"disconnect and refresh recover from persistent seq without submitting a new command or Run",
"PWA service worker stores the shell and no API/project response",
"desktop revocation removes mobile project content immediately on the next read while preserving the original completed tool"
],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\desktop-certificate.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\desktop-pairing.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-task-list.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-original-approval.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-original-diff.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-original-report.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-disconnected.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\tablet-task-list.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\desktop-management-narrow.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d\\mobile-revoked.png"
],
"errors": [],
"viewports": [
1440,
390,
768
],
"browser": "Microsoft Edge via Playwright; owned loopback QA relay with actual CA verification",
"nativeSafariTrustCookiePWA": "pending-real-iPhone",
"osTrustChanged": false,
"certificateWarningsBypassed": false,
"realModelRequests": 0,
"taskId": "dbc1a9be-e1e4-462f-9592-176445bedaea",
"runId": "4c000837-51f3-4b0a-8c15-aaa307f027d6"
}
@@ -0,0 +1,34 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:53.341Z",
"passed": [
"desktop request estimate, actual usage, complete goal and history identity are visible",
"paged complete history opens actual tool result artifacts without executing tools",
"historical and resumed Runs retain their own request records",
"390px history, original JSON and sent-body dialogs fit and retain close controls",
"late old history failure stays in its original scope after switching projects",
"late old Run failure stays in its original scope after switching projects",
"late old request-body failure stays in its original scope after switching projects",
"context-limit pause explains the intact requirement and explicit continuation",
"390px repeated-read pause explains the cause and explicit continuation retains the same Task",
"desktop working evidence shows actual code, original result provenance and the current Task",
"390px working evidence and sent request stay readable and closing the artifact retains task navigation"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-desktop-plan.png",
".qa/screenshots/engineering-evals-desktop-history.png",
".qa/screenshots/engineering-evals-mobile-history.png",
".qa/screenshots/engineering-evals-mobile-original.png",
".qa/screenshots/engineering-evals-mobile-request-body.png",
".qa/screenshots/engineering-evals-mobile-read-pause.png",
".qa/screenshots/engineering-evals-desktop-working-evidence.png",
".qa/screenshots/engineering-evals-mobile-working-evidence.png"
],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8",
"data": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8\\data",
"mode": "saved synthetic context evidence; no real model or project commands executed by this UI verifier",
"browser": "156.0.4314.50"
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,31 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:19.417Z",
"browser": "156.0.4314.50",
"passed": [
"actual failing tests and four source proposals retain the original project and task",
"reviewed changes continue the same Task through 14 real tests and model-prepared Git review",
"review shows actual paths, diffs, tests, author and policy; cancelling leaves Git unchanged",
"an index change after confirmation preview refuses the stale job and preserves both staged owners",
"390px confirmation keeps file hashes, diffs and actions inside the modal",
"double confirmation creates one four-file commit, retains owner bytes and publishes report with completion",
"report viewing and Markdown/JSON downloads preserve verified artifact bytes and truthful acceptance limits",
"mobile report preview closes cleanly and keeps the task input fixed",
"unknown Git results block new submission and the explicit reconcile action restores the existing commit"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\delivery-ui-03321e56-2fe5-43f1-ab75-7962aad14cda\\四模块交付工程",
"projectId": "d666ea37-de8b-4053-8b45-59b2611c8762",
"sessionId": "550fa45e-8d3b-4300-b0a3-3c75e5b3aa7f",
"taskId": "6b4c6889-8ffa-4bba-9b2e-5fc4e0e636f6",
"commit": "a1d376946a61912a9fad43fc434724a63cddd269",
"recoveryCommit": "53b5ba8647f38bbb3fb7c080cee64e5ca508ceaa",
"testCounts": {
"baselineFailed": 13,
"passed": 14
},
"model": "controlled local HTTP fixture",
"confirmations": 2
}
@@ -0,0 +1,20 @@
{
"success": true,
"version": "1.20.0",
"url": "http://127.0.0.1:49479",
"date": "2026-11-01T02:44:11.121Z",
"passed": [
"model response validation checks the tentative connection before saving",
"a model failure after successful tools shows source, attempts and local runtime diagnosis",
"explicit retry preserves the completed tool result without replaying the task",
"an error question receives the actual session diagnosis and formatted answer",
"review state exposes the review action and prevents application during a running request",
"approved Unicode commands execute in the declared shell and retain Chinese output",
"authentication errors do not retry and error/diagnostic controls fit a 390 px viewport",
"stop cancels pending retry and clears running model state",
"a transient service failure recovers within the bounded retry policy"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; actual configured model is verified separately"
}
@@ -0,0 +1,232 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:47:38.534Z",
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009",
"browser": "156.0.4314.50",
"passed": [
"independent desktop engine entry detects the declared installation and clearly separates connection from project execution",
"missing installations and edited directories cannot launch a check until detection succeeds",
"UI launch seals the selected installation into the current Task/Run and renders actual startup and process-close facts",
"original record paging, full download SHA256 and nested-dialog keyboard close preserve the exact evidence",
"an explicit new check creates a different process and record while retaining the original check unchanged",
"declared pending-initialize fixture stops its owned process and explicit retry preserves the stopped result",
"the same product UI verifies the actual installed DeepSeek SDK without a prompt or configured-model call",
"390px installation paths, source chain, original record, paging and keyboard close remain readable without page overflow",
"late detection failure from a closed panel cannot appear in a different task or reveal its prior engine records",
"actual host restart preserves all native and declared-fixture records with no protocol replay or project modification"
],
"pageErrors": [],
"requestFailures": [],
"expectedRequestFailures": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\screenshots\\engines-native-desktop.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\screenshots\\engines-record-mobile.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\screenshots\\engines-native-mobile.png"
],
"starts": [
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\本地 SDK #",
"identitySha256": "2bb6a7bfdabf12931a04404bff2b0b5eb0a813d4e199ebca87cb8b36b5b1a3be"
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\本地 SDK #",
"retry": true
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\本地 SDK #",
"identitySha256": "2bb6a7bfdabf12931a04404bff2b0b5eb0a813d4e199ebca87cb8b36b5b1a3be"
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009\\本地 SDK #",
"retry": true
},
{
"root": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness",
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3"
}
],
"nativeJob": {
"schemaVersion": 1,
"id": "28d1d9fd-f0fa-4e09-ae2f-695e815b0c4b",
"sessionId": "93a5acbd-9286-462a-827b-2f8055fb36fe",
"projectId": "a5d6751e-16ad-4ff7-b56c-6db742ce9b60",
"taskId": "4ce3a736-4ebf-4b11-b1bf-fd3615eef69a",
"runId": "d31b170a-fbc3-4ee4-9291-c1f0a13cb0f5",
"engineId": "deepseek-harness",
"scope": "deepseek-sdk-connection-probe",
"source": "user",
"installation": {
"engineId": "deepseek-harness",
"name": "DeepSeek Harness",
"profile": "sdk-minimal",
"expectedVersion": "0.2.1-rc.2",
"root": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness",
"capabilities": {
"connectionProbe": true,
"projectExecution": false,
"prompt": false,
"singleSessionCancel": false,
"protocolVersionNegotiation": false,
"cancellationUnit": "owned-process",
"tokenStreaming": false
},
"limitations": [
"当前接入核验启动、会话目录、协议错误和关闭;工程执行接入开发中。",
"SDK没有单会话cancel或close;停止以所属独立进程为单位。",
"SDK serverInfo.version与发行包版本分别核对,没有有效协议版本协商。",
"SDK事件覆盖运行时会话树,idle事件不能直接判项目交付完成。"
],
"status": "available",
"version": "0.2.1-rc.2",
"entry": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\lib\\bin.js",
"inputs": [
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\package.json",
"bytes": 8138,
"sha256": "d42efe9f3ff424f602f11598af8805ad25039953ebbbd3c163d67875f7e8658b",
"relative": "apps/cli/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\lib\\bin.js",
"bytes": 11772,
"sha256": "80112efe368efb1a39720c7ada0af00442e5131fb2744edaaff8a3e8bb499e6f",
"relative": "apps/cli/lib/bin.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\boot\\cmdline\\lib\\index.js",
"bytes": 6973,
"sha256": "7253190611566485f8b6f836fae6e0f2a7abbc59bb807c42e874844016e6d3a0",
"relative": "packages/boot/cmdline/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-app\\lib\\index.js",
"bytes": 1921,
"sha256": "cc7e6c38b0b38c0e92a0dffb45210c1dac6ef518547436e805e84b772f91a475",
"relative": "packages/bundle/sdk-app/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-minimal\\package.json",
"bytes": 2920,
"sha256": "0e177cbca85148207343db5afd7f12829723cf3f2afedfa8e85a5c5dcd58f604",
"relative": "packages/bundle/sdk-minimal/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-minimal\\cordis.patch.yml",
"bytes": 5636,
"sha256": "464ea07c03d3639c2c387fa3a684f5d4001e7ca39f8257b361c604f19487af66",
"relative": "packages/bundle/sdk-minimal/cordis.patch.yml"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\server\\package.json",
"bytes": 2155,
"sha256": "2690f99763c3e1e7bd57f680f26e53010c2a3d7c4dffe06ff64a07ae3928cb17",
"relative": "packages/sdk/server/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\server\\lib\\index.js",
"bytes": 16454,
"sha256": "55412923f9f7c279f7e0b2a1e2853eaf238f390b3d84046cb9c94dc5f22a1e4a",
"relative": "packages/sdk/server/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\protocol\\package.json",
"bytes": 1237,
"sha256": "b030b0431d69723b5424dc2519cd4b381ec91acd22b73e0b30d6b8a19f1f2f94",
"relative": "packages/sdk/protocol/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\protocol\\lib\\index.js",
"bytes": 7336,
"sha256": "371c38ca3514797d86df5f4bb78a56c40a2637294b83aababe8145bec6a20253",
"relative": "packages/sdk/protocol/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\client\\package.json",
"bytes": 1325,
"sha256": "ff33f2ecec2d48bb8a24397cc664fc2dd50ba49d5288eb11fea1cb12931e5d5f",
"relative": "packages/sdk/client/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\pnpm-lock.yaml",
"bytes": 1090222,
"sha256": "4637cca3b89c4c8d5a147321710e597aa62ec2444a3772ab542be5690893dfe4",
"relative": "pnpm-lock.yaml"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\vendor\\cordis\\lib\\index.js",
"bytes": 60361,
"sha256": "6a9394c0877ff45218818c6e815edd038f8057e1a1deb390a8d43ec81c57691e",
"relative": "vendor/cordis/lib/index.js"
}
],
"node": {
"path": "D:\\Ai-project\\REA逆向\\tools\\node-v24.22.1-win-x64\\node.exe",
"bytes": 93915464,
"sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
"version": "24.22.1"
},
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"serverInfo": {
"name": "deepseek-harness-sdk-runtime",
"version": "0.0.1"
},
"message": "已找到匹配版本,可验证原程序的连接与停止。"
},
"sdkSessionId": "4483959b-e3e3-405a-9d6e-c0bbfafcdcb5",
"directory": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\28d1d9fd-f0fa-4e09-ae2f-695e815b0c4b",
"status": "completed",
"startedAt": "2026-11-01T02:47:34.325Z",
"finishedAt": "2026-11-01T02:47:35.367Z",
"requiresVerification": false,
"verification": {
"verified": true,
"installationSha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"readySignal": "appReady",
"sdkSessionId": "4483959b-e3e3-405a-9d6e-c0bbfafcdcb5",
"connectionId": "22498390-07b7-4097-ac69-69120f02c2e2",
"rootExited": true,
"modelRequests": 0
},
"summary": "连接通过,启动、协议返回、会话目录与进程结束均已核对。",
"contractArtifactId": "a0cad9ce-80c2-4d81-b10c-866cf58b6e61",
"contractSha256": "371a7e6dfdd9bd9b4e62b6598971386f8469e465e01b3e715537e74ef36dc13a",
"eventId": "0d620a27-f223-4767-8522-36a9194de7df",
"pid": 40580,
"connectionId": "22498390-07b7-4097-ac69-69120f02c2e2",
"readiness": {
"schemaVersion": 1,
"nonce": "22f55dae-a86a-4c83-a681-324439492013",
"pid": 40580,
"signal": "appReady",
"readyAt": "2026-11-01T02:47:35.185Z",
"artifact": {
"path": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\28d1d9fd-f0fa-4e09-ae2f-695e815b0c4b\\ready.json",
"bytes": 135,
"sha256": "503d56c8a64741ead9449094fc552df6b4ab48e2c77bde7721a98c8b69d53721"
}
},
"serverInfo": {
"name": "deepseek-harness-sdk-runtime",
"version": "0.0.1"
},
"reportArtifactId": "e2d9be0f-08d8-4892-9be2-22f89a91ecc2",
"reportSha256": "0eb7c70ac27b9ed870eee7de91b9a68ec84e6bc4c07ab096a18de0a470cb573b",
"reportSummary": {
"status": "verified",
"modelRequests": 0,
"providerRequests": 0,
"observedResponses": 6,
"rootExited": true
}
},
"actualSdk": {
"version": "0.2.1-rc.2",
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"nativeMethods": 6,
"modelRequests": 0,
"rootExited": true
},
"stopScope": "declared private SDK pending-initialize fixture",
"scope": "Independent service and data. Original 4318 Provider, tasks and credentials were not accessed."
