From 057d91f14a1ed84f4967458f0e91c2430917f775 Mon Sep 17 00:00:00 2001 From: Agent Workbench Dev Date: Fri, 30 Oct 2026 23:38:53 +0800 Subject: [PATCH] docs: audit milestones, record confirmed fixes and gate the next development plan --- CHANGELOG.md | 8 + docs/CAPABILITIES.md | 50 +- docs/MILESTONE-AUDIT.md | 78 + docs/NEXT-STEPS.md | 51 + docs/PRODUCT-PLAN.md | 4 +- docs/QA-1.12.1.md | 36 + docs/RESEARCH-ROADMAP.md | 2 +- docs/VALIDATION.md | 12 + docs/milestone-audit-all-ui-validation.json | 169 ++ docs/milestone-audit-basic-ui-validation.json | 27 + docs/milestone-audit-batch-ui-validation.json | 29 + ...milestone-audit-browser-ui-validation.json | 175 ++ ...stone-audit-change-sets-ui-validation.json | 29 + docs/milestone-audit-code-baseline.json | 1130 +++++++++ ...milestone-audit-context-ui-validation.json | 34 + ...ilestone-audit-delivery-ui-validation.json | 31 + docs/milestone-audit-dependency-summary.json | 26 + ...stone-audit-diagnostics-ui-validation.json | 20 + ...milestone-audit-engines-ui-validation.json | 232 ++ ...stone-audit-environment-initial-repro.json | 28 + ...lestone-audit-execution-ui-validation.json | 19 + ...estone-audit-first-candidate-baseline.json | 264 ++ ...ne-audit-first-source-package-failure.json | 1140 +++++++++ ...stone-audit-first-source-package-tests.tap | 2242 +++++++++++++++++ docs/milestone-audit-index-ui-validation.json | 19 + ...tone-audit-mcp-recovery-ui-validation.json | 16 + docs/milestone-audit-mcp-ui-validation.json | 24 + ...tone-audit-model-center-ui-validation.json | 22 + ...estone-audit-model-save-initial-repro.json | 17 + docs/milestone-audit-npm-audit.json | 22 + docs/milestone-audit-path-initial-repro.json | 34 + ...ne-audit-project-memory-ui-validation.json | 24 + .../milestone-audit-python-ui-validation.json | 35 + ...stone-audit-react-delivery-validation.json | 76 + ...ilestone-audit-research-ui-validation.json | 138 + ...one-audit-security-ui-initial-failure.json | 12 + ...ilestone-audit-security-ui-validation.json | 83 + docs/milestone-audit-security-ui-verifier.mjs | 119 + docs/milestone-audit-service-preflight.json | 21 + .../milestone-audit-skills-ui-validation.json | 22 + ...stone-audit-targeted-tests-validation.json | 35 + docs/milestone-audit-targeted-tests.tap | 490 ++++ ...-audit-task-checkpoints-ui-validation.json | 20 + docs/milestone-audit-task-ui-validation.json | 31 + ...estone-audit-workspaces-ui-validation.json | 28 + findings.md | 53 + progress.md | 20 + task_plan.md | 12 + 48 files changed, 7181 insertions(+), 28 deletions(-) create mode 100644 docs/MILESTONE-AUDIT.md create mode 100644 docs/NEXT-STEPS.md create mode 100644 docs/QA-1.12.1.md create mode 100644 docs/milestone-audit-all-ui-validation.json create mode 100644 docs/milestone-audit-basic-ui-validation.json create mode 100644 docs/milestone-audit-batch-ui-validation.json create mode 100644 docs/milestone-audit-browser-ui-validation.json create mode 100644 docs/milestone-audit-change-sets-ui-validation.json create mode 100644 docs/milestone-audit-code-baseline.json create mode 100644 docs/milestone-audit-context-ui-validation.json create mode 100644 docs/milestone-audit-delivery-ui-validation.json create mode 100644 docs/milestone-audit-dependency-summary.json create mode 100644 docs/milestone-audit-diagnostics-ui-validation.json create mode 100644 docs/milestone-audit-engines-ui-validation.json create mode 100644 docs/milestone-audit-environment-initial-repro.json create mode 100644 docs/milestone-audit-execution-ui-validation.json create mode 100644 docs/milestone-audit-first-candidate-baseline.json create mode 100644 docs/milestone-audit-first-source-package-failure.json create mode 100644 docs/milestone-audit-first-source-package-tests.tap create mode 100644 docs/milestone-audit-index-ui-validation.json create mode 100644 docs/milestone-audit-mcp-recovery-ui-validation.json create mode 100644 docs/milestone-audit-mcp-ui-validation.json create mode 100644 docs/milestone-audit-model-center-ui-validation.json create mode 100644 docs/milestone-audit-model-save-initial-repro.json create mode 100644 docs/milestone-audit-npm-audit.json create mode 100644 docs/milestone-audit-path-initial-repro.json create mode 100644 docs/milestone-audit-project-memory-ui-validation.json create mode 100644 docs/milestone-audit-python-ui-validation.json create mode 100644 docs/milestone-audit-react-delivery-validation.json create mode 100644 docs/milestone-audit-research-ui-validation.json create mode 100644 docs/milestone-audit-security-ui-initial-failure.json create mode 100644 docs/milestone-audit-security-ui-validation.json create mode 100644 docs/milestone-audit-security-ui-verifier.mjs create mode 100644 docs/milestone-audit-service-preflight.json create mode 100644 docs/milestone-audit-skills-ui-validation.json create mode 100644 docs/milestone-audit-targeted-tests-validation.json create mode 100644 docs/milestone-audit-targeted-tests.tap create mode 100644 docs/milestone-audit-task-checkpoints-ui-validation.json create mode 100644 docs/milestone-audit-task-ui-validation.json create mode 100644 docs/milestone-audit-workspaces-ui-validation.json diff --git a/CHANGELOG.md b/CHANGELOG.md index 6ac643d1..0147fe5d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,13 @@ # Agent Workbench 更新记录 +## 1.12.1 · 2026-10-30 + +- 项目文件保护同时核对实际链接目标及父目录,拒绝指向Git/凭据的内部别名和Windows尾点/空格路径;多硬链接文件在读取、提案与自动规则前拒绝,普通项目文档链接与独立副本仍可使用。 +- 模型选择与配置同事务保存;磁盘失败恢复已提交状态,整批导入不留下部分连接,失败预览可继续核对。 +- 热升级保留原模型中心/导入器/凭据对象并更新方法;在途模型探针、排队与租约阻止冲突的配置变更或升级。 +- 本地页面禁止嵌入,脚本和API限定同源;终端及Node/Python检查只接收明确的系统/运行环境,避免继承宿主未知凭据。 +- 完成1.0–1.12里程碑与24项能力核对,记录[后续计划](docs/NEXT-STEPS.md);补丁独立验收、原失败与部署状态见[审查报告](docs/MILESTONE-AUDIT.md)及[1.12.1验收](docs/QA-1.12.1.md)。 + ## 1.12.0 · 2026-10-30 - 新增专业模型中心:多连接增改/启停、轮询/权重、Run内粘连、并发租约、限流/故障冷却和逐次请求账本;临时凭据重启后如实显示待配置。 diff --git a/docs/CAPABILITIES.md b/docs/CAPABILITIES.md index 51bc4cd6..c029218e 100644 --- a/docs/CAPABILITIES.md +++ b/docs/CAPABILITIES.md @@ -107,32 +107,32 @@ - C12/C13:成功准备Git预览后保存审查边界并停止模型;后续同消息工具不执行且协议完整。确认后内核完成原Task与报告,不继续请求模型,预览可修改/撤回。 - 192项回归和72组界面通过;合成模型子工作区真实3项失败→3项通过/build/Git报告通过。不可变包、原进程更新与真实配置模型结果见[QA-1.6](QA-1.6.md),完整三类工程及M2/M6能力继续验收。 -| ID / 能力 | 1.0.0基础与缺口 | 后续产品目标 | 参考问题 / 模块 / 阶段 | 必须看到的验收证据 | +| ID / 能力 | 当前已交付能力与缺口(至1.12.0) | 后续产品目标 | 参考问题 / 模块 / 阶段 | 必须看到的验收证据 | | --- | --- | --- | --- | --- | -| C01 需求与任务规划 | 有对话和有限步数工具循环,没有任务依赖图 | 固定目标、约束和完成标准;拆任务、判断依赖、接收追加要求与重规划 | CX-1、WB-1 / tasks / M1–M2 | 追加要求后仍保留原目标;任务完成由验收条件决定 | -| C02 执行状态与恢复 | 会话JSON保存,active/waiters在内存;重启不重放命令 | 独立Task/Run/Step身份、持久事件、检查点与未知结果核对 | CC-2、CU-1、DS-1 / storage、tasks / M1 | 在审批、调用、结果与落盘等切点中断;恢复不重复已完成副作用 | -| C03 工程识别与索引 | 提供有界文件清单/文本搜索,没有工程索引 | 识别语言、入口、规则、脚本、依赖和Git;增量索引;符号/引用与必要的语义检索 | CU-2、DS-3 / context / M2 | 对Node/React/Python样本定位实际修改入口;代码变动后索引更新 | -| C04 上下文与项目归属 | 有提取式消息投影、运行诊断和当前项目资料 | 为Run组合需求、规则、代码、错误与验证结果;引用来源;严格绑定项目 | CC-2、CU-1 / context、contracts / M1–M2 | 切换两个项目/任务后,错误与工具结果仍归属正确;大输出用工件引用 | -| C05 长期项目记忆 | 项目所属持久条目、来源/工程指纹、到期/归档、不完整扫描降级、有界且脱敏的请求接入与原快照已实现 | 自动提取/归并、长任务恢复包及真实模型收益继续验收 | CC-2、WB-1 / context、storage / M4 | 长任务压缩/重启后完成标准不丢;过期代码事实被更新或标记 | -| C06 工具、Skills与MCP | 自有工程工具/固定REA MCP;1.12源码支持项目Skills登记、启停/修订、按需读取与请求证据,见SKILLS.md | 动态MCP、schema与能力声明;插件安装/调用有来源和范围 | CC-1、CU-1、WB-2 / tools / M3 | 未知工具、错误参数、工具失联有原调用身份;新工具可按契约接入 | -| C07 执行控制 | 文件范围/基线检查、逐次命令确认与进程停止 | 操作范围、授权记录、预算、进程所有权、并发准入和取消传播;沿用用户已授权的范围 | CC-1、CU-1、DS-1 / tools、tasks / M1–M4 | 过期授权不能用于新Run;停止只处理所属任务;修改后的输入重新校验 | -| C08 精确编辑与多文件变更 | 完整替换单文件提案,有备份与冲突拒绝 | patch、创建/改名/删除、多文件ChangeSet、基线校验、隔离应用与可恢复合并 | CU-2 / workspaces / M2 | 跨4文件修改保留无关内容;外部改动引起冲突;部分失败有明确状态 | -| C09 用户工程Git | 本产品源码已建Git;界面内用户工程Git未实现 | 仓库/dirty状态、基线、任务分支/worktree、diff、审查后提交与合并 | CX-1、CU-3、DS-3 / workspaces / M2 | 保留用户已有修改;每个交付可定位commit;冲突合并可审查 | -| C10 长命令与开发服务 | 命令最长60秒,stdout/stderr分别截取32k字符 | 持久job、完整日志工件、心跳/退出码/超时、后台开发服务及所属进程树 | DS-3、CU-3 / tools、artifacts / M2 | 超过60秒的检查可观察和停止;失联结果标未知;重启不擅自再运行 | -| C11 真实检查与TestRunner | 可执行命令,没有结构化检查计划与报告 | 识别真实项目检查;计划绑定planId,执行返回jobId;保存退出码、测试数和报告 | DS-3 / tools / M2 | 构建失败、零测试、拒绝/取消均不算通过;结果绑定相同工作区与ChangeSet | -| C12 修复与代码审查 | 模型可根据普通工具输出继续,没有独立修复/审查闭环 | 从真实失败定位并有限轮修复;核对需求、diff、回归与风险;保留失败历史 | CX-1、DS-3 / tasks、workspaces / M2–M4 | 能复现的失败先出现再修复;实际重跑通过;审查不能用“模型说成功”代替 | -| C13 可交付成果 | 有提案/会话导出,没有工程交付清单 | 需求与结果对应、diff/commit、测试报告、运行方法、限制与工件引用 | WB-1 / artifacts / M2–M6 | 用户按交付说明能启动并验证;报告与实际文件、检查及commit一致 | -| C14 模型协议与路由 | 一个全局兼容连接;stream:false;基本usage记录 | ModelProvider能力探测、流式文本/工具参数、模型配置快照、按任务角色路由与可解释回退 | CX-2、DS-1 / models / M1、M3 | 支持/不支持的工具/流式能力可见;Run绑定实际模型;故障不串结果或重放工具 | -| C15 预算与用量 | 可设上下文/输出/步数,没有任务总成本控制 | 时间、token、费用、步骤、重试与worker总预算;无进展检测;可配置价格与未知usage标记 | CC-2、DS-2 / models、tasks / M1–M4 | 子任务/重试纳入总预算;耗尽时保存检查点;缺失usage不伪造准确费用 | -| C16 多代理协作 | 单会话串行执行,没有worker调度 | 独立问题分工、上下文/预算隔离、独立worktree、结果与证据汇总、冲突合并 | CC-1、CU-3、DS-2、WB-1 / tasks、workspaces / M4 | 两个独立任务并行完成可合并;重叠编辑被发现;父任务停止可传播 | -| C17 REA能力研究 | 产品内展示既有研究报告,没有REA执行入口 | 目标清单、版本/hash、inventory/analyze/trace、分析job、Evidence查看与研究结论登记 | 全部目标 / tools、artifacts / M3 | 从能力结论能追到确切工件与Evidence;静态/运行证据和未知范围分别显示 | -| C18 Purge增强实验 | 外部目录有1.1.78/1.1.81,未集成或验证收益 | 独立实验profile、兼容版本、策略分类、开关/回退和同题对照;有效机制按接口采纳 | PG-1 / engines、models、tasks / M3 | 同模型/任务/预算重复比较成功率、成本与错误修改;插件失效可恢复基线 | -| C19 外部代理引擎 | 尚无Codex/DeepSeek运行时适配 | EngineAdapter管理握手、会话/进程、事件、停止/恢复和真实能力限制 | CX-2、DS-1 / engines / M3 | 引擎事件有Task/Run映射;协议缺失能力明确;root idle不直接判工程完成 | -| C20 浏览器与界面验证 | 开发者用Playwright验证产品,代理尚无浏览器工具 | 可选浏览器工具、页面状态/截图、请求/控制台结果、交互验收与开发预览 | CU-2、WB-1 / tools、artifacts / M3–M6 | React真实交互/失败场景可复现;结果含页面与任务身份,不只保存截图 | -| C21 桌面产品 | 已有Windows浏览器便携包,没有原生桌面壳 | 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 | 已验证390px响应式界面;仅绑定电脑127.0.0.1 | 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 | Key仅内存、JSON与备份;便携/源码包已验证 | 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 | 基础行为/UI及少量真实模型场景 | 封存真实工程任务、独立验收、重复运行和错误分类;追踪人工介入/成本/恢复 | 全部目标 / evaluation、artifacts / M1–M6 | 发布能力可链接实际任务记录;报告含失败样本与环境,不能只展示成功演示 | +| C01 需求与任务规划 | Task固定目标/追加要求、Run身份和不可变依赖步骤/真实证明已交付;跨worker任务调度待做 | 固定目标、约束和完成标准;拆任务、判断依赖、接收追加要求与重规划 | CX-1、WB-1 / tasks / M1–M2 | 追加要求后仍保留原目标;任务完成由验收条件决定 | +| C02 执行状态与恢复 | SQLite事件/状态、原工件、Task检查点、unknown核对及显式同Task续接已交付;不重放已完成副作用 | 独立Task/Run/Step身份、持久事件、检查点与未知结果核对 | CC-2、CU-1、DS-1 / storage、tasks / M1 | 在审批、调用、结果与落盘等切点中断;恢复不重复已完成副作用 | +| C03 工程识别与索引 | 项目识别、JS/TS/React声明/导入索引与增量核对、Python候选已交付;完整语义/运行时依赖待做 | 识别语言、入口、规则、脚本、依赖和Git;增量索引;符号/引用与必要的语义检索 | CU-2、DS-3 / context / M2 | 对Node/React/Python样本定位实际修改入口;代码变动后索引更新 | +| C04 上下文与项目归属 | 有界原请求、工作依据/分页、实际工具反馈、来源记忆及Task/Run归属已交付 | 为Run组合需求、规则、代码、错误与验证结果;引用来源;严格绑定项目 | CC-2、CU-1 / context、contracts / M1–M2 | 切换两个项目/任务后,错误与工具结果仍归属正确;大输出用工件引用 | +| C05 长期项目记忆 | 项目持久记忆、来源/工程指纹、到期/归档、不完整扫描降级、脱敏请求快照与Task恢复包已交付 | 自动提取/归并、更长任务恢复与真实模型收益继续验收 | CC-2、WB-1 / context、storage / M4 | 长任务压缩/重启后完成标准不丢;过期代码事实被更新或标记 | +| C06 工具、Skills与MCP | 自有工程工具、固定REA、版本化本地Skills和项目所属受控stdio MCP已交付;远程MCP/任意插件安装待做 | 远程MCP、更多实际协议及插件安装/调用有来源和范围 | CC-1、CU-1、WB-2 / tools / M3 | 未知工具、错误参数、工具失联有原调用身份;新工具可按契约接入 | +| C07 执行控制 | 项目路径/原字节、逐次命令审批、预算、所属活动准入、停止和unknown门控已交付;OS沙箱与远程设备权限待做 | 操作范围、授权记录、预算、进程所有权、并发准入和取消传播;沿用用户已授权的范围 | CC-1、CU-1、DS-1 / tools、tasks / M1–M4 | 过期授权不能用于新Run;停止只处理所属任务;修改后的输入重新校验 | +| C08 精确编辑与多文件变更 | 精确文本patch、创建/修改、封存多文件变更集、逐文件恢复已交付;改名/删除及自动合并待做,跨文件非原子 | patch、创建/改名/删除、多文件ChangeSet、基线校验、隔离应用与可恢复合并 | CU-2 / workspaces / M2 | 跨4文件修改保留无关内容;外部改动引起冲突;部分失败有明确状态 | +| C09 用户工程Git | 用户工程Git预览/所属提交、私有索引、独立worktree及原修改保护已交付;自动合并/归档待做 | 仓库/dirty状态、基线、任务分支/worktree、diff、审查后提交与合并 | CX-1、CU-3、DS-3 / workspaces / M2 | 保留用户已有修改;每个交付可定位commit;冲突合并可审查 | +| C10 长命令与开发服务 | 终端60秒/有界输出;工程检查、REA/MCP/引擎/浏览器有所属job、原工件/退出与停止;后台开发服务待做 | 持久job、完整日志工件、心跳/退出码/超时、后台开发服务及所属进程树 | DS-3、CU-3 / tools、artifacts / M2 | 超过60秒的检查可观察和停止;失联结果标未知;重启不擅自再运行 | +| C11 真实检查与TestRunner | 实际Node/React/Python检查计划、测试数量/退出码/原日志、源码/范围绑定已交付;零测试/跳过不能算通过 | 识别真实项目检查;计划绑定planId,执行返回jobId;保存退出码、测试数和报告 | DS-3 / tools / M2 | 构建失败、零测试、拒绝/取消均不算通过;结果绑定相同工作区与ChangeSet | +| C12 修复与代码审查 | 实际失败反馈、有界修改/修复、无进展暂停、审查/Git门槛已交付;独立多模型复核与稳定自主完成率待验 | 从真实失败定位并有限轮修复;核对需求、diff、回归与风险;保留失败历史 | CX-1、DS-3 / tasks、workspaces / M2–M4 | 能复现的失败先出现再修复;实际重跑通过;审查不能用“模型说成功”代替 | +| C13 可交付成果 | Task所属diff/Git/检查/浏览器原工件与交付报告已交付;完整真实任务基准与专业交付指标待做 | 需求与结果对应、diff/commit、测试报告、运行方法、限制与工件引用 | WB-1 / artifacts / M2–M6 | 用户按交付说明能启动并验证;报告与实际文件、检查及commit一致 | +| C14 模型协议与路由 | 多连接兼容Chat协议池、Run固定路由、轮询/权重/租约/冷却、已验证格式导入已交付;stream:false,多协议/多模态待做 | ModelProvider能力探测、流式文本/工具参数、模型配置快照、按任务角色路由与可解释回退 | CX-2、DS-1 / models / M1、M3 | 支持/不支持的工具/流式能力可见;Run绑定实际模型;故障不串结果或重放工具 | +| C15 预算与用量 | 完整请求预检、Run/Task累计步数/token预算、重试/用量账本及unknown usage已交付;费用价格与worker总预算待做 | 时间、token、费用、步骤、重试与worker总预算;无进展检测;可配置价格与未知usage标记 | CC-2、DS-2 / models、tasks / M1–M4 | 子任务/重试纳入总预算;耗尽时保存检查点;缺失usage不伪造准确费用 | +| C16 多代理协作 | 单会话串行工具执行,已有独立worktree;没有worker调度、成果合并与父子停止传播 | 独立问题分工、上下文/预算隔离、独立worktree、结果与证据汇总、冲突合并 | CC-1、CU-3、DS-2、WB-1 / tasks、workspaces / M4 | 两个独立任务并行完成可合并;重叠编辑被发现;父任务停止可传播 | +| C17 REA能力研究 | 固定REA6.8.0的ASAR/PE三项静态操作、所属job/目标SHA256/原Evidence已交付;其余工具与运行trace待做 | 目标清单、版本/hash、inventory/analyze/trace、分析job、Evidence查看与研究结论登记 | 全部目标 / tools、artifacts / M3 | 从能力结论能追到确切工件与Evidence;静态/运行证据和未知范围分别显示 | +| C18 Purge增强实验 | DSH-purge来源/机制研究已登记,未集成工程执行或验证收益;兼容组合与同题对照待做 | 独立实验profile、兼容版本、策略分类、开关/回退和同题对照;有效机制按接口采纳 | PG-1 / engines、models、tasks / M3 | 同模型/任务/预算重复比较成功率、成本与错误修改;插件失效可恢复基线 | +| C19 外部代理引擎 | 固定DeepSeek0.2.1-rc.2的六方法连接/所属进程/原协议已交付;Codex适配及引擎prompt/工程写入待做 | EngineAdapter管理握手、会话/进程、事件、停止/恢复和真实能力限制 | CX-2、DS-1 / engines / M3 | 引擎事件有Task/Run映射;协议缺失能力明确;root idle不直接判工程完成 | +| C20 浏览器与界面验证 | 代理固定静态构建、真实Edge交互/DOM/PNG/原报告与Task绑定已交付;任意在线浏览与电脑操作待做 | 可选浏览器工具、页面状态/截图、请求/控制台结果、交互验收与开发预览 | CU-2、WB-1 / tools、artifacts / M3–M6 | React真实交互/失败场景可复现;结果含页面与任务身份,不只保存截图 | +| C21 桌面产品 | Windows浏览器便携/源码包及保留原进程升级已交付;Electron安装版、后台宿主/窗口拆分待做 | 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 | 390px响应式界面已验证;电脑仅绑定127.0.0.1,真实手机PWA配对/撤销待做 | 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 | Key仅内存、SQLite/旧JSON迁移、不可变包/保留Provider与历史升级已交付;本机加密凭据、完整回退和设备配置待做 | 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 | 行为/UI与Node/React/Python实际样本、失败/人工介入证据已保留;封存成套基准、重复评测与整体稳定完成率待做 | 封存真实工程任务、独立验收、重复运行和错误分类;追踪人工介入/成本/恢复 | 全部目标 / evaluation、artifacts / M1–M6 | 发布能力可链接实际任务记录;报告含失败样本与环境,不能只展示成功演示 | ### 1.6.1 M2实际工作依据切片 diff --git a/docs/MILESTONE-AUDIT.md b/docs/MILESTONE-AUDIT.md new file mode 100644 index 00000000..0b8c22fd --- /dev/null +++ b/docs/MILESTONE-AUDIT.md @@ -0,0 +1,78 @@ +# 里程碑回顾与修复审查 + +日期:2026-10-30。审查基线为1.12.0实现3f6797b和交付记录ca9042e;本地正式服务为已验收的不可变发行20261030124454517。用户要求本阶段先审查、修复及记录计划,随后再开发新能力。 + +本报告区分历史发行证据、当前源码检查、当前隔离复验及未完成项。各版本原报告和失败记录保持原字节,不把过去的局部验证推断成整体自主交付能力。 + +## 执行与产物 + +- 后续计划:逐项记录范围、前置条件、真实完成标准及未知能力。 +- 里程碑:核对计划、模块、原验收与实际部署,整理阶段遗留项。 +- 可靠性与安全:检查本地HTTP权限、项目文件/Git范围、任务/审批归属、持久恢复、模型池/凭据、Skills/MCP/REA/外部引擎和交付证据。 +- 修复:先以独立端口、临时项目和自有凭据夹具复现,再做相关验证;不读取真实Key、不发送真实模型请求,不普通重启正式服务。 +- 收尾:本地小步提交、必要的补丁发行、最终证据与未完成能力说明。 + +## 当前进度 + +已核对1.12.0交付:357/357独立源码、150组完整界面和部署后8个页面通过;原PID19084/Provider以及15项目、26会话、2505记录、4476事件在升级时保持。此记录是历史发行基线,本阶段新的检查另行记录。 + +后续顺序、前置条件与完成标准已保存于[NEXT-STEPS.md](NEXT-STEPS.md)。80项相关专项、额外实际配置HTTP故障检查、旧发行进程升级/Edge8组已通过。首个源码候选368/369,唯一失败来自Windows尾点提案提前拒绝后的旧测试假设;追加硬链接复现、补强及路径/提案/变更集29项复验通过。包含全部修复的新构建20类150组UI全部通过、0页面/请求异常;最终独立源码和正式补丁部署另行登记,首失败候选不得部署。 + +## 逐版本对照 + +下表数字来自各版本原报告,不是本轮重新运行所有旧版本。原真实模型失败保持失败;各版本的源码、便携、正式部署及原失败详见对应QA。 + +| 节点 | 原计划与已实现能力 | 原验收 | 原真实工程及遗留项 | +| --- | --- | --- | --- | +| [1.0](QA-1.0.md) | 基础对话、工具、代码提案/审批、诊断及旧会话 | 34项测试、19组UI | 是基础可运行版本,尚无完整工程交付与可靠Task内核 | +| [1.1](QA-1.1.md) | Task/Run/Tool、SQLite/工件、预算、实际检查及中断恢复 | 68项、26组UI | 内核与检查链路交付;真实工程完成率需另验 | +| [1.2](QA-1.2.md) | 当前Task的Git预览/确认、所属提交、交付报告与unknown核对 | 92项、35组UI | 真实Node样本四文件修改/检查/Git通过;三类工程完整基准未完成 | +| [1.3](QA-1.3.md) | 工程声明/导入索引、精确补丁、保留原格式与Git范围 | 112项、43组UI | 真实精确四文件样本通过;索引不代表完整运行时依赖,成本收益未对照 | +| [1.4](QA-1.4.md) | 封存多文件变更集、整批预检、逐文件账本与显式回退 | 141项、54组UI,13个实际退出切点 | 真实样本工程交付通过,模型最终因token预算暂停;跨文件写入并非原子事务 | +| [1.5](QA-1.5.md) | 完整请求预算、有界上下文、原工件与历史保留 | 158项、62组UI | 原真实模型27次响应后超时,无提案;不能记为自主交付 | +| [1.5.1](QA-1.5.1.md) | 按实际预算分页、有界最新结果、重复读取暂停 | 163项、63组UI | 真实代码/检查通过,Git预览后循环;人工核对收尾,不算全自主 | +| [1.6](QA-1.6.md) | 独立Git工作区、身份/创建unknown、保留已有修改及审查收尾 | 192项独立源码、72组UI | 工作区执行链路通过,原真实模型仍无提案;自动合并/归档未交付 | +| [1.6.1](QA-1.6.1.md) | 原结果可核对的Task工作依据与预算观察 | 200项独立源码、74组UI | 界面和观察通过,真实工作依据仍被挤出;下一补丁修复 | +| [1.6.2](QA-1.6.2.md) | 工作依据优先保留、旧发送视图兼容和原工件分页 | 205项独立源码、74组UI | 原依据保留已修;真实模型仍重复查询且无提案,原失败未改写 | +| [1.7](QA-1.7.md) | 最新工具反馈/无进展暂停、Python结构化检查、React工程验证 | 224项独立源码、87组UI | 受控React/Python执行样本通过;原真实模型no_progress失败保留 | +| [1.8](QA-1.8.md) | 固定REA 6.8.0 stdio与ASAR/PE三项静态操作、所属原Evidence | 244项独立源码、98组UI、真实REA三操作 | 真实Node四模块工程Task的14项检查/build/Git通过;REA其他工具与引擎执行未交付 | +| [1.9](QA-1.9.md) | 固定DeepSeek Harness 0.2.1-rc.2 SDK连接、所属进程/原协议/停止 | 261项独立源码、108组UI、六方法连接核验 | 真实React/Python样本通过;尚未向引擎发送prompt/开放工程写入,Purge未做收益对照 | +| [1.10/1.10.1](QA-1.10.md) | 封存静态构建与真实Edge交互/PNG;热升级旧工件对象API修复 | 274/276项独立源码、118组UI | 实模桌面8/8,390px选择器匹配三个按钮而失败;整体真实页面任务未完成 | +| [1.11](QA-1.11.md) | Task不可变依赖计划、所选范围真实证明、唯一DOM定位/字段读取 | 298项独立源码、126组UI | 源码/便携/正式部署通过;真实模型续接按用户选择暂缓 | +| [1.12](QA-1.12.md) | 模型中心/池、已验证格式导入与可关闭同步、巡检、来源记忆、检查点、Skills、stdio MCP | 357项独立源码、150组UI、部署后8个页面 | 正式部署通过;实模工程暂缓;WorkBuddy未知格式、加密凭据、跨协议/流式/多模态待做 | + +## 总计划实现情况 + +| 计划 | 本轮核对后的状态 | 下一实际门槛 | +| --- | --- | --- | +| M0工程基线 | 已建立本地Git、原发行、来源/能力矩阵和研究规范 | 后续独立实现通过相关检查后及时本地提交 | +| M1可靠内核 | Task/Run、SQLite、审批/预算、原工件与恢复已交付;本轮补持久化/升级/凭据传递边界 | 保持未知副作用核对、失败回滚和原进程升级回归 | +| M2真实工程闭环 | 代码、检查、浏览器、Git和报告已接通;部分真实样本成功、部分失败 | 固定Node/React/Python各两个任务,独立验收并统计人工介入/完成率,不能用测试数量代替 | +| M3研究与引擎 | REA三项与DeepSeek连接已交付;受控引擎工程执行和Purge收益未完成 | 固定实际写入/取消/审批协议,隔离工程与同题对照 | +| M4长任务/多worker | 记忆、上下文工件、检查点和独立worktree已交付;worker调度/成果合并未完成 | 两个受限worker及真实冲突/停止/恢复验收 | +| M5桌面/手机 | Web界面及390px布局已验证;安装版与真实设备配对未实现 | 单实例后台宿主、保留数据更新、可撤销配对和断线补发 | +| M6专业交付 | 不可变包、输入/构建/日志散列、独立源码/便携验证已有 | 加密凭据/隔离、真实任务质量指标、候选回滚及隔离自我迭代 | + +## 本轮确定问题与修复 + +| 编号 | 问题与复现 | 修复范围 | 当前验收 | +| --- | --- | --- | --- | +| A01 | 项目内junction指向.git或credentials可绕过词法保护,创建预检也允许;受保护文件硬链接为AGENTS.md可被普通读取及自动规则加载 | safePath同时核对真实目标/父目录、凭据目录和Windows尾点/空格别名;常规文件要求单一路径,清单跳过多硬链接;普通项目内链接及独立副本可用 | 原junction/硬链接复现均保留;新增读取/提案/清单/自动规则与旧提案兼容检查,相关29/29通过,最终回归另验 | +| A02 | SQLite保存失败后模型注册内存状态与已提交数据库不一致;选择/运行模式及批量导入可能部分生效 | 保存失败恢复已提交注册;模式与选择同事务;整批连接/来源/凭据引用回滚;成功提交后才替换原Key | 原复现milestone-model-save-initial-repro.json;10项模型中心通过,最终回归另验 | +| A03 | 热升级保留已初始化ModelHub/Importer对象却不更新方法;模型探针未参与活动门控 | 保留对象/凭据/预览并更新原型,失败恢复旧原型;在途请求/队列/租约阻止配置变更与升级 | 原对象/失败回滚和探针专项通过;实际旧1.12初始化对象升级及原凭据/预览保持通过 | +| A04 | 本地审批页面可被外部页面嵌入,缺少同源脚本/连接策略 | 禁止frame嵌入、仅同源脚本/API、禁止object/base、no-referrer;已有动态布局保留内联style | HTTP与实际Edge旧/新iframe对照、外部脚本拒绝、1280/390正常页面及PNG Blob通过;完整UI150组通过 | +| A05 | PowerShell、npm及Python检查继承未知宿主凭据环境变量 | 统一仅传系统/运行路径和内核显式字段,保留Python检查隔离设置 | 三条实际执行链路原标记复现及新增shell/npm/Python实际检查通过,Node/Python相关回归通过 | + +初始复现与失败记录都在独立`.qa/milestone-*`目录;不涉及用户项目、真实Key或模型请求。目录和报告将在最终身份清单中逐项绑定。 + +## 审查覆盖与结论边界 + +- HTTP:实际本地Host/Origin/token、JSON限制、事件游标/慢客户端、只读与副作用路由;新增防嵌入和同源策略。当前本机token不等同于OS沙箱或远程设备权限。 +- 文件/Git:词法与实际路径、受保护目录、提案原字节、ChangeSet预检/恢复、私有Git索引/所属提交、工作区HEAD/身份与unknown。保留已有用户修改;外部并发替换链接的完整OS隔离仍属后续能力。 +- 执行:Task/Run/审批归属、稳定工具身份、请求预算、检查计划/测试数量与原日志、进程取消和未知结果;补齐宿主环境隔离。当前审批命令仍使用宿主账户权限。 +- 计划/上下文/恢复:有界原请求、最新工具反馈、来源记忆、Skills目录/原修订、检查点及证明原工件;来源/要求/源码改变导致失效,不重写历史发送证据。 +- 模型:配置事务、选择/Run固定快照、队列/租约/冷却、401/429、停止、原请求账本与导入预览指纹。Key目前仅在内存,实际多协议/真实模型工程另验。 +- REA/MCP/引擎/浏览器:固定身份与协议、所属进程、受控范围、原报告/PNG/退出、unknown核对和不重放。连接核验、静态构建和夹具不宣称为任意引擎/桌面操作。 +- 依赖:2026-10-30 npm audit的153项依赖元数据中0已知漏洞;原JSON与SHA256单独保存。此结果不证明不存在未知漏洞;REA等随包依赖另按锁/清单和实际运行验证。 + +当前确定修复、最终全量回归、实际UI与补丁部署需全部完成后才能关闭本轮审查。后续新能力按NEXT-STEPS执行,真实模型验收继续暂缓。 diff --git a/docs/NEXT-STEPS.md b/docs/NEXT-STEPS.md new file mode 100644 index 00000000..852c4ee5 --- /dev/null +++ b/docs/NEXT-STEPS.md @@ -0,0 +1,51 @@ +# 后续执行计划 + +更新:2026-10-30。当前交付基线为1.12.0;本轮先完成[里程碑审查](MILESTONE-AUDIT.md)及补丁验收,再进入下一阶段。历史研究、局部测试与连接核验不能代替真实工程交付。其他项目不进入本计划。 + +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。 + +## 执行顺序与完成门槛 + +| 顺序 | 开发范围 | 前置条件 | 完成标准 | +| --- | --- | --- | --- | +| 0:审查闭环 | 对照1.0–1.12计划、模块、原始报告;修复确认问题;补丁发行和回滚验证 | 保留旧发行、历史失败和正式服务连接 | 当前源码、实际进程、桌面/390px、独立源码及便携包通过;正式升级保留原Provider及全部历史;未完成能力明确登记 | +| 1:隔离执行与多worker | 父任务拆分、所属worker、独立worktree、预算分配、停止传播、结果归集及冲突审查 | 当前Task/Run、工作区、计划和未知结果恢复契约 | 两个worker各自在隔离工程完成真实修改/检查;重叠修改被识别;父任务停止后无所属进程继续写入;超时/崩溃不重放工具;只合并已审查成果 | +| 2:引擎执行与增强对照 | 固定版本的Codex/DeepSeek适配、受控工具桥;Claude Code/Cursor/WorkBuddy机制研究;DSH-purge实验 | 外部SDK的实际审批、取消、写入与事件契约;阶段1隔离工作区 | 引擎能完成一个指定工程任务,原输入、工具与结果可追溯;Purge按同模型、同题、同预算进行有/无插件对照,记录失败和人工介入;仅采纳有证据的机制 | +| 3:Windows桌面 | 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 | 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:模型与多模态 | 更多实际协议、流式取消、按能力选路、可恢复池策略、视觉/语音/附件、项目缓存 | 每种协议的工具调用/用量/取消实测;凭据和附件隔离 | 图像、语音、文本各有真实样本;流式断开保留unknown而不重复副作用;不兼容成员不被调度;缓存绑定项目/权限/源码版本并可清除;429/401/超时/冷却有独立证据 | +| 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 | + +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。 + +## 下一开发切片:隔离worker + +先实现两个受限worker的完整流程,再扩展并发规模。父Task固定目标、验收条件和总预算;子任务保存范围、工作区、所属进程与原证据。调度器负责分配/释放预算和租约,不让模型自行绕过权限。 + +1. 建立父子任务与worker状态契约:queued、running、stopping、completed、failed、unknown;完成状态需关联真实工件与检查结果。 +2. 在独立worktree创建工程快照,保留用户原暂存/工作区修改;来源身份改变、创建结果未知和未审查冲突阻止下一次写入。 +3. 实现预算、并发与停止传播;父任务取消后结束所属进程树,等待退出并保存原结果,失联状态显式核对。 +4. 归集diff/测试/报告,校验来源与基线;分离修改可审查合并,重叠修改显示具体文件与冲突,不覆盖父工程。 +5. 使用Node、React、Python各一个固定工程任务,验证正常、测试失败后修复、冲突、停止、宿主退出和恢复。真实模型语义验收待用户在工作台配置后单独执行。 + +## 跨阶段必须保持的能力 + +| 能力 | 当前基础与后续要求 | +| --- | --- | +| 凭据 | 当前Key仅在内存;后续采用Windows本机加密或系统凭据库,导入由明确格式和用户授权驱动,不读取未知登录态;重启/密钥失效可见 | +| 权限与执行范围 | 当前本地token、同源请求、审批和项目路径保护;增加任务/设备/工具作用域及OS隔离;模型、插件与外部引擎均受执行内核控制 | +| 恢复与可靠性 | 保留Task/Run、工件、计划、检查点和unknown;增加故障注入、迁移/回滚演练、所属进程核对及资源上限,不自动补造结果 | +| Skills/MCP/插件 | 保留来源、版本、启停、范围与原调用证据;实际协议逐项接入,远程服务/安装和未知副作用独立核验 | +| 项目记忆/上下文/缓存 | 当前来源复核记忆和有界请求工件;后续缓存按源码/模型/权限版本失效,长任务依据与原结果始终可追溯 | +| 浏览器/电脑操作 | 当前固定静态构建与真实Edge验收;后续真实浏览器/桌面操作限定目标、登录态和权限,并验证停止与敏感操作审批 | +| 号池 | 当前兼容Chat协议、轮询/权重/租约/冷却、已验证格式导入和可关闭同步;后续按能力、上下文、成本选路,跨协议实际验证,不承诺上游永不中断 | +| 巡检 | 当前只读运行巡检;增加任务账本、工件、来源、池健康、空间/进程/迁移检查。修复与巡检分别授权,巡检不偷偷执行模型或项目命令 | +| 交付质量 | 固定任务基线、需求、原测试/构建/交互、实际diff/Git和报告;用完成率、人工介入、失败类型、耗时及已报告用量评价改善 | + +## 研究依据与未知项 + +REA用于发行工件或运行证据,完整公开源码直接分析。研究以实际版本、来源、问题、证据和拟落地模块登记,见[研究路线](RESEARCH-ROADMAP.md)。参考产品的名称不证明对应能力已经接入。 + +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。当前DeepSeek六个SDK方法只完成连接核验,Purge的工程收益尚未获得对照证据。 + +尚未交付:OS沙箱、任意外部引擎工程写入、未知WorkBuddy格式自动导入、本机加密持久凭据、多协议流式/多模态、Windows安装版、真实手机配对,以及稳定的全自主工程成功率。按上表逐项实现和验收,不用界面入口或夹具结果替代完成。 diff --git a/docs/PRODUCT-PLAN.md b/docs/PRODUCT-PLAN.md index 6850f791..e75ba111 100644 --- a/docs/PRODUCT-PLAN.md +++ b/docs/PRODUCT-PLAN.md @@ -1,6 +1,6 @@ # Agent Workbench 后续产品与执行开发方案 -日期:2026-10-30。本文保留完整产品规划;1.8.0已交付内置REA与真实Node工程修复,1.9.0已完成DeepSeek Harness连接核验、独立发行和真实React/Python工程样本。1.10.1完成276项独立源码、不可变发行和保留原Provider升级,实模页面仍保留手机定位失败。1.11.0已完成持久依赖计划、原证据核验、实际DOM唯一定位与页面读取进展,最终独立源码298/298、126组界面、源码/便携与正式本地升级通过;真实模型续接按用户选择暂缓。下一阶段的专业UI、连接注册、模型池、导入和巡检详见[1.12执行方案](PLAN-1.12.md)。实际实现、验收与部署分别见[能力矩阵](CAPABILITIES.md)及[验证记录](VALIDATION.md),完整阶段目标继续实施。 +日期:2026-10-30。本文保留完整产品规划;1.8.0已交付内置REA与真实Node工程修复,1.9.0已完成DeepSeek Harness连接核验、独立发行和真实React/Python工程样本。1.10.1完成276项独立源码、不可变发行和保留原Provider升级,实模页面仍保留手机定位失败。1.11.0已交付持久依赖计划、原证据核验与实际DOM唯一定位;1.12.0已正式交付模型中心/池、已验证格式导入、巡检、项目记忆、检查点、Skills和受控stdio MCP,357/357独立源码及150组界面通过。真实模型续接按用户选择暂缓。当前先做[里程碑审查](MILESTONE-AUDIT.md),再按[后续执行计划](NEXT-STEPS.md)推进隔离worker、受控引擎、桌面/手机及其余能力。实际实现、验收与部署分别见[能力矩阵](CAPABILITIES.md)及[验证记录](VALIDATION.md)。 ## 1. 产品目标 @@ -29,7 +29,7 @@ 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。 -正式基础增加了1.11的Task所属依赖计划及原结果核验。1.12源码已增加多连接与兼容Chat协议模型池、本地格式导入/巡检,以及带来源核对和有界请求快照的[项目记忆](PROJECT-MEMORY.md),尚未作为新不可变发行部署。多worker、动态REA/MCP/外部引擎注册、桌面壳和手机配对继续开发;已有不同阶段的Node/React/Python工程样本,整体自主交付能力按真实任务评估。1.7.0已接入Python专用检查和混合范围选择,并完成受控React/TypeScript实际类型/构建/交互/Git样本;来源和验收分别见[Python契约](PYTHON-CHECKS.md)、[React基准](../benchmarks/react-delivery-v1/README.md)及[QA-1.7](QA-1.7.md)。1.6.0已有独立Git工作区创建/身份/恢复,自动合并和归档继续开发。批次支持文本创建/修改,不提供跨文件原子事务。正式1.11仍为原单连接,协议仍使用stream:false;跨协议与真实模型池工程验收另行记录。 +正式1.12基础包括Task所属依赖计划与原结果核验、多连接兼容Chat协议模型池、本地格式导入/巡检、带来源核对和有界请求快照的[项目记忆](PROJECT-MEMORY.md)、Task检查点、本地Skills和受控stdio MCP。多worker、动态REA/外部引擎注册、桌面壳和手机配对仍待开发;已有不同阶段的Node/React/Python工程样本,整体自主交付能力按真实任务评估。1.7.0已接入Python专用检查和混合范围选择,并完成受控React/TypeScript实际类型/构建/交互/Git样本;来源和验收分别见[Python契约](PYTHON-CHECKS.md)、[React基准](../benchmarks/react-delivery-v1/README.md)及[QA-1.7](QA-1.7.md)。1.6.0已有独立Git工作区创建/身份/恢复,自动合并和归档继续开发。批次支持文本创建/修改,不提供跨文件原子事务。当前模型协议仍使用stream:false;跨协议与真实模型池工程验收另行记录。 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;1.6.0补齐独立工作区,自动合并、归档及完整工程验收继续实施。 diff --git a/docs/QA-1.12.1.md b/docs/QA-1.12.1.md new file mode 100644 index 00000000..74c92eef --- /dev/null +++ b/docs/QA-1.12.1.md @@ -0,0 +1,36 @@ +# 1.12.1 里程碑审查补丁验收 + +日期:2026-10-30。基线1.12.0/3f6797b/ca9042e保持原报告。修复提交:c1e9575(实际路径保护)、f4bd0ad(配置/升级、环境与HTTP边界、独立发行入口)、7b1f529(硬链接保护及旧Windows提案兼容验证)。 + +本补丁完成[逐里程碑审查](MILESTONE-AUDIT.md)和[后续执行计划](NEXT-STEPS.md),修复五类确认的安全与可靠性问题。当前完成专项与完整UI,独立源码、最终不可变包和正式升级仍按下述流程验收;完成前不登记为正式交付。 + +| 验证 | 当前结果 | 原证据 | +| --- | --- | --- | +| 路径/Git及凭据内部junction保护 | 实际旧逻辑复现,修复后相关检查通过 | [原复现](milestone-audit-path-initial-repro.json) | +| 硬链接及路径/变更集追加复核 | 自有受保护规则硬链接实际复现;修复后读取/提案/清单/自动规则及旧提案兼容29/29、0失败/取消/跳过 | [硬链接原复现](milestone-audit-hardlink-initial-repro.json)、[追加复验](milestone-audit-path-followup-validation.json)、[原TAP](milestone-audit-path-followup-tests.tap) | +| 模型SQLite提交失败、选择/模式及批量导入回滚 | 实际旧逻辑复现、10项模型中心和额外HTTP故障/非法Key/重试通过 | [原复现](milestone-audit-model-save-initial-repro.json) | +| 终端/npm/Python环境边界 | 三条旧执行链路都继承3个自有标记;新实际执行专项通过 | [原复现](milestone-audit-environment-initial-repro.json) | +| 相关源码/API/实际退出与升级 | 80/80、0失败/取消/跳过 | [专项](milestone-audit-targeted-tests-validation.json)、[原TAP](milestone-audit-targeted-tests.tap) | +| 真实旧1.12进程→补丁、已初始化Hub/Importer、CSP与Edge | 8组通过;原PID/预览/两类夹具凭据保持;失败批量不部分导入;iframe/外部脚本拒绝;1280/390与PNG Blob可用 | [实际进程与Edge](milestone-audit-security-ui-validation.json)、[验收器](milestone-audit-security-ui-verifier.mjs) | +| 全部功能界面 | 包含硬链接追加修复的新构建20类150组全部通过、0页面/请求异常;原首轮UI另存,不覆盖失败候选依据 | [全部UI](milestone-audit-all-ui-validation.json)、[首轮基线](milestone-audit-first-candidate-baseline.json) | +| 首个独立源码候选20261030150404738 | 离线构建/6份构建匹配与REA/DeepSeek/Edge通过;368/369,旧测试假设提前拒绝时机导致唯一失败;此候选不部署 | [首轮失败](milestone-audit-first-source-package-failure.json)、[首轮原TAP](milestone-audit-first-source-package-tests.tap) | +| npm依赖 | 153项元数据、0已知漏洞;lock仅根版本变化,依赖内容与原审计严格相同 | [原审计](milestone-audit-npm-audit.json)、[摘要](milestone-audit-dependency-summary.json) | + +专项使用Node24.22.1、独立Python3.10.11/pytest8.4.2、自有项目/本地HTTP凭据和独立端口。实际Edge验证的两张界面/拒绝嵌入截图已目视核对,功能UI包含真实浏览器结果/PNG展示;没有使用正式模型连接。 + +## 最终发行流程 + +1. 冻结当前已提交源码、测试、脚本和构建;从不可变源码ZIP独立离线安装/构建及完整回归,核对输入/6份构建/逐阶段日志。 +2. 封存原结果后仅更新交付文档;最终不可变ZIP的实现输入、原生依赖、构建必须与通过的独立源码相同。REA-RUNTIME只允许明确登记的builtAt打包时间变化。 +3. 最终归档CRC/清单/目录/散列、实际便携Node/npm/REA/DeepSeek/Edge验证后,核对正式服务当前PID、公开配置和全部项目/会话/记录/事件及每份导出。当前只读实测1.12.0/PID23172、hasKey=true、16项目/20可见会话,无忙任务,见[当前服务身份](milestone-audit-service-preflight.json);旧PID19084是历史交付记录,最新全部数据需重新快照。 +4. 保留原Provider进行升级;部署后桌面/390px只读UI与数据库复核,关闭9229,保存最终身份和本地Git提交。 + +## 原失败与范围 + +首个源码候选的Windows尾点路径已在当前提案入口拒绝,旧测试仍试图先生成提案后核对批次错误,导致368/369。已分别核对当前入口提前拒绝和旧宿主保留提案在批次层拒绝,相关29项通过;新增硬链接补强不在首候选中,须重新构建封包及独立完整回归。 + +首轮19/20的探针专项在成功探针之后提交不完整/config夹具而失败,修正完整地址/模型后80项专项通过。首轮Edge导入故障夹具用无效URL,来源解析按契约预先跳过,原失败保留[初始记录](milestone-audit-security-ui-initial-failure.json);改用超长自有凭据后实际回滚通过。 + +首次构建子进程PATH仍找到Node16,前置本次Node24后通过;三个验收入口原来未实现--help,曾额外运行一次旧版独立验收,未改历史docs或正式服务,现已增加先行帮助/未知参数拒绝。所有环境和工具查询失败见findings/progress,不用新结果覆盖旧记录。 + +真实模型请求为0。真实模型工程验收按用户选择暂缓。OS沙箱、加密持久凭据、任意引擎工程写入、Purge收益、未知WorkBuddy格式、多协议/流式/多模态、安装版/真实手机与稳定全自主完成率仍按NEXT-STEPS开发或验证。 diff --git a/docs/RESEARCH-ROADMAP.md b/docs/RESEARCH-ROADMAP.md index 573f074c..8861992c 100644 --- a/docs/RESEARCH-ROADMAP.md +++ b/docs/RESEARCH-ROADMAP.md @@ -1,6 +1,6 @@ # REA与代理机制研究路线 -日期:2026-10-29。本文交付的是研究与落地路线;当前没有完成五款客户端全部能力的逆向,也没有把Purge或外部SDK集成到工作台。 +更新:2026-10-30。本文记录研究与落地路线;1.8已将REA三项静态分析接入工作台,1.9已将固定DeepSeek Harness六个SDK方法接入连接核验。五款客户端完整机制、受控外部引擎工程执行及Purge增强收益仍需研究和实测。当前先完成[里程碑审查](MILESTONE-AUDIT.md),后续按[NEXT-STEPS](NEXT-STEPS.md)推进。 来源身份登记见 [research/targets.json](../research/targets.json)。产品目标见 [PRODUCT-PLAN.md](PRODUCT-PLAN.md),能力ID见 [CAPABILITIES.md](CAPABILITIES.md)。 diff --git a/docs/VALIDATION.md b/docs/VALIDATION.md index 422eafe5..cf470798 100644 --- a/docs/VALIDATION.md +++ b/docs/VALIDATION.md @@ -12,6 +12,18 @@ 1.10.0完成274/274独立源码、13类118组界面、170份冻结输入及不可变源码/便携验证。实模首轮发现旧SQLite工件对象缺少新增字节读取API,原失败保留;1.10.1修复后最终独立源码276/276、174份冻结输入、实际随包REA/DeepSeek/Edge与便携/归档均通过。正式4318保留PID23080/Provider、14项目和全部24会话升级1.10.1。实模复验桌面8/8断言通过,390px因按钮选择器匹配三个元素而失败,210秒内未完成整体任务;18次响应/152837tokens及人工停止按原结果封存,见[QA-1.10](QA-1.10.md)。 +## 1.9.0 · DeepSeek连接核验与真实工程样本 + +261/261独立源码、108组界面、不可变包与保留原Provider升级通过;固定DeepSeek Harness 0.2.1-rc.2的六个SDK方法与所属进程退出验证完成。真实React/Python工程样本分别保留实际Task、检查和Git证据。当前SDK只完成连接核验,未发送引擎prompt、开放工程写入或证明Purge提升,见[QA-1.9](QA-1.9.md)。 + +## 1.8.0 · 内置REA与工程修复 + +244/244独立源码、98组界面、源码/便携及正式升级通过。固定REA 6.8.0的ASAR/PE三项静态操作有实际Evidence与所属Task/Run/目标SHA256,真实Node四模块工程Task的14项测试、build与Git交付通过。其余REA工具和外部引擎完整执行不计入此版本,见[QA-1.8](QA-1.8.md)。 + +## 1.7.0 · 最新工具反馈与Python/React检查 + +224/224独立源码、87组界面及不可变发行通过;最新工具结果反馈、相同工程状态暂停、Python结构化测试/编译与检查范围选择已交付,受控React/TypeScript交互/检查/Git样本通过。原真实模型因no_progress暂停且无提案,不能登记为真实自主交付,见[QA-1.7](QA-1.7.md)。 + ## 1.6.2 · 工作依据保留与旧发送视图兼容 不可变发行20261029180412072的独立源码205/205项、离线安装和6份构建比对通过;74组界面及便携/ZIP验收通过。原PID23080、Provider、10项目/12会话和全部执行证据保留升级,模型配置与预算未改变。见[QA-1.6.2](QA-1.6.2.md)、[源码](working-retention-source-package-validation.json)和[升级](working-retention-upgrade-live-validation.json)。七份真实冻结请求全部保留四模块/README,原结果可核验;离线回放不算实际模型完成。 diff --git a/docs/milestone-audit-all-ui-validation.json b/docs/milestone-audit-all-ui-validation.json new file mode 100644 index 00000000..89fa6ec9 --- /dev/null +++ b/docs/milestone-audit-all-ui-validation.json @@ -0,0 +1,169 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T15:37:24.953Z", + "groups": 150, + "results": [ + { + "script": "verify-task-plans-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 9081, + "evidence": "docs/milestone-audit-task-ui-validation.json", + "log": ".qa/milestone-audit-verify-task-plans-ui.log" + }, + { + "script": "verify-browser-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 19968, + "evidence": "docs/milestone-audit-browser-ui-validation.json", + "log": ".qa/milestone-audit-verify-browser-ui.log" + }, + { + "script": "verify-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 19171, + "evidence": "docs/milestone-audit-basic-ui-validation.json", + "log": ".qa/milestone-audit-verify-ui.log" + }, + { + "script": "verify-diagnostics-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 19578, + "evidence": "docs/milestone-audit-diagnostics-ui-validation.json", + "log": ".qa/milestone-audit-verify-diagnostics-ui.log" + }, + { + "script": "verify-execution-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 24935, + "evidence": "docs/milestone-audit-execution-ui-validation.json", + "log": ".qa/milestone-audit-verify-execution-ui.log" + }, + { + "script": "verify-delivery-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 38865, + "evidence": "docs/milestone-audit-delivery-ui-validation.json", + "log": ".qa/milestone-audit-verify-delivery-ui.log" + }, + { + "script": "verify-index-ui.mjs", + "success": true, + "groups": 8, + "durationMs": 5702, + "evidence": "docs/milestone-audit-index-ui-validation.json", + "log": ".qa/milestone-audit-verify-index-ui.log" + }, + { + "script": "verify-change-sets-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 10331, + "evidence": "docs/milestone-audit-change-sets-ui-validation.json", + "log": ".qa/milestone-audit-verify-change-sets-ui.log" + }, + { + "script": "verify-context-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 16116, + "evidence": "docs/milestone-audit-context-ui-validation.json", + "log": ".qa/milestone-audit-verify-context-ui.log" + }, + { + "script": "verify-workspaces-ui.mjs", + "success": true, + "groups": 9, + "durationMs": 20712, + "evidence": "docs/milestone-audit-workspaces-ui-validation.json", + "log": ".qa/milestone-audit-verify-workspaces-ui.log" + }, + { + "script": "verify-python-ui.mjs", + "success": true, + "groups": 7, + "durationMs": 17306, + "evidence": "docs/milestone-audit-python-ui-validation.json", + "log": ".qa/milestone-audit-verify-python-ui.log" + }, + { + "script": "verify-react-delivery.mjs", + "success": true, + "groups": 6, + "durationMs": 20241, + "evidence": "docs/milestone-audit-react-delivery-validation.json", + "log": ".qa/milestone-audit-verify-react-delivery.log" + }, + { + "script": "verify-research-ui.mjs", + "success": true, + "groups": 11, + "durationMs": 20732, + "evidence": "docs/milestone-audit-research-ui-validation.json", + "log": ".qa/milestone-audit-verify-research-ui.log" + }, + { + "script": "verify-engines-ui.mjs", + "success": true, + "groups": 10, + "durationMs": 9639, + "evidence": "docs/milestone-audit-engines-ui-validation.json", + "log": ".qa/milestone-audit-verify-engines-ui.log" + }, + { + "script": "verify-model-center-ui.mjs", + "success": true, + "groups": 5, + "durationMs": 4232, + "evidence": "docs/milestone-audit-model-center-ui-validation.json", + "log": ".qa/milestone-audit-verify-model-center-ui.log" + }, + { + "script": "verify-project-memory-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 5398, + "evidence": "docs/milestone-audit-project-memory-ui-validation.json", + "log": ".qa/milestone-audit-verify-project-memory-ui.log" + }, + { + "script": "verify-task-checkpoints-ui.mjs", + "success": true, + "groups": 3, + "durationMs": 5983, + "evidence": "docs/milestone-audit-task-checkpoints-ui-validation.json", + "log": ".qa/milestone-audit-verify-task-checkpoints-ui.log" + }, + { + "script": "verify-skills-ui.mjs", + "success": true, + "groups": 4, + "durationMs": 6365, + "evidence": "docs/milestone-audit-skills-ui-validation.json", + "log": ".qa/milestone-audit-verify-skills-ui.log" + }, + { + "script": "verify-mcp-ui.mjs", + "success": true, + "groups": 6, + "durationMs": 9265, + "evidence": "docs/milestone-audit-mcp-ui-validation.json", + "log": ".qa/milestone-audit-verify-mcp-ui.log" + }, + { + "script": "verify-mcp-recovery-ui.mjs", + "success": true, + "groups": 2, + "durationMs": 5636, + "evidence": "docs/milestone-audit-mcp-recovery-ui-validation.json", + "log": ".qa/milestone-audit-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." +} diff --git a/docs/milestone-audit-basic-ui-validation.json b/docs/milestone-audit-basic-ui-validation.json new file mode 100644 index 00000000..cebac34a --- /dev/null +++ b/docs/milestone-audit-basic-ui-validation.json @@ -0,0 +1,27 @@ +{ + "success": true, + "url": "http://127.0.0.1:62044", + "browser": "Microsoft Edge 156.0.4314.50", + "date": "2026-10-30T15:33:22.785Z", + "projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\ui-e91e622c-b16b-41c3-a42f-e139034db17e\\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" +} \ No newline at end of file diff --git a/docs/milestone-audit-batch-ui-validation.json b/docs/milestone-audit-batch-ui-validation.json new file mode 100644 index 00000000..41cbce34 --- /dev/null +++ b/docs/milestone-audit-batch-ui-validation.json @@ -0,0 +1,29 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:35:02.875Z", + "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/milestone-audit-batch-desktop-review.png", + ".qa/screenshots/milestone-audit-batch-desktop-conflict.png", + ".qa/screenshots/milestone-audit-batch-desktop-recovery.png", + ".qa/screenshots/milestone-audit-batch-mobile-review.png", + ".qa/screenshots/milestone-audit-batch-mobile-rollback.png" + ], + "projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-d2725d6a-4d2b-4023-bac5-8e539be91e34", + "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." +} diff --git a/docs/milestone-audit-browser-ui-validation.json b/docs/milestone-audit-browser-ui-validation.json new file mode 100644 index 00000000..be63ae60 --- /dev/null +++ b/docs/milestone-audit-browser-ui-validation.json @@ -0,0 +1,175 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:33:03.495Z", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-f085de99-e76f-42b4-8a57-e58b64852e15", + "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-f085de99-e76f-42b4-8a57-e58b64852e15\\browser-desktop-results.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-f085de99-e76f-42b4-8a57-e58b64852e15\\browser-desktop-original-image.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-f085de99-e76f-42b4-8a57-e58b64852e15\\browser-mobile-results.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-f085de99-e76f-42b4-8a57-e58b64852e15\\browser-mobile-original-image.png" + ], + "taskId": "18f51708-f98f-4028-b0f0-d528517d004b", + "sessionId": "88e522fb-75be-479e-b1a8-a7540153552d", + "jobs": [ + { + "id": "deaced0d-8a49-4cec-9c72-efe447265f51", + "status": "passed", + "planId": "12ed8d3c-831c-48c6-b855-45ca0106c9db", + "assertions": { + "total": 2, + "passed": 2, + "failed": 0 + }, + "resultSha256": "02097a77a6ad9a55bf4285e08577c2fd402a111ce6c889647e93240572c55227", + "cleanup": { + "pid": 33724, + "exited": true, + "exitCode": 0, + "signal": null, + "finishedAt": "2026-10-30T15:32:48.847Z", + "previewClosed": true, + "snapshotDisposed": true + }, + "screenshots": [ + { + "artifactId": "e9ac2479-943a-457b-978e-9bfb7e738217", + "sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef", + "bytes": 101061, + "width": 1280, + "height": 900, + "label": "initial" + }, + { + "artifactId": "45e34136-62af-42ab-98e4-48d8639f3dde", + "sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7", + "bytes": 85261, + "width": 1280, + "height": 900, + "label": "final" + } + ] + }, + { + "id": "0dffbb92-c53b-4e13-92d8-eb4891887d94", + "status": "failed", + "planId": "70bf237a-a3e6-49d3-a14d-b85428731d0c", + "assertions": { + "total": 2, + "passed": 1, + "failed": 1 + }, + "resultSha256": "78f972e9998e45671c72873570da7e4b797a4b423b7cc821d8d6dd10a03feb26", + "cleanup": { + "pid": 31476, + "exited": true, + "exitCode": 0, + "signal": null, + "finishedAt": "2026-10-30T15:32:55.947Z", + "previewClosed": true, + "snapshotDisposed": true + }, + "screenshots": [ + { + "artifactId": "f24f2aad-e1d2-4c16-9afe-8da0bb26fc75", + "sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef", + "bytes": 101061, + "width": 1280, + "height": 900, + "label": "initial" + }, + { + "artifactId": "5c76f367-f893-44ba-a911-7dd3d6228326", + "sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7", + "bytes": 85261, + "width": 1280, + "height": 900, + "label": "failure" + } + ] + }, + { + "id": "6c5a11f7-f777-45c6-9508-3af32e3c04ba", + "status": "passed", + "planId": "248491fa-e1f7-4813-b672-fe8c7a2fb236", + "assertions": { + "total": 2, + "passed": 2, + "failed": 0 + }, + "resultSha256": "ef94eb9b8d4a4b38508e076cfbe3e10d76be2ef78052b16c760699a1dee9553e", + "cleanup": { + "pid": 44264, + "exited": true, + "exitCode": 0, + "signal": null, + "finishedAt": "2026-10-30T15:32:58.384Z", + "previewClosed": true, + "snapshotDisposed": true + }, + "screenshots": [ + { + "artifactId": "b8f1e9e6-ea64-486d-b95a-5f7a0a244fde", + "sha256": "93969f1954eec1f7fa4736d7a3035631c6066b6727132ff1179180eadb745602", + "bytes": 11011, + "width": 390, + "height": 844, + "label": "initial" + }, + { + "artifactId": "3e5da9ee-d515-4f23-88a7-77234bf884eb", + "sha256": "a6908ecfcfd239721ec6bbb916a5054d2f61183b6dea3f014db89216d371d0e3", + "bytes": 18832, + "width": 390, + "height": 844, + "label": "final" + } + ] + }, + { + "id": "16bfde86-5828-4bef-9f8b-3dc4979e6012", + "status": "interrupted", + "planId": "401d5a66-74e9-40dd-b46f-d168e56e6da4", + "assertions": { + "total": 3, + "passed": 2, + "failed": 1 + }, + "resultSha256": "b6b6fb35eed88b5fcf6b0dcdf219877d0b18eb315700d39a481de634dbd1e206", + "cleanup": { + "pid": 43720, + "exited": true, + "exitCode": 