}
@@ -0,0 +1,73 @@
{
"passed": true,
"version": "1.20.0",
"evidenceKind": "owned fixed response, actual isolated Git/checks and desktop/390px UI",
"realModelRequests": 0,
"fixtureRequests": 6,
"assertions": [
"desktop/390px form rejects candidate test edits, keeps entered requirements, persists fixed model/source/budget and reloads the original plan",
"explicit preparation seals two same-source checkouts and actual commands; original real three-test failure is retained with zero model requests",
"candidate navigates to its original restricted task for real change review and check approval, runs the original test/build and preserves the parent source",
"parallel comparison preserves original failure, candidate pass, real approval/application counts and absent cost; export and refresh retain the original report and fixture label",
"adoption forms a fresh parent review batch; completion requires applied source, fresh real parent checks and local Git delivery while owner modifications remain exact",
"stop waits for the owned candidate request, preserves stopped outcome and never turns cancellation into a passed sample or a replay",
"changed owner source is rejected before workspace creation and the error stays attached to the original batch instead of a generic chat reply"
],
"screenshots": [
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\desktop-empty.png",
"sha256": "f53794c251f2d9e9b3ed350b7819645a9f1a01c03c54b02e74b0f01d0a45cc21"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\mobile-form-scope-error.png",
"sha256": "79ff7a3dd7a3e016cbc61ded4e41f7298085fbd0a7256ba0d5d6aa15c403f7ac"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\desktop-ready.png",
"sha256": "8cf613177b043f2e040afaa1b2109e1d86decb668e8f008da8417fe843492ca2"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\desktop-candidate-complete.png",
"sha256": "5d16682ce18ad49841140e6dd8caea9c1ad6d86289b7aa9fea5109312f2e0d8b"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\desktop-comparison.png",
"sha256": "63b1bb1cbeb00de77192a523031a2b5b0e2c3474be3f76df656f1fdce47fad09"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\mobile-comparison.png",
"sha256": "4d88b0a2eea7af7e86b430371707bc7e2701d160058a76b2b59794179f5d1235"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\mobile-candidate-evidence.png",
"sha256": "fa3728c5d87d07239a160243a16a5ac19aa59717099db9f6def2e8c3688f262b"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\desktop-delivered.png",
"sha256": "7d1f52794c2e645aed7dd676ea64b714521f45501bc21a6ccbddc789dd6cf677"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\mobile-stopped.png",
"sha256": "40682e85d4adbaa326d9eb2b1b10f8e037c06fcbfb9831a6dfdafb8a540092e9"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\mobile-source-error.png",
"sha256": "910e0c48f11e5e16a6a5669bc9a98b037df55ae5072688bc7ee34a8ca26dee71"
}
],
"exports": [
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\downloaded-report.json",
"sha256": "01c1b22a5f12eb2daeb593a67515aa2f2e034b83c6707762f6bc497ca0088fb4"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\report-ec40f97b-58fe-426d-b1a7-95a304a915ab.json",
"sha256": "01c1b22a5f12eb2daeb593a67515aa2f2e034b83c6707762f6bc497ca0088fb4"
},
{
"file": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367\\report-f46b1468-de62-40cb-b56a-a3d3caa8b822.json",
"sha256": "ca542a2d25677821b86a51263c7e04a7b43191ed7816096bac125d889a88b84a"
}
],
"errors": []
}
@@ -0,0 +1,19 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:44:36.236Z",
"browser": "156.0.4314.50",
"passed": [
"model-selected checks wait for approval and display actual counted results",
"verified artifact preview shows the real check log and hash",
"changed source invalidates old checks and manual confirmation runs the new plan",
"390px task drawer, log preview, close controls and fixed composer remain operable",
"reconnection synchronizes missed session changes in other projects",
"budget controls pause before tools and preserve the goal across recorded runs",
"applied proposals continue the original task into actual engineering verification"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\execution-ui-a6416377-66c1-42a0-9bb6-2d108691e1bb\\project",
"model": "controlled local HTTP fixture"
}
@@ -0,0 +1 @@
* -text -whitespace
@@ -0,0 +1,21 @@
{
"success": true,
"phase": "archives",
"startedAt": "2026-11-01T02:51:56.040Z",
"finishedAt": "2026-11-01T02:52:37.867Z",
"exitCode": 0,
"logPath": ".qa/evals-f-archives.log",
"logBytes": 815,
"logSha256": "56c6cc7e23b4c5d5bf6d47ecf4b13c64d62fb8edf3e659e55aed4ef3ffc5799f",
"pointer": {
"path": ".qa/archives-validation.json",
"sha256": "fae667f1d7a9b5ed06caf3126a65ce65431ccd855f179cdd836feacb89030665"
},
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success": true, "version": "1.20.0", "testedAt": "2026-11-01T02:52:37.820798+00:00", "archives": [{"kind": "portable", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846.zip", "files": 17737, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "1a07ba9f313bd012abcf924de24dd19c6b02b3e3f1d0bed9606cdee92ac6a019"}, {"kind": "source", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846.zip", "files": 18058, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "6f7321fdeb04fc42daa78aaf94a6dfbc3b0ff83b002fc60654f6c815872b1594"}], "extractionRoot": "D:\\AWQA20\\source-check-347074c8a9464ad1927bda77e371ec0a\\Agent-Workbench-1.20.0-source-20261101024825846"}
@@ -0,0 +1,21 @@
{
"success": true,
"phase": "source",
"startedAt": "2026-11-01T02:54:29.793Z",
"finishedAt": "2026-11-01T03:40:39.295Z",
"exitCode": 0,
"logPath": ".qa/evals-f-source.log",
"logBytes": 1840,
"logSha256": "967554e19b30a69cca419ca2441321eb35a948fffebd489d5de03ac69656991c",
"pointer": {
"path": ".qa/source-package-validation.json",
"sha256": "6a0b55beeecd68dc898d880a898008a630d7709ee757802183b9c03310bba883"
},
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,21 @@
{"sourceRoot":"D:\\AWQA20\\s-6187caf2","directory":"D:\\AWQA20\\s-6187caf2\\.qa\\package-validation-1f2dd86e-d6a2-4528-af07-be6cb8d3df7e","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"}}
Source package: install
Source package: build
Source package: contained REA
Source package: native DeepSeek SDK
Source package: contained browser runtime
Source package: compiled controlled-engine delivery
Source package: contained companion gateway and UI
Source package: contained model protocols and mobile streams
Source package: contained screenshot inputs and exact Task budget resume
Source package: contained source-verified parsing cache controls
Source package: tests
Source package: actual contained Electron window
Source package: actual contained Electron engine UI
Source package: actual contained Electron engineering projects
Source package: Responses SSE actual Node React Python engineering
Source package: screenshot Task Node React Python engineering
Source package: cached index original requests and Node React Python engineering
Source package: compiled fixed engineering evaluations
Source package: fixed Node React Python and source-bound module engineering
{"success":true,"version":"1.20.0","sourceRoot":"D:\\AWQA20\\s-6187caf2","directory":"D:\\AWQA20\\s-6187caf2\\.qa\\package-validation-1f2dd86e-d6a2-4528-af07-be6cb8d3df7e","tests":{"tests":604,"pass":604,"fail":0,"cancelled":0,"skipped":0,"todo":0},"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"},"inputFiles":415,"buildMatchedFiles":22,"rea":true,"engine":true,"browser":true,"controlled":true}
@@ -0,0 +1,21 @@
{
"success": true,
"phase": "portable",
"startedAt": "2026-11-01T03:40:39.361Z",
"finishedAt": "2026-11-01T03:42:13.717Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable.log",
"logBytes": 1166939,
"logSha256": "e0c09f708bce6d5c21d658134f0c3baf78c5c04268ec4e6ca484b83c7f69f43a",
"pointer": {
"path": ".qa/release-validation.json",
"sha256": "7475f30f21b991113e5827e579becc1188d2a695bbf91975f1722eba6ad7951a"
},
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "portable-companion",
"startedAt": "2026-11-01T03:42:13.785Z",
"finishedAt": "2026-11-01T03:42:28.702Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable-companion.log",
"logBytes": 806,
"logSha256": "75220b62ab01e67c148f6ae9e18bb40f4324235d33c3a3327b934f4241d88928",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,8 @@
PASS desktop explicitly enables HTTPS and downloads the actual public CA without changing OS trust
PASS 390px real gateway pairing clears fragment, displays scoped task list and registers the same device in desktop
PASS phone UI confirms original Task/Run approval and the existing Runtime executes one command
PASS original paginated diff and counted check/report display verified content from the same Task
PASS disconnect and refresh recover from persistent seq without submitting a new command or Run
PASS PWA service worker stores the shell and no API/project response
PASS desktop revocation removes mobile project content immediately on the next read while preserving the original completed tool
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\companion-ui-4b713f53-63bc-43a1-948c-a1d62a594452
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "portable-protocols",
"startedAt": "2026-11-01T03:42:28.774Z",
"finishedAt": "2026-11-01T03:42:40.373Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable-protocols.log",
"logBytes": 715,
"logSha256": "5306173806e65a451143531b8783a41480786ffed927f53d0c716dadf01ffdee",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,6 @@
PASS actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable
PASS separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts
PASS actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE
PASS desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay
PASS truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\model-protocols-ui-af53870d-a592-4f9a-9583-947a6628aeb7
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "portable-vision",
"startedAt": "2026-11-01T03:42:40.439Z",
"finishedAt": "2026-11-01T03:42:54.121Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable-vision.log",
"logBytes": 618,
"logSha256": "0f72df605eef4e137472a12b2c901636377542653a9b71f03a22e9cf49a4f8b0",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,6 @@
PASS desktop upload, explicit route, refreshed draft, original download SHA, one paired tool and narrow task history
PASS forged image rejects without losing task text or sending a model request
PASS explicit budget preview and confirmation retain Task, attachment and completed tool while global capacity stays unchanged
PASS paired TLS companion verifies same screenshot, refresh restores it and revoke clears project/image content
PASS stopping screenshot SSE closes original HTTP and dispatches zero partial tools
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\vision-ui-5950091e-9d61-4dc8-9aea-1de3e3d6793c
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "portable-cache",
"startedAt": "2026-11-01T03:42:54.181Z",
"finishedAt": "2026-11-01T03:42:59.189Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable-cache.log",
"logBytes": 796,
"logSha256": "a368635d54db779a85312a3e6b305c1cd01559873f840443b26936316668678a",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,8 @@
PASS desktop query shows two-pass current SHA verification and real parsing reuse
PASS same-size restored-mtime edit invalidates the actual source and displays the reason
PASS disable persists across page reload and future queries parse current sources
PASS clear removes only derived project material; next query rebuilds while sessions and configuration remain byte-semantically unchanged
PASS failed settings keep actual switch and query state; the same operation can recover
PASS diagnostics displays bounded cache and last project verification without triggering another query
PASS 390px controls support keyboard, 44px targets, readable metrics and no horizontal page/panel overflow
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\project-cache-ui-9a3db89c-e9e5-48f7-a9b0-be8052bafb22
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "portable-evals",
"startedAt": "2026-11-01T03:42:59.265Z",
"finishedAt": "2026-11-01T03:44:23.308Z",
"exitCode": 0,
"logPath": ".qa/evals-f-portable-evals.log",
"logBytes": 942,
"logSha256": "b8e98be91d88a6bb0b880aedf8bd3536e2133e51d93c4c81ee8d59a902d45a11",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,6 @@
PASS selected compiled host prepares same-source workspaces and retains original three-test failure with zero original model requests and unchanged owner staging
PASS real owned HTTP tools, applied candidate review and approved original checks pass; unsealed attempted outcomes stay unknown and sealed report retains original failure
PASS compiled desktop/390px UI renders original and candidate checks, fixed-response label, unknown fee, keyboard focus and downloadable report; refresh preserves the same batch
PASS fresh parent review, actual original parent checks and exact-scope local Git complete adoption while preserving owner staged/unstaged/untracked bytes
PASS bundled candidate stop closes only its original owned HTTP request and keeps stopped outcome; changed source rejects before new workspaces without replay
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\engineering-evals-release-a1765e6e-72b6-449e-9ecc-437cd9d04f2d
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "prepare-install",
"startedAt": "2026-11-01T03:44:23.376Z",
"finishedAt": "2026-11-01T03:45:44.974Z",
"exitCode": 0,
"logPath": ".qa/evals-f-prepare-install.log",
"logBytes": 256,
"logSha256": "8ed7fd1a36c450a20963d0203aaac717639f7551f09b827d638d880ce15b6ec1",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"appId":"47d81ad0-b8ed-4fa3-b788-599d00aa5328","installerSha256":"7a03f0c8420a6eb79302a751b3e0a8494fcf15a926019a022ad9ae47136b9829","productSetupSha256":"8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e","samePayload":true}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "install",
"startedAt": "2026-11-01T03:45:45.047Z",
"finishedAt": "2026-11-01T03:52:13.717Z",
"exitCode": 0,
"logPath": ".qa/evals-f-install.log",
"logBytes": 566,
"logSha256": "104e581af26630514edb39ea279afe6cff396ad18fc851085a274773b5ad655d",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,8 @@
PASS exact final installer
PASS actual installed native bootstrap and bundled execution host
PASS actual installed owned DPAPI credential and HTTP authentication
PASS actual installed owned approval and bundled npm project check
PASS actual owned Electron crash preserves final installed host and data
PASS actual installed host restart preserves every row and loads owned saved connection
PASS actual exact final installer uninstall preserves all owned user data
{"success":true,"version":"1.20.0","root":"C:\\AWQA20\\i-1d12d1634cf54601844b105ae63e8847","cases":7}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-stage",
"startedAt": "2026-11-01T03:52:13.833Z",
"finishedAt": "2026-11-01T04:06:44.432Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-stage.log",
"logBytes": 94,
"logSha256": "55caee1ffdce0babb81b051369becccba5426c98a82447de7432c3654770269c",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"phase":"staged","version":"1.20.0","output":".qa/evals-f-formal-stage.json"}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-upgrade",
"startedAt": "2026-11-01T04:06:44.502Z",
"finishedAt": "2026-11-01T04:09:21.037Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-upgrade.log",
"logBytes": 98,
"logSha256": "1521ec3370451943028a37ed274efa4e5df49a7d1e1d0f665ca6a9f25c2dde63",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"phase":"upgraded","version":"1.20.0","output":".qa/evals-f-formal-upgrade.json"}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-activate",
"startedAt": "2026-11-01T04:09:21.104Z",
"finishedAt": "2026-11-01T04:21:27.743Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-activate.log",
"logBytes": 100,
"logSha256": "137c86fee8171da0dd7916ae67f47e412195e9593ca8fe47dcf93958bcf6b62c",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"phase":"activated","version":"1.20.0","output":".qa/evals-f-formal-activate.json"}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-ui-retry",
"startedAt": "2026-11-01T04:26:12.063Z",
"finishedAt": "2026-11-01T04:26:19.351Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-ui-retry.log",