0, + "signal": null, + "finishedAt": "2026-10-30T15:33:01.561Z", + "previewClosed": true, + "snapshotDisposed": true + }, + "screenshots": [ + { + "artifactId": "93392adf-5be2-4a45-99dd-f6966dd09d57", + "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." +} diff --git a/docs/milestone-audit-change-sets-ui-validation.json b/docs/milestone-audit-change-sets-ui-validation.json new file mode 100644 index 00000000..41cbce34 --- /dev/null +++ b/docs/milestone-audit-change-sets-ui-validation.json @@ -0,0 +1,29 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:35:02.875Z", + "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/milestone-audit-batch-desktop-review.png", + ".qa/screenshots/milestone-audit-batch-desktop-conflict.png", + ".qa/screenshots/milestone-audit-batch-desktop-recovery.png", + ".qa/screenshots/milestone-audit-batch-mobile-review.png", + ".qa/screenshots/milestone-audit-batch-mobile-rollback.png" + ], + "projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-d2725d6a-4d2b-4023-bac5-8e539be91e34", + "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." +} diff --git a/docs/milestone-audit-code-baseline.json b/docs/milestone-audit-code-baseline.json new file mode 100644 index 00000000..ec6787d1 --- /dev/null +++ b/docs/milestone-audit-code-baseline.json @@ -0,0 +1,1130 @@ +{ + "version": "1.12.1", + "codeCommit": "7b1f529ed69ae6eea129c49a47496e0cb93bfc73", + "capturedAt": "2026-10-30T15:35:23.335Z", + "inputs": [ + { + "path": "index.html", + "bytes": 411, + "sha256": "893c264c5c1293d6af54a6ca65280cf637b5afffee3cd2156ff88e4a44c370c5" + }, + { + "path": "package-lock.json", + "bytes": 79507, + "sha256": "89318a78d080b8d5b4a2a4d9188e687f0b42620c0ac6451b6cfc908b7aeb051b" + }, + { + "path": "package.json", + "bytes": 2005, + "sha256": "3d89c54106223fcb89c1a9fd98e5755ee0f06fcb018128ed18570093a15b3144" + }, + { + "path": "scripts/Start-Workbench.ps1", + "bytes": 3211, + "sha256": "36d8ab194974369afa47ff717e60cad763432ee1f1abb6ccc4e6b1b6b11da253" + }, + { + "path": "scripts/Stop-Workbench.ps1", + "bytes": 980, + "sha256": "f6d12d32006c17fcb20192a73b762592f900ddfcda0cabda6f202e37405d1331" + }, + { + "path": "scripts/build-server.mjs", + "bytes": 553, + "sha256": "67e4ae3f5bd9214bfbf2596e3fb9c2af465ec7364293d37da07c7810c789d15e" + }, + { + "path": "scripts/bundle-browser.mjs", + "bytes": 2629, + "sha256": "c9bd500e469d5aa60a69a35d5863a5f2d56b336cbd8f2d5268b5e05f0687d23b" + }, + { + "path": "scripts/bundle-rea.mjs", + "bytes": 5700, + "sha256": "90fbc4af57eb2e92d4d92de5be5ac26eb8c99f132efdafe8f3e133ec1db7ffbe" + }, + { + "path": "scripts/engine-fixtures.mjs", + "bytes": 5241, + "sha256": "8ca536f1a6f4edb6a03b0508e6f175879eeb39a835149f4f6c8ba806e07266e8" + }, + { + "path": "scripts/inspect-ui.mjs", + "bytes": 1187, + "sha256": "81a6e6f96aae44b60c9f382e53d54f673868b3705a4c3eb1d0107c11ff790b88" + }, + { + "path": "scripts/live-react-client.mjs", + "bytes": 4278, + "sha256": "6c01ae7b2be7e2b82831c718e72bebe353bab864f97373ed95c5d478ac28b32b" + }, + { + "path": "scripts/package.mjs", + "bytes": 9925, + "sha256": "22ffb0a5dc23d654ac4bf6e9d261fc6dd034d4f17a402b5a5356bc08f24365b2" + }, + { + "path": "scripts/python-check-runner.py", + "bytes": 9553, + "sha256": "17bd6fd64ad93b8f806e0f5d325e75fd4534c065f4fcb597ad45fb9152caf657" + }, + { + "path": "scripts/qa-evidence.mjs", + "bytes": 679, + "sha256": "d887eb11f5e0a4f64540db1bcb693d2b2adbdbd97ed8f7a0abfb46be1ad544e2" + }, + { + "path": "scripts/qa-python-requirements.txt", + "bytes": 14, + "sha256": "bf4dc0555928a3facf67b3370001388d4b65e69a071c339f8b201310bde4486a" + }, + { + "path": "scripts/research-fixtures.mjs", + "bytes": 3712, + "sha256": "ba1f5644045ddba894a787cc4d9fa85c9a7e00730e3ea2e9b18d594a43498a8c" + }, + { + "path": "scripts/tune-styles.mjs", + "bytes": 1369, + "sha256": "8909eaaff060753745d7d6945377689ca531d784390cdd7d84acf97551d7b1c0" + }, + { + "path": "scripts/upgrade-running.mjs", + "bytes": 12304, + "sha256": "fd3d8e026b2b135ad6b145a4235918385511e0d8d6f58a8fdd059d686098e943" + }, + { + "path": "scripts/verify-all-ui.mjs", + "bytes": 8760, + "sha256": "681e94b0457b3035e3972de70e555055efd469eeaf0ce7884f39f427bafdceda" + }, + { + "path": "scripts/verify-archives.py", + "bytes": 4529, + "sha256": "66e5d6b31e04e4c143bf73860635f0da2ea1f707822ca638bc4197a397ca4dde" + }, + { + "path": "scripts/verify-browser-ui.mjs", + "bytes": 14638, + "sha256": "c4a99fcf45fc0e1d39024937d481119965349c486422a14b3084264539c4157a" + }, + { + "path": "scripts/verify-browser.mjs", + "bytes": 10768, + "sha256": "8ccbe961ce26363079fc8ea30559e57ee78f88926b438e1004d5b3528beacb76" + }, + { + "path": "scripts/verify-change-sets-ui.mjs", + "bytes": 15972, + "sha256": "87c60f25d2d4c226fecd35c253a68368a3c53e33aa2b8b332c72760490705866" + }, + { + "path": "scripts/verify-context-ui.mjs", + "bytes": 18445, + "sha256": "f78fed61f844edaa674db9c768247a45b7eb434fe94b1b29b3a5e3798922272a" + }, + { + "path": "scripts/verify-delivery-ui.mjs", + "bytes": 22757, + "sha256": "eae0e07b901f0a3da4d595bbc8e214e032d7da45d7d8ea033c034ad45dc34c3d" + }, + { + "path": "scripts/verify-diagnostics-ui.mjs", + "bytes": 15521, + "sha256": "476d284fc1b8c086f8d7f44013a44d200ec5b5df2d8b58e52caaedd46e569ab0" + }, + { + "path": "scripts/verify-engines-ui.mjs", + "bytes": 15763, + "sha256": "b1ae2b6274d2584ba190faa1818f53f1bc775430f9140cb68ca77d9952756f2e" + }, + { + "path": "scripts/verify-engines.mjs", + "bytes": 4748, + "sha256": "c1f0d9949230527cc4933a90e64a68053ef8bc040b14384119998a5a2f223b4d" + }, + { + "path": "scripts/verify-execution-ui.mjs", + "bytes": 15157, + "sha256": "f78149dda36baea05cd1f7c36dab0301e3c1c94df70cefb1bb12f51313d383be" + }, + { + "path": "scripts/verify-index-ui.mjs", + "bytes": 13822, + "sha256": "04f1b925aff59f06583325d18e69a6160bfae98e87254b3ee2e6fd0dabccdbfb" + }, + { + "path": "scripts/verify-live-browser.mjs", + "bytes": 11765, + "sha256": "b1bb7e3ac8ac6c1abec0c90b996bbde0a335e87acb956a05918fc31245ee0b33" + }, + { + "path": "scripts/verify-live-delivery.mjs", + "bytes": 24628, + "sha256": "4c45acd05841ddf2a6e0a04ee1d0a9f4c003e34d794318bfe3892a29d474117e" + }, + { + "path": "scripts/verify-live-engineering.mjs", + "bytes": 18301, + "sha256": "2e42a1347069c56beb4022627f760a2088751d4f0829606b49d2edd0833d934c" + }, + { + "path": "scripts/verify-live-model.mjs", + "bytes": 5607, + "sha256": "848495e2488125eb5e79c9d8b121025f9f740551535dc8529b415b4246da455b" + }, + { + "path": "scripts/verify-live-session.mjs", + "bytes": 6727, + "sha256": "f71f22f2355d499afa501f9ba37a04f8b8cf5d404fdfe95b65cc1d324775ac9b" + }, + { + "path": "scripts/verify-live-task-plans.mjs", + "bytes": 13181, + "sha256": "577fc325a6b13f7cd21fb8b1ab96f8940afe94e65bffa74046b47af572b1c510" + }, + { + "path": "scripts/verify-mcp-recovery-ui.mjs", + "bytes": 6336, + "sha256": "b11e321e0d92efb57d8e76b612c053e6a0229f0f3641721c606a28a61fe12a18" + }, + { + "path": "scripts/verify-mcp-ui.mjs", + "bytes": 9714, + "sha256": "c3c93d4ea8109dce1bfb4c91bf3a8b11dc2c7bbee3986c55ed2a4fcde0446d34" + }, + { + "path": "scripts/verify-model-center-ui.mjs", + "bytes": 8760, + "sha256": "d4c13f9e328172f973143f7333cdc4f5627c7d33f188f59a6588c1cbd1f8745a" + }, + { + "path": "scripts/verify-project-memory-ui.mjs", + "bytes": 8405, + "sha256": "b197345800d805ca3e52094ea660f8eb8d4d90defde2c49dc1a17a4b97270bdb" + }, + { + "path": "scripts/verify-python-ui.mjs", + "bytes": 11489, + "sha256": "676e4222a25ca68ed5bbb6661b9f7ec5eac4abaa9de70d9a5eb07a3429ba2457" + }, + { + "path": "scripts/verify-rea.mjs", + "bytes": 5166, + "sha256": "cdca5f73ee9f5b2b1fc4cd58ce98a7c0fcd551164879ae3192d67edd8e69491d" + }, + { + "path": "scripts/verify-react-delivery.mjs", + "bytes": 13013, + "sha256": "51a6c000d6ff148204d500b8505e2f7589f55a68947b9eabd4097ed0e477d118" + }, + { + "path": "scripts/verify-release.mjs", + "bytes": 14613, + "sha256": "480d101518119dc1dda7bc4e520b60079d583212d07626a49c11ffa8279ebcef" + }, + { + "path": "scripts/verify-research-ui.mjs", + "bytes": 18573, + "sha256": "0844a6d22e843123afc0d133302096a08c35b9cb7d9dd3bafacf85a2a50b260d" + }, + { + "path": "scripts/verify-skills-ui.mjs", + "bytes": 7956, + "sha256": "2139b2caa764c17752edb13f8cc43e0d4643e9c0d4d47c34e6c95b0374efd974" + }, + { + "path": "scripts/verify-source-package.mjs", + "bytes": 10176, + "sha256": "0ed25b24eff2f95fa6c890b22ad72c6b7318bb8e80b1c46993036f0a7bc50ff0" + }, + { + "path": "scripts/verify-task-checkpoints-ui.mjs", + "bytes": 6176, + "sha256": "2af7d9abf21b2a13a618ed080e324f61c21a42a386d09c5bd62c7bdf70ec5de2" + }, + { + "path": "scripts/verify-task-plans-ui.mjs", + "bytes": 16078, + "sha256": "7a0d5a0c5c59040bd203c65453a0ff9c6282e9bd46c14b573a67a59a8920a5fa" + }, + { + "path": "scripts/verify-tests.mjs", + "bytes": 5124, + "sha256": "3e9140831477df004d39187e240ce8e27e8680d051a9353dc6b9b17de81994f4" + }, + { + "path": "scripts/verify-ui.mjs", + "bytes": 18880, + "sha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6" + }, + { + "path": "scripts/verify-workspaces-ui.mjs", + "bytes": 15427, + "sha256": "fdf5900e0936b681d030f18a7a5245beacf8ab091b79a495ca823df65e8bb4a7" + }, + { + "path": "src/client/App.tsx", + "bytes": 61296, + "sha256": "678223d317c091e2dceef71dfb326eba47ceb57551375371e70d84cbef74882b" + }, + { + "path": "src/client/BrowserPanel.css", + "bytes": 5050, + "sha256": "3032abddc1cfeea3100cb4b34bb2e9e25e965f470c4fd38c73d564dfc80f3450" + }, + { + "path": "src/client/BrowserPanel.tsx", + "bytes": 16962, + "sha256": "24a7479a2740ac72de22dadb556565904fb4525117cddc2a08ab1b766437ce30" + }, + { + "path": "src/client/ChangeSetPanel.css", + "bytes": 4477, + "sha256": "c1ac9307b78e4e42159398e499074d85da395faf7c88f2f485c6b7901d142459" + }, + { + "path": "src/client/ChangeSetPanel.tsx", + "bytes": 11104, + "sha256": "b3a3b3e73bf74a23c08f74d124fe98c6b45e0c048d3fabb745fd488140d58f61" + }, + { + "path": "src/client/ChangesInspector.tsx", + "bytes": 3324, + "sha256": "5799507f52e1414ec573eb1d0452bb3c173728836d3c1644c760b31cab4a3ee4" + }, + { + "path": "src/client/CodeIndexPanel.css", + "bytes": 5796, + "sha256": "76f6f2b32e25df3b3f4c8761273de4963b7b25dff01cbe97b2f5171ec8358286" + }, + { + "path": "src/client/CodeIndexPanel.tsx", + "bytes": 7715, + "sha256": "2574080bbb0aa9ff05571ef406dadd3c008f792cf2443ff1f779f0975a6d97d4" + }, + { + "path": "src/client/DeliveryPanel.css", + "bytes": 5070, + "sha256": "8c12813290c171b616ffb36c002395fc40ff2c7d5b63cd2f13613be435a2d3c6" + }, + { + "path": "src/client/DeliveryPanel.tsx", + "bytes": 14267, + "sha256": "23a9c1519c6b94508f2cabaedd47ccf43f0cdae26d5f956d81b3c26f37f6d531" + }, + { + "path": "src/client/DiagnosticsPanel.tsx", + "bytes": 3823, + "sha256": "a5746d019da37c99af60c69f556b007ea307e2f3a02fcde504b547ed468dd07f" + }, + { + "path": "src/client/EnginePanel.css", + "bytes": 6275, + "sha256": "5a0fc3b6fab7038751f346cdd40e6b4540e8886c0f0c54478c09c18eeaeec1d3" + }, + { + "path": "src/client/EnginePanel.tsx", + "bytes": 12950, + "sha256": "d36f3058ab8e0a5d327f68f6894d34fc4b1f721949c873e1356dcb28907a4e07" + }, + { + "path": "src/client/McpJobHistory.tsx", + "bytes": 7508, + "sha256": "207ba78dce96c85dedf7ff34f7678dff1e925118fb93dd1d5a144f38c7aaf618" + }, + { + "path": "src/client/McpPanel.css", + "bytes": 9547, + "sha256": "e1c89f3229acb0bb739fcf91e605d09f7d8f38f4f367da1f11835b2b9452538d" + }, + { + "path": "src/client/McpPanel.tsx", + "bytes": 15591, + "sha256": "f1ea14216c4340f6cd76b267763a468bf0d311dd6f8b273afe3ee9cf6768a260" + }, + { + "path": "src/client/ModelCenter.css", + "bytes": 9222, + "sha256": "99f81bc87f634fa77bedd00247500b99314412db36574a58e6e382cca19f903f" + }, + { + "path": "src/client/ModelCenter.tsx", + "bytes": 22142, + "sha256": "bde2746b5e2d3595a5459dff3f6154c44d67853cc57bd8aa3c744428bac3823a" + }, + { + "path": "src/client/ProjectMemory.css", + "bytes": 4322, + "sha256": "0d6c9a23afafa77e7230edd9294299a3d233aa7b49c191d522ee9c106839a1f1" + }, + { + "path": "src/client/ProjectMemoryPanel.tsx", + "bytes": 7381, + "sha256": "b7c140f126bc2d48df00fe4111517e3ea2f43926d52797d26733e1f2522f6a03" + }, + { + "path": "src/client/RequestContextPanel.tsx", + "bytes": 9245, + "sha256": "9b7bd92ff4afc6a8e4c1fd129dea053acb8b135330582643beef62608b737e79" + }, + { + "path": "src/client/ResearchPanel.css", + "bytes": 7271, + "sha256": "f24f8eb283c0b419037adcd680bc1bbe84002abf661bfda94891dcea5fc92682" + }, + { + "path": "src/client/ResearchPanel.tsx", + "bytes": 16684, + "sha256": "cae237fc267a491db18f24f88e0b6926a635225886bfa58683a37f6d4586c8e1" + }, + { + "path": "src/client/SkillCenter.css", + "bytes": 6453, + "sha256": "d9f79bba3be7369a0231434aa29fe061e0c5d1f792aeb7e15e3f2a7744165242" + }, + { + "path": "src/client/SkillCenter.tsx", + "bytes": 9303, + "sha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10" + }, + { + "path": "src/client/TaskCheckpointPanel.tsx", + "bytes": 5367, + "sha256": "77b552924379531eff51c81c5bf4e2512c1201f39641245c781a468e6a7e397a" + }, + { + "path": "src/client/TaskPanel.css", + "bytes": 8906, + "sha256": "6dc737d84406fafd2f1b36ba1eaf02c8b0f59594b30a1fadcf2d3451ada285db" + }, + { + "path": "src/client/TaskPanel.tsx", + "bytes": 18980, + "sha256": "cb781e0c81f4f24b822b4b7472bd4d14cc6591f78a96558f259bc0bd587cb3ec" + }, + { + "path": "src/client/TaskPlanPanel.css", + "bytes": 4257, + "sha256": "e47eb1195a61400d60817de793893d9e4924f334bdf452ffb744ed69741c43fc" + }, + { + "path": "src/client/TaskPlanPanel.tsx", + "bytes": 16038, + "sha256": "3ead0b021ae550b0bc3891b8e852c297f05f895ce3516f693a91d23456ebc1f1" + }, + { + "path": "src/client/WorkspacePanel.css", + "bytes": 3743, + "sha256": "d8c4558f6c559ff8b4bbc7723aca08e4e37f8fef8f5b8d5619faec8332314ba3" + }, + { + "path": "src/client/WorkspacePanel.tsx", + "bytes": 10026, + "sha256": "c91d097edd5e044f72583bdccd39848f35a5b82c4d9abf7c09648e21ecfdb8c2" + }, + { + "path": "src/client/api.ts", + "bytes": 3058, + "sha256": "6e706020502cc3e079ddc46f4f843571cfb883852fb7ea21bd2c3c9ff463d56c" + }, + { + "path": "src/client/components.tsx", + "bytes": 13189, + "sha256": "7b735a151ceb1889702f3127a15a8a2918f6fba7140304c3b81b5662f1b43741" + }, + { + "path": "src/client/control-console.css", + "bytes": 4836, + "sha256": "bbb0f00ff90ea4c8d0f969b4fa95df4e95413b97ab28a204a893a99671a10bc7" + }, + { + "path": "src/client/main.tsx", + "bytes": 256, + "sha256": "6dec6d76306f0e47b1a9e77004377daa5312270d519a685f169c025a9e071792" + }, + { + "path": "src/client/styles.css", + "bytes": 38537, + "sha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218" + }, + { + "path": "src/client/types.ts", + "bytes": 24332, + "sha256": "ffc135242245843efe42b8df2614afafe7b8c8c98731dfc3fa6b10e1b9d8cfd8" + }, + { + "path": "src/core/browser/browser-driver.mjs", + "bytes": 18254, + "sha256": "d63e3ae49bdec13f2f86923c21d4af4d7f1ea1b07c768be3cc85b4833836bdd2" + }, + { + "path": "src/core/browser/browser-manager.mjs", + "bytes": 24633, + "sha256": "0efc0e30f19a8649c964e1193c455d6cc6f32bfd4a4a5e18fc6ff8014d67b820" + }, + { + "path": "src/core/browser/build-snapshot.mjs", + "bytes": 4309, + "sha256": "2424f37847e72621327b5c0157f9fc03c1e7dd266ca71292b4b70571f17170a9" + }, + { + "path": "src/core/check-runner.mjs", + "bytes": 20806, + "sha256": "e37224b56ba664af7d99e8ac1f3270aa15ed9d1d48239e26109e7ff1cf16a28a" + }, + { + "path": "src/core/context/project-index.mjs", + "bytes": 18380, + "sha256": "acaa896eca725bcce13a6d34a46267ce70a8a824eac8ca2ffccb91c4d18bd304" + }, + { + "path": "src/core/context/read-budget.mjs", + "bytes": 10437, + "sha256": "7544a22f8a0f2aeb9f06cd3d43f9eae77cc3141503930571a8c170b1ff4bb0cd" + }, + { + "path": "src/core/context/request-plan.mjs", + "bytes": 36015, + "sha256": "3d8c158f8b0d7e696a311f642a95f184cf69d38db9859498dbb8d2db6ab85108" + }, + { + "path": "src/core/context/tool-feedback.mjs", + "bytes": 9598, + "sha256": "7523f2ef18d9fea975d15e665c8c122293fdf52f3c7093ad08e16b8a83b6c95f" + }, + { + "path": "src/core/context/working-set.mjs", + "bytes": 10948, + "sha256": "61220be2142fff4194b633cf85e39f87c0a71ddf0745ce1406a5bc54977bdb0a" + }, + { + "path": "src/core/delivery-report.mjs", + "bytes": 22037, + "sha256": "a0bb895459be2805684b881f80674f5592c2d55c285adcc30a0657c3a9c7bb5d" + }, + { + "path": "src/core/engine-manager.mjs", + "bytes": 12455, + "sha256": "ec29a945c84ee79a41d30ac3a70296281bdd7d7898cc727a85bb6d78af62f015" + }, + { + "path": "src/core/engines/deepseek-adapter.mjs", + "bytes": 10977, + "sha256": "b5d3e3f1ba74b8d15b002594f13652bbc98761226a3e5e3fb408071762958fa9" + }, + { + "path": "src/core/engines/deepseek-installation.mjs", + "bytes": 5979, + "sha256": "5bca6da6d1fd972405762b81a4be7936ac597337e310aec2a7d88aa9e5cce7a9" + }, + { + "path": "src/core/git-delivery.mjs", + "bytes": 40952, + "sha256": "4c53fcb82813a559b1e61615fb879dd7afe48686832d2ffd992f81dc56579bad" + }, + { + "path": "src/core/git-process.mjs", + "bytes": 2655, + "sha256": "80547ec8928610ac4df5a05c5aef12d1aab0dca9e7b1def2773fc745f5adf5f5" + }, + { + "path": "src/core/memory/project-memory.mjs", + "bytes": 13871, + "sha256": "9c7da0ef9c7f36b431015fd4414f55304f8d5e25a61bc527fb7e3be0b7971e51" + }, + { + "path": "src/core/models/config-import.mjs", + "bytes": 8293, + "sha256": "70e5884606565d930685b0d0b55f73d9ceaf00dd3525f0fe6d2fdad2f87366bf" + }, + { + "path": "src/core/models/model-hub.mjs", + "bytes": 17756, + "sha256": "652581d91c8c0e9f1059880aa6ee31016790e06e53e20fff18d36c2c56bad379" + }, + { + "path": "src/core/process-environment.mjs", + "bytes": 910, + "sha256": "05f7ca9bad79ed96a184c96643edffc320aef45567e888341531448f23c89702" + }, + { + "path": "src/core/project-inspector.mjs", + "bytes": 10892, + "sha256": "9e81ed2928fc5dcdb20915a406a8cdc69068deb04fd9d36d0792a86598405782" + }, + { + "path": "src/core/python-project.mjs", + "bytes": 4721, + "sha256": "74e09a96f2e1970b155d37af176379807add0d5a05f72ccd9491d4d494d58707" + }, + { + "path": "src/core/python-runtime.mjs", + "bytes": 12568, + "sha256": "9e9f1b9128295f46404839ad95eaf8bcad60a8c4964756e7c1a1b21cc4add0d7" + }, + { + "path": "src/core/research-manager.mjs", + "bytes": 19987, + "sha256": "15981370de1f02db4acec2c3e1450d068236e1f6ab70f677ec8617aa968fc2dc" + }, + { + "path": "src/core/skills/skill-registry.mjs", + "bytes": 15494, + "sha256": "63e435d65e3dfe7dff1b1711590b5a4a5ca2efddaa67822087de06facdadf3bb" + }, + { + "path": "src/core/storage/artifact-store.mjs", + "bytes": 2918, + "sha256": "2934d31a28da215f7ea73a3b5e56d106b723b34539ea8605d523b121762e488a" + }, + { + "path": "src/core/storage/legacy-import.mjs", + "bytes": 4825, + "sha256": "aa6a6b95d4049c5091d39e8c65ee301a0d6e533e081da59c87f2733bfb5a15ed" + }, + { + "path": "src/core/storage/state-database.mjs", + "bytes": 8565, + "sha256": "2a38f7564df44c4ee5183d850064be1d46fba7e072e2b87f73afb8e1a85a1517" + }, + { + "path": "src/core/tasks/task-checkpoint-manager.mjs", + "bytes": 13524, + "sha256": "2f50f9de2e6b8c90376028ed2814eb795633e1ea917ab944a977299220ad820f" + }, + { + "path": "src/core/tasks/task-plan-manager.mjs", + "bytes": 22026, + "sha256": "4feafa9462ab57f694854c79c846a9ba58fe9313b343341f2ca2a334255eec24" + }, + { + "path": "src/core/tools/mcp-contract.mjs", + "bytes": 8366, + "sha256": "4860792132e2d18caa075ddca8c24687b3692c005a1c6c4c81933e6dc9e0a6bc" + }, + { + "path": "src/core/tools/mcp-registry.mjs", + "bytes": 26252, + "sha256": "8f52b11ba37d1c350aa279e4890a0c5b00fff3b77fc4f2211a4ea1c07bbadebc" + }, + { + "path": "src/core/tools/mcp-stdio.mjs", + "bytes": 8109, + "sha256": "1c1081b9356855db5c8964ac5b9f5fb2c79fef5323ff1f933447a06f77cac447" + }, + { + "path": "src/core/tools/rea-adapter.mjs", + "bytes": 9010, + "sha256": "36f7d2a095fcaef4e1ca056a1f2475e0b15fe1fc48d0179589b41abadf39c6c4" + }, + { + "path": "src/core/tools/research-output.mjs", + "bytes": 1750, + "sha256": "b9d53487192f12b0d2b0f0922c918b5b3d88a276777cd64903395800ff07c1c0" + }, + { + "path": "src/core/workspaces/change-sets.mjs", + "bytes": 