"logBytes": 265,
"logSha256": "03cc44f968fe6ed9f1fc897b855c2988378fd2365c8f0bc12f0dac5061b93864",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1,3 @@
{"width":1280,"passedPanels":13}
{"width":390,"passedPanels":13}
{"success":true,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\evals-f-formal-ui-5b9055ca-55a0-45de-ba0c-2be1bc1c8be8","panels":26,"pageErrors":0,"requestFailures":0,"blockedWrites":0}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-verify",
"startedAt": "2026-11-01T04:21:27.809Z",
"finishedAt": "2026-11-01T04:24:06.778Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-verify.log",
"logBytes": 97,
"logSha256": "12bf1f6fedd1fa53ddce1ac11b14f4f61bef55f69d75e79ccb2489ac82a7f825",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"phase":"verified","version":"1.20.0","output":".qa/evals-f-formal-verify.json"}
@@ -0,0 +1,18 @@
{
"success": true,
"phase": "formal-artifacts",
"startedAt": "2026-11-01T04:26:19.418Z",
"finishedAt": "2026-11-01T04:26:26.228Z",
"exitCode": 0,
"logPath": ".qa/evals-f-formal-artifacts.log",
"logBytes": 138,
"logSha256": "2c77e41eee2e5aed431687c0f083fc75b1f17f01c1915c299e44ac1ad881b654",
"pointer": null,
"unchangedInputs": true,
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"release": {
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846",
"setupSha256": "8d0030e0187cff264f6901044840b53d3fa61016be9c5e4e3735d63db7a2b19e"
}
}
@@ -0,0 +1 @@
{"success":true,"total":1824,"checked":1824,"pages":19,"reportSha256":"96dc25a56d53b56f95e90d6badd13ab05c30f7cbdd47cfa7e990703b48ee21d5"}
@@ -0,0 +1,32 @@
import fs from 'node:fs';
import assert from 'node:assert/strict';
import { createHash } from 'node:crypto';
import { execFileSync } from 'node:child_process';
const hash = bytes => createHash('sha256').update(bytes).digest('hex');
const git = args => execFileSync('git', args, { windowsHide: true, maxBuffer: 20000000 });
const baseline = JSON.parse(fs.readFileSync('docs/engineering-evals-release-code-baseline.json', 'utf8'));
const tree = new Map(git(['ls-tree', '-r', '-z', baseline.codeCommit]).toString('utf8').split('\0').filter(Boolean).map(line => { const [header, name] = line.split('\t'); return [name, header.split(' ')[2]]; }));
const exact = [], normalized = [], generated = [];
const generator = 'examples/delivery-report/scripts/build.mjs'; assert.deepEqual(fs.readFileSync(generator), git(['show', baseline.codeCommit + ':' + generator]));
for (const item of baseline.inputs) {
const bytes = fs.readFileSync(item.path); assert.equal(hash(bytes), item.sha256); assert.equal(bytes.length, item.bytes);
if (tree.has(item.path)) {
const committed = git(['show', baseline.codeCommit + ':' + item.path]);
if (bytes.equals(committed)) exact.push(item.path);
else {
const normalizedBytes = Buffer.from(bytes.toString('utf8').replaceAll('\r\n', '\n'));
assert.deepEqual(Buffer.from(bytes.toString('utf8')), bytes, 'Only valid UTF-8 text may normalize.'); assert.deepEqual(normalizedBytes, committed, 'Difference beyond CRLF/LF: ' + item.path);
const attr = git(['check-attr', 'text', 'eol', '--', item.path]).toString('utf8'); assert.doesNotMatch(attr, /: text: unset/); assert.match(attr, /: eol: (lf|crlf)/);
normalized.push({ ...item, gitBytes: committed.length, gitSha256: hash(committed), attributes: attr.trim().split('\n'), scope: 'Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob.' });
}
} else {
assert.ok(/^examples\/delivery-report\/dist\/(?:[^/]+\.mjs|package\.json)$/.test(item.path), 'Unexpected uncommitted frozen input: ' + item.path);
const source = item.path.endsWith('/package.json') ? null : item.path.replace('/dist/', '/src/');
const expected = source ? git(['show', baseline.codeCommit + ':' + source]) : Buffer.from('{"type":"module"}\n'); assert.deepEqual(bytes, expected);
generated.push({ ...item, source, generator, generatorSha256: hash(fs.readFileSync(generator)) });
}
}
assert.equal(generated.length, 5);
const result = { success: true, at: new Date().toISOString(), codeCommit: baseline.codeCommit, inputFiles: baseline.inputs.length, exactInputs: exact.length, normalized, generated, scope: 'Every frozen source/QA/build input tied to the committed source or exact generated example derivation; unchanged build bytes independently recorded.' };
fs.writeFileSync('.qa/evals-f-code-git-audit.json', JSON.stringify(result, null, 2) + '\n', { flag: 'wx' });
console.log(JSON.stringify({ success: true, inputs: baseline.inputs.length, exact: exact.length, normalized: normalized.map(item => item.path), generated: generated.length }));
@@ -0,0 +1,33 @@
import fs from 'node:fs';
import path from 'node:path';
import assert from 'node:assert/strict';
import { createHash } from 'node:crypto';
const hash = bytes => createHash('sha256').update(bytes).digest('hex');
const read = file => JSON.parse(fs.readFileSync(file, 'utf8'));
const install = read(read('.qa/evals-f-install-location.json').result);
assert.equal(install.success, true);
const references = install.cases.flatMap(item => ['processLog', 'setupLog', 'uninstallLog'].filter(key => item[key]).map(key => ({ key, path: item[key], sha256: item[key + 'Sha256'] })));
const formal = read(read('.qa/evals-f-formal-baseline-location.json').staged); assert.equal(formal.success, true);
references.push({ key: 'setupLog', path: formal.setupLog, sha256: formal.setupLogSha256 });
const directory = '.qa/evals-f-log-completions'; assert.equal(fs.existsSync(directory), false);
const checked = [], completions = [];
for (const item of references) {
const bytes = fs.readFileSync(item.path), current = hash(bytes);
if (current === item.sha256) { checked.push({ ...item, bytes: bytes.length, exact: true }); continue; }
assert.equal(item.key, 'uninstallLog', 'Only the declared uninstall completion trailer may append.');
const prefix = bytes.subarray(0, bytes.length - 199), tail = bytes.subarray(bytes.length - 199);
assert.equal(hash(prefix), item.sha256, 'The original receipt must match the exact prefix.');
const lines = tail.toString('utf8').split('\r\n'); assert.equal(lines.pop(), '');
assert.deepEqual(lines.map(line => { assert.match(line, /^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}\.\d{3} /); return line.slice(26); }),
['Uninstallation process succeeded.', 'Removed all? Yes', 'Need to restart Windows? No', 'Log closed.']);
const archived = path.join(directory, String(completions.length + 1) + '-original-receipt-prefix-log.txt');
completions.push({ source: path.resolve(item.path), original: { path: archived, bytes: prefix.length, sha256: item.sha256 },
completed: { path: path.resolve(item.path), bytes: bytes.length, sha256: current }, appendedBytes: 199, appendedText: tail.toString('utf8'), prefix });
checked.push({ ...item, bytes: bytes.length, exact: false, exactOriginalPrefix: true });
}
fs.mkdirSync(directory);
for (const item of completions) { fs.writeFileSync(item.original.path, item.prefix, { flag: 'wx' }); delete item.prefix; }
const result = { success: true, at: new Date().toISOString(), checked, completions,
scope: 'All declared installer/process logs match their original SHA, or the uninstall receipt matches the exact original prefix followed solely by the four fixed 199-byte success/removed-all/no-restart/closed lines. Preserve both original prefix and final log; never rewrite the original receipt.' };
fs.writeFileSync(path.join(directory, 'index.json'), JSON.stringify(result, null, 2) + '\n', { flag: 'wx' });
console.log(JSON.stringify({ success: true, references: checked.length, exact: checked.filter(item => item.exact).length, completions: completions.length }));
@@ -0,0 +1,50 @@
import fs from 'node:fs';
import path from 'node:path';
import assert from 'node:assert/strict';
import { createHash } from 'node:crypto';
import { execFileSync } from 'node:child_process';
import { publicSnapshot, compareOriginalState } from './evals-f-state.mjs';
const hash = bytes => createHash('sha256').update(bytes).digest('hex');
const git = (args, options = {}) => execFileSync('git', args, { windowsHide: true, maxBuffer: 512 * 1024 * 1024, ...options });
const read = file => JSON.parse(fs.readFileSync(file, 'utf8'));
const identity = read('docs/engineering-evals-release-identity.json');
const baseline = read('docs/engineering-evals-release-code-baseline.json');
assert.equal(identity.success, true); assert.equal(identity.version, '1.20.0'); assert.equal(identity.codeCommit, baseline.codeCommit);
assert.equal(git(['status', '--porcelain']).toString().trim(), '');
const commit = git(['rev-parse', 'HEAD']).toString().trim(), records = [];
const check = (file, expected) => { const bytes = fs.readFileSync(file); assert.equal(bytes.length, expected.bytes, file); assert.equal(hash(bytes), expected.sha256, file); return bytes; };
for (const file of ['docs/engineering-evals-abc-evidence/manifest.json', 'docs/engineering-evals-de-evidence/manifest.json', 'docs/engineering-evals-f-release-evidence/manifest.json', 'docs/engineering-evals-f-seal-evidence/manifest.json']) {
const manifest = read(file);
if (file === 'docs/engineering-evals-abc-evidence/manifest.json') { assert.equal(manifest.stage, '1.20 A-C'); assert.equal(manifest.realModelRequests, 0); }
else assert.equal(manifest.success, true);
for (const row of manifest.files) {
const target = row.archived ?? path.join(path.dirname(file), row.file).replaceAll('\\', '/'); check(target, row);
records.push({ path: target, bytes: row.bytes, sha256: row.sha256 });
}
}
const objects = git(['cat-file', '--batch'], { input: records.map(row => commit + ':' + row.path.replaceAll('\\', '/') + '\n').join('') });
let offset = 0;
for (const row of records) {
const newline = objects.indexOf(10, offset), header = objects.subarray(offset, newline).toString(); assert.match(header, /^[a-f0-9]+ blob \d+$/);
const count = Number(header.split(' ').at(-1)), bytes = objects.subarray(newline + 1, newline + 1 + count); offset = newline + 2 + count;
assert.equal(count, row.bytes, row.path); assert.equal(hash(bytes), row.sha256, row.path); assert.deepEqual(bytes, fs.readFileSync(row.path));
}
assert.equal(offset, objects.length);
for (const row of [...baseline.inputs, ...baseline.builds, ...baseline.benchmarks]) check(row.path, row);
for (const kind of ['portable', 'source', 'installer']) check(identity.release[kind].path, identity.release[kind]);
const current = await publicSnapshot('http://127.0.0.1:4318', identity.formal.dataRoot), retained = compareOriginalState(read(identity.formal.baseline.before), current);
assert.equal(current.version, '1.20.0'); assert.equal(current.pid, identity.formal.pid); assert.equal(current.runtimeRoot, identity.formal.runtimeRoot); assert.deepEqual(current.active, []);
const docFiles = ['README.md', 'AGENTS.md', 'CHANGELOG.md', 'docs/QA-1.20.md', 'docs/RETROSPECTIVE-1.20.md', 'docs/PLAN-1.21.md', 'docs/NEXT-STEPS.md', 'docs/CAPABILITIES.md', 'docs/MILESTONE-AUDIT.md', 'docs/PRODUCT-PLAN.md'];
let localLinks = 0;
for (const file of docFiles) {
const text = fs.readFileSync(file, 'utf8'); assert.match(text, /1\.20|1\.21/);
for (const match of text.matchAll(/\[[^\]\r\n]*\]\(([^)\r\n]+)\)/g)) {
const target = match[1].replace(/^<|>$/g, '').split(/[#?]/)[0]; if (!target || /^[a-z][a-z0-9+.-]*:/i.test(target)) continue;
assert.ok(fs.existsSync(path.resolve(path.dirname(file), decodeURIComponent(target))), file + ': ' + target); localLinks++;
}
}
assert.doesNotMatch(fs.readFileSync('README.md', 'utf8').split(/\r?\n\r?\n/)[1], /候选正在|暂时保持1\.19/);
assert.doesNotMatch(fs.readFileSync('docs/PRODUCT-PLAN.md', 'utf8').split(/\r?\n\r?\n/)[1], /当前正式基线1\.19|下一\[1\.20\][^\n]*仅方案/);
const output = '.qa/evals-f-final-audit.json'; assert.equal(fs.existsSync(output), false);
fs.writeFileSync(output, JSON.stringify({ success: true, at: new Date().toISOString(), finalGitCommit: commit, codeCommit: baseline.codeCommit, retained, version: current.version, pid: current.pid, exactEvidence: records.length, evidenceBytes: records.reduce((sum, row) => sum + row.bytes, 0), frozenInputs: baseline.inputs.length, frozenBuilds: baseline.builds.length, localLinks, realModelRequests: 0, scope: 'Committed original A–F and post-seal evidence, frozen executable inputs/builds/benchmarks, immutable artifacts and all original formal state. Final documentation does not rewrite immutable packages.' }, null, 2) + '\n', { flag: 'wx' });
console.log(JSON.stringify({ success: true, output, commit, exactEvidence: records.length, localLinks, retained }));
@@ -0,0 +1,26 @@
import fs from 'node:fs';
import path from 'node:path';
import assert from 'node:assert/strict';
import { createHash } from 'node:crypto';
const hash = bytes => createHash('sha256').update(bytes).digest('hex');
const lock = JSON.parse(fs.readFileSync('package-lock.json', 'utf8')), release = JSON.parse(fs.readFileSync('releases/latest.json', 'utf8'));
const records = [];
for (const [location] of Object.entries(lock.packages)) {
if (!location.startsWith('node_modules/') || !fs.existsSync(location)) continue;
const meta = JSON.parse(fs.readFileSync(path.join(location, 'package.json'), 'utf8'));
for (const name of fs.readdirSync(location).filter(name => /^(licen[cs]e|copying)([.-].*)?$/i.test(name) && fs.statSync(path.join(location, name)).isFile())) {
const original = path.join(location, name), archived = path.join('licenses', (meta.name + '-' + meta.version + '-' + name).replace(/[^a-z0-9_.-]/gi, '_') + '.txt');
const expected = Buffer.from(fs.readFileSync(original, 'utf8')); assert.deepEqual(fs.readFileSync(archived), expected);
for (const root of [release.portableRoot, release.sourceRoot]) assert.deepEqual(fs.readFileSync(path.join(root, archived)), expected);
records.push({ original, archived, bytes: expected.length, sha256: hash(expected) });
}
}
const notices = fs.readFileSync('THIRD_PARTY_NOTICES.txt');
for (const root of [release.portableRoot, release.sourceRoot]) {
assert.deepEqual(fs.readFileSync(path.join(root, 'THIRD_PARTY_NOTICES.txt')), notices);
for (const name of fs.readdirSync('licenses')) { const bytes = fs.readFileSync(path.join('licenses', name)); assert.deepEqual(fs.readFileSync(path.join(root, 'licenses', name)), bytes); }
}
const result = { success: true, at: new Date().toISOString(), dependencyLicenseCopies: records.length, availableLicenseFiles: fs.readdirSync('licenses').length,
notices: { bytes: notices.length, sha256: hash(notices) }, records, scope: 'Generated dependency license texts match each installed locked package; every available license and notice exactly matches both immutable package directories. Original upstream whitespace is preserved, with a scoped Git whitespace exemption for those verbatim texts.' };
fs.writeFileSync('.qa/evals-f-license-audit.json', JSON.stringify(result, null, 2) + '\n', { flag: 'wx' });
console.log(JSON.stringify({ success: true, dependencyLicenseCopies: result.dependencyLicenseCopies, availableLicenseFiles: result.availableLicenseFiles, noticesSha256: result.notices.sha256 }));
@@ -0,0 +1,92 @@
import fs from 'node:fs';
import path from 'node:path';
import net from 'node:net';
import assert from 'node:assert/strict';
import { execFile } from 'node:child_process';
import { promisify } from 'node:util';
import { DatabaseSync, backup } from 'node:sqlite';
import { publicSnapshot, compareOriginalState, hash } from './evals-f-state.mjs';
import { InstallationManager, validateInstalledVersion } from '../src/core/desktop/install-manager.mjs';
import { HostController } from '../src/core/desktop/host-controller.mjs';
import { observeWindowsProcess } from '../src/core/desktop/process-identity.mjs';
import { projectEnvironment } from '../src/core/process-environment.mjs';
import { upgradeRunning } from '../scripts/upgrade-running.mjs';
const read = file => JSON.parse(fs.readFileSync(file, 'utf8'));
const save = (file, value) => fs.writeFileSync(file, JSON.stringify(value, null, 2) + '\n', { flag: 'wx' });
const mode = process.argv[2]; assert.ok(['stage', 'upgrade', 'activate', 'verify'].includes(mode));
const release = read('releases/latest.json'); assert.equal(release.installer.version, '1.20.0'); assert.equal(release.installer.qaFixture, null);
assert.equal(hash(fs.readFileSync(release.installer.path)), release.installer.sha256);
for (const phase of ['archives', 'source', 'portable', 'portable-companion', 'portable-protocols', 'portable-vision', 'portable-cache', 'portable-evals', 'install']) {
const result = read('.qa/evals-f-' + phase + '-result.json'); assert.equal(result.success, true, phase);
assert.equal(result.unchangedInputs, true); assert.equal(result.release.setupSha256, release.installer.sha256);
}
const source = read('.qa/evals-f-source-original-validation.json'); assert.equal(source.success, true); assert.ok(source.tests.tests >= 604); assert.equal(source.tests.pass, source.tests.tests); for (const key of ['fail', 'cancelled', 'skipped', 'todo']) assert.equal(source.tests[key], 0);
const allUi = read('docs/engineering-evals-all-ui-validation.json'); assert.equal(allUi.success, true); assert.equal(allUi.version, '1.20.0'); assert.equal(allUi.results.length, 28); assert.equal(allUi.groups, 210);
assert.equal(source.actualVision.success, true); assert.equal(source.actualVision.passed.length, 5); assert.equal(source.actualVisionEngineering.success, true);
assert.deepEqual(source.actualVisionEngineering.results.map(value => value.check.results[0].tests.passed), [8, 9, 10]);
assert.equal(source.actualProjectCache.success, true); assert.equal(source.actualProjectCache.passed.length, 7); assert.equal(source.actualCacheEngineering.success, true);
assert.deepEqual(source.actualCacheEngineering.results.map(value => value.check.results[0].tests.passed), [8, 9, 10]);
assert.equal(source.actualEvaluations.success, true); assert.equal(source.actualEvaluations.assertions.length, 5); assert.equal(source.actualEvaluationEngineering.success, true); assert.equal(source.actualEvaluationEngineering.assertions.length, 14);
const location = read('.qa/evals-f-install-location.json'), installed = read(location.result);
assert.equal(installed.success, true); assert.equal(installed.cases.length, 7); assert.equal(installed.installer.productSetup.sha256, release.installer.sha256);
const installRoot = 'C:/Users/wangy/AppData/Local/Programs/AgentWorkbench';
const originalPointer = read(path.join(installRoot, 'current.json')), dataRoot = fs.realpathSync.native(originalPointer.dataRoot);
const candidate = path.resolve(installRoot, 'versions', release.installer.candidateDirectory), url = 'http://127.0.0.1:4318', port = 4318, expectedPid = 36552;
const baselineLocation=fs.existsSync('.qa/evals-f-formal-baseline-location.json')?read('.qa/evals-f-formal-baseline-location.json'):null;
const output = '.qa/evals-f-formal-' + mode + '.json', beforeFile = baselineLocation?.before??'.qa/evals-f-formal-before.json'; assert.equal(fs.existsSync(output), false, 'Preserve a phase result instead of repeating the operation.');
const startedAt = new Date().toISOString();
const originalProcess = () => { const value = observeWindowsProcess(expectedPid); assert.ok(value); assert.equal(value.createdAt, '2026-10-31T06:30:34.359Z'); assert.equal(hash(fs.readFileSync(value.executable)), 'd702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5'); return value; };
async function inspectorClosed() { return new Promise((resolve, reject) => { const socket = net.createConnection({ host: '127.0.0.1', port: 9229 }); socket.setTimeout(1500); socket.once('connect', () => { socket.destroy(); reject(Error('An inspector is already open.')); }); socket.once('timeout', () => { socket.destroy(); reject(Error('Inspector state could not be verified.')); }); socket.once('error', error => { socket.destroy(); error.code === 'ECONNREFUSED' ? resolve(true) : reject(error); }); }); }
let result;
try {
originalProcess(); await inspectorClosed();
if (mode === 'stage') {
assert.equal(fs.existsSync(candidate), false); assert.equal(fs.existsSync(beforeFile), false);
const before = await publicSnapshot(url, dataRoot); assert.equal(before.version, '1.19.0'); assert.equal(before.pid, expectedPid); assert.deepEqual(before.active, []);
const controller = new HostController({ appRoot: before.runtimeRoot, dataRoot, port, nodePath: process.execPath }); assert.ok(await controller.connect());
const status = await controller.status(); assert.equal(status.desktopWindows.count, 0); assert.equal(status.activity.active, false);
save(beforeFile, before); save('.qa/evals-f-formal-original-pointer.json', originalPointer);
save('.qa/evals-f-formal-baseline-location.json', { before: beforeFile, staged: '.qa/evals-f-formal-stage.json', source: 'Fresh complete idle original 1.19 state; no historical counts reused.' });
const db = new DatabaseSync(path.join(dataRoot, 'workbench.sqlite'), { readOnly: true });
const backupPath = path.resolve('.qa/evals-f-formal-original.sqlite'); assert.equal(fs.existsSync(backupPath), false);
try { await backup(db, backupPath); } finally { db.close(); }
const copy = new DatabaseSync(backupPath, { readOnly: true });
try { assert.equal(copy.prepare('PRAGMA quick_check').get().quick_check, 'ok'); } finally { copy.close(); }
save('.qa/evals-f-formal-private-backup-receipt.json', { path: backupPath, bytes: fs.statSync(backupPath).size, sha256: hash(fs.readFileSync(backupPath)), credentialsExtracted: false, committed: false });
compareOriginalState(before, await publicSnapshot(url, dataRoot));
const log = path.resolve('.qa/evals-f-formal-setup.log'); assert.equal(fs.existsSync(log), false);
const execution = await promisify(execFile)(release.installer.path, ['/VERYSILENT', '/SUPPRESSMSGBOXES', '/NORESTART', '/TASKS=desktopicon', '/DIR=' + installRoot, '/DATA_ROOT=' + dataRoot, '/PORT=' + port, '/STAGE_ONLY=1', '/LOG=' + log],
{ windowsHide: true, env: projectEnvironment(), timeout: 900000, maxBuffer: 1024 * 1024 });
const identity = validateInstalledVersion(candidate), after = await publicSnapshot(url, dataRoot), retained = compareOriginalState(before, after);
assert.equal(after.version, '1.19.0'); assert.deepEqual(read(path.join(installRoot, 'current.json')), originalPointer);
result = { success: true, phase: 'staged', version: '1.20.0', candidateIdentity: identity.identitySha256, manifestSha256: identity.manifestSha256, retained, setupLog: log, setupLogSha256: hash(fs.readFileSync(log)), setupOutputEmpty: execution.stdout === '' };
} else {
const staged = read(baselineLocation?.staged??'.qa/evals-f-formal-stage.json'), before = read(beforeFile); assert.equal(staged.success, true); assert.equal(staged.setupSha256, release.installer.sha256);
const identity = validateInstalledVersion(candidate); assert.equal(identity.identitySha256, staged.candidateIdentity);
const current = await publicSnapshot(url, dataRoot); compareOriginalState(before, current); assert.deepEqual(current.active, []);
if (mode === 'upgrade') {
assert.equal(current.version, '1.19.0');
const info = read(path.join(dataRoot, 'service-info.json')); assert.equal(info.pid, expectedPid);
const upgraded = await upgradeRunning({ url, pid: expectedPid, currentRoot: info.appRoot, handlerRoot: current.runtimeRoot, newRoot: candidate });
assert.equal(upgraded.connectionPreserved, true);
const after = await publicSnapshot(url, dataRoot), retained = compareOriginalState(before, after); assert.equal(after.version, '1.20.0'); assert.equal(after.runtimeRoot, candidate);
await inspectorClosed(); save('.qa/evals-f-formal-after-upgrade.json', after);
result = { success: true, phase: 'upgraded', version: '1.20.0', upgraded, retained, currentProviderPreserved: true };
} else {
assert.equal(read('.qa/evals-f-formal-upgrade.json').success, true); assert.equal(current.version, '1.20.0'); assert.equal(current.runtimeRoot, candidate);
let activated = null;
if (mode === 'activate') { activated = await new InstallationManager({ installRoot, dataRoot, candidateRoot: candidate, port }).activate(); assert.equal(activated.phase, 'activated'); assert.equal(activated.hostRetained, false, 'Activation must not upgrade the already migrated handler again.'); }
const controller = new HostController({ appRoot: candidate, dataRoot, port, nodePath: process.execPath }); assert.ok(await controller.connect()); const status = await controller.status();
assert.equal(status.identity.pid, expectedPid); assert.equal(status.activity.active, false);
const gateway = await controller.api('/companion'); assert.equal(gateway.enabled, false); assert.deepEqual(gateway.devices, []); assert.equal(gateway.certificate, null);
const pointer = read(path.join(installRoot, 'current.json')); assert.equal(pointer.active.directory, release.installer.candidateDirectory); assert.equal(pointer.active.runtimeIdentity, identity.identitySha256);
assert.equal(fs.realpathSync.native(pointer.dataRoot), dataRoot); assert.equal(hash(fs.readFileSync(path.join(installRoot, 'AgentWorkbench.exe'))), hash(fs.readFileSync(path.join(release.portableRoot, 'AgentWorkbench.exe'))));
const after = await publicSnapshot(url, dataRoot), retained = compareOriginalState(before, after); await inspectorClosed(); save('.qa/evals-f-formal-after-' + mode + '.json', after);
result = { success: true, phase: mode === 'activate' ? 'activated' : 'verified', version: '1.20.0', activated, identity: status.identity, pointer, retained, companion: { enabled: gateway.enabled, devices: gateway.devices.length, certificate: gateway.certificate }, currentProviderPreserved: true,
counts: { projects: after.projects, sessions: after.database.sessionIds.length, records: after.database.tables.records.count, events: after.database.tables.events.count, artifacts: after.persistent.artifacts.length }, inspectorClosed: true };
}
}
} catch (error) { result = { success: false, phase: mode, error: error.stack }; process.exitCode = 1; }
save(output, { ...result, startedAt, finishedAt: new Date().toISOString(), installRoot, dataRoot, candidate, setupSha256: release.installer.sha256, originalProcess: originalProcess(), realModelRequests: 0,
scope: 'Accepted product setup stages the existing install, one in-memory handler upgrade preserves the original PID/Provider, pointer activation and final read-only validation. Every original table/row, all session exports and artifact bytes compared; no model Key extraction or QA certificate/device migration.' });
console.log(JSON.stringify({ success: result.success, phase: result.phase, version: result.version, output, ...(result.error ? { error: result.error } : {}) }));
@@ -0,0 +1,233 @@
{
"success": true,
"version": "1.20.0",
"at": "2026-11-01T02:48:23.918Z",
"groups": 210,
"results": [
{
"script": "verify-evaluations-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 89515,
"evidence": "docs/engineering-evals-evaluations-ui-validation.json",
"log": ".qa/engineering-evals-verify-evaluations-ui.log"
},
{
"script": "verify-project-cache-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 5144,
"evidence": "docs/engineering-evals-project-cache-ui-validation.json",
"log": ".qa/engineering-evals-verify-project-cache-ui.log"
},
{
"script": "verify-vision-ui.mjs",
"success": true,
"groups": 5,
"durationMs": 13531,
"evidence": "docs/engineering-evals-vision-ui-validation.json",
"log": ".qa/engineering-evals-verify-vision-ui.log"
},
{
"script": "verify-model-protocols-ui.mjs",
"success": true,
"groups": 5,
"durationMs": 12000,
"evidence": "docs/engineering-evals-model-protocols-ui-validation.json",
"log": ".qa/engineering-evals-verify-model-protocols-ui.log"
},
{
"script": "verify-companion-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 14796,
"evidence": "docs/engineering-evals-companion-ui-validation.json",
"log": ".qa/engineering-evals-verify-companion-ui.log"
},
{
"script": "verify-controlled-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 57195,
"evidence": "docs/engineering-evals-controlled-final-ui-validation.json",
"log": ".qa/engineering-evals-verify-controlled-ui.log"
},
{
"script": "verify-purge-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 20707,
"evidence": "docs/engineering-evals-purge-final-ui-validation.json",
"log": ".qa/engineering-evals-verify-purge-ui.log"
},
{
"script": "verify-workers-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 118630,
"evidence": "docs/engineering-evals-workers-ui-validation.json",
"log": ".qa/engineering-evals-verify-workers-ui.log"
},
{
"script": "verify-task-plans-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 13486,
"evidence": "docs/engineering-evals-task-ui-validation.json",
"log": ".qa/engineering-evals-verify-task-plans-ui.log"
},
{
"script": "verify-browser-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 23298,
"evidence": "docs/engineering-evals-browser-ui-validation.json",
"log": ".qa/engineering-evals-verify-browser-ui.log"
},
{
"script": "verify-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 20636,
"evidence": "docs/engineering-evals-basic-ui-validation.json",
"log": ".qa/engineering-evals-verify-ui.log"
},
{
"script": "verify-diagnostics-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 19350,
"evidence": "docs/engineering-evals-diagnostics-ui-validation.json",
"log": ".qa/engineering-evals-verify-diagnostics-ui.log"
},
{
"script": "verify-execution-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 24911,
"evidence": "docs/engineering-evals-execution-ui-validation.json",
"log": ".qa/engineering-evals-verify-execution-ui.log"
},
{
"script": "verify-delivery-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 43178,
"evidence": "docs/engineering-evals-delivery-ui-validation.json",
"log": ".qa/engineering-evals-verify-delivery-ui.log"
},
{
"script": "verify-index-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 7202,
"evidence": "docs/engineering-evals-index-ui-validation.json",
"log": ".qa/engineering-evals-verify-index-ui.log"
},
{
"script": "verify-change-sets-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 10906,
"evidence": "docs/engineering-evals-change-sets-ui-validation.json",
"log": ".qa/engineering-evals-verify-change-sets-ui.log"
},
{
"script": "verify-context-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 16096,
"evidence": "docs/engineering-evals-context-ui-validation.json",
"log": ".qa/engineering-evals-verify-context-ui.log"
},
{
"script": "verify-workspaces-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 26946,
"evidence": "docs/engineering-evals-workspaces-ui-validation.json",
"log": ".qa/engineering-evals-verify-workspaces-ui.log"
},
{
"script": "verify-python-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 19179,
"evidence": "docs/engineering-evals-python-ui-validation.json",
"log": ".qa/engineering-evals-verify-python-ui.log"
},
{
"script": "verify-react-delivery.mjs",
"success": true,
"groups": 6,
"durationMs": 23473,
"evidence": "docs/engineering-evals-react-delivery-validation.json",
"log": ".qa/engineering-evals-verify-react-delivery.log"
},
{
"script": "verify-research-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 23490,
"evidence": "docs/engineering-evals-research-ui-validation.json",
"log": ".qa/engineering-evals-verify-research-ui.log"
},
{
"script": "verify-engines-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 11574,
"evidence": "docs/engineering-evals-engines-ui-validation.json",
"log": ".qa/engineering-evals-verify-engines-ui.log"
},
{
"script": "verify-model-center-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 7405,
"evidence": "docs/engineering-evals-model-center-ui-validation.json",
"log": ".qa/engineering-evals-verify-model-center-ui.log"
},
{
"script": "verify-project-memory-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 6291,
"evidence": "docs/engineering-evals-project-memory-ui-validation.json",
"log": ".qa/engineering-evals-verify-project-memory-ui.log"
},
{
"script": "verify-task-checkpoints-ui.mjs",
"success": true,
"groups": 3,
"durationMs": 6414,
"evidence": "docs/engineering-evals-task-checkpoints-ui-validation.json",
"log": ".qa/engineering-evals-verify-task-checkpoints-ui.log"
},
{
"script": "verify-skills-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 8465,
"evidence": "docs/engineering-evals-skills-ui-validation.json",
"log": ".qa/engineering-evals-verify-skills-ui.log"
},
{
"script": "verify-mcp-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 9923,
"evidence": "docs/engineering-evals-mcp-ui-validation.json",
"log": ".qa/engineering-evals-verify-mcp-ui.log"
},
{
"script": "verify-mcp-recovery-ui.mjs",
"success": true,
"groups": 2,
"durationMs": 6446,
"evidence": "docs/engineering-evals-mcp-recovery-ui-validation.json",
"log": ".qa/engineering-evals-verify-mcp-recovery-ui.log"
}
],
"scope": "Every verifier owns an independent port and synthetic data directory. Synthetic provider fixtures verify protocols; configured-model acceptance is separate. No production service or real key read/copied."