25967, + "sha256": "759315b541c127b9eabb411f9b61975dff88daac063af63520cac81f7f8a18c0" + }, + { + "path": "src/core/workspaces/git-workspaces.mjs", + "bytes": 36568, + "sha256": "2b123a1e92e7f07fbfdd650ccbf44908d6b2e1d7504f893034e12a0cd0f32839" + }, + { + "path": "src/server/app.mjs", + "bytes": 50418, + "sha256": "de400aa4380343943f967f9a6fcec0f71d8650853bd8eaf08a0cfc4e064bbb2a" + }, + { + "path": "src/server/diagnostics.mjs", + "bytes": 7965, + "sha256": "55bd70f30f0e6666374965ea96e59b98fd85d223dacb863377a36c2be427c3fa" + }, + { + "path": "src/server/files.mjs", + "bytes": 15377, + "sha256": "fa52ef72410d09b17aadf6dfd8cd742dc9f3ada2880e36aa4e2a403637eaaa3b" + }, + { + "path": "src/server/hot-upgrade.mjs", + "bytes": 6364, + "sha256": "5fc691140bc7b380a0fbf412c4a709a684057896a7d8cdb58db55ac96d8f68f7" + }, + { + "path": "src/server/index.mjs", + "bytes": 2668, + "sha256": "16b9d751870188d185ca6b03429376f19b5e7b94fd91a6ce401a096fae74ef64" + }, + { + "path": "src/server/provider.mjs", + "bytes": 28611, + "sha256": "3072dd4dfaa4053e75bd57916a60a39a98c29bc2b08fe4fbbc0ff4002aa61749" + }, + { + "path": "src/server/runtime.mjs", + "bytes": 55479, + "sha256": "e3ca70df57743a185d40389a127e34b6895862954b0f5bc080f499dbd1947a1f" + }, + { + "path": "src/server/store.mjs", + "bytes": 41695, + "sha256": "1417841521a31d63672e74cb986614ceb5bb9ba8fbb0e9b8dcc92e02dcff0646" + }, + { + "path": "src/shared/contracts/browser.mjs", + "bytes": 4775, + "sha256": "af8f71616097dbbb08bde31bf1cc42c90708802f17ad89b4ba220351fb30f439" + }, + { + "path": "src/shared/contracts/change-sets.mjs", + "bytes": 1189, + "sha256": "01586cdcffe00129c2b61e4cbf4a622b22306cd5a893620f4a7db441f978f1da" + }, + { + "path": "src/shared/contracts/delivery-review.mjs", + "bytes": 1368, + "sha256": "1b17efdfa2549801db72eabe439907419a4d85ea07e4d010563db2d483d565f9" + }, + { + "path": "src/shared/contracts/engines.mjs", + "bytes": 2234, + "sha256": "8d52facab1b7c1941637ae86756e73a7050467be04a0e036259bff6aad42c42b" + }, + { + "path": "src/shared/contracts/execution.mjs", + "bytes": 5035, + "sha256": "2ceb700eaa3f8f2adf01b348575f7deb381f970e30eabe553e3ee30840d699a5" + }, + { + "path": "src/shared/contracts/model-request.mjs", + "bytes": 901, + "sha256": "3744dfa7302dde72d1c24c54e7c00672ff063b45786add2fb19d46233b759e78" + }, + { + "path": "src/shared/contracts/research.mjs", + "bytes": 6860, + "sha256": "eb970b52f923d7dbfd8e7da49381ce135b8a2ae9d04c0d4321958a2e93d12003" + }, + { + "path": "src/shared/contracts/task-plan-tools.mjs", + "bytes": 3029, + "sha256": "b14392919e1b551751a6c311004d9d200bc494a7873987c8c0f34a8c4bec1ec1" + }, + { + "path": "src/shared/contracts/task-plans.mjs", + "bytes": 7290, + "sha256": "c312f4511f495b90ec8983e5c8ecc357e85f67d97b8deda2d052651c3f491adb" + }, + { + "path": "src/shared/contracts/workspaces.mjs", + "bytes": 3975, + "sha256": "4cd6873ca73de9dac5e73f3aaabe062674c5ca1d50c28a2e2b6eb9e138c32be9" + }, + { + "path": "tests/api.test.mjs", + "bytes": 12277, + "sha256": "86fbee40af8a7afb6e295ac52c7a46e3e4476c4667543e9756d916fbce8e335f" + }, + { + "path": "tests/browser-api.test.mjs", + "bytes": 9597, + "sha256": "30c8f5adb89bd60277c48e9f4e1e9f5c3a0fc8652cda447a4d6c273210e2576b" + }, + { + "path": "tests/browser-delivery.test.mjs", + "bytes": 4085, + "sha256": "21c1280d95f070504840c94c4bdf556559653636332f8e38d355144fc080dc2e" + }, + { + "path": "tests/browser-locators.test.mjs", + "bytes": 4926, + "sha256": "cad3236d3ac1e17524ad304e159659d4009ce3ae265ccb9047a36df00dbd31f3" + }, + { + "path": "tests/browser.test.mjs", + "bytes": 8150, + "sha256": "2e4a0d1d5136a9729b015b977af9344a9802a2015583d7e2cf5825d606888242" + }, + { + "path": "tests/change-set-api.test.mjs", + "bytes": 12753, + "sha256": "44170084aea8e31cfd4c59e4c96006413f0f66151e6241d27b7a0aacf5d1a328" + }, + { + "path": "tests/change-set-recovery.test.mjs", + "bytes": 3435, + "sha256": "8cfa9ae1526975111f6ec7fa60afb79e40a994c5fdbf86abcf1edd2cc69077e0" + }, + { + "path": "tests/change-sets.test.mjs", + "bytes": 14453, + "sha256": "3ac85e2a0946e0590ba9f2ad9727ba49160839643977132516a8c7746b658166" + }, + { + "path": "tests/checks.test.mjs", + "bytes": 21968, + "sha256": "d7936ef6fa5c0421976cdb30e435a910e7a0c461829e991091b4c6ee00e924ab" + }, + { + "path": "tests/code-tools.test.mjs", + "bytes": 7518, + "sha256": "f6c120892e86ec21c67b010e256e359b2f1ba7196b48937961f4e8c62deeef93" + }, + { + "path": "tests/config-transaction-api.test.mjs", + "bytes": 3506, + "sha256": "0e9f7d2e2f5f8cc0510a6e3f96f03e921b758aac78de659b3d8f999c0abaa4f8" + }, + { + "path": "tests/delivery-recovery.test.mjs", + "bytes": 10733, + "sha256": "bec27e3d4bdd8777d7a08e146019e79436cbb463131cd2b07f6f819e002652b1" + }, + { + "path": "tests/delivery.test.mjs", + "bytes": 22944, + "sha256": "d6e05886de2d27395cc6f2d0cd8581e87150ac95a7b017337fd59d1ce388c489" + }, + { + "path": "tests/diagnostics.test.mjs", + "bytes": 13318, + "sha256": "88a3b333ddc9da6c65eaafc1e73b16e28c79e617d9a8348d1a7b925b1cf99615" + }, + { + "path": "tests/engine-api.test.mjs", + "bytes": 5089, + "sha256": "da7dd728a5a30039cda74e5b67a451908384527d7946600fc2170335cc2e64cd" + }, + { + "path": "tests/engine.test.mjs", + "bytes": 14173, + "sha256": "77a917ae867a4b7e509c10e10f36b75f5755e18066b44f6ebd73552cf9355e03" + }, + { + "path": "tests/execution.test.mjs", + "bytes": 14144, + "sha256": "f3004d5cc4fcf5ac65eea0c24c864fa63227d9d1127f32b41621e6c3b7bc52ba" + }, + { + "path": "tests/file-boundaries.test.mjs", + "bytes": 2385, + "sha256": "e87e7b5e65c7b72d3d686330c395f92fb20eeb8b8adb7b8906d11a4832f58ee8" + }, + { + "path": "tests/files.test.mjs", + "bytes": 7050, + "sha256": "b0a4b9c385c5d0ed8e4a8bf6b43c2b679488882a19f25572d7b89a1ed3d5b378" + }, + { + "path": "tests/fixtures/browser-project.mjs", + "bytes": 1972, + "sha256": "cb682a64f65953bfcdb577768b82b1f7a7e86e530379ea8580ecdbf864132ff2" + }, + { + "path": "tests/fixtures/change-set-crash-worker.mjs", + "bytes": 909, + "sha256": "0f564eea935f576de9ef6db7a09cc95db2f95a38b654d476de67e3b5eb166c96" + }, + { + "path": "tests/fixtures/change-set-project.mjs", + "bytes": 1688, + "sha256": "b597f7ec0d32975673fdc36284d6688af401040b06e6fe8370a3e565a98016c2" + }, + { + "path": "tests/fixtures/check-crash-worker.mjs", + "bytes": 654, + "sha256": "3de4749fb0b016e44c16029a71366231acd021c2196b075029d55d767e0c4c84" + }, + { + "path": "tests/fixtures/context-plan-crash-worker.mjs", + "bytes": 558, + "sha256": "9ebc5980e78d39a3d382d6336eb021e2088baeff4ff670f427617c01c4e509d8" + }, + { + "path": "tests/fixtures/core-crash-worker.mjs", + "bytes": 2852, + "sha256": "ff6a92e7600844f47a49eecdf800a3e7219ee193547cb0008568a578854303ed" + }, + { + "path": "tests/fixtures/delivery-crash-worker.mjs", + "bytes": 744, + "sha256": "a2f5e2ba4382e6ef0a614a9d07928a06a07a74a748441b1404570dd714428492" + }, + { + "path": "tests/fixtures/delivery-project.mjs", + "bytes": 4095, + "sha256": "578fa6074b9d4d375a31f94d02b34acada63e85df1dce22ac7dfbd259c5d55cb" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/README.md", + "bytes": 346, + "sha256": "ec995a6accae2d5bdd4e43b1a698ea5a3b13241cfb70d57dc103650d665c3d1b" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/artifact-store.mjs", + "bytes": 2655, + "sha256": "b5e7d5dba4614c9e93aa118e1765266be22b7871c0751aa1b902c5ad358ab10f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/README.md", + "bytes": 524, + "sha256": "e5d044b72eea8ad836196a8e86abab366453b14addd9f206f9a2da75511da52f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/dist-server/hot-upgrade.mjs", + "bytes": 95288, + "sha256": "0a701a6cb3063bf8459bdaf2adb6e93af33682592ab67f3c69e96a32c8b92148" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/README.md", + "bytes": 536, + "sha256": "ebee2fdec8207c66d172604f7fa28d10be1c7f2a01e26f92c6e4c41da0d6aabd" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/dist-server/server.mjs", + "bytes": 73087, + "sha256": "00770b85ea3372259b5a481616616aa1dc1bdefac00c210b5b307898f63ad934" + }, + { + "path": "tests/fixtures/mcp-host-crash.mjs", + "bytes": 1238, + "sha256": "a7ceecb6419270bb918e72704d0cf124623afd037da433b7b4c9af6f769aafa7" + }, + { + "path": "tests/fixtures/python-project.mjs", + "bytes": 3277, + "sha256": "4b20f285de410302839782d544257483c666609ae519c1a6facea5a8dbcaecc2" + }, + { + "path": "tests/fixtures/registered-mcp-server.mjs", + "bytes": 2200, + "sha256": "e6479755be0d7d0e08a7f98cbc59cf4ea494c8092bdab40e5dff752d5b8840c1" + }, + { + "path": "tests/fixtures/research-mcp.cjs", + "bytes": 1744, + "sha256": "8fe82e55327f6e32ab2bafc66d9374b4b542959656d5a341c50779d1ae579458" + }, + { + "path": "tests/fixtures/task-checkpoint-crash-worker.mjs", + "bytes": 884, + "sha256": "835b95c4baf1f4a69228f88e7da99092dfc77238d2cbea6b08600bdafc18017b" + }, + { + "path": "tests/fixtures/task-plan-crash-worker.mjs", + "bytes": 1089, + "sha256": "a3f0b614dfdc2c14906fe0435a7b8fb07d3267cd0732f63e174c44c59909cd6c" + }, + { + "path": "tests/fixtures/task-plan-fixture.mjs", + "bytes": 1698, + "sha256": "036fa5f0e1dc3a55a2adba55700d4f597396fbf5cf216fc2404ec101df2544d9" + }, + { + "path": "tests/fixtures/workspace-crash-worker.mjs", + "bytes": 1006, + "sha256": "c12bc83f501fc2eb522c6f30235d2e089ab6129a96c44e0d4edb4fb135d9215c" + }, + { + "path": "tests/fixtures/workspace-project.mjs", + "bytes": 995, + "sha256": "69002bf2e6940f314aec3e8d7f758e53d6376f0814e6b4e1b16505abbe46a699" + }, + { + "path": "tests/helpers.mjs", + "bytes": 6248, + "sha256": "71ac890f4278cb664bbc313dfe1df2cd063e77544a65f528c6428a822da2425b" + }, + { + "path": "tests/mcp-registry.test.mjs", + "bytes": 22599, + "sha256": "b6059a9c3966ded29450e85e5a43ad088a181049d218eb5ecb7c76782db93d05" + }, + { + "path": "tests/mcp-stdio.test.mjs", + "bytes": 5402, + "sha256": "58510c241450d5300f1ca4a4f7ad4adecf6a7abdae295197c311934883c5b23b" + }, + { + "path": "tests/model-center.test.mjs", + "bytes": 16620, + "sha256": "51d477629c2654bf9b1fde30b50865b8b6fff221267609d848579ae98df91fa3" + }, + { + "path": "tests/patch.test.mjs", + "bytes": 6579, + "sha256": "d90404327527e820e3195d04edbf1a7349a450564d80e7dbc4e0c582559e6102" + }, + { + "path": "tests/process-environment.test.mjs", + "bytes": 4553, + "sha256": "03e14e7f48e414330098c14c878cc990d134d5909976dcf849b4da0c3ecffd3d" + }, + { + "path": "tests/project-index.test.mjs", + "bytes": 15256, + "sha256": "83fbc65f713e68e29395ad1053bcbf7272922fb932c6e17f62f4ea402878519d" + }, + { + "path": "tests/project-memory-context.test.mjs", + "bytes": 13430, + "sha256": "bf2996b50e26a69eba737d09de1e5273f5332d695c93f708e508269a29e8bfaf" + }, + { + "path": "tests/project-memory.test.mjs", + "bytes": 7438, + "sha256": "811da36aeffaeddfc496809f00f81ec2cfd722c7411614c6f6b282de2e5d3764" + }, + { + "path": "tests/python-api.test.mjs", + "bytes": 9733, + "sha256": "7694d82dc70d458371d347dbd54886cfa3fb1118c37f59fc4773dd1921fca173" + }, + { + "path": "tests/python-checks.test.mjs", + "bytes": 18057, + "sha256": "b60bde10ac220570a6fc59555b287061d1325783be7532a613885d834ee58078" + }, + { + "path": "tests/read-budget.test.mjs", + "bytes": 13724, + "sha256": "106ddd1eae179c03a01d4952aa3f72d68057badf572e093156f6cc3b37e8edbf" + }, + { + "path": "tests/request-plan-api.test.mjs", + "bytes": 4837, + "sha256": "f3d9a63ee319d44a2ae74d293eb229a8b2cd77bdd29119abcdc23040496d1b57" + }, + { + "path": "tests/request-plan.test.mjs", + "bytes": 18997, + "sha256": "d9e816d4258f9ad4fc35b72d12071e8cb529c7ce708f77a22292760f97c5302b" + }, + { + "path": "tests/research.test.mjs", + "bytes": 16967, + "sha256": "76c8f486bb1fdc4bbef25246ff219bcaa8b8242fb8b7add89c831f9de8ede219" + }, + { + "path": "tests/runtime.test.mjs", + "bytes": 15006, + "sha256": "cf4ce1675cd5f5ab7f81ebd9cd9c949eed1a8121db15cd5349d3c45a732a2b1e" + }, + { + "path": "tests/skills.test.mjs", + "bytes": 17628, + "sha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6" + }, + { + "path": "tests/store.test.mjs", + "bytes": 3880, + "sha256": "e932cdf3a682a3c10309e04d4373f2180f0466443eda2b7d29865ca5eb5f9437" + }, + { + "path": "tests/task-checkpoints.test.mjs", + "bytes": 16172, + "sha256": "bca05de242d6ca7705e7f07e03744b831748e7e6569e00ad540d95cb0fc6ce19" + }, + { + "path": "tests/task-plans-api.test.mjs", + "bytes": 3657, + "sha256": "e0f067eed3e748a39b864e26f8d844a28cc45709aac305a04230cbb19ccd7684" + }, + { + "path": "tests/task-plans.test.mjs", + "bytes": 21545, + "sha256": "99e9b5ba17818bdd8bd8b035868beec4bb2d6bb520b5e1592b02bb3008054461" + }, + { + "path": "tests/tool-feedback.test.mjs", + "bytes": 8409, + "sha256": "61cb597fcd7f8ec32c072f70e0937086535fe50eaa0997479ca06968425bcee3" + }, + { + "path": "tests/upgrade-artifacts.test.mjs", + "bytes": 6267, + "sha256": "6cfb50727f8601f03300de605a4021f7b3e388cba597814a2089438b8a0eb957" + }, + { + "path": "tests/upgrade-model-center.test.mjs", + "bytes": 3774, + "sha256": "f44240a1caa4c1a8554623e3b53530093c98df07d5fb548f27d69230517665c3" + }, + { + "path": "tests/upgrade.test.mjs", + "bytes": 9711, + "sha256": "1a6ded4be5e89ac7a41c9a60c4b37569723ad7d5f80f48c9406940ad727455d3" + }, + { + "path": "tests/working-set.test.mjs", + "bytes": 23492, + "sha256": "b5a163c4d441c49b68a906508156f1e0792d2f0a5a6fe76ebe4429970c432d76" + }, + { + "path": "tests/workspace-api.test.mjs", + "bytes": 9444, + "sha256": "b1dd1ed7a2b14cdd8851a6ff6e15b8f5f9dce85a4e70f1314dcfce98e66d8dd8" + }, + { + "path": "tests/workspace-policy.test.mjs", + "bytes": 12247, + "sha256": "ff8cc7ea014bb630951ae61e7fdda80d5333155823a91986f52f998d011d010c" + }, + { + "path": "tests/workspace-recovery.test.mjs", + "bytes": 5382, + "sha256": "7aeaf03ae89a7de7641d260704aafca4a330b532e46d2d0468a64932c1ab057c" + }, + { + "path": "tests/workspaces.test.mjs", + "bytes": 5490, + "sha256": "4118e9208fed31b3ea2ab55276ed1477291c2daf83809753764a5f17dee7bc60" + }, + { + "path": "tsconfig.json", + "bytes": 398, + "sha256": "aca51bc97061d8ee755197b432ce24f70eb37e02cf8c60445edcfe35305d0510" + }, + { + "path": "vite.config.ts", + "bytes": 247, + "sha256": "6ad3b1bd9d5390876535ba189200fa08e46e5fb481f3f57581376859998e63f4" + } + ], + "builds": [ + { + "path": "dist-client/assets/index-3yiFGvdV.js", + "bytes": 454165, + "sha256": "2a51e2f00a83216bd72916ebf6371de4e556132c7f25e287236f3481170ae533" + }, + { + "path": "dist-client/assets/index-D_6ySsfn.css", + "bytes": 116467, + "sha256": "a0297d773dda8cd837f7dfcd8ceed79611b59b46a5954b06f7e832c315e415b4" + }, + { + "path": "dist-client/favicon.svg", + "bytes": 268, + "sha256": "538fa42445dfd8e78135717e2f30dada6d790d5c05b9011ae7a9bf80d416ae1d" + }, + { + "path": "dist-client/index.html", + "bytes": 503, + "sha256": "3dafb8b8a44877d5f21dfc50672eddc06358b5e68b53715fe240b036304427fe" + }, + { + "path": "dist-server/hot-upgrade.mjs", + "bytes": 1468735, + "sha256": "03b1a6672b3ff4d79bc1654258d83be1dab244264f4de94a11d9436955862264" + }, + { + "path": "dist-server/server.mjs", + "bytes": 1465775, + "sha256": "27d1f7f3682b76395f4c92f14b2c6570ec9fa23a693241e9958003dc0ff78f89" + } + ], + "scope": "Snapshot captured during current UI run after 7b1f529 and its build; no implementation edits since that run started. Independently extracted source will be compared to every input/build." +} diff --git a/docs/milestone-audit-context-ui-validation.json b/docs/milestone-audit-context-ui-validation.json new file mode 100644 index 00000000..62d948c0 --- /dev/null +++ b/docs/milestone-audit-context-ui-validation.json @@ -0,0 +1,34 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:35:18.503Z", + "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/milestone-audit-desktop-plan.png", + ".qa/screenshots/milestone-audit-desktop-history.png", + ".qa/screenshots/milestone-audit-mobile-history.png", + ".qa/screenshots/milestone-audit-mobile-original.png", + ".qa/screenshots/milestone-audit-mobile-request-body.png", + ".qa/screenshots/milestone-audit-mobile-read-pause.png", + ".qa/screenshots/milestone-audit-desktop-working-evidence.png", + ".qa/screenshots/milestone-audit-mobile-working-evidence.png" + ], + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-f82e3e7d-f745-450c-aca6-f9e36f3ab43d", + "data": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-f82e3e7d-f745-450c-aca6-f9e36f3ab43d\\data", + "mode": "saved synthetic context evidence; no real model or project commands executed by this UI verifier", + "browser": "156.0.4314.50" +} diff --git a/docs/milestone-audit-delivery-ui-validation.json b/docs/milestone-audit-delivery-ui-validation.json new file mode 100644 index 00000000..ec814aaa --- /dev/null +++ b/docs/milestone-audit-delivery-ui-validation.json @@ -0,0 +1,31 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:34:46.656Z", + "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-74712e04-69ea-4a10-a449-bb1b393fb957\\四模块交付工程", + "projectId": "d18c3b65-68ff-4167-96e1-7790bc5bf360", + "sessionId": "de562ac7-8f05-4dd3-a0d4-5590c71b805b", + "taskId": "7afcdf67-c120-4c45-b045-4bddca74bbe7", + "commit": "d67e17670937ab0a577527a6790eb31e23ac8f95", + "recoveryCommit": "67d0de7aba5c67ef627090cf8e5e1b1f638d5ae2", + "testCounts": { + "baselineFailed": 13, + "passed": 14 + }, + "model": "controlled local HTTP fixture", + "confirmations": 2 +} \ No newline at end of file diff --git a/docs/milestone-audit-dependency-summary.json b/docs/milestone-audit-dependency-summary.json new file mode 100644 index 00000000..d678d582 --- /dev/null +++ b/docs/milestone-audit-dependency-summary.json @@ -0,0 +1,26 @@ +{ + "testedAt": "2026-10-30T14:11:39.966Z", + "command": "npm audit --json --ignore-scripts", + "exitCode": 0, + "metadata": { + "vulnerabilities": { + "info": 0, + "low": 0, + "moderate": 0, + "high": 0, + "critical": 0, + "total": 0 + }, + "dependencies": { + "prod": 13, + "dev": 141, + "optional": 79, + "peer": 0, + "peerOptional": 0, + "total": 153 + } + }, + "error": null, + "outputSha256": "fb8761bffb39edf97e113a34db5f3d673ed9354a74251aa3a31255462d8ad025", + "findings": [] +} diff --git a/docs/milestone-audit-diagnostics-ui-validation.json b/docs/milestone-audit-diagnostics-ui-validation.json new file mode 100644 index 00000000..13995a68 --- /dev/null +++ b/docs/milestone-audit-diagnostics-ui-validation.json @@ -0,0 +1,20 @@ +{ + "success": true, + "version": "1.12.1", + "url": "http://127.0.0.1:57675", + "date": "2026-10-30T15:33:42.571Z", + "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" +} \ No newline at end of file diff --git a/docs/milestone-audit-engines-ui-validation.json b/docs/milestone-audit-engines-ui-validation.json new file mode 100644 index 00000000..e4bc87d1 --- /dev/null +++ b/docs/milestone-audit-engines-ui-validation.json @@ -0,0 +1,232 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:36:47.681Z", + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae", + "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-cbc842de-b91c-49e2-b603-144d8dfc57ae\\screenshots\\engines-native-desktop.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\screenshots\\engines-record-mobile.