}
@@ -0,0 +1 @@
{"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-projects-e250b730-f85f-4450-bbfc-1aeaf231c12e","result":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engineering-evals-projects-e250b730-f85f-4450-bbfc-1aeaf231c12e\\result.json"}
@@ -0,0 +1,34 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:53.341Z",
"passed": [
"desktop request estimate, actual usage, complete goal and history identity are visible",
"paged complete history opens actual tool result artifacts without executing tools",
"historical and resumed Runs retain their own request records",
"390px history, original JSON and sent-body dialogs fit and retain close controls",
"late old history failure stays in its original scope after switching projects",
"late old Run failure stays in its original scope after switching projects",
"late old request-body failure stays in its original scope after switching projects",
"context-limit pause explains the intact requirement and explicit continuation",
"390px repeated-read pause explains the cause and explicit continuation retains the same Task",
"desktop working evidence shows actual code, original result provenance and the current Task",
"390px working evidence and sent request stay readable and closing the artifact retains task navigation"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-desktop-plan.png",
".qa/screenshots/engineering-evals-desktop-history.png",
".qa/screenshots/engineering-evals-mobile-history.png",
".qa/screenshots/engineering-evals-mobile-original.png",
".qa/screenshots/engineering-evals-mobile-request-body.png",
".qa/screenshots/engineering-evals-mobile-read-pause.png",
".qa/screenshots/engineering-evals-desktop-working-evidence.png",
".qa/screenshots/engineering-evals-mobile-working-evidence.png"
],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8",
"data": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8\\data",
"mode": "saved synthetic context evidence; no real model or project commands executed by this UI verifier",
"browser": "156.0.4314.50"
}
@@ -0,0 +1,11 @@
PASS actual step editor seals the chosen build, viewport and three CSS interactions without opening the page
PASS review shows exact build identity and planned assertions; cancelling executes no browser work
PASS real inner Edge clicks the intended element and the two counted assertions display with original Task/Run/build identity
PASS original large JSON is paged in the UI and downloads the complete hash-identical result
PASS the original screenshot renders at its actual resolution and downloads identical PNG bytes
PASS a real failed assertion retains actual count one and requires a newly reviewed plan instead of replaying
PASS 390px forms and result records remain usable and the inner browser captures its real 390px layout
PASS stopping an actual in-flight assertion closes its owned browser and preserves prior successful and failed jobs
PASS a delayed original-record failure stays with its source and does not appear in a newly selected task
PASS actual host restart preserves the four original browser jobs and PNGs without model requests or execution replay
{"success":true,"version":"1.20.0","groups":10,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-e4663bef-525f-4c81-82d5-be5dd5e049ee"}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:37.798Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-batch-desktop-review.png",
".qa/screenshots/engineering-evals-batch-desktop-conflict.png",
".qa/screenshots/engineering-evals-batch-desktop-recovery.png",
".qa/screenshots/engineering-evals-batch-mobile-review.png",
".qa/screenshots/engineering-evals-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-c242d13f-8948-469e-8fad-ac64c9a4faa0",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,8 @@
PASS desktop explicitly enables HTTPS and downloads the actual public CA without changing OS trust
PASS 390px real gateway pairing clears fragment, displays scoped task list and registers the same device in desktop
PASS phone UI confirms original Task/Run approval and the existing Runtime executes one command
PASS original paginated diff and counted check/report display verified content from the same Task
PASS disconnect and refresh recover from persistent seq without submitting a new command or Run
PASS PWA service worker stores the shell and no API/project response
PASS desktop revocation removes mobile project content immediately on the next read while preserving the original completed tool
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\companion-ui-bd09d780-6ccc-43ab-ac46-82c2c274787d
@@ -0,0 +1,45 @@
PASS desktop request estimate, actual usage, complete goal and history identity are visible
PASS paged complete history opens actual tool result artifacts without executing tools
PASS historical and resumed Runs retain their own request records
PASS 390px history, original JSON and sent-body dialogs fit and retain close controls
PASS late old history failure stays in its original scope after switching projects
PASS late old Run failure stays in its original scope after switching projects
PASS late old request-body failure stays in its original scope after switching projects
PASS context-limit pause explains the intact requirement and explicit continuation
PASS 390px repeated-read pause explains the cause and explicit continuation retains the same Task
PASS desktop working evidence shows actual code, original result provenance and the current Task
PASS 390px working evidence and sent request stay readable and closing the artifact retains task navigation
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:53.341Z",
"passed": [
"desktop request estimate, actual usage, complete goal and history identity are visible",
"paged complete history opens actual tool result artifacts without executing tools",
"historical and resumed Runs retain their own request records",
"390px history, original JSON and sent-body dialogs fit and retain close controls",
"late old history failure stays in its original scope after switching projects",
"late old Run failure stays in its original scope after switching projects",
"late old request-body failure stays in its original scope after switching projects",
"context-limit pause explains the intact requirement and explicit continuation",
"390px repeated-read pause explains the cause and explicit continuation retains the same Task",
"desktop working evidence shows actual code, original result provenance and the current Task",
"390px working evidence and sent request stay readable and closing the artifact retains task navigation"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-desktop-plan.png",
".qa/screenshots/engineering-evals-desktop-history.png",
".qa/screenshots/engineering-evals-mobile-history.png",
".qa/screenshots/engineering-evals-mobile-original.png",
".qa/screenshots/engineering-evals-mobile-request-body.png",
".qa/screenshots/engineering-evals-mobile-read-pause.png",
".qa/screenshots/engineering-evals-desktop-working-evidence.png",
".qa/screenshots/engineering-evals-mobile-working-evidence.png"
],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8",
"data": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-4f682d58-d7c4-4302-b3f9-da38a3b6b2a8\\data",
"mode": "saved synthetic context evidence; no real model or project commands executed by this UI verifier",
"browser": "156.0.4314.50"
}
@@ -0,0 +1,10 @@
PASS desktop engine selector rejects a missing source, pins the actual installation and seals one original scope without model calls
PASS actual Harness runs the owned bridge and returns reviewable proposals after confirmed process-tree closure
PASS 390px keeps the real single-engine scope, header and a single-line 42px refresh action without horizontal overflow
PASS mobile child run view shows actual counts and closure, pages original inputs and downloads the exact original report bytes
PASS closing a run view ignores an old delayed record failure and keeps the selected task unchanged
PASS explicit child file review and check approval create a new native Run, retain previous evidence and account actual model requests once
PASS parent collection reads the original controlled-worker proof and explicit retention preserves every owner byte
PASS actual native stop closes the owned process tree, preserves one unknown model attempt and dispatches no late tool
PASS 390px recovery requires reading the owned observation before explicit review and preserves original outcome/report and cumulative budget
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\controlled-ui-613f723d-dc2b-4f1c-9575-0261bbd7583f
@@ -0,0 +1,40 @@
PASS actual failing tests and four source proposals retain the original project and task
PASS reviewed changes continue the same Task through 14 real tests and model-prepared Git review
PASS review shows actual paths, diffs, tests, author and policy; cancelling leaves Git unchanged
PASS an index change after confirmation preview refuses the stale job and preserves both staged owners
PASS 390px confirmation keeps file hashes, diffs and actions inside the modal
PASS double confirmation creates one four-file commit, retains owner bytes and publishes report with completion
PASS report viewing and Markdown/JSON downloads preserve verified artifact bytes and truthful acceptance limits
PASS mobile report preview closes cleanly and keeps the task input fixed
PASS unknown Git results block new submission and the explicit reconcile action restores the existing commit
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:45:19.417Z",
"browser": "156.0.4314.50",
"passed": [
"actual failing tests and four source proposals retain the original project and task",
"reviewed changes continue the same Task through 14 real tests and model-prepared Git review",
"review shows actual paths, diffs, tests, author and policy; cancelling leaves Git unchanged",
"an index change after confirmation preview refuses the stale job and preserves both staged owners",
"390px confirmation keeps file hashes, diffs and actions inside the modal",
"double confirmation creates one four-file commit, retains owner bytes and publishes report with completion",
"report viewing and Markdown/JSON downloads preserve verified artifact bytes and truthful acceptance limits",
"mobile report preview closes cleanly and keeps the task input fixed",
"unknown Git results block new submission and the explicit reconcile action restores the existing commit"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\delivery-ui-03321e56-2fe5-43f1-ab75-7962aad14cda\\四模块交付工程",
"projectId": "d666ea37-de8b-4053-8b45-59b2611c8762",
"sessionId": "550fa45e-8d3b-4300-b0a3-3c75e5b3aa7f",
"taskId": "6b4c6889-8ffa-4bba-9b2e-5fc4e0e636f6",
"commit": "a1d376946a61912a9fad43fc434724a63cddd269",
"recoveryCommit": "53b5ba8647f38bbb3fb7c080cee64e5ca508ceaa",
"testCounts": {
"baselineFailed": 13,
"passed": 14
},
"model": "controlled local HTTP fixture",
"confirmations": 2
}
@@ -0,0 +1,29 @@
PASS model response validation checks the tentative connection before saving
PASS a model failure after successful tools shows source, attempts and local runtime diagnosis
PASS explicit retry preserves the completed tool result without replaying the task
PASS an error question receives the actual session diagnosis and formatted answer
PASS review state exposes the review action and prevents application during a running request
PASS approved Unicode commands execute in the declared shell and retain Chinese output
PASS authentication errors do not retry and error/diagnostic controls fit a 390 px viewport
PASS stop cancels pending retry and clears running model state
PASS a transient service failure recovers within the bounded retry policy
{
"success": true,
"version": "1.20.0",
"url": "http://127.0.0.1:49479",
"date": "2026-11-01T02:44:11.121Z",
"passed": [
"model response validation checks the tentative connection before saving",
"a model failure after successful tools shows source, attempts and local runtime diagnosis",
"explicit retry preserves the completed tool result without replaying the task",
"an error question receives the actual session diagnosis and formatted answer",
"review state exposes the review action and prevents application during a running request",
"approved Unicode commands execute in the declared shell and retain Chinese output",
"authentication errors do not retry and error/diagnostic controls fit a 390 px viewport",
"stop cancels pending retry and clears running model state",
"a transient service failure recovers within the bounded retry policy"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; actual configured model is verified separately"
}
@@ -0,0 +1,11 @@
PASS independent desktop engine entry detects the declared installation and clearly separates connection from project execution
PASS missing installations and edited directories cannot launch a check until detection succeeds
PASS UI launch seals the selected installation into the current Task/Run and renders actual startup and process-close facts
PASS original record paging, full download SHA256 and nested-dialog keyboard close preserve the exact evidence
PASS an explicit new check creates a different process and record while retaining the original check unchanged
PASS declared pending-initialize fixture stops its owned process and explicit retry preserves the stopped result
PASS the same product UI verifies the actual installed DeepSeek SDK without a prompt or configured-model call
PASS 390px installation paths, source chain, original record, paging and keyboard close remain readable without page overflow
PASS late detection failure from a closed panel cannot appear in a different task or reveal its prior engine records
PASS actual host restart preserves all native and declared-fixture records with no protocol replay or project modification
{"success":true,"version":"1.20.0","groups":10,"root":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-d3eff124-d48d-49ec-a8ee-053ece5ea009","pageErrors":[],"requestFailures":[]}
@@ -0,0 +1,8 @@
PASS desktop/390px form rejects candidate test edits, keeps entered requirements, persists fixed model/source/budget and reloads the original plan
PASS explicit preparation seals two same-source checkouts and actual commands; original real three-test failure is retained with zero model requests
PASS candidate navigates to its original restricted task for real change review and check approval, runs the original test/build and preserves the parent source
PASS parallel comparison preserves original failure, candidate pass, real approval/application counts and absent cost; export and refresh retain the original report and fixture label
PASS adoption forms a fresh parent review batch; completion requires applied source, fresh real parent checks and local Git delivery while owner modifications remain exact
PASS stop waits for the owned candidate request, preserves stopped outcome and never turns cancellation into a passed sample or a replay
PASS changed owner source is rejected before workspace creation and the error stays attached to the original batch instead of a generic chat reply
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\engineering-evals-ui-3e05302e-714b-4746-9c16-9750cd4c8367
@@ -0,0 +1,26 @@
PASS model-selected checks wait for approval and display actual counted results
PASS verified artifact preview shows the real check log and hash
PASS changed source invalidates old checks and manual confirmation runs the new plan
PASS 390px task drawer, log preview, close controls and fixed composer remain operable
PASS reconnection synchronizes missed session changes in other projects
PASS budget controls pause before tools and preserve the goal across recorded runs
PASS applied proposals continue the original task into actual engineering verification
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:44:36.236Z",
"browser": "156.0.4314.50",
"passed": [
"model-selected checks wait for approval and display actual counted results",
"verified artifact preview shows the real check log and hash",
"changed source invalidates old checks and manual confirmation runs the new plan",
"390px task drawer, log preview, close controls and fixed composer remain operable",
"reconnection synchronizes missed session changes in other projects",
"budget controls pause before tools and preserve the goal across recorded runs",
"applied proposals continue the original task into actual engineering verification"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\execution-ui-a6416377-66c1-42a0-9bb6-2d108691e1bb\\project",
"model": "controlled local HTTP fixture"
}
@@ -0,0 +1,19 @@
{
"checkedAt": "2026-11-01T02:45:26.878Z",
"version": "1.20.0",
"passed": [
"工程索引可独立于任务使用,实际覆盖范围与损坏文件显示明确",
"真实AST查询打开原文件第181行并仅滚动代码容器,输入区和顶部保持可见",
"查询词保留;过期SHA不高亮旧位置,增量刷新后正确定位第184行",
"切换项目时延迟返回的旧索引不覆盖新项目结果",
"Python候选、字符串误报排除和局部导入文件候选保留真实证据标签",
"两处唯一锚点成为待审核提案,真实界面应用后BOM/CRLF和未选择原字节保留",
"390px索引查询、范围和完整指纹可读且无横向溢出,实际文件行定位通过",
"索引刷新失败保留归属和解释,旧结果禁用并可重试恢复"
],
"pageErrors": [],
"requestFailures": [],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\index-ui-ce0ffa00-0b75-404c-baeb-f35ba914f7b2",
"primaryProjectId": "1384a8cc-24d1-405b-8dc6-24f231c2d1ca",
"otherProjectId": "e54f273a-fb66-48fd-b621-dd1ff10b107e"
}
@@ -0,0 +1,3 @@
PASS actual host crash with no result report exposes its original verified input and unknown status
PASS 390px original-input review clears the job and invocation gates while retaining unknown, no report and no automatic model replay
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\mcp-recovery-ui-0887b3ed-42f9-46b0-8575-8b192de4c85b
@@ -0,0 +1,7 @@
PASS MCP registration stays disabled and shows the hashed local executable and Node entry
PASS actual stdio tools/list schema is visible; only the reviewed echo tool is enabled
PASS an enabled program whose source changes can be disabled immediately without executing the changed entry
PASS approved external call interrupted after dispatch remains unknown and does not replay
PASS TaskPanel exposes Task/Run source, original report, and human acknowledgement without marking unknown as success
PASS 390px MCP registry, long executable paths, controls, and operation history have no horizontal overflow
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\mcp-ui-6c870a9d-67e9-47a4-af39-e9c80274aed4
@@ -0,0 +1,7 @@
PASS connection form stores only the volatile credential and renders configured status without exposing it
PASS pool editor saves weighted members and binds selection for new Runs
PASS schema-bound import preview, opt-in automatic sync, revision update and sync shutdown keep credentials hidden
PASS real historical pagination detects the owned corrupted older artifact, retains its identity and leaves original bytes unchanged
PASS local inspection shows real database and artifact checks and emits zero model requests
PASS 390px model-center modal and connection cards remain operable without horizontal page overflow
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\model-center-ui-5859ab88-1815-4562-afc3-b50ed481b1a4
@@ -0,0 +1,6 @@
PASS actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable
PASS separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts
PASS actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE
PASS desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay
PASS truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\model-protocols-ui-ab35cd74-a07c-4241-8f01-97dcdb612a5d
@@ -0,0 +1,8 @@
PASS desktop query shows two-pass current SHA verification and real parsing reuse
PASS same-size restored-mtime edit invalidates the actual source and displays the reason
PASS disable persists across page reload and future queries parse current sources
PASS clear removes only derived project material; next query rebuilds while sessions and configuration remain byte-semantically unchanged
PASS failed settings keep actual switch and query state; the same operation can recover
PASS diagnostics displays bounded cache and last project verification without triggering another query
PASS 390px controls support keyboard, 44px targets, readable metrics and no horizontal page/panel overflow
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\project-cache-ui-f943f2c3-af0e-4b1f-bfc2-bce1357ab796
@@ -0,0 +1,5 @@
PASS source hashes remain visible and a changed file is explicitly expired with retained provenance
PASS incomplete inventory marks existing facts unverified and blocks new saves
PASS 390px memory review stays within the viewport with the incomplete-scan warning visible
PASS desktop and 390px request records expose the exact memory snapshot used by one owned local HTTP request
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\project-memory-ui-38030e70-3ca0-4ed7-80fa-a0ab36b0c4f0
@@ -0,0 +1,11 @@
PASS desktop prompt experiment is off by default and does not require, import or run Purge when disabled
PASS missing sources block sealing and an actual source change after UI detection is refused before creating a Task
PASS successfully detecting the replacement source clears the obsolete failed-sealing feedback
PASS both source versions are detected explicitly and disabling the experiment removes its required source and prompt fields
PASS a late detection failure after disabling cannot overwrite or leak into the current experiment form
PASS 390px controls remain readable and touchable; sealing retains the exact selected source and literal prompt without model requests
PASS actual Harness applies the exact non-interpolated prompt once in every owned model request and closes its complete process tree
PASS owned Run UI displays the original source/text/strategy hashes and downloads the exact report bytes after real native execution
PASS retaining the original Run and starting the next parent goal restores default-off without changing prior strategy, report or usage
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\controlled-purge-ui-9fb6bb20-842e-4f2a-a744-d3dcaecf01b5
{"passed":true,"nodes":9,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\controlled-purge-ui-9fb6bb20-842e-4f2a-a744-d3dcaecf01b5","error":null}
@@ -0,0 +1,42 @@
PASS mixed projects retain npm defaults and explicitly seal the selected Python checks
PASS the confirmation shows the actual interpreter and cancellation executes no checks
PASS actual unittest failures and the separately passed compilation display their counted results
PASS the log and original structured result are independently viewable and hash-bound
PASS a reviewed three-file repair runs new checks while retaining the original failed job and protected files
PASS 390px checks, interpreter paths, original result dialog and composer remain operable without page overflow
PASS Git confirmation and the Python execution report deliver only the three reviewed sources and preserve owner changes
{
"success": true,
"version": "1.20.0",
"at": "2026-11-01T02:46:40.000Z",
"browser": "156.0.4314.50",
"passed": [
"mixed projects retain npm defaults and explicitly seal the selected Python checks",
"the confirmation shows the actual interpreter and cancellation executes no checks",
"actual unittest failures and the separately passed compilation display their counted results",
"the log and original structured result are independently viewable and hash-bound",
"a reviewed three-file repair runs new checks while retaining the original failed job and protected files",
"390px checks, interpreter paths, original result dialog and composer remain operable without page overflow",
"Git confirmation and the Python execution report deliver only the three reviewed sources and preserve owner changes"
],
"pageErrors": [],
"requestFailures": [],
"checks": {
"before": {
"total": 6,
"passed": 1,
"failed": 5,
"skipped": 0,
"cancelled": 0
},
"after": {
"total": 6,
"passed": 6,
"failed": 0,
"skipped": 0,
"cancelled": 0
}
},
"commit": "cd0b554a3e9e1905f314034f6c33479ed336b47b",
"scope": "Independent host and owned fixture. Real Python processes, reviewed API repairs and actual local Git. No configured model requests or production credentials."
}
@@ -0,0 +1,82 @@
PASS the sealed React TypeScript project builds but its real domain tests first expose the functional failures
PASS a real browser separately observes that the broken pending filter wrongly shows all three tasks
PASS the four-file reviewed repair passes all nine domain tests, actual TypeScript checking and the Vite production build
PASS the production React app passes real filtering, search, single-task toggling and updated statistics
PASS the same built React app remains operable at 390px without horizontal overflow
PASS Workbench Git commits only the four reviewed files and binds the actual checks while preserving tests, configuration and owner changes
{
"success": true,
"version": "1.20.0",
"at": "2026-11-01T02:47:03.094Z",
"browser": "156.0.4314.50",
"passed": [
"the sealed React TypeScript project builds but its real domain tests first expose the functional failures",
"a real browser separately observes that the broken pending filter wrongly shows all three tasks",
"the four-file reviewed repair passes all nine domain tests, actual TypeScript checking and the Vite production build",
"the production React app passes real filtering, search, single-task toggling and updated statistics",
"the same built React app remains operable at 390px without horizontal overflow",
"Workbench Git commits only the four reviewed files and binds the actual checks while preserving tests, configuration and owner changes"
],
"pageErrors": [],
"requestFailures": [],
"originalTests": {
"total": 9,
"passed": 2,
"failed": 7,
"cancelled": 0,
"skipped": 0
},
"repairedTests": {
"total": 9,
"passed": 9,
"failed": 0,
"cancelled": 0,
"skipped": 0
},
"beforePending": 3,
"checks": [
{
"name": "test",
"status": "passed",
"exitCode": 0,
"tests": {
"total": 9,
"passed": 9,
"failed": 0,
"cancelled": 0,
"skipped": 0
}
},
{
"name": "typecheck",
"status": "passed",
"exitCode": 0,
"tests": null
},
{
"name": "build",
"status": "passed",
"exitCode": 0,
"tests": null
}
],
"commit": "73ba3a1f224e41cb71d0d17b75fc24e854abb5d9",
"changes": [
"src/App.tsx",
"src/query.ts",
"src/summary.ts",
"src/transition.ts"
],
"protectedFiles": {
"package.json": "db3c6bfd79d1ebb1f5692727715e2b48d3f09e0314d9f1d455d335774f5e7db8",
"package-lock.json": "48c138a05408667bbd332000731598415c9ae281d5072daa18544025ad89f7ff",
"tsconfig.json": "9dcf064d622cb31ae94ef348655f4f7af84076241601148929232314ef1b0c8a",
"vite.config.mjs": "0ea84b4e2909b04e4c1cb1b92392a9f85bcb46605472763b15935d3498ba8ed3",
"index.html": "37e9fd3172422ecca3902378c567331363dc1277ac749dd9f6bdf74f04540787",
"test/domain.test.mjs": "3fbd155cfc4919f3d0570a7ee26ff5ff4243e3e94250f3d0dbebe93c2b925ec0",
"src/types.ts": "d2bbcac2cb175e7bcafe087915f02c3cf2e0ea4b65235d6231bbcd4c3a682246",
"src/main.tsx": "c9a5787f5544788757ab654e1dfd83b5bc51495144e17aa078c2ee2f4412a302",
"src/styles.css": "60bcb8f7f73f4328274096132a3d73b7ef1fc9e6fbf6a3a3477fb9d519f2c25c"
},
"scope": "Owned frozen React TypeScript project with offline-installed fixed dependencies, real npm/typecheck/build/browser and Workbench review/Git/report. API fixtures supply repairs; configured-model success is separate."