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\screenshots\\engines-native-mobile.png" + ], + "starts": [ + { + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\本地 SDK #", + "identitySha256": "e9b0fb8df3c1b703b020d144f1c01c48b6eb6c896104f12a39b5a5fadb3b615f" + }, + { + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\本地 SDK #", + "retry": true + }, + { + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\本地 SDK #", + "identitySha256": "e9b0fb8df3c1b703b020d144f1c01c48b6eb6c896104f12a39b5a5fadb3b615f" + }, + { + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-cbc842de-b91c-49e2-b603-144d8dfc57ae\\本地 SDK #", + "retry": true + }, + { + "root": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness", + "identitySha256": "a60f7733d6eaf91bcd31ce5d1da38d6d267a16ad29bc03bba548f314fddec22a" + } + ], + "nativeJob": { + "schemaVersion": 1, + "id": "007ca020-bbfb-482d-8357-1f39f21d4f3e", + "sessionId": "6de0e0b8-d03b-43a5-901b-5cee65114430", + "projectId": "a88c3e16-e6ea-4d75-9187-bc3140c37e42", + "taskId": "bfed1813-8b7a-44fc-881a-23bdccf7ac2e", + "runId": "2da1ea69-3436-45b0-8b87-05afbf8e69a2", + "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": "C:\\Program Files\\nodejs\\node.exe", + "bytes": 93915464, + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5", + "version": "24.22.1" + }, + "identitySha256": "a60f7733d6eaf91bcd31ce5d1da38d6d267a16ad29bc03bba548f314fddec22a", + "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": "9db6910d-75d0-41cd-a446-861406f2417b", + "directory": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\007ca020-bbfb-482d-8357-1f39f21d4f3e", + "status": "completed", + "startedAt": "2026-10-30T15:36:44.645Z", + "finishedAt": "2026-10-30T15:36:45.705Z", + "requiresVerification": false, + "verification": { + "verified": true, + "installationSha256": "a60f7733d6eaf91bcd31ce5d1da38d6d267a16ad29bc03bba548f314fddec22a", + "readySignal": "appReady", + "sdkSessionId": "9db6910d-75d0-41cd-a446-861406f2417b", + "connectionId": "8817a1b8-9253-4364-96ec-2fdc5157ff36", + "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": "6c4abd20-07e6-45ac-9dd1-724bd14e60b6", + "contractSha256": "e03e183842b77c48211adb14410f49b484eba9f2b2b846f9ab762f6ce4194b29", + "eventId": "4ca0b22b-1e6a-416a-bdbc-63ab0ea4dac5", + "pid": 41192, + "connectionId": "8817a1b8-9253-4364-96ec-2fdc5157ff36", + "readiness": { + "schemaVersion": 1, + "nonce": "d31c8e64-f0e9-424a-be17-faa74f27bda4", + "pid": 41192, + "signal": "appReady", + "readyAt": "2026-10-30T15:36:45.505Z", + "artifact": { + "path": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\007ca020-bbfb-482d-8357-1f39f21d4f3e\\ready.json", + "bytes": 135, + "sha256": "c34502c77b73eb915f0eaef17b5050fd53a4d9bcfdc26581ff6eaa2413747a53" + } + }, + "serverInfo": { + "name": "deepseek-harness-sdk-runtime", + "version": "0.0.1" + }, + "reportArtifactId": "d25e6269-9c27-4135-9bfe-d9e20a084c25", + "reportSha256": "cf9718d81e153f4d337627ff63e0fbc6c45b556c8c866bc117f3aafc0f2af480", + "reportSummary": { + "status": "verified", + "modelRequests": 0, + "providerRequests": 0, + "observedResponses": 6, + "rootExited": true + } + }, + "actualSdk": { + "version": "0.2.1-rc.2", + "identitySha256": "a60f7733d6eaf91bcd31ce5d1da38d6d267a16ad29bc03bba548f314fddec22a", + "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." +} diff --git a/docs/milestone-audit-environment-initial-repro.json b/docs/milestone-audit-environment-initial-repro.json new file mode 100644 index 00000000..5a711c40 --- /dev/null +++ b/docs/milestone-audit-environment-initial-repro.json @@ -0,0 +1,28 @@ +{ + "at": "2026-10-30T14:30:44.640Z", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-environment-tR5epo", + "shell": { + "status": "completed", + "inherited": { + "OPENAI_API_KEY": true, + "MODEL_ROUTER_TOKEN": true, + "CUSTOM_SERVICE_SECRET": true + } + }, + "npm": { + "status": "passed", + "inherited": { + "OPENAI_API_KEY": true, + "MODEL_ROUTER_TOKEN": true, + "CUSTOM_SERVICE_SECRET": true + } + }, + "python": { + "inherited": { + "OPENAI_API_KEY": true, + "MODEL_ROUTER_TOKEN": true, + "CUSTOM_SERVICE_SECRET": true + } + }, + "realCredentials": "none; worker receives only system paths and owned markers" +} diff --git a/docs/milestone-audit-execution-ui-validation.json b/docs/milestone-audit-execution-ui-validation.json new file mode 100644 index 00000000..218c423e --- /dev/null +++ b/docs/milestone-audit-execution-ui-validation.json @@ -0,0 +1,19 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:34:07.743Z", + "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-80ed42a5-0f92-43fa-8eda-2a60bbf07314\\project", + "model": "controlled local HTTP fixture" +} \ No newline at end of file diff --git a/docs/milestone-audit-first-candidate-baseline.json b/docs/milestone-audit-first-candidate-baseline.json new file mode 100644 index 00000000..181d34b3 --- /dev/null +++ b/docs/milestone-audit-first-candidate-baseline.json @@ -0,0 +1,264 @@ +{ + "codeCommit": "f4bd0ad", + "releaseId": "20261030150404738", + "uiGroups": 150, + "sourceSuccess": false, + "sourceTests": { + "tests": 369, + "pass": 368, + "fail": 1, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "originals": [ + { + "path": "docs/milestone-audit-all-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-all-ui-validation.json", + "sha256": "79f87769d56cfdef78c62078726c6b14005d4c330e8f19043892a54f57414168", + "bytes": 5409 + }, + { + "path": "docs/milestone-audit-task-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-task-ui-validation.json", + "sha256": "1aaa5de3d630901056df0a81f67b3b73c87c7266ac982eb32cdc1aa470c38d85", + "bytes": 2303 + }, + { + "path": ".qa/milestone-audit-verify-task-plans-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-task-plans-ui.log", + "sha256": "40c7e0623140f96de42078471826acdaab74345c3964b2cb144d040d33bb6432", + "bytes": 993 + }, + { + "path": "docs/milestone-audit-browser-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-browser-ui-validation.json", + "sha256": "897df7efc1d005712f5d999c00aeef9cb015a0c815116503b6b843d4ea6726d0", + "bytes": 6537 + }, + { + "path": ".qa/milestone-audit-verify-browser-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-browser-ui.log", + "sha256": "9e845542bfcfb421c30a872a46f5479ceb8fa83c3f94063716545a0e0f4e481f", + "bytes": 1235 + }, + { + "path": "docs/milestone-audit-basic-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-basic-ui-validation.json", + "sha256": "ab10ccbb0d771728f851ec32a4d0ddec408d158330026e85a5a56ec4dbdafbcb", + "bytes": 1083 + }, + { + "path": ".qa/milestone-audit-verify-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-ui.log", + "sha256": "c5c4973a94fd979685551a97ac8ba0e6db3290331d60425f5ba1eebec06a4f8c", + "bytes": 1706 + }, + { + "path": "docs/milestone-audit-diagnostics-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-diagnostics-ui-validation.json", + "sha256": "8ad68eaad9b19e8f325a7587d35972142f22273081e87dff2119e679eae482fa", + "bytes": 1047 + }, + { + "path": ".qa/milestone-audit-verify-diagnostics-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-diagnostics-ui.log", + "sha256": "f8c859409fac2a036041c2eebabe39cb86c98037fdf1ea16ed28b89d3c07178f", + "bytes": 1795 + }, + { + "path": "docs/milestone-audit-execution-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-execution-ui-validation.json", + "sha256": "5dca13e15274d8017b3a71b52b82ad228a187554dae16c2c32ea1567a6058168", + "bytes": 924 + }, + { + "path": ".qa/milestone-audit-verify-execution-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-execution-ui.log", + "sha256": "f24594006927caeb0425b9ca6bfec1869ebda1c8742306d126a692752e86771c", + "bytes": 1484 + }, + { + "path": "docs/milestone-audit-delivery-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-delivery-ui-validation.json", + "sha256": "ea2b5e458da4015fcedc471e704e8eb1e01251f0c49d424681636089af61da1e", + "bytes": 1622 + }, + { + "path": ".qa/milestone-audit-verify-delivery-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-delivery-ui.log", + "sha256": "94138e47ce181eff372e06a5d072c6b2c91c1270b9880eb8b04425d0377398e4", + "bytes": 2493 + }, + { + "path": "docs/milestone-audit-index-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-index-ui-validation.json", + "sha256": "b7fa50d9fad9152d7fefd50ba6ada520daf0da17b7415b8837aa476ec3ccd1cc", + "bytes": 1108 + }, + { + "path": ".qa/milestone-audit-verify-index-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-index-ui.log", + "sha256": "b7fa50d9fad9152d7fefd50ba6ada520daf0da17b7415b8837aa476ec3ccd1cc", + "bytes": 1108 + }, + { + "path": "docs/milestone-audit-change-sets-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-change-sets-ui-validation.json", + "sha256": "60e452263e54872b03b87b87c20377b2bbb48222c6d61ed117182aaac84fbc21", + "bytes": 1913 + }, + { + "path": ".qa/milestone-audit-verify-change-sets-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-change-sets-ui.log", + "sha256": "60e452263e54872b03b87b87c20377b2bbb48222c6d61ed117182aaac84fbc21", + "bytes": 1913 + }, + { + "path": "docs/milestone-audit-context-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-context-ui-validation.json", + "sha256": "37aa07bb4e8d03d1291efcf7ecea483fad7567a8c390ea57d0be45c7944af857", + "bytes": 2019 + }, + { + "path": ".qa/milestone-audit-verify-context-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-context-ui.log", + "sha256": "46231edc520113f36edcfd63679ca0e3182b975b180d737008bf8ac8e4d7bf09", + "bytes": 2986 + }, + { + "path": "docs/milestone-audit-workspaces-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-workspaces-ui-validation.json", + "sha256": "c95f933fafc7a6fa6e7e310d268536617ce54fa3b693eb0efb420ea2055d04d2", + "bytes": 1780 + }, + { + "path": ".qa/milestone-audit-verify-workspaces-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-workspaces-ui.log", + "sha256": "18fba3fd6ef6ed389fb4d74beaffb6c339a7240466c1b8e869c269840b78495a", + "bytes": 2608 + }, + { + "path": "docs/milestone-audit-python-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-python-ui-validation.json", + "sha256": "966f446b85071212edb8d2e767c70ed1baed10e44972ce8a99eb97a7bf0ff1e1", + "bytes": 1374 + }, + { + "path": ".qa/milestone-audit-verify-python-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-python-ui.log", + "sha256": "755ebc650e88ef352b7cd2a0d4e6cce618c3c3d134b99a3935fc98c42bc7fec4", + "bytes": 2075 + }, + { + "path": "docs/milestone-audit-react-delivery-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-react-delivery-validation.json", + "sha256": "85cf65007ac5721bf259d8837da0aa2a471171e6bf4021d8062cdc4edf8c06ee", + "bytes": 2763 + }, + { + "path": ".qa/milestone-audit-verify-react-delivery.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-react-delivery.log", + "sha256": "e6a396c5cf3e152862d4a842b013ce6d6520bc7bcc3f4728b216ad5a70f90ac3", + "bytes": 3426 + }, + { + "path": "docs/milestone-audit-research-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-research-ui-validation.json", + "sha256": "554651c017eda8545cef34d30e5dfa561a32c7a32845f64643ba41f0ec45945a", + "bytes": 5419 + }, + { + "path": ".qa/milestone-audit-verify-research-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-research-ui.log", + "sha256": "5bc0378631934e45b6fb654d6c0ff148aa69f2f454ba3d871c833061139099ee", + "bytes": 1412 + }, + { + "path": "docs/milestone-audit-engines-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-engines-ui-validation.json", + "sha256": "4e465d2360df5c36a9d8b5be6c5527495cc1e8a5bae24639b874890959a9efb8", + "bytes": 11332 + }, + { + "path": ".qa/milestone-audit-verify-engines-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-engines-ui.log", + "sha256": "5302b2109ab32773323203ad2b1276d6593573fc46168fcae9182b96fdd0280b", + "bytes": 1351 + }, + { + "path": "docs/milestone-audit-model-center-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-model-center-ui-validation.json", + "sha256": "86579b41233e65c925699849247ac4c0e23e72b8cb7a926636b0a8581ebe7446", + "bytes": 780 + }, + { + "path": ".qa/milestone-audit-verify-model-center-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-model-center-ui.log", + "sha256": "0411af598092f0ce33d2408999cc94fcf99ec91e208ba6259bf5b28114815278", + "bytes": 593 + }, + { + "path": "docs/milestone-audit-project-memory-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-project-memory-ui-validation.json", + "sha256": "6db3c3236fcd13bb49d22bd899ccad65ed88ae2bde02d8553a9b3ca58a23c0f2", + "bytes": 770 + }, + { + "path": ".qa/milestone-audit-verify-project-memory-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-project-memory-ui.log", + "sha256": "d31104015d899cdf37d1989fd3101597293165edb85b94e44689eb2b95b4fa53", + "bytes": 488 + }, + { + "path": "docs/milestone-audit-task-checkpoints-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-task-checkpoints-ui-validation.json", + "sha256": "15cea3ed0910cdb30784e688b3a68538a7030c5c120601dcbfdac3711bdcc6b1", + "bytes": 610 + }, + { + "path": ".qa/milestone-audit-verify-task-checkpoints-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-task-checkpoints-ui.log", + "sha256": "3dcdbc2ad5cc33638d6807552712c59beedccd91e74322901d214e1506c394b0", + "bytes": 427 + }, + { + "path": "docs/milestone-audit-skills-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-skills-ui-validation.json", + "sha256": "f318e8454e547a6e460beac80378c730b81456ebe87f0ce308c6dd34fe4c7792", + "bytes": 801 + }, + { + "path": ".qa/milestone-audit-verify-skills-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-skills-ui.log", + "sha256": "a6fea246baa09979534bcdeae07b93768ca69dc05a73daf81dec3319f384a2e1", + "bytes": 576 + }, + { + "path": "docs/milestone-audit-mcp-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-mcp-ui-validation.json", + "sha256": "abe21da92912205e6dd7a29b303ce7b47cdc9adde0c0c70449994be3191db5db", + "bytes": 952 + }, + { + "path": ".qa/milestone-audit-verify-mcp-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-mcp-ui.log", + "sha256": "f1acbfb8cae75f01506fe108f25bba021267ad2a7c7f406fc4a8cbe950d928e2", + "bytes": 700 + }, + { + "path": "docs/milestone-audit-mcp-recovery-ui-validation.json", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\docs\\milestone-audit-mcp-recovery-ui-validation.json", + "sha256": "5fd28ed4bbc7740c01e9afff6fa099350c094bf3eb73213f263c7003d68ec8e1", + "bytes": 482 + }, + { + "path": ".qa/milestone-audit-verify-mcp-recovery-ui.log", + "saved": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2\\.qa\\milestone-audit-verify-mcp-recovery-ui.log", + "sha256": "5c52cb33a03c5ce5937d808c58fa26ec8467fcd7fb0decda1307d8191490be03", + "bytes": 340 + } + ], + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-first-candidate-3bd2cc18-321b-4a9e-800e-9ad645be72c2", + "purpose": "Preserved initial candidate before hard-link boundary follow-up and earlier Windows alias rejection assertion; not final release evidence." +} diff --git a/docs/milestone-audit-first-source-package-failure.json b/docs/milestone-audit-first-source-package-failure.json new file mode 100644 index 00000000..5bb41362 --- /dev/null +++ b/docs/milestone-audit-first-source-package-failure.json @@ -0,0 +1,1140 @@ +{ + "success": false, + "version": "1.12.1", + "testedAt": "2026-10-30T15:18:01.975Z", + "stage": "tests", + "error": "tests failed (1): and routing objects\nok 326 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects\n ---\n duration_ms: 1023.3738\n type: 'test'\n ...\n# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails\nok 327 - hot upgrade refuses active probes and restores retained model methods if installation fails\n ---\n duration_ms: 1047.1487\n type: 'test'\n ...\n# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider\nok 328 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider\n ---\n duration_ms: 3179.4364\n type: 'test'\n ...\n# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection\nok 329 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection\n ---\n duration_ms: 12106.7432\n type: 'test'\n ...\n# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit\nok 330 - small code and actual failed command stay visible when their original multi-tool group cannot fit\n ---\n duration_ms: 1641.2226\n type: 'test'\n ...\n# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes\nok 331 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes\n ---\n duration_ms: 2180.9829\n type: 'test'\n ...\n# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence\nok 332 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence\n ---\n duration_ms: 2428.9374\n type: 'test'\n ...\n# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence\nok 333 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence\n ---\n duration_ms: 1556.1137\n type: 'test'\n ...\n# Subtest: a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid\nok 334 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid\n ---\n duration_ms: 4814.5831\n type: 'test'\n ...\n# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries\nok 335 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries\n ---\n duration_ms: 4.0731\n type: 'test'\n ...\n# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening\nok 336 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening\n ---\n duration_ms: 12050.212\n type: 'test'\n ...\n# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request\nok 337 - actual HTTP file pagination advances over a long file with each returned page visible in the next request\n ---\n duration_ms: 3410.4774\n type: 'test'\n ...\n# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements\nok 338 - later mixed history pages cannot displace the actual module sources and complete requirements\n ---\n duration_ms: 7373.7702\n type: 'test'\n ...\n# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation\nok 339 - a later narrow page of the same file revision cannot evict the wider actual observation\n ---\n duration_ms: 3966.4272\n type: 'test'\n ...\n# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper\nok 340 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper\n ---\n duration_ms: 1467.5338\n type: 'test'\n ...\n# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view\nok 341 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view\n ---\n duration_ms: 2049.7986\n type: 'test'\n ...\n# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes\nok 342 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes\n ---\n duration_ms: 16821.9879\n type: 'test'\n ...\n# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files\nok 343 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files\n ---\n duration_ms: 7236.2834\n type: 'test'\n ...\n# Subtest: isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report\nok 344 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report\n ---\n duration_ms: 31565.8869\n type: 'test'\n ...\n# warning: in the working copy of 'src/空 格.mjs', LF will be replaced by CRLF the next time Git touches it\n# Subtest: worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion\nok 345 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion\n ---\n duration_ms: 7894.0116\n type: 'test'\n ...\n# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation\nok 346 - an ignored external file at checkout is observed and never accepted as pristine creation\n ---\n duration_ms: 4833.6187\n type: 'test'\n ...\n# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution\nok 347 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution\n ---\n duration_ms: 4731.1268\n type: 'test'\n ...\n# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions\nok 348 - workspace preparation refuses known shared-repository activity and preserves archived child sessions\n ---\n duration_ms: 5300.9913\n type: 'test'\n ...\n# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name\nok 349 - compact checkout identities create in deep Unicode source directories while retaining the human branch name\n ---\n duration_ms: 5440.5868\n type: 'test'\n ...\n# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes\nok 350 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes\n ---\n duration_ms: 2485.2391\n type: 'test'\n ...\n# Subtest: a pending source snapshot participates in shutdown and completes before storage can close\nok 351 - a pending source snapshot participates in shutdown and completes before storage can close\n ---\n duration_ms: 2006.4079\n type: 'test'\n ...\n# Subtest: source configuration values stay private and a configuration change invalidates a saved review\nok 352 - source configuration values stay private and a configuration change invalidates a saved review\n ---\n duration_ms: 2404.6565\n type: 'test'\n ...\n# Subtest: workspace review rejects excluded dependency before any checkout\nok 353 - workspace review rejects excluded dependency before any checkout\n ---\n duration_ms: 2350.061\n type: 'test'\n ...