}
@@ -0,0 +1,19 @@
PASS independent desktop research entry detects the installed fixed REA version
PASS UI registration seals the artifact identity in the current project and creates no model request
PASS actual REA ASAR analysis renders the verified source chain and downloads the exact original Bundle
PASS original field selection, paging and limitations retain exact bytes; Escape closes only the top dialog
PASS raw responses and connection records are readable; repeat analysis reuses the verified original without dispatch
PASS UI PE operation selection performs actual import and resource analysis with independently verified target hashes
PASS changed artifact versions refuse dispatch, retain the stale record and require a separately registered version
PASS 390px research, long identities and original evidence dialogs fit the viewport and retain usable close controls
PASS a real host restart preserves exact target/job identities and serves sealed Evidence without producer replay
PASS a delayed evidence response cannot reopen a closed research panel or change another task
PASS declared owned stdio fault fixture stops its root process and explicit retry adds a new record without changing history
{
"success": true,
"version": "1.20.0",
"groups": 11,
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\research-ui-c5846d63-4aab-44dc-87de-bad4dc8b1393",
"pageErrors": [],
"requestFailures": []
}
@@ -0,0 +1,5 @@
PASS desktop registers a disabled skill, reviews original UTF-8 instructions and explicitly enables it with no model calls
PASS source edit blocks activation until a new reviewed revision is registered; original revision remains available
PASS 390px review and activation retain readable paths, revision history and visible source state without horizontal overflow
PASS actual local HTTP task reads precisely revision 2 and exposes its SHA-bound sent catalog in task evidence
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\skills-ui-b290493c-20e3-44c0-8118-0c0f97b6aeb1
@@ -0,0 +1,4 @@
PASS desktop saves and inspects the full original Task and tool provenance without another model request
PASS an outside source change is visible and removes the checkpoint continuation action
PASS 390px explicit continuation keeps the same Task and one original read; a second resume of the old checkpoint is blocked
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\task-checkpoint-ui-acec9eba-09b0-4791-8805-bb960a1affea
@@ -0,0 +1,9 @@
PASS structured editor seals two real steps and their dependency without running tools
PASS original owned read verifies the prerequisite and opens its hashed proof without replay
PASS real two-test and build job supplies the current-source proof and completes the sealed plan
PASS outside source edits invalidate the current proof, retain the rejection and block a passed delivery report
PASS 390px immutable revision adds a mobile step, preserves old criteria and keeps evidence dialogs operable
PASS a delayed plan-read failure stays with the original task after selection changes
PASS controlled tab unmount during a delayed successful save retains the original task result without restoring the closed editor
PASS real host restart retains all plan revisions, accepted/rejected proofs and the original operations without replay
{"success":true,"version":"1.20.0","groups":8,"directory":"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-10c27c49-90cb-40fb-ab28-1f7648eaf2f1"}
@@ -0,0 +1,37 @@
PASS project selection and real file preview
PASS real command consent, execution and stale snapshot rejection
PASS diff review and verified file application
PASS manual editor creates a reviewable proposal
PASS file responses stay with the current selection
PASS denial, session selection, reload, stale response rejection and export
PASS project inventory responses cannot replace another project
PASS 780 and 390 px: project drawer, file, diff and trace controls, no page overflow
PASS unified and detailed research reports render
PASS model list, ephemeral key, compatible fixture tool loop and return to offline mode
{
"success": true,
"url": "http://127.0.0.1:51791",
"browser": "Microsoft Edge 156.0.4314.50",
"date": "2026-11-01T02:43:51.519Z",
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\ui-4ec29e73-f604-4521-ae99-ca646e8e3a0b\\ui-project",
"viewports": [
1440,
780,
390
],
"passed": [
"project selection and real file preview",
"real command consent, execution and stale snapshot rejection",
"diff review and verified file application",
"manual editor creates a reviewable proposal",
"file responses stay with the current selection",
"denial, session selection, reload, stale response rejection and export",
"project inventory responses cannot replace another project",
"780 and 390 px: project drawer, file, diff and trace controls, no page overflow",
"unified and detailed research reports render",
"model list, ephemeral key, compatible fixture tool loop and return to offline mode"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; no real model"
}
@@ -0,0 +1,6 @@
PASS desktop upload, explicit route, refreshed draft, original download SHA, one paired tool and narrow task history
PASS forged image rejects without losing task text or sending a model request
PASS explicit budget preview and confirmation retain Task, attachment and completed tool while global capacity stays unchanged
PASS paired TLS companion verifies same screenshot, refresh restores it and revoke clears project/image content
PASS stopping screenshot SSE closes original HTTP and dispatches zero partial tools
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\vision-ui-700b4667-d3d6-4378-8dc0-dc9ca9ee109d
@@ -0,0 +1,11 @@
PASS desktop/390px editor seals the actual parent goal, two scopes and shared budget without model calls or source writes
PASS explicit workspace confirmation creates two distinct Git checkouts and keeps every original source/staging byte
PASS each lane navigates to its original child task, hides unsupported actions and applies only an explicitly reviewed child batch
PASS both UI approvals run real three-test/build checks and collect the original hashed outputs before any parent write
PASS parent UI review applies a new two-file batch and accepts completion only after a fresh real parent check and local Git delivery
PASS 390px conflict review names the real overlapping path, leaves parent files untouched and explicitly retains the original child results
PASS mobile parent stop waits for both held requests, preserves estimated unknown usage and retains the original deadline
PASS switching historical groups quarantines a deliberately late previous-group error and its preview
PASS recovery UI requires reading the original record and rejects changed source instead of acknowledging stale evidence
PASS explicit recovery retention preserves changed owner source and unknown usage, closes the original goal and unlocks the next plan
EVIDENCE D:\Ai-project\REA逆向\Agent-Workbench\.qa\workers-ui-f19aa43d-dece-4e0d-b46d-da58150bbfbd
@@ -0,0 +1,37 @@
PASS desktop preview seals the committed version and shows existing staged/unstaged/untracked source changes
PASS repeated create clicks execute once and preserve the exact source index and owner files
PASS opening the child, returning to the source and reloading retain stable project/session identity
PASS a record owned by another session navigates to that saved owner instead of accepting its actions
PASS explicit recovery preserves outside content and acknowledgement does not report successful creation
PASS 390×844 preview/create/open/return stays within viewport and preserves source ownership
PASS late-failure stays with the original session after project switching
PASS late-success stays with the original session after project switching
PASS a delayed bootstrap cannot navigate after the task panel has unmounted
{
"success": true,
"version": "1.20.0",
"at": "2026-11-01T02:46:20.828Z",
"browser": "156.0.4314.50",
"passed": [
"desktop preview seals the committed version and shows existing staged/unstaged/untracked source changes",
"repeated create clicks execute once and preserve the exact source index and owner files",
"opening the child, returning to the source and reloading retain stable project/session identity",
"a record owned by another session navigates to that saved owner instead of accepting its actions",
"explicit recovery preserves outside content and acknowledgement does not report successful creation",
"390×844 preview/create/open/return stays within viewport and preserves source ownership",
"late-failure stays with the original session after project switching",
"late-success stays with the original session after project switching",
"a delayed bootstrap cannot navigate after the task panel has unmounted"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/engineering-evals-workspaces-review-desktop.png",
".qa/screenshots/engineering-evals-workspaces-ready-desktop.png",
".qa/screenshots/engineering-evals-workspaces-recovery-desktop.png",
".qa/screenshots/engineering-evals-workspaces-review-mobile.png",
".qa/screenshots/engineering-evals-workspaces-child-mobile.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\workspace-ui-931b206a-7bb0-4bce-b29d-d29d91468261",
"scope": "Independent synthetic Git projects and real browser flows. Desktop/390×844, actual worktree creation, source preservation, explicit external recovery, ownership navigation, delayed success/error/navigation. No production service or real model credential used."
}
@@ -0,0 +1,24 @@
{
"success": true,
"version": "1.20.0",
"testedAt": "2026-11-01T02:52:37.820798+00:00",
"archives": [
{
"kind": "portable",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-win-x64-20261101024825846.zip",
"files": 17737,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "1a07ba9f313bd012abcf924de24dd19c6b02b3e3f1d0bed9606cdee92ac6a019"
},
{
"kind": "source",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.20.0-source-20261101024825846.zip",
"files": 18058,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "6f7321fdeb04fc42daa78aaf94a6dfbc3b0ff83b002fc60654f6c815872b1594"
}
],
"extractionRoot": "D:\\AWQA20\\source-check-347074c8a9464ad1927bda77e371ec0a\\Agent-Workbench-1.20.0-source-20261101024825846"
}
@@ -0,0 +1,316 @@
{
"success": true,
"at": "2026-11-01T02:22:33.554Z",
"codeCommit": "49314764f571ad48b7cef38d62c32b0bb66a8e9f",
"inputFiles": 415,
"exactInputs": 388,
"normalized": [
{
"path": "scripts/package.mjs",
"bytes": 11486,
"sha256": "a083e2b6058c35641de30ceee3f8d4226afccbd7569f7d9cbd9d3ca216eadbfe",
"gitBytes": 11349,
"gitSha256": "bb34f3de1c67ce6411d7ff9fdbe304da1b2f269a337957b98d6a407b94b38a2d",
"attributes": [
"scripts/package.mjs: text: auto",
"scripts/package.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/qa-evidence.mjs",
"bytes": 936,
"sha256": "055f87c9a203265410a21b44ce0dd326dc120fadb04b4cd94ddc6903321a86ac",
"gitBytes": 917,
"gitSha256": "245157aa482948aeb2eb461af66b2235a50e60aab98f791b24931d19710a2227",
"attributes": [
"scripts/qa-evidence.mjs: text: auto",
"scripts/qa-evidence.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/upgrade-running.mjs",
"bytes": 13565,
"sha256": "79e04602824fbbf701c7a57200e09096c77d37d98a8706df772df7bd22efdf04",
"gitBytes": 13399,
"gitSha256": "f9da386bc69e3d40cbbc48f0cfb24308fe659913a43f0639e966100ac8df3ad5",
"attributes": [
"scripts/upgrade-running.mjs: text: auto",
"scripts/upgrade-running.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-all-ui.mjs",
"bytes": 10965,
"sha256": "d8da9b99b8c76ddcb2d87d9108d83d489c5c4d67f49e785058afc25e8bf67223",
"gitBytes": 10857,
"gitSha256": "e0f9558006ed0539a539185ec81cfb6e62f1fd78bdaa71b1eeb26ac5bd78843b",
"attributes": [
"scripts/verify-all-ui.mjs: text: auto",
"scripts/verify-all-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-change-sets-ui.mjs",
"bytes": 16256,
"sha256": "1b546aeb1c128cad5b7b4ff94373c0ea19508d2bf2aa72f812fdbbad6ee2e88f",
"gitBytes": 16115,
"gitSha256": "df142a1fc61dc9275d438a296f071c75429bfbd05c311a407195c62ac5e56519",
"attributes": [
"scripts/verify-change-sets-ui.mjs: text: auto",
"scripts/verify-change-sets-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-context-ui.mjs",
"bytes": 18649,
"sha256": "f9711fedbc7bdd82b302f60e9fbd0319e08952a99721fca4e4688e7cc7af73a7",
"gitBytes": 18453,
"gitSha256": "d5f243d4376c31d7a07aa8c25be03fbc014c52fbf2d783987bce5ed882e4cb40",
"attributes": [
"scripts/verify-context-ui.mjs: text: auto",
"scripts/verify-context-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-controlled-release.mjs",
"bytes": 21862,
"sha256": "7a3ed455cb555210ea83b511ec6796d1996b669a0119c83c20ef0bc31e9228b2",
"gitBytes": 21663,
"gitSha256": "192065d19323b05a864eeb3cb842c46e3a8fb9296511bc93d35e53e5b64c7183",
"attributes": [
"scripts/verify-controlled-release.mjs: text: auto",
"scripts/verify-controlled-release.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-release.mjs",
"bytes": 17704,
"sha256": "641186015226404ff392e1a96ef4f2aa1e6de28bfb036e56c2baa8578a824bcc",
"gitBytes": 17522,
"gitSha256": "873fbb0bb282742eae8921b6b050155c85b90adfcec9c61aedb429735fdaa0c3",
"attributes": [
"scripts/verify-release.mjs: text: auto",
"scripts/verify-release.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-source-package.mjs",
"bytes": 22247,
"sha256": "f983ea23ae9a31cfaa5a1f6d59c9ab2b08bd5e7ab598cf17cc4fda2dffb93840",
"gitBytes": 22029,
"gitSha256": "7b4b36529cf6e37e91b89d89ea455b75ff5cd69a153db57d55898e0014376057",
"attributes": [
"scripts/verify-source-package.mjs: text: auto",
"scripts/verify-source-package.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-ui.mjs",
"bytes": 18880,
"sha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6",
"gitBytes": 18623,
"gitSha256": "cd57dd67aada66f667a4e62b7a8f76a79d3c09acd7ba7c658b89e6d38dc6be9f",
"attributes": [
"scripts/verify-ui.mjs: text: auto",
"scripts/verify-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-workers-ui.mjs",
"bytes": 19096,
"sha256": "a01c2a298dedc2390282bee1703966de511bcc98a5149b5ab3dcd2fdc052fc8a",
"gitBytes": 18949,
"gitSha256": "c687dd25b85291532c790cdc4a74fb9bbae10014554817ef52c2440250dde7e2",
"attributes": [
"scripts/verify-workers-ui.mjs: text: auto",
"scripts/verify-workers-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/App.tsx",
"bytes": 68855,
"sha256": "2a345ac80a84d1833a56ddc351ab8c61c131a781a554a21fc5b65c394dae0d58",
"gitBytes": 68247,
"gitSha256": "c374f8b2332c3fca124b3d489cb630e6ab3a5c2b4f93d073b851ebc3f28436b7",
"attributes": [
"src/client/App.tsx: text: auto",
"src/client/App.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/BudgetPausePanel.tsx",
"bytes": 7143,
"sha256": "ac71ff1a5960bd71bec082ecf44c8b06596d4afe8e5eb2b71a803a3a19ce0b9e",
"gitBytes": 7116,
"gitSha256": "aab7e4e01ddf988059e762460d8aad1cf24566592a8cf1cb58414dc7c03d8720",
"attributes": [
"src/client/BudgetPausePanel.tsx: text: auto",
"src/client/BudgetPausePanel.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/ModelCenter.css",
"bytes": 10343,
"sha256": "13a8be33b8806275830eabc1f1c1a8bff0335850df7f0b1c8b28b1e5e7beb8a5",
"gitBytes": 10342,
"gitSha256": "4e7737b23113cbbdab2a94082e3644942210ef9e6bd5b957f9384d4b48187244",
"attributes": [
"src/client/ModelCenter.css: text: auto",
"src/client/ModelCenter.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/ModelCenter.tsx",
"bytes": 35795,
"sha256": "bc6e8404b11b0aa07b73d7660a41442909cf150354082e73e3b27eb77c30defe",
"gitBytes": 35646,
"gitSha256": "0dfacce109fd2ef91c2e8a2353ce0abc2567a0f9e356281f231cbbc1504287cf",
"attributes": [
"src/client/ModelCenter.tsx: text: auto",
"src/client/ModelCenter.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/SkillCenter.tsx",
"bytes": 9303,
"sha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10",
"gitBytes": 9240,
"gitSha256": "de7a4426aef468a73a9522da9883592ab0cc29a1f2b3786b764cd51a304347b2",
"attributes": [
"src/client/SkillCenter.tsx: text: auto",
"src/client/SkillCenter.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/input-attachments.css",
"bytes": 3104,
"sha256": "4e9b964b6ecb9eed2bf345ed5b689f5a56320b45e02c01a9cc6ac8cddd259db3",
"gitBytes": 3101,
"gitSha256": "c5a267b7f77a95b0dd601c306600283c1a8d9f64c60b5c438f1e21880b6853cb",
"attributes": [
"src/client/input-attachments.css: text: auto",
"src/client/input-attachments.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/mobile/mobile.css",
"bytes": 11978,
"sha256": "9a5ac0fb2cabc2dbb0b9f9ef3edbeb5ff26e31d1347fa712485c00605b3980a0",
"gitBytes": 11969,
"gitSha256": "c36c8156bcc2ba8e8289859a775eebf968d0a53f66ce97c765e74617be2e3cb6",
"attributes": [
"src/client/mobile/mobile.css: text: auto",
"src/client/mobile/mobile.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/styles.css",
"bytes": 40574,
"sha256": "f982b39cdc159ac45ad70e1cfc0df7e46ee11502a8613bc5cc70babf92ea2325",
"gitBytes": 40545,
"gitSha256": "44a12c0ce323a0e82da55056043ca70b2af78c7a343fe4668380eabf11502c9d",
"attributes": [
"src/client/styles.css: text: auto",
"src/client/styles.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/server/diagnostics.mjs",
"bytes": 8093,
"sha256": "500364c61fb4af7e547cae474c825c9425eab568a2d1b15b41c3c738bac249d5",
"gitBytes": 7965,
"gitSha256": "e6cdc9fe00ad74554d123e40ed97483e52f23b8e46d5e48e3bb3fb148617d013",
"attributes": [
"src/server/diagnostics.mjs: text: auto",
"src/server/diagnostics.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "tests/companion.test.mjs",
"bytes": 30054,
"sha256": "1cf4202abef9171db76b09778fbcb00f6db47c61a3b5890f024a0dfe05210258",
"gitBytes": 30053,
"gitSha256": "39c1867c8092304a30e2e2d4536006a281082ed72d76759bd20eb541ac21d969",
"attributes": [
"tests/companion.test.mjs: text: auto",
"tests/companion.test.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "tests/skills.test.mjs",
"bytes": 17628,
"sha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6",
"gitBytes": 17438,
"gitSha256": "977e987ccdeab5bf07fd3dd1788d8ba866a3dc3715c9dd947982a9abfbab7e06",
"attributes": [
"tests/skills.test.mjs: text: auto",
"tests/skills.test.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
}
],
"generated": [
{
"path": "examples/delivery-report/dist/cli.mjs",
"bytes": 818,
"sha256": "b8223dd1c0a98b3b7a0cd716db0ae053a2ca17fbd8272b005adcedd3ce5f7a69",
"source": "examples/delivery-report/src/cli.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/normalize.mjs",
"bytes": 1254,
"sha256": "57eb47b09913b131982a14c276ba5292aba4c94e0f475c97955221f6a7b7cdcd",
"source": "examples/delivery-report/src/normalize.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/package.json",
"bytes": 18,
"sha256": "1239d4d885dcad42201a27ed9324f8f0f760b78700d8db9ced39a511cffe7eae",
"source": null,
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/render.mjs",
"bytes": 375,
"sha256": "d449524d731a55ef51d0143f38ee8b73db56363c78babc385fa58df7f2a542f0",
"source": "examples/delivery-report/src/render.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/summary.mjs",
"bytes": 427,
"sha256": "bf7ada9e5dbca167df2b9a5306c1d9399b4a658fb0777c73812856687ad0c5ef",
"source": "examples/delivery-report/src/summary.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
}
],
"scope": "Every frozen source/QA/build input tied to the committed source or exact generated example derivation; unchanged build bytes independently recorded."
}
@@ -0,0 +1,316 @@
{
"success": true,
"at": "2026-11-01T02:05:42.388Z",
"codeCommit": "97bf5edddc47ff305965431a59ee5e47592908c3",
"inputFiles": 415,
"exactInputs": 388,
"normalized": [
{
"path": "scripts/package.mjs",
"bytes": 11486,
"sha256": "a083e2b6058c35641de30ceee3f8d4226afccbd7569f7d9cbd9d3ca216eadbfe",
"gitBytes": 11349,
"gitSha256": "bb34f3de1c67ce6411d7ff9fdbe304da1b2f269a337957b98d6a407b94b38a2d",
"attributes": [
"scripts/package.mjs: text: auto",
"scripts/package.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/qa-evidence.mjs",
"bytes": 936,
"sha256": "055f87c9a203265410a21b44ce0dd326dc120fadb04b4cd94ddc6903321a86ac",
"gitBytes": 917,
"gitSha256": "245157aa482948aeb2eb461af66b2235a50e60aab98f791b24931d19710a2227",
"attributes": [
"scripts/qa-evidence.mjs: text: auto",
"scripts/qa-evidence.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/upgrade-running.mjs",
"bytes": 13565,
"sha256": "79e04602824fbbf701c7a57200e09096c77d37d98a8706df772df7bd22efdf04",
"gitBytes": 13399,
"gitSha256": "f9da386bc69e3d40cbbc48f0cfb24308fe659913a43f0639e966100ac8df3ad5",
"attributes": [
"scripts/upgrade-running.mjs: text: auto",
"scripts/upgrade-running.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-all-ui.mjs",
"bytes": 10965,
"sha256": "d8da9b99b8c76ddcb2d87d9108d83d489c5c4d67f49e785058afc25e8bf67223",
"gitBytes": 10857,
"gitSha256": "e0f9558006ed0539a539185ec81cfb6e62f1fd78bdaa71b1eeb26ac5bd78843b",
"attributes": [
"scripts/verify-all-ui.mjs: text: auto",
"scripts/verify-all-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-change-sets-ui.mjs",
"bytes": 16327,
"sha256": "204a2831c67465f1f5e438ad8b806c106470d7f1cd1b6d9590569e863b952020",
"gitBytes": 16186,
"gitSha256": "be22e7d84e34bd154c65f9909a5d8db9fef2381f32714e7bb8c6507b9056b9bb",
"attributes": [
"scripts/verify-change-sets-ui.mjs: text: auto",
"scripts/verify-change-sets-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-context-ui.mjs",
"bytes": 18721,
"sha256": "9f3e74ef7775ede898c64865719181ccc2ad584f54e137f4fb9a1b5d05c9fac9",
"gitBytes": 18525,
"gitSha256": "2ab3af68998c889bd281c9ac741c76e70b21296f78aa36542e83577c5e913ca3",
"attributes": [
"scripts/verify-context-ui.mjs: text: auto",
"scripts/verify-context-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-controlled-release.mjs",
"bytes": 21862,
"sha256": "7a3ed455cb555210ea83b511ec6796d1996b669a0119c83c20ef0bc31e9228b2",
"gitBytes": 21663,
"gitSha256": "192065d19323b05a864eeb3cb842c46e3a8fb9296511bc93d35e53e5b64c7183",
"attributes": [
"scripts/verify-controlled-release.mjs: text: auto",
"scripts/verify-controlled-release.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-release.mjs",
"bytes": 17704,
"sha256": "641186015226404ff392e1a96ef4f2aa1e6de28bfb036e56c2baa8578a824bcc",
"gitBytes": 17522,
"gitSha256": "873fbb0bb282742eae8921b6b050155c85b90adfcec9c61aedb429735fdaa0c3",
"attributes": [
"scripts/verify-release.mjs: text: auto",
"scripts/verify-release.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-source-package.mjs",
"bytes": 22247,
"sha256": "f983ea23ae9a31cfaa5a1f6d59c9ab2b08bd5e7ab598cf17cc4fda2dffb93840",
"gitBytes": 22029,
"gitSha256": "7b4b36529cf6e37e91b89d89ea455b75ff5cd69a153db57d55898e0014376057",
"attributes": [
"scripts/verify-source-package.mjs: text: auto",
"scripts/verify-source-package.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-ui.mjs",
"bytes": 18880,
"sha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6",
"gitBytes": 18623,
"gitSha256": "cd57dd67aada66f667a4e62b7a8f76a79d3c09acd7ba7c658b89e6d38dc6be9f",
"attributes": [
"scripts/verify-ui.mjs: text: auto",
"scripts/verify-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "scripts/verify-workers-ui.mjs",
"bytes": 19096,
"sha256": "a01c2a298dedc2390282bee1703966de511bcc98a5149b5ab3dcd2fdc052fc8a",
"gitBytes": 18949,
"gitSha256": "c687dd25b85291532c790cdc4a74fb9bbae10014554817ef52c2440250dde7e2",
"attributes": [
"scripts/verify-workers-ui.mjs: text: auto",
"scripts/verify-workers-ui.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/App.tsx",
"bytes": 68855,
"sha256": "2a345ac80a84d1833a56ddc351ab8c61c131a781a554a21fc5b65c394dae0d58",
"gitBytes": 68247,
"gitSha256": "c374f8b2332c3fca124b3d489cb630e6ab3a5c2b4f93d073b851ebc3f28436b7",
"attributes": [
"src/client/App.tsx: text: auto",
"src/client/App.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/BudgetPausePanel.tsx",
"bytes": 7143,
"sha256": "ac71ff1a5960bd71bec082ecf44c8b06596d4afe8e5eb2b71a803a3a19ce0b9e",
"gitBytes": 7116,
"gitSha256": "aab7e4e01ddf988059e762460d8aad1cf24566592a8cf1cb58414dc7c03d8720",
"attributes": [
"src/client/BudgetPausePanel.tsx: text: auto",
"src/client/BudgetPausePanel.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/ModelCenter.css",
"bytes": 10343,
"sha256": "13a8be33b8806275830eabc1f1c1a8bff0335850df7f0b1c8b28b1e5e7beb8a5",
"gitBytes": 10342,
"gitSha256": "4e7737b23113cbbdab2a94082e3644942210ef9e6bd5b957f9384d4b48187244",
"attributes": [
"src/client/ModelCenter.css: text: auto",
"src/client/ModelCenter.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/ModelCenter.tsx",
"bytes": 35795,
"sha256": "bc6e8404b11b0aa07b73d7660a41442909cf150354082e73e3b27eb77c30defe",
"gitBytes": 35646,
"gitSha256": "0dfacce109fd2ef91c2e8a2353ce0abc2567a0f9e356281f231cbbc1504287cf",
"attributes": [
"src/client/ModelCenter.tsx: text: auto",
"src/client/ModelCenter.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/SkillCenter.tsx",
"bytes": 9303,
"sha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10",
"gitBytes": 9240,
"gitSha256": "de7a4426aef468a73a9522da9883592ab0cc29a1f2b3786b764cd51a304347b2",
"attributes": [
"src/client/SkillCenter.tsx: text: auto",
"src/client/SkillCenter.tsx: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/input-attachments.css",
"bytes": 3104,
"sha256": "4e9b964b6ecb9eed2bf345ed5b689f5a56320b45e02c01a9cc6ac8cddd259db3",
"gitBytes": 3101,
"gitSha256": "c5a267b7f77a95b0dd601c306600283c1a8d9f64c60b5c438f1e21880b6853cb",
"attributes": [
"src/client/input-attachments.css: text: auto",
"src/client/input-attachments.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/mobile/mobile.css",
"bytes": 11978,
"sha256": "9a5ac0fb2cabc2dbb0b9f9ef3edbeb5ff26e31d1347fa712485c00605b3980a0",
"gitBytes": 11969,
"gitSha256": "c36c8156bcc2ba8e8289859a775eebf968d0a53f66ce97c765e74617be2e3cb6",
"attributes": [
"src/client/mobile/mobile.css: text: auto",
"src/client/mobile/mobile.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/client/styles.css",
"bytes": 40574,
"sha256": "f982b39cdc159ac45ad70e1cfc0df7e46ee11502a8613bc5cc70babf92ea2325",
"gitBytes": 40545,
"gitSha256": "44a12c0ce323a0e82da55056043ca70b2af78c7a343fe4668380eabf11502c9d",
"attributes": [
"src/client/styles.css: text: auto",
"src/client/styles.css: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "src/server/diagnostics.mjs",
"bytes": 8093,
"sha256": "d754ad26bcdf8fb33e3c6d171f27e2726e3591c6acf87811d8cdbc2c3c406aad",
"gitBytes": 7965,
"gitSha256": "ea590cc291496bf1d8ec86ce0d99b36dfc30fe333ae21ee93d4e3814bfa5f3d1",
"attributes": [
"src/server/diagnostics.mjs: text: auto",
"src/server/diagnostics.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "tests/companion.test.mjs",
"bytes": 30054,
"sha256": "1cf4202abef9171db76b09778fbcb00f6db47c61a3b5890f024a0dfe05210258",
"gitBytes": 30053,
"gitSha256": "39c1867c8092304a30e2e2d4536006a281082ed72d76759bd20eb541ac21d969",
"attributes": [
"tests/companion.test.mjs: text: auto",
"tests/companion.test.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
},
{
"path": "tests/skills.test.mjs",
"bytes": 17628,
"sha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6",
"gitBytes": 17438,
"gitSha256": "977e987ccdeab5bf07fd3dd1788d8ba866a3dc3715c9dd947982a9abfbab7e06",
"attributes": [
"tests/skills.test.mjs: text: auto",
"tests/skills.test.mjs: eol: lf"
],
"scope": "Only repository-declared CRLF/LF normalization; full normalized buffer matches committed blob."
}
],
"generated": [
{
"path": "examples/delivery-report/dist/cli.mjs",
"bytes": 818,
"sha256": "b8223dd1c0a98b3b7a0cd716db0ae053a2ca17fbd8272b005adcedd3ce5f7a69",
"source": "examples/delivery-report/src/cli.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/normalize.mjs",
"bytes": 1254,
"sha256": "57eb47b09913b131982a14c276ba5292aba4c94e0f475c97955221f6a7b7cdcd",
"source": "examples/delivery-report/src/normalize.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/package.json",
"bytes": 18,
"sha256": "1239d4d885dcad42201a27ed9324f8f0f760b78700d8db9ced39a511cffe7eae",
"source": null,
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/render.mjs",
"bytes": 375,
"sha256": "d449524d731a55ef51d0143f38ee8b73db56363c78babc385fa58df7f2a542f0",
"source": "examples/delivery-report/src/render.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
},
{
"path": "examples/delivery-report/dist/summary.mjs",
"bytes": 427,
"sha256": "bf7ada9e5dbca167df2b9a5306c1d9399b4a658fb0777c73812856687ad0c5ef",
"source": "examples/delivery-report/src/summary.mjs",
"generator": "examples/delivery-report/scripts/build.mjs",
"generatorSha256": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302"
}
],
"scope": "Every frozen source/QA/build input tied to the committed source or exact generated example derivation; unchanged build bytes independently recorded."
}

Some files were not shown because too many files have changed in this diff Show More