\n# Subtest: workspace review rejects large committed blob before any checkout\nok 354 - workspace review rejects large committed blob before any checkout\n ---\n duration_ms: 2230.1343\n type: 'test'\n ...\n# Subtest: workspace review rejects case collision before any checkout\nok 355 - workspace review rejects case collision before any checkout\n ---\n duration_ms: 2859.0228\n type: 'test'\n ...\n# Subtest: workspace review rejects committed symbolic link before any checkout\nok 356 - workspace review rejects committed symbolic link before any checkout\n ---\n duration_ms: 2380.4922\n type: 'test'\n ...\n# Subtest: workspace review rejects external config include before any checkout\nok 357 - workspace review rejects external config include before any checkout\n ---\n duration_ms: 2041.6831\n type: 'test'\n ...\n# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay\nok 358 - actual process exit at workspace intent preserves source and reconciles without creation replay\n ---\n duration_ms: 4966.0767\n type: 'test'\n ...\n# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay\nok 359 - actual process exit at workspace git_started preserves source and reconciles without creation replay\n ---\n duration_ms: 5816.4892\n type: 'test'\n ...\n# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay\nok 360 - actual process exit at workspace git_finished preserves source and reconciles without creation replay\n ---\n duration_ms: 5562.692\n type: 'test'\n ...\n# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay\nok 361 - actual process exit at workspace verifying preserves source and reconciles without creation replay\n ---\n duration_ms: 5708.721\n type: 'test'\n ...\n# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay\nok 362 - actual process exit at workspace registering preserves source and reconciles without creation replay\n ---\n duration_ms: 6096.653\n type: 'test'\n ...\n# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay\nok 363 - actual process exit at workspace project_registered preserves source and reconciles without creation replay\n ---\n duration_ms: 6602.502\n type: 'test'\n ...\n# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay\nok 364 - actual process exit at workspace session_registered preserves source and reconciles without creation replay\n ---\n duration_ms: 6482.765\n type: 'test'\n ...\n# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay\nok 365 - actual process exit at workspace ready preserves source and reconciles without creation replay\n ---\n duration_ms: 5099.8905\n type: 'test'\n ...\n# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity\nok 366 - outside changes at project registration remain unknown and preserve the already registered child identity\n ---\n duration_ms: 4846.2468\n type: 'test'\n ...\n# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity\nok 367 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity\n ---\n duration_ms: 4767.7338\n type: 'test'\n ...\n# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation\nok 368 - stale review, branch/path collisions and forged ownership do not run worktree creation\n ---\n duration_ms: 3336.2073\n type: 'test'\n ...\n# Subtest: workspace project verification is read-only and rejects physical Git identity changes\nok 369 - workspace project verification is read-only and rejects physical Git identity changes\n ---\n duration_ms: 4389.6571\n type: 'test'\n ...\n1..369\n# tests 369\n# suites 0\n# pass 368\n# fail 1\n# cancelled 0\n# skipped 0\n# todo 0\n# duration_ms 643373.065\n", + "sourceRoot": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738", + "directory": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4", + "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" + }, + "inputs": [ + { + "path": "index.html", + "bytes": 411, + "sha256": "893c264c5c1293d6af54a6ca65280cf637b5afffee3cd2156ff88e4a44c370c5" + }, + { + "path": "package-lock.json", + "bytes": 79507, + "sha256": "89318a78d080b8d5b4a2a4d9188e687f0b42620c0ac6451b6cfc908b7aeb051b" + }, + { + "path": "package.json", + "bytes": 2005, + "sha256": "3d89c54106223fcb89c1a9fd98e5755ee0f06fcb018128ed18570093a15b3144" + }, + { + "path": "scripts/Start-Workbench.ps1", + "bytes": 3211, + "sha256": "36d8ab194974369afa47ff717e60cad763432ee1f1abb6ccc4e6b1b6b11da253" + }, + { + "path": "scripts/Stop-Workbench.ps1", + "bytes": 980, + "sha256": "f6d12d32006c17fcb20192a73b762592f900ddfcda0cabda6f202e37405d1331" + }, + { + "path": "scripts/build-server.mjs", + "bytes": 553, + "sha256": "67e4ae3f5bd9214bfbf2596e3fb9c2af465ec7364293d37da07c7810c789d15e" + }, + { + "path": "scripts/bundle-browser.mjs", + "bytes": 2629, + "sha256": "c9bd500e469d5aa60a69a35d5863a5f2d56b336cbd8f2d5268b5e05f0687d23b" + }, + { + "path": "scripts/bundle-rea.mjs", + "bytes": 5700, + "sha256": "90fbc4af57eb2e92d4d92de5be5ac26eb8c99f132efdafe8f3e133ec1db7ffbe" + }, + { + "path": "scripts/engine-fixtures.mjs", + "bytes": 5241, + "sha256": "8ca536f1a6f4edb6a03b0508e6f175879eeb39a835149f4f6c8ba806e07266e8" + }, + { + "path": "scripts/inspect-ui.mjs", + "bytes": 1187, + "sha256": "81a6e6f96aae44b60c9f382e53d54f673868b3705a4c3eb1d0107c11ff790b88" + }, + { + "path": "scripts/live-react-client.mjs", + "bytes": 4278, + "sha256": "6c01ae7b2be7e2b82831c718e72bebe353bab864f97373ed95c5d478ac28b32b" + }, + { + "path": "scripts/package.mjs", + "bytes": 9925, + "sha256": "22ffb0a5dc23d654ac4bf6e9d261fc6dd034d4f17a402b5a5356bc08f24365b2" + }, + { + "path": "scripts/python-check-runner.py", + "bytes": 9553, + "sha256": "17bd6fd64ad93b8f806e0f5d325e75fd4534c065f4fcb597ad45fb9152caf657" + }, + { + "path": "scripts/qa-evidence.mjs", + "bytes": 679, + "sha256": "d887eb11f5e0a4f64540db1bcb693d2b2adbdbd97ed8f7a0abfb46be1ad544e2" + }, + { + "path": "scripts/qa-python-requirements.txt", + "bytes": 14, + "sha256": "bf4dc0555928a3facf67b3370001388d4b65e69a071c339f8b201310bde4486a" + }, + { + "path": "scripts/research-fixtures.mjs", + "bytes": 3712, + "sha256": "ba1f5644045ddba894a787cc4d9fa85c9a7e00730e3ea2e9b18d594a43498a8c" + }, + { + "path": "scripts/tune-styles.mjs", + "bytes": 1369, + "sha256": "8909eaaff060753745d7d6945377689ca531d784390cdd7d84acf97551d7b1c0" + }, + { + "path": "scripts/upgrade-running.mjs", + "bytes": 12304, + "sha256": "fd3d8e026b2b135ad6b145a4235918385511e0d8d6f58a8fdd059d686098e943" + }, + { + "path": "scripts/verify-all-ui.mjs", + "bytes": 8760, + "sha256": "681e94b0457b3035e3972de70e555055efd469eeaf0ce7884f39f427bafdceda" + }, + { + "path": "scripts/verify-archives.py", + "bytes": 4529, + "sha256": "66e5d6b31e04e4c143bf73860635f0da2ea1f707822ca638bc4197a397ca4dde" + }, + { + "path": "scripts/verify-browser-ui.mjs", + "bytes": 14638, + "sha256": "c4a99fcf45fc0e1d39024937d481119965349c486422a14b3084264539c4157a" + }, + { + "path": "scripts/verify-browser.mjs", + "bytes": 10768, + "sha256": "8ccbe961ce26363079fc8ea30559e57ee78f88926b438e1004d5b3528beacb76" + }, + { + "path": "scripts/verify-change-sets-ui.mjs", + "bytes": 15972, + "sha256": "87c60f25d2d4c226fecd35c253a68368a3c53e33aa2b8b332c72760490705866" + }, + { + "path": "scripts/verify-context-ui.mjs", + "bytes": 18445, + "sha256": "f78fed61f844edaa674db9c768247a45b7eb434fe94b1b29b3a5e3798922272a" + }, + { + "path": "scripts/verify-delivery-ui.mjs", + "bytes": 22757, + "sha256": "eae0e07b901f0a3da4d595bbc8e214e032d7da45d7d8ea033c034ad45dc34c3d" + }, + { + "path": "scripts/verify-diagnostics-ui.mjs", + "bytes": 15521, + "sha256": "476d284fc1b8c086f8d7f44013a44d200ec5b5df2d8b58e52caaedd46e569ab0" + }, + { + "path": "scripts/verify-engines-ui.mjs", + "bytes": 15763, + "sha256": "b1ae2b6274d2584ba190faa1818f53f1bc775430f9140cb68ca77d9952756f2e" + }, + { + "path": "scripts/verify-engines.mjs", + "bytes": 4748, + "sha256": "c1f0d9949230527cc4933a90e64a68053ef8bc040b14384119998a5a2f223b4d" + }, + { + "path": "scripts/verify-execution-ui.mjs", + "bytes": 15157, + "sha256": "f78149dda36baea05cd1f7c36dab0301e3c1c94df70cefb1bb12f51313d383be" + }, + { + "path": "scripts/verify-index-ui.mjs", + "bytes": 13822, + "sha256": "04f1b925aff59f06583325d18e69a6160bfae98e87254b3ee2e6fd0dabccdbfb" + }, + { + "path": "scripts/verify-live-browser.mjs", + "bytes": 11765, + "sha256": "b1bb7e3ac8ac6c1abec0c90b996bbde0a335e87acb956a05918fc31245ee0b33" + }, + { + "path": "scripts/verify-live-delivery.mjs", + "bytes": 24628, + "sha256": "4c45acd05841ddf2a6e0a04ee1d0a9f4c003e34d794318bfe3892a29d474117e" + }, + { + "path": "scripts/verify-live-engineering.mjs", + "bytes": 18301, + "sha256": "2e42a1347069c56beb4022627f760a2088751d4f0829606b49d2edd0833d934c" + }, + { + "path": "scripts/verify-live-model.mjs", + "bytes": 5607, + "sha256": "848495e2488125eb5e79c9d8b121025f9f740551535dc8529b415b4246da455b" + }, + { + "path": "scripts/verify-live-session.mjs", + "bytes": 6727, + "sha256": "f71f22f2355d499afa501f9ba37a04f8b8cf5d404fdfe95b65cc1d324775ac9b" + }, + { + "path": "scripts/verify-live-task-plans.mjs", + "bytes": 13181, + "sha256": "577fc325a6b13f7cd21fb8b1ab96f8940afe94e65bffa74046b47af572b1c510" + }, + { + "path": "scripts/verify-mcp-recovery-ui.mjs", + "bytes": 6336, + "sha256": "b11e321e0d92efb57d8e76b612c053e6a0229f0f3641721c606a28a61fe12a18" + }, + { + "path": "scripts/verify-mcp-ui.mjs", + "bytes": 9714, + "sha256": "c3c93d4ea8109dce1bfb4c91bf3a8b11dc2c7bbee3986c55ed2a4fcde0446d34" + }, + { + "path": "scripts/verify-model-center-ui.mjs", + "bytes": 8760, + "sha256": "d4c13f9e328172f973143f7333cdc4f5627c7d33f188f59a6588c1cbd1f8745a" + }, + { + "path": "scripts/verify-project-memory-ui.mjs", + "bytes": 8405, + "sha256": "b197345800d805ca3e52094ea660f8eb8d4d90defde2c49dc1a17a4b97270bdb" + }, + { + "path": "scripts/verify-python-ui.mjs", + "bytes": 11489, + "sha256": "676e4222a25ca68ed5bbb6661b9f7ec5eac4abaa9de70d9a5eb07a3429ba2457" + }, + { + "path": "scripts/verify-rea.mjs", + "bytes": 5166, + "sha256": "cdca5f73ee9f5b2b1fc4cd58ce98a7c0fcd551164879ae3192d67edd8e69491d" + }, + { + "path": "scripts/verify-react-delivery.mjs", + "bytes": 13013, + "sha256": "51a6c000d6ff148204d500b8505e2f7589f55a68947b9eabd4097ed0e477d118" + }, + { + "path": "scripts/verify-release.mjs", + "bytes": 14613, + "sha256": "480d101518119dc1dda7bc4e520b60079d583212d07626a49c11ffa8279ebcef" + }, + { + "path": "scripts/verify-research-ui.mjs", + "bytes": 18573, + "sha256": "0844a6d22e843123afc0d133302096a08c35b9cb7d9dd3bafacf85a2a50b260d" + }, + { + "path": "scripts/verify-skills-ui.mjs", + "bytes": 7956, + "sha256": "2139b2caa764c17752edb13f8cc43e0d4643e9c0d4d47c34e6c95b0374efd974" + }, + { + "path": "scripts/verify-source-package.mjs", + "bytes": 10176, + "sha256": "0ed25b24eff2f95fa6c890b22ad72c6b7318bb8e80b1c46993036f0a7bc50ff0" + }, + { + "path": "scripts/verify-task-checkpoints-ui.mjs", + "bytes": 6176, + "sha256": "2af7d9abf21b2a13a618ed080e324f61c21a42a386d09c5bd62c7bdf70ec5de2" + }, + { + "path": "scripts/verify-task-plans-ui.mjs", + "bytes": 16078, + "sha256": "7a0d5a0c5c59040bd203c65453a0ff9c6282e9bd46c14b573a67a59a8920a5fa" + }, + { + "path": "scripts/verify-tests.mjs", + "bytes": 5124, + "sha256": "3e9140831477df004d39187e240ce8e27e8680d051a9353dc6b9b17de81994f4" + }, + { + "path": "scripts/verify-ui.mjs", + "bytes": 18880, + "sha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6" + }, + { + "path": "scripts/verify-workspaces-ui.mjs", + "bytes": 15427, + "sha256": "fdf5900e0936b681d030f18a7a5245beacf8ab091b79a495ca823df65e8bb4a7" + }, + { + "path": "src/client/App.tsx", + "bytes": 61296, + "sha256": "678223d317c091e2dceef71dfb326eba47ceb57551375371e70d84cbef74882b" + }, + { + "path": "src/client/BrowserPanel.css", + "bytes": 5050, + "sha256": "3032abddc1cfeea3100cb4b34bb2e9e25e965f470c4fd38c73d564dfc80f3450" + }, + { + "path": "src/client/BrowserPanel.tsx", + "bytes": 16962, + "sha256": "24a7479a2740ac72de22dadb556565904fb4525117cddc2a08ab1b766437ce30" + }, + { + "path": "src/client/ChangeSetPanel.css", + "bytes": 4477, + "sha256": "c1ac9307b78e4e42159398e499074d85da395faf7c88f2f485c6b7901d142459" + }, + { + "path": "src/client/ChangeSetPanel.tsx", + "bytes": 11104, + "sha256": "b3a3b3e73bf74a23c08f74d124fe98c6b45e0c048d3fabb745fd488140d58f61" + }, + { + "path": "src/client/ChangesInspector.tsx", + "bytes": 3324, + "sha256": "5799507f52e1414ec573eb1d0452bb3c173728836d3c1644c760b31cab4a3ee4" + }, + { + "path": "src/client/CodeIndexPanel.css", + "bytes": 5796, + "sha256": "76f6f2b32e25df3b3f4c8761273de4963b7b25dff01cbe97b2f5171ec8358286" + }, + { + "path": "src/client/CodeIndexPanel.tsx", + "bytes": 7715, + "sha256": "2574080bbb0aa9ff05571ef406dadd3c008f792cf2443ff1f779f0975a6d97d4" + }, + { + "path": "src/client/DeliveryPanel.css", + "bytes": 5070, + "sha256": "8c12813290c171b616ffb36c002395fc40ff2c7d5b63cd2f13613be435a2d3c6" + }, + { + "path": "src/client/DeliveryPanel.tsx", + "bytes": 14267, + "sha256": "23a9c1519c6b94508f2cabaedd47ccf43f0cdae26d5f956d81b3c26f37f6d531" + }, + { + "path": "src/client/DiagnosticsPanel.tsx", + "bytes": 3823, + "sha256": "a5746d019da37c99af60c69f556b007ea307e2f3a02fcde504b547ed468dd07f" + }, + { + "path": "src/client/EnginePanel.css", + "bytes": 6275, + "sha256": "5a0fc3b6fab7038751f346cdd40e6b4540e8886c0f0c54478c09c18eeaeec1d3" + }, + { + "path": "src/client/EnginePanel.tsx", + "bytes": 12950, + "sha256": "d36f3058ab8e0a5d327f68f6894d34fc4b1f721949c873e1356dcb28907a4e07" + }, + { + "path": "src/client/McpJobHistory.tsx", + "bytes": 7508, + "sha256": "207ba78dce96c85dedf7ff34f7678dff1e925118fb93dd1d5a144f38c7aaf618" + }, + { + "path": "src/client/McpPanel.css", + "bytes": 9547, + "sha256": "e1c89f3229acb0bb739fcf91e605d09f7d8f38f4f367da1f11835b2b9452538d" + }, + { + "path": "src/client/McpPanel.tsx", + "bytes": 15591, + "sha256": "f1ea14216c4340f6cd76b267763a468bf0d311dd6f8b273afe3ee9cf6768a260" + }, + { + "path": "src/client/ModelCenter.css", + "bytes": 9222, + "sha256": "99f81bc87f634fa77bedd00247500b99314412db36574a58e6e382cca19f903f" + }, + { + "path": "src/client/ModelCenter.tsx", + "bytes": 22142, + "sha256": "bde2746b5e2d3595a5459dff3f6154c44d67853cc57bd8aa3c744428bac3823a" + }, + { + "path": "src/client/ProjectMemory.css", + "bytes": 4322, + "sha256": "0d6c9a23afafa77e7230edd9294299a3d233aa7b49c191d522ee9c106839a1f1" + }, + { + "path": "src/client/ProjectMemoryPanel.tsx", + "bytes": 7381, + "sha256": "b7c140f126bc2d48df00fe4111517e3ea2f43926d52797d26733e1f2522f6a03" + }, + { + "path": "src/client/RequestContextPanel.tsx", + "bytes": 9245, + "sha256": "9b7bd92ff4afc6a8e4c1fd129dea053acb8b135330582643beef62608b737e79" + }, + { + "path": "src/client/ResearchPanel.css", + "bytes": 7271, + "sha256": "f24f8eb283c0b419037adcd680bc1bbe84002abf661bfda94891dcea5fc92682" + }, + { + "path": "src/client/ResearchPanel.tsx", + "bytes": 16684, + "sha256": "cae237fc267a491db18f24f88e0b6926a635225886bfa58683a37f6d4586c8e1" + }, + { + "path": "src/client/SkillCenter.css", + "bytes": 6453, + "sha256": "d9f79bba3be7369a0231434aa29fe061e0c5d1f792aeb7e15e3f2a7744165242" + }, + { + "path": "src/client/SkillCenter.tsx", + "bytes": 9303, + "sha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10" + }, + { + "path": "src/client/TaskCheckpointPanel.tsx", + "bytes": 5367, + "sha256": "77b552924379531eff51c81c5bf4e2512c1201f39641245c781a468e6a7e397a" + }, + { + "path": "src/client/TaskPanel.css", + "bytes": 8906, + "sha256": "6dc737d84406fafd2f1b36ba1eaf02c8b0f59594b30a1fadcf2d3451ada285db" + }, + { + "path": "src/client/TaskPanel.tsx", + "bytes": 18980, + "sha256": "cb781e0c81f4f24b822b4b7472bd4d14cc6591f78a96558f259bc0bd587cb3ec" + }, + { + "path": "src/client/TaskPlanPanel.css", + "bytes": 4257, + "sha256": "e47eb1195a61400d60817de793893d9e4924f334bdf452ffb744ed69741c43fc" + }, + { + "path": "src/client/TaskPlanPanel.tsx", + "bytes": 16038, + "sha256": "3ead0b021ae550b0bc3891b8e852c297f05f895ce3516f693a91d23456ebc1f1" + }, + { + "path": "src/client/WorkspacePanel.css", + "bytes": 3743, + "sha256": "d8c4558f6c559ff8b4bbc7723aca08e4e37f8fef8f5b8d5619faec8332314ba3" + }, + { + "path": "src/client/WorkspacePanel.tsx", + "bytes": 10026, + "sha256": "c91d097edd5e044f72583bdccd39848f35a5b82c4d9abf7c09648e21ecfdb8c2" + }, + { + "path": "src/client/api.ts", + "bytes": 3058, + "sha256": "6e706020502cc3e079ddc46f4f843571cfb883852fb7ea21bd2c3c9ff463d56c" + }, + { + "path": "src/client/components.tsx", + "bytes": 13189, + "sha256": "7b735a151ceb1889702f3127a15a8a2918f6fba7140304c3b81b5662f1b43741" + }, + { + "path": "src/client/control-console.css", + "bytes": 4836, + "sha256": "bbb0f00ff90ea4c8d0f969b4fa95df4e95413b97ab28a204a893a99671a10bc7" + }, + { + "path": "src/client/main.tsx", + "bytes": 256, + "sha256": "6dec6d76306f0e47b1a9e77004377daa5312270d519a685f169c025a9e071792" + }, + { + "path": "src/client/styles.css", + "bytes": 38537, + "sha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218" + }, + { + "path": "src/client/types.ts", + "bytes": 24332, + "sha256": "ffc135242245843efe42b8df2614afafe7b8c8c98731dfc3fa6b10e1b9d8cfd8" + }, + { + "path": "src/core/browser/browser-driver.mjs", + "bytes": 18254, + "sha256": "d63e3ae49bdec13f2f86923c21d4af4d7f1ea1b07c768be3cc85b4833836bdd2" + }, + { + "path": "src/core/browser/browser-manager.mjs", + "bytes": 24633, + "sha256": "0efc0e30f19a8649c964e1193c455d6cc6f32bfd4a4a5e18fc6ff8014d67b820" + }, + { + "path": "src/core/browser/build-snapshot.mjs", + "bytes": 4309, + "sha256": "2424f37847e72621327b5c0157f9fc03c1e7dd266ca71292b4b70571f17170a9" + }, + { + "path": "src/core/check-runner.mjs", + "bytes": 20806, + "sha256": "e37224b56ba664af7d99e8ac1f3270aa15ed9d1d48239e26109e7ff1cf16a28a" + }, + { + "path": "src/core/context/project-index.mjs", + "bytes": 18380, + "sha256": "acaa896eca725bcce13a6d34a46267ce70a8a824eac8ca2ffccb91c4d18bd304" + }, + { + "path": "src/core/context/read-budget.mjs", + "bytes": 10437, + "sha256": "7544a22f8a0f2aeb9f06cd3d43f9eae77cc3141503930571a8c170b1ff4bb0cd" + }, + { + "path": "src/core/context/request-plan.mjs", + "bytes": 36015, + "sha256": "3d8c158f8b0d7e696a311f642a95f184cf69d38db9859498dbb8d2db6ab85108" + }, + { + "path": "src/core/context/tool-feedback.mjs", + "bytes": 9598, + "sha256": "7523f2ef18d9fea975d15e665c8c122293fdf52f3c7093ad08e16b8a83b6c95f" + }, + { + "path": "src/core/context/working-set.mjs", + "bytes": 10948, + "sha256": "61220be2142fff4194b633cf85e39f87c0a71ddf0745ce1406a5bc54977bdb0a" + }, + { + "path": "src/core/delivery-report.mjs", + "bytes": 22037, + "sha256": "a0bb895459be2805684b881f80674f5592c2d55c285adcc30a0657c3a9c7bb5d" + }, + { + "path": "src/core/engine-manager.mjs", + "bytes": 12455, + "sha256": "ec29a945c84ee79a41d30ac3a70296281bdd7d7898cc727a85bb6d78af62f015" + }, + { + "path": "src/core/engines/deepseek-adapter.mjs", + "bytes": 10977, + "sha256": "b5d3e3f1ba74b8d15b002594f13652bbc98761226a3e5e3fb408071762958fa9" + }, + { + "path": "src/core/engines/deepseek-installation.mjs", + "bytes": 5979, + "sha256": "5bca6da6d1fd972405762b81a4be7936ac597337e310aec2a7d88aa9e5cce7a9" + }, + { + "path": "src/core/git-delivery.mjs", + "bytes": 40952, + "sha256": "4c53fcb82813a559b1e61615fb879dd7afe48686832d2ffd992f81dc56579bad" + }, + { + "path": "src/core/git-process.mjs", + "bytes": 2655, + "sha256": "80547ec8928610ac4df5a05c5aef12d1aab0dca9e7b1def2773fc745f5adf5f5" + }, + { + "path": "src/core/memory/project-memory.mjs", + "bytes": 13871, + "sha256": "9c7da0ef9c7f36b431015fd4414f55304f8d5e25a61bc527fb7e3be0b7971e51" + }, + { + "path": "src/core/models/config-import.mjs", + "bytes": 8293, + "sha256": "70e5884606565d930685b0d0b55f73d9ceaf00dd3525f0fe6d2fdad2f87366bf" + }, + { + "path": "src/core/models/model-hub.mjs", + "bytes": 17756, + "sha256": "652581d91c8c0e9f1059880aa6ee31016790e06e53e20fff18d36c2c56bad379" + }, + { + "path": "src/core/process-environment.mjs", + "bytes": 910, + "sha256": "05f7ca9bad79ed96a184c96643edffc320aef45567e888341531448f23c89702" + }, + { + "path": "src/core/project-inspector.mjs", + "bytes": 10892, + "sha256": "9e81ed2928fc5dcdb20915a406a8cdc69068deb04fd9d36d0792a86598405782" + }, + { + "path": "src/core/python-project.mjs", + "bytes": 4721, + "sha256": "74e09a96f2e1970b155d37af176379807add0d5a05f72ccd9491d4d494d58707" + }, + { + "path": "src/core/python-runtime.mjs", + "bytes": 12568, + "sha256": "9e9f1b9128295f46404839ad95eaf8bcad60a8c4964756e7c1a1b21cc4add0d7" + }, + { + "path": "src/core/research-manager.mjs", + "bytes": 19987, + "sha256": "15981370de1f02db4acec2c3e1450d068236e1f6ab70f677ec8617aa968fc2dc" + }, + { + "path": "src/core/skills/skill-registry.mjs", + "bytes": 15494, + "sha256": "63e435d65e3dfe7dff1b1711590b5a4a5ca2efddaa67822087de06facdadf3bb" + }, + { + "path": "src/core/storage/artifact-store.mjs", + "bytes": 2918, + "sha256": "2934d31a28da215f7ea73a3b5e56d106b723b34539ea8605d523b121762e488a" + }, + { + "path": "src/core/storage/legacy-import.mjs", + "bytes": 4825, + "sha256": "aa6a6b95d4049c5091d39e8c65ee301a0d6e533e081da59c87f2733bfb5a15ed" + }, + { + "path": "src/core/storage/state-database.mjs", + "bytes": 8565, + "sha256": "2a38f7564df44c4ee5183d850064be1d46fba7e072e2b87f73afb8e1a85a1517" + }, + { + "path": "src/core/tasks/task-checkpoint-manager.mjs", + "bytes": 13524, + "sha256": "2f50f9de2e6b8c90376028ed2814eb795633e1ea917ab944a977299220ad820f" + }, + { + "path": "src/core/tasks/task-plan-manager.mjs", + "bytes": 22026, + "sha256": "4feafa9462ab57f694854c79c846a9ba58fe9313b343341f2ca2a334255eec24" + }, + { + "path": "src/core/tools/mcp-contract.mjs", + "bytes": 8366, + "sha256": "4860792132e2d18caa075ddca8c24687b3692c005a1c6c4c81933e6dc9e0a6bc" + }, + { + "path": "src/core/tools/mcp-registry.mjs", + "bytes": 26252, + "sha256": "8f52b11ba37d1c350aa279e4890a0c5b00fff3b77fc4f2211a4ea1c07bbadebc" + }, + { + "path": "src/core/tools/mcp-stdio.mjs", + "bytes": 8109, + "sha256": "1c1081b9356855db5c8964ac5b9f5fb2c79fef5323ff1f933447a06f77cac447" + }, + { + "path": "src/core/tools/rea-adapter.mjs", + "bytes": 9010, + "sha256": "36f7d2a095fcaef4e1ca056a1f2475e0b15fe1fc48d0179589b41abadf39c6c4" + }, + { + "path": "src/core/tools/research-output.mjs", + "bytes": 1750, + "sha256": "b9d53487192f12b0d2b0f0922c918b5b3d88a276777cd64903395800ff07c1c0" + }, + { + "path": "src/core/workspaces/change-sets.mjs", + "bytes": 25967, + "sha256": "759315b541c127b9eabb411f9b61975dff88daac063af63520cac81f7f8a18c0" + }, + { + "path": "src/core/workspaces/git-workspaces.mjs", + "bytes": 36568, + "sha256": "2b123a1e92e7f07fbfdd650ccbf44908d6b2e1d7504f893034e12a0cd0f32839" + }, + { + "path": "src/server/app.mjs", + "bytes": 50418, + "sha256": "de400aa4380343943f967f9a6fcec0f71d8650853bd8eaf08a0cfc4e064bbb2a" + }, + { + "path": "src/server/diagnostics.mjs", + "bytes": 7965, + "sha256": "55bd70f30f0e6666374965ea96e59b98fd85d223dacb863377a36c2be427c3fa" + }, + { + "path": "src/server/files.mjs", + "bytes": 14914, + "sha256": "65e5386d075536b4a341f62b03eceba88e08b13201c426c503a2e260b6a55b9d" + }, + { + "path": "src/server/hot-upgrade.mjs", + "bytes": 6364, + "sha256": "5fc691140bc7b380a0fbf412c4a709a684057896a7d8cdb58db55ac96d8f68f7" + }, + { + "path": "src/server/index.mjs", + "bytes": 2668, + "sha256": "16b9d751870188d185ca6b03429376f19b5e7b94fd91a6ce401a096fae74ef64" + }, + { + "path": "src/server/provider.mjs", + "bytes": 28611, + "sha256": "3072dd4dfaa4053e75bd57916a60a39a98c29bc2b08fe4fbbc0ff4002aa61749" + }, + { + "path": "src/server/runtime.mjs", + "bytes": 55479, + "sha256": "e3ca70df57743a185d40389a127e34b6895862954b0f5bc080f499dbd1947a1f" + }, + { + "path": "src/server/store.mjs", + "bytes": 41695, + "sha256": "1417841521a31d63672e74cb986614ceb5bb9ba8fbb0e9b8dcc92e02dcff0646" + }, + { + "path": "src/shared/contracts/browser.mjs", + "bytes": 4775, + "sha256": "af8f71616097dbbb08bde31bf1cc42c90708802f17ad89b4ba220351fb30f439" + }, + { + "path": "src/shared/contracts/change-sets.mjs", + "bytes": 1189, + "sha256": "01586cdcffe00129c2b61e4cbf4a622b22306cd5a893620f4a7db441f978f1da" + }, + { + "path": "src/shared/contracts/delivery-review.mjs", + "bytes": 1368, + "sha256": "1b17efdfa2549801db72eabe439907419a4d85ea07e4d010563db2d483d565f9" + }, + { + "path": "src/shared/contracts/engines.mjs", + "bytes": 2234, + "sha256": "8d52facab1b7c1941637ae86756e73a7050467be04a0e036259bff6aad42c42b" + }, + { + "path": "src/shared/contracts/execution.mjs", + "bytes": 5035, + "sha256": "2ceb700eaa3f8f2adf01b348575f7deb381f970e30eabe553e3ee30840d699a5" + }, + { + "path": "src/shared/contracts/model-request.mjs", + "bytes": 901, + "sha256": "3744dfa7302dde72d1c24c54e7c00672ff063b45786add2fb19d46233b759e78" + }, + { + "path": "src/shared/contracts/research.mjs", + "bytes": 6860, + "sha256": "eb970b52f923d7dbfd8e7da49381ce135b8a2ae9d04c0d4321958a2e93d12003" + }, + { + "path": "src/shared/contracts/task-plan-tools.mjs", + "bytes": 3029, + "sha256": "b14392919e1b551751a6c311004d9d200bc494a7873987c8c0f34a8c4bec1ec1" + }, + { + "path": "src/shared/contracts/task-plans.mjs", + "bytes": 7290, + "sha256": "c312f4511f495b90ec8983e5c8ecc357e85f67d97b8deda2d052651c3f491adb" + }, + { + "path": "src/shared/contracts/workspaces.mjs", + "bytes": 3975, + "sha256": "4cd6873ca73de9dac5e73f3aaabe062674c5ca1d50c28a2e2b6eb9e138c32be9" + }, + { + "path": "tests/api.test.mjs", + "bytes": 12277, + "sha256": "86fbee40af8a7afb6e295ac52c7a46e3e4476c4667543e9756d916fbce8e335f" + }, + { + "path": "tests/browser-api.test.mjs", + "bytes": 9597, + "sha256": "30c8f5adb89bd60277c48e9f4e1e9f5c3a0fc8652cda447a4d6c273210e2576b" + }, + { + "path": "tests/browser-delivery.test.mjs", + "bytes": 4085, + "sha256": "21c1280d95f070504840c94c4bdf556559653636332f8e38d355144fc080dc2e" + }, + { + "path": "tests/browser-locators.test.mjs", + "bytes": 4926, + "sha256": "cad3236d3ac1e17524ad304e159659d4009ce3ae265ccb9047a36df00dbd31f3" + }, + { + "path": "tests/browser.test.mjs", + "bytes": 8150, + "sha256": "2e4a0d1d5136a9729b015b977af9344a9802a2015583d7e2cf5825d606888242" + }, + { + "path": "tests/change-set-api.test.mjs", + "bytes": 12753, + "sha256": "44170084aea8e31cfd4c59e4c96006413f0f66151e6241d27b7a0aacf5d1a328" + }, + { + "path": "tests/change-set-recovery.test.mjs", + "bytes": 3435, + "sha256": "8cfa9ae1526975111f6ec7fa60afb79e40a994c5fdbf86abcf1edd2cc69077e0" + }, + { + "path": "tests/change-sets.test.mjs", + "bytes": 14054, + "sha256": "b5a72b65da8f6ee239c8d6bd51e3dcbc901f1e43b16708548f2f082eccaeaa20" + }, + { + "path": "tests/checks.test.mjs", + "bytes": 21968, + "sha256": "d7936ef6fa5c0421976cdb30e435a910e7a0c461829e991091b4c6ee00e924ab" + }, + { + "path": "tests/code-tools.test.mjs", + "bytes": 7518, + "sha256": "f6c120892e86ec21c67b010e256e359b2f1ba7196b48937961f4e8c62deeef93" + }, + { + "path": "tests/config-transaction-api.test.mjs", + "bytes": 3506, + "sha256": "0e9f7d2e2f5f8cc0510a6e3f96f03e921b758aac78de659b3d8f999c0abaa4f8" + }, + { + "path": "tests/delivery-recovery.test.mjs", + "bytes": 10733, + "sha256": "bec27e3d4bdd8777d7a08e146019e79436cbb463131cd2b07f6f819e002652b1" + }, + { + "path": "tests/delivery.test.mjs", + "bytes": 22944, + "sha256": "d6e05886de2d27395cc6f2d0cd8581e87150ac95a7b017337fd59d1ce388c489" + }, + { + "path": "tests/diagnostics.test.mjs", + "bytes": 13318, + "sha256": "88a3b333ddc9da6c65eaafc1e73b16e28c79e617d9a8348d1a7b925b1cf99615" + }, + { + "path": "tests/engine-api.test.mjs", + "bytes": 5089, + "sha256": "da7dd728a5a30039cda74e5b67a451908384527d7946600fc2170335cc2e64cd" + }, + { + "path": "tests/engine.test.mjs", + "bytes": 14173, + "sha256": "77a917ae867a4b7e509c10e10f36b75f5755e18066b44f6ebd73552cf9355e03" + }, + { + "path": "tests/execution.test.mjs", + "bytes": 14144, + "sha256": "f3004d5cc4fcf5ac65eea0c24c864fa63227d9d1127f32b41621e6c3b7bc52ba" + }, + { + "path": "tests/files.test.mjs", + "bytes": 7050, + "sha256": "b0a4b9c385c5d0ed8e4a8bf6b43c2b679488882a19f25572d7b89a1ed3d5b378" + }, + { + "path": "tests/fixtures/browser-project.mjs", + "bytes": 1972, + "sha256": "cb682a64f65953bfcdb577768b82b1f7a7e86e530379ea8580ecdbf864132ff2" + }, + { + "path": "tests/fixtures/change-set-crash-worker.mjs", + "bytes": 909, + "sha256": "0f564eea935f576de9ef6db7a09cc95db2f95a38b654d476de67e3b5eb166c96" + }, + { + "path": "tests/fixtures/change-set-project.mjs", + "bytes": 1688, + "sha256": "b597f7ec0d32975673fdc36284d6688af401040b06e6fe8370a3e565a98016c2" + }, + { + "path": "tests/fixtures/check-crash-worker.mjs", + "bytes": 654, + "sha256": "3de4749fb0b016e44c16029a71366231acd021c2196b075029d55d767e0c4c84" + }, + { + "path": "tests/fixtures/context-plan-crash-worker.mjs", + "bytes": 558, + "sha256": "9ebc5980e78d39a3d382d6336eb021e2088baeff4ff670f427617c01c4e509d8" + }, + { + "path": "tests/fixtures/core-crash-worker.mjs", + "bytes": 2852, + "sha256": "ff6a92e7600844f47a49eecdf800a3e7219ee193547cb0008568a578854303ed" + }, + { + "path": "tests/fixtures/delivery-crash-worker.mjs", + "bytes": 744, + "sha256": "a2f5e2ba4382e6ef0a614a9d07928a06a07a74a748441b1404570dd714428492" + }, + { + "path": "tests/fixtures/delivery-project.mjs", + "bytes": 4095, + "sha256": "578fa6074b9d4d375a31f94d02b34acada63e85df1dce22ac7dfbd259c5d55cb" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/README.md", + "bytes": 346, + "sha256": "ec995a6accae2d5bdd4e43b1a698ea5a3b13241cfb70d57dc103650d665c3d1b" + }, + { + "path": "tests/fixtures/legacy-artifacts-1.9/artifact-store.mjs", + "bytes": 2655, + "sha256": "b5e7d5dba4614c9e93aa118e1765266be22b7871c0751aa1b902c5ad358ab10f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/README.md", + "bytes": 524, + "sha256": "e5d044b72eea8ad836196a8e86abab366453b14addd9f206f9a2da75511da52f" + }, + { + "path": "tests/fixtures/legacy-hot-1.0/dist-server/hot-upgrade.mjs", + "bytes": 95288, + "sha256": "0a701a6cb3063bf8459bdaf2adb6e93af33682592ab67f3c69e96a32c8b92148" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/README.md", + "bytes": 536, + "sha256": "ebee2fdec8207c66d172604f7fa28d10be1c7f2a01e26f92c6e4c41da0d6aabd" + }, + { + "path": "tests/fixtures/legacy-workbench-0.1/dist-server/server.mjs", + "bytes": 73087, + "sha256": "00770b85ea3372259b5a481616616aa1dc1bdefac00c210b5b307898f63ad934" + }, + { + "path": "tests/fixtures/mcp-host-crash.mjs", + "bytes": 1238, + "sha256": "a7ceecb6419270bb918e72704d0cf124623afd037da433b7b4c9af6f769aafa7" + }, + { + "path": "tests/fixtures/python-project.mjs", + "bytes": 3277, + "sha256": "4b20f285de410302839782d544257483c666609ae519c1a6facea5a8dbcaecc2" + }, + { + "path": "tests/fixtures/registered-mcp-server.mjs", + "bytes": 2200, + "sha256": "e6479755be0d7d0e08a7f98cbc59cf4ea494c8092bdab40e5dff752d5b8840c1" + }, + { + "path": "tests/fixtures/research-mcp.cjs", + "bytes": 1744, + "sha256": "8fe82e55327f6e32ab2bafc66d9374b4b542959656d5a341c50779d1ae579458" + }, + { + "path": "tests/fixtures/task-checkpoint-crash-worker.mjs", + "bytes": 884, + "sha256": "835b95c4baf1f4a69228f88e7da99092dfc77238d2cbea6b08600bdafc18017b" + }, + { + "path": "tests/fixtures/task-plan-crash-worker.mjs", + "bytes": 1089, + "sha256": "a3f0b614dfdc2c14906fe0435a7b8fb07d3267cd0732f63e174c44c59909cd6c" + }, + { + "path": "tests/fixtures/task-plan-fixture.mjs", + "bytes": 1698, + "sha256": "036fa5f0e1dc3a55a2adba55700d4f597396fbf5cf216fc2404ec101df2544d9" + }, + { + "path": "tests/fixtures/workspace-crash-worker.mjs", + "bytes": 1006, + "sha256": "c12bc83f501fc2eb522c6f30235d2e089ab6129a96c44e0d4edb4fb135d9215c" + }, + { + "path": "tests/fixtures/workspace-project.mjs", + "bytes": 995, + "sha256": "69002bf2e6940f314aec3e8d7f758e53d6376f0814e6b4e1b16505abbe46a699" + }, + { + "path": "tests/helpers.mjs", + "bytes": 6248, + "sha256": "71ac890f4278cb664bbc313dfe1df2cd063e77544a65f528c6428a822da2425b" + }, + { + "path": "tests/mcp-registry.test.mjs", + "bytes": 22599, + "sha256": "b6059a9c3966ded29450e85e5a43ad088a181049d218eb5ecb7c76782db93d05" + }, + { + "path": "tests/mcp-stdio.test.mjs", + "bytes": 5402, + "sha256": "58510c241450d5300f1ca4a4f7ad4adecf6a7abdae295197c311934883c5b23b" + }, + { + "path": "tests/model-center.test.mjs", + "bytes": 16620, + "sha256": "51d477629c2654bf9b1fde30b50865b8b6fff221267609d848579ae98df91fa3" + }, + { + "path": "tests/patch.test.mjs", + "bytes": 6579, + "sha256": "d90404327527e820e3195d04edbf1a7349a450564d80e7dbc4e0c582559e6102" + }, + { + "path": "tests/process-environment.test.mjs", + "bytes": 4553, + "sha256": "03e14e7f48e414330098c14c878cc990d134d5909976dcf849b4da0c3ecffd3d" + }, + { + "path": "tests/project-index.test.mjs", + "bytes": 15256, + "sha256": "83fbc65f713e68e29395ad1053bcbf7272922fb932c6e17f62f4ea402878519d" + }, + { + "path": "tests/project-memory-context.test.mjs", + "bytes": 13430, + "sha256": "bf2996b50e26a69eba737d09de1e5273f5332d695c93f708e508269a29e8bfaf" + }, + { + "path": "tests/project-memory.test.mjs", + "bytes": 7438, + "sha256": "811da36aeffaeddfc496809f00f81ec2cfd722c7411614c6f6b282de2e5d3764" + }, + { + "path": "tests/python-api.test.mjs", + "bytes": 9733, + "sha256": "7694d82dc70d458371d347dbd54886cfa3fb1118c37f59fc4773dd1921fca173" + }, + { + "path": "tests/python-checks.test.mjs", + "bytes": 18057, + "sha256": "b60bde10ac220570a6fc59555b287061d1325783be7532a613885d834ee58078" + }, + { + "path": "tests/read-budget.test.mjs", + "bytes": 13724, + "sha256": "106ddd1eae179c03a01d4952aa3f72d68057badf572e093156f6cc3b37e8edbf" + }, + { + "path": "tests/request-plan-api.test.mjs", + "bytes": 4837, + "sha256": "f3d9a63ee319d44a2ae74d293eb229a8b2cd77bdd29119abcdc23040496d1b57" + }, + { + "path": "tests/request-plan.test.mjs", + "bytes": 18997, + "sha256": "d9e816d4258f9ad4fc35b72d12071e8cb529c7ce708f77a22292760f97c5302b" + }, + { + "path": "tests/research.test.mjs", + "bytes": 16967, + "sha256": "76c8f486bb1fdc4bbef25246ff219bcaa8b8242fb8b7add89c831f9de8ede219" + }, + { + "path": "tests/runtime.test.mjs", + "bytes": 15006, + "sha256": "cf4ce1675cd5f5ab7f81ebd9cd9c949eed1a8121db15cd5349d3c45a732a2b1e" + }, + { + "path": "tests/skills.test.mjs", + "bytes": 17628, + "sha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6" + }, + { + "path": "tests/store.test.mjs", + "bytes": 3880, + "sha256": "e932cdf3a682a3c10309e04d4373f2180f0466443eda2b7d29865ca5eb5f9437" + }, + { + "path": "tests/task-checkpoints.test.mjs", + "bytes": 16172, + "sha256": "bca05de242d6ca7705e7f07e03744b831748e7e6569e00ad540d95cb0fc6ce19" + }, + { + "path": "tests/task-plans-api.test.mjs", + "bytes": 3657, + "sha256": "e0f067eed3e748a39b864e26f8d844a28cc45709aac305a04230cbb19ccd7684" + }, + { + "path": "tests/task-plans.test.mjs", + "bytes": 21545, + "sha256": "99e9b5ba17818bdd8bd8b035868beec4bb2d6bb520b5e1592b02bb3008054461" + }, + { + "path": "tests/tool-feedback.test.mjs", + "bytes": 8409, + "sha256": "61cb597fcd7f8ec32c072f70e0937086535fe50eaa0997479ca06968425bcee3" + }, + { + "path": "tests/upgrade-artifacts.test.mjs", + "bytes": 6267, + "sha256": "6cfb50727f8601f03300de605a4021f7b3e388cba597814a2089438b8a0eb957" + }, + { + "path": "tests/upgrade-model-center.test.mjs", + "bytes": 3774, + "sha256": "f44240a1caa4c1a8554623e3b53530093c98df07d5fb548f27d69230517665c3" + }, + { + "path": "tests/upgrade.test.mjs", + "bytes": 9711, + "sha256": "1a6ded4be5e89ac7a41c9a60c4b37569723ad7d5f80f48c9406940ad727455d3" + }, + { + "path": "tests/working-set.test.mjs", + "bytes": 23492, + "sha256": "b5a163c4d441c49b68a906508156f1e0792d2f0a5a6fe76ebe4429970c432d76" + }, + { + "path": "tests/workspace-api.test.mjs", + "bytes": 9444, + "sha256": "b1dd1ed7a2b14cdd8851a6ff6e15b8f5f9dce85a4e70f1314dcfce98e66d8dd8" + }, + { + "path": "tests/workspace-policy.test.mjs", + "bytes": 12247, + "sha256": "ff8cc7ea014bb630951ae61e7fdda80d5333155823a91986f52f998d011d010c" + }, + { + "path": "tests/workspace-recovery.test.mjs", + "bytes": 5382, + "sha256": "7aeaf03ae89a7de7641d260704aafca4a330b532e46d2d0468a64932c1ab057c" + }, + { + "path": "tests/workspaces.test.mjs", + "bytes": 5490, + "sha256": "4118e9208fed31b3ea2ab55276ed1477291c2daf83809753764a5f17dee7bc60" + }, + { + "path": "tsconfig.json", + "bytes": 398, + "sha256": "aca51bc97061d8ee755197b432ce24f70eb37e02cf8c60445edcfe35305d0510" + }, + { + "path": "vite.config.ts", + "bytes": 247, + "sha256": "6ad3b1bd9d5390876535ba189200fa08e46e5fb481f3f57581376859998e63f4" + } + ], + "logs": [ + { + "stage": "install", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\install.log", + "sha256": "d004705f9743512ff45730927b3cc7f185b3c61eb38e5412e95df8d0843125a2", + "bytes": 401 + }, + { + "stage": "build", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\build.log", + "sha256": "00d1930e01723451fb74dce449c2dcccea3467cbbbb620117bc279236a0de09b", + "bytes": 685 + }, + { + "stage": "contained REA", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\rea.log", + "sha256": "534b5743809ae29b207243703415413c0b285cf72f10b3601eb72cddbe811312", + "bytes": 923 + }, + { + "stage": "native DeepSeek SDK", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\engines.log", + "sha256": "93c351646d7e521f8659e9b2759897df1913ded978dfd8bd6a61a1d36b7181d3", + "bytes": 396 + }, + { + "stage": "contained browser runtime", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\browser.log", + "sha256": "850cf29cd9a055518580565ef2e0516248f53d733651a516c27251e2e557a260", + "bytes": 1251 + }, + { + "stage": "tests", + "path": "D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\.qa\\package-validation-f278d1da-79e8-4fd7-8611-c6534a6007d4\\tests.tap", + "sha256": "d6093860654364b4f81c8a4c4d131c5aa2048dc111ba89962bc24a8b3970e516", + "bytes": 101016 + } + ] +} \ No newline at end of file diff --git a/docs/milestone-audit-first-source-package-tests.tap b/docs/milestone-audit-first-source-package-tests.tap new file mode 100644 index 00000000..1c7f77cc --- /dev/null +++ b/docs/milestone-audit-first-source-package-tests.tap @@ -0,0 +1,2242 @@ +TAP version 13 +# Subtest: the bundled local service enforces host, origin, token and JSON object contracts +ok 1 - the bundled local service enforces host, origin, token and JSON object contracts + --- + duration_ms: 1248.8065 + type: 'test' + ... +# Subtest: an in-flight connection probe prevents configuration changes and another probe until its actual result returns +ok 2 - an in-flight connection probe prevents configuration changes and another probe until its actual result returns + --- + duration_ms: 1251.1275 + type: 'test' + ... +# Subtest: API review applies verified content, detects conflicts, exports sessions and keeps keys in memory +ok 3 - API review applies verified content, detects conflicts, exports sessions and keeps keys in memory + --- + duration_ms: 1858.3266 + type: 'test' + ... +# Subtest: a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume +ok 4 - a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume + --- + duration_ms: 7191.5803 + type: 'test' + ... +# Subtest: runtime diagnostics and model-response validation use actual records and preserve the saved connection +ok 5 - runtime diagnostics and model-response validation use actual records and preserve the saved connection + --- + duration_ms: 1131.9407 + type: 'test' + ... +# Subtest: persistent event replay is read-only and keeps run/artifact identity across reconnects +ok 6 - persistent event replay is read-only and keeps run/artifact identity across reconnects + --- + duration_ms: 5410.9265 + type: 'test' + ... +# Subtest: real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart +ok 7 - real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart + --- + duration_ms: 5209.7785 + type: 'test' + ... +# Subtest: self harness browser tools require approval and feed verified actual page fields back to the original Task +ok 8 - self harness browser tools require approval and feed verified actual page fields back to the original Task + --- + duration_ms: 10345.8574 + type: 'test' + ... +# Subtest: browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement +ok 9 - browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement + --- + duration_ms: 3572.8775 + type: 'test' + ... +# Subtest: late HTTP stop of a finished browser job cannot interrupt a later job in the same Task +ok 10 - late HTTP stop of a finished browser job cannot interrupt a later job in the same Task + --- + duration_ms: 6017.8636 + type: 'test' + ... +# Subtest: actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records +ok 11 - actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records + --- + duration_ms: 15234.267 + type: 'test' + ... +# Subtest: a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact +ok 12 - a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact + --- + duration_ms: 7013.3031 + type: 'test' + ... +# Subtest: actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels +ok 13 - actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels + --- + duration_ms: 6230.1536 + type: 'test' + ... +# Subtest: browser field coverage distinguishes sections and Run windows while retaining original source identity +ok 14 - browser field coverage distinguishes sections and Run windows while retaining original source identity + --- + duration_ms: 0.4656 + type: 'test' + ... +# Subtest: repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing +ok 15 - repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing + --- + duration_ms: 4590.0166 + type: 'test' + ... +# Subtest: browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution +ok 16 - browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution + --- + duration_ms: 0.8844 + type: 'test' + ... +# Subtest: real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen +ok 17 - real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen + --- + duration_ms: 3165.7097 + type: 'test' + ... +# Subtest: failed real page assertion preserves actual value and forbids silent retry of the original plan +ok 18 - failed real page assertion preserves actual value and forbids silent retry of the original plan + --- + duration_ms: 7637.3105 + type: 'test' + ... +# Subtest: build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan +ok 19 - build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan + --- + duration_ms: 1528.8554 + type: 'test' + ... +# Subtest: outside network never reaches another local service, and original JavaScript/console failures remain failures +ok 20 - outside network never reaches another local service, and original JavaScript/console failures remain failures + --- + duration_ms: 2881.7261 + type: 'test' + ... +# Subtest: stopping a real in-flight browser preserves finished steps, closes its owned root and never replays +ok 21 - stopping a real in-flight browser preserves finished steps, closes its owned root and never replays + --- + duration_ms: 2866.1549 + type: 'test' + ... +# Subtest: 原PNG损坏使原结果校验失败,不能以已有通过状态复用 +ok 22 - 原PNG损坏使原结果校验失败,不能以已有通过状态复用 + --- + duration_ms: 2981.8991 + type: 'test' + ... +# Subtest: batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart +ok 23 - batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart + --- + duration_ms: 2097.0548 + type: 'test' + ... +# Subtest: delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files +ok 24 - delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files + --- + duration_ms: 1900.8175 + type: 'test' + ... +# Subtest: a compatible model can seal proposals through the real HTTP loop while application stays behind user review +ok 25 - a compatible model can seal proposals through the real HTTP loop while application stays behind user review + --- + duration_ms: 5026.2993 + type: 'test' + ... +# Subtest: a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools +ok 26 - a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools + --- + duration_ms: 10128.5361 + type: 'test' + ... +# Subtest: applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation +ok 27 - applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation + --- + duration_ms: 2169.01 + type: 'test' + ... +# Subtest: actual process exit at file-batch prepared preserves durable identity and never replays writes +ok 28 - actual process exit at file-batch prepared preserves durable identity and never replays writes + --- + duration_ms: 1828.4635 + type: 'test' + ... +# Subtest: actual process exit at file-batch application_started preserves durable identity and never replays writes +ok 29 - actual process exit at file-batch application_started preserves durable identity and never replays writes + --- + duration_ms: 2073.554 + type: 'test' + ... +# Subtest: actual process exit at file-batch write_intent preserves durable identity and never replays writes +ok 30 - actual process exit at file-batch write_intent preserves durable identity and never replays writes + --- + duration_ms: 1912.7482 + type: 'test' + ... +# Subtest: actual process exit at file-batch staged preserves durable identity and never replays writes +ok 31 - actual process exit at file-batch staged preserves durable identity and never replays writes + --- + duration_ms: 1984.8517 + type: 'test' + ... +# Subtest: actual process exit at file-batch replaced preserves durable identity and never replays writes +ok 32 - actual process exit at file-batch replaced preserves durable identity and never replays writes + --- + duration_ms: 2058.9767 + type: 'test' + ... +# Subtest: actual process exit at file-batch file_recorded preserves durable identity and never replays writes +ok 33 - actual process exit at file-batch file_recorded preserves durable identity and never replays writes + --- + duration_ms: 2344.2734 + type: 'test' + ... +# Subtest: actual process exit at file-batch finished preserves durable identity and never replays writes +ok 34 - actual process exit at file-batch finished preserves durable identity and never replays writes + --- + duration_ms: 2741.1361 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_started preserves durable identity and never replays writes +ok 35 - actual process exit at file-batch rollback_started preserves durable identity and never replays writes + --- + duration_ms: 3278.165 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_intent preserves durable identity and never replays writes +ok 36 - actual process exit at file-batch restore_intent preserves durable identity and never replays writes + --- + duration_ms: 3045.1603 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_staged preserves durable identity and never replays writes +ok 37 - actual process exit at file-batch restore_staged preserves durable identity and never replays writes + --- + duration_ms: 2987.7076 + type: 'test' + ... +# Subtest: actual process exit at file-batch restored preserves durable identity and never replays writes +ok 38 - actual process exit at file-batch restored preserves durable identity and never replays writes + --- + duration_ms: 2925.229 + type: 'test' + ... +# Subtest: actual process exit at file-batch restore_recorded preserves durable identity and never replays writes +ok 39 - actual process exit at file-batch restore_recorded preserves durable identity and never replays writes + --- + duration_ms: 3611.4855 + type: 'test' + ... +# Subtest: actual process exit at file-batch rollback_finished preserves durable identity and never replays writes +ok 40 - actual process exit at file-batch rollback_finished preserves durable identity and never replays writes + --- + duration_ms: 2936.1393 + type: 'test' + ... +# warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it +# warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files +ok 41 - sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files + --- + duration_ms: 2515.3878 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: a conflict in the last file or Git branch prevents writing every file in the batch +ok 42 - a conflict in the last file or Git branch prevents writing every file in the batch + --- + duration_ms: 2934.0103 + type: 'test' + ... +# Subtest: duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch +not ok 43 - duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch + --- + duration_ms: 1070.8012 + type: 'test' + location: 'D:\\awb\\source-check-0ea425360f4948ccacadfad6bbb9d68b\\Agent-Workbench-1.12.1-source-20261030150404738\\tests\\change-sets.test.mjs:50:1' + failureType: 'testCodeFailure' + error: '该路径不在可读取的项目范围内。' + code: 'ERR_TEST_FAILURE' + stack: |- + safePath (file:///D:/awb/source-check-0ea425360f4948ccacadfad6bbb9d68b/Agent-Workbench-1.12.1-source-20261030150404738/src/server/files.mjs:30:73) + proposeFile (file:///D:/awb/source-check-0ea425360f4948ccacadfad6bbb9d68b/Agent-Workbench-1.12.1-source-20261030150404738/src/server/files.mjs:129:18) + TestContext. (file:///D:/awb/source-check-0ea425360f4948ccacadfad6bbb9d68b/Agent-Workbench-1.12.1-source-20261030150404738/tests/change-sets.test.mjs:63:21) + process.processTicksAndRejections (node:internal/process/task_queues:104:5) + async Test.run (node:internal/test_runner/test:1409:7) + async Test.processPendingSubtests (node:internal/test_runner/test:974:7) + ... +# Subtest: fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target +ok 44 - fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target + --- + duration_ms: 2453.5641 + type: 'test' + ... +# Subtest: a failure after replacement restores only batch bytes and never retries an old application +ok 45 - a failure after replacement restores only batch bytes and never retries an old application + --- + duration_ms: 2112.7148 + type: 'test' + ... +# Subtest: rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery +ok 46 - rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery + --- + duration_ms: 2126.6169 + type: 'test' + ... +# Subtest: an unattempted owner-created file identical to a suggestion remains external and is never removed +ok 47 - an unattempted owner-created file identical to a suggestion remains external and is never removed + --- + duration_ms: 1847.8166 + type: 'test' + ... +# Subtest: active batch requests are serialized and cancellation leaves a verifiable ended batch +ok 48 - active batch requests are serialized and cancellation leaves a verifiable ended batch + --- + duration_ms: 1645.4367 + type: 'test' + ... +# Subtest: batch application and rollback preserve unrelated Git index and worktree bytes +ok 49 - batch application and rollback preserve unrelated Git index and worktree bytes + --- + duration_ms: 3629.3834 + type: 'test' + ... +# Subtest: recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection +ok 50 - recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection + --- + duration_ms: 2372.2442 + type: 'test' + ... +# Subtest: one Task can seal pending proposals from earlier Runs while snapshots retain each source Run +ok 51 - one Task can seal pending proposals from earlier Runs while snapshots retain each source Run + --- + duration_ms: 2190.7183 + type: 'test' + ... +# Subtest: engineering inspection preserves a dirty Git baseline and treats project rules as data +ok 52 - engineering inspection preserves a dirty Git baseline and treats project rules as data + --- + duration_ms: 2916.1895 + type: 'test' + ... +# Subtest: real npm tests and build produce counted results, log artifacts and persistent verification +ok 53 - real npm tests and build produce counted results, log artifacts and persistent verification + --- + duration_ms: 2227.6855 + type: 'test' + ... +# Subtest: an actual failing test retains the nonzero exit code and failed count +ok 54 - an actual failing test retains the nonzero exit code and failed count + --- + duration_ms: 2171.7716 + type: 'test' + ... +# Subtest: zero tests, skipped tests and unrecognized stdout cannot become verification passes +ok 55 - zero tests, skipped tests and unrecognized stdout cannot become verification passes + --- + duration_ms: 7528.6255 + type: 'test' + ... +# Subtest: a successful build with no selected tests does not verify the task +ok 56 - a successful build with no selected tests does not verify the task + --- + duration_ms: 1573.6368 + type: 'test' + ... +# Subtest: stale check plans and forged script names execute no project commands +ok 57 - stale check plans and forged script names execute no project commands + --- + duration_ms: 982.3869 + type: 'test' + ... +# Subtest: applying a later proposal invalidates the prior passed engineering snapshot +ok 58 - applying a later proposal invalidates the prior passed engineering snapshot + --- + duration_ms: 1999.3614 + type: 'test' + ... +# Subtest: stopping an actual check terminates its child process and blocks concurrent jobs +ok 59 - stopping an actual check terminates its child process and blocks concurrent jobs + --- + duration_ms: 1608.0066 + type: 'test' + ... +# Subtest: check timeout records a failure with its actual termination result +ok 60 - check timeout records a failure with its actual termination result + --- + duration_ms: 1908.3431 + type: 'test' + ... +# Subtest: source edits during a successful check make the result stale +ok 61 - source edits during a successful check make the result stale + --- + duration_ms: 2680.6924 + type: 'test' + ... +# Subtest: bounded large logs retain the test footer and readable artifact instead of inventing counts +ok 62 - bounded large logs retain the test footer and readable artifact instead of inventing counts + --- + duration_ms: 1753.4318 + type: 'test' + ... +# Subtest: model-selected checks require a run-bound decision and denial creates no check job +ok 63 - model-selected checks require a run-bound decision and denial creates no check job + --- + duration_ms: 2196.8855 + type: 'test' + ... +# Subtest: check APIs expose owned plans and jobs and preserve the authoritative results across restart +ok 64 - check APIs expose owned plans and jobs and preserve the authoritative results across restart + --- + duration_ms: 3305.7163 + type: 'test' + ... +# Subtest: reviewed changes continue the original task without reopening a generic completed run +ok 65 - reviewed changes continue the original task without reopening a generic completed run + --- + duration_ms: 2048.242 + type: 'test' + ... +# Subtest: concurrent review-continuation API requests accept one run and retain the goal after restart +ok 66 - concurrent review-continuation API requests accept one run and retain the goal after restart + --- + duration_ms: 5307.3373 + type: 'test' + ... +# Subtest: the model reads owned failure logs without running the check again +ok 67 - the model reads owned failure logs without running the check again + --- + duration_ms: 3218.3632 + type: 'test' + ... +# Subtest: process exit at check queued preserves results and never replays commands +ok 68 - process exit at check queued preserves results and never replays commands + --- + duration_ms: 1182.9462 + type: 'test' + ... +# Subtest: process exit at check result_committed preserves results and never replays commands +ok 69 - process exit at check result_committed preserves results and never replays commands + --- + duration_ms: 1720.3354 + type: 'test' + ... +# Subtest: model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery +ok 70 - model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery + --- + duration_ms: 4805.8176 + type: 'test' + ... +# Subtest: bundled code APIs isolate project results, validate queries and create review-only patches with conflicts +ok 71 - bundled code APIs isolate project results, validate queries and create review-only patches with conflicts + --- + duration_ms: 2134.5698 + type: 'test' + ... +# Subtest: code tool arguments reject malformed ownership-independent inputs before side effects +ok 72 - code tool arguments reject malformed ownership-independent inputs before side effects + --- + duration_ms: 1.0578 + type: 'test' + ... +# Subtest: actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry +ok 73 - actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry + --- + duration_ms: 1240.4136 + type: 'test' + ... +# Subtest: actual process exit at Git queued never replays a commit and can reconcile the durable result +ok 74 - actual process exit at Git queued never replays a commit and can reconcile the durable result + --- + duration_ms: 9092.9877 + type: 'test' + ... +# Subtest: actual process exit at Git preparing never replays a commit and can reconcile the durable result +ok 75 - actual process exit at Git preparing never replays a commit and can reconcile the durable result + --- + duration_ms: 9163.3382 + type: 'test' + ... +# Subtest: actual process exit at Git index_locked never replays a commit and can reconcile the durable result +ok 76 - actual process exit at Git index_locked never replays a commit and can reconcile the durable result + --- + duration_ms: 9189.1088 + type: 'test' + ... +# Subtest: actual process exit at Git prepared never replays a commit and can reconcile the durable result +ok 77 - actual process exit at Git prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 9266.8351 + type: 'test' + ... +# Subtest: actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result +ok 78 - actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result + --- + duration_ms: 9143.9668 + type: 'test' + ... +# Subtest: actual process exit at Git publishing never replays a commit and can reconcile the durable result +ok 79 - actual process exit at Git publishing never replays a commit and can reconcile the durable result + --- + duration_ms: 10022.8722 + type: 'test' + ... +# Subtest: actual process exit at Git committed never replays a commit and can reconcile the durable result +ok 80 - actual process exit at Git committed never replays a commit and can reconcile the durable result + --- + duration_ms: 8287.7891 + type: 'test' + ... +# Subtest: actual process exit at Git index_published never replays a commit and can reconcile the durable result +ok 81 - actual process exit at Git index_published never replays a commit and can reconcile the durable result + --- + duration_ms: 9220.8507 + type: 'test' + ... +# Subtest: actual process exit at Git finished never replays a commit and can reconcile the durable result +ok 82 - actual process exit at Git finished never replays a commit and can reconcile the durable result + --- + duration_ms: 7002.9095 + type: 'test' + ... +# Subtest: an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock +ok 83 - an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock + --- + duration_ms: 6278.4547 + type: 'test' + ... +# Subtest: known publication with a later source edit retains the commit and marks the delivery for inspection +ok 84 - known publication with a later source edit retains the commit and marks the delivery for inspection + --- + duration_ms: 7669.5886 + type: 'test' + ... +# Subtest: CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership +ok 85 - CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership + --- + duration_ms: 8378.1994 + type: 'test' + ... +# Subtest: adding new durable record kinds to an existing hot Store preserves all existing Maps and records +ok 86 - adding new durable record kinds to an existing hot Store preserves all existing Maps and records + --- + duration_ms: 5874.7248 + type: 'test' + ... +# Subtest: an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected +ok 87 - an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected + --- + duration_ms: 10297.2158 + type: 'test' + ... +# Subtest: actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files +ok 88 - actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files + --- + duration_ms: 8887.4964 + type: 'test' + ... +# Subtest: selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit +ok 89 - selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit + --- + duration_ms: 12408.7734 + type: 'test' + ... +# Switched to a new branch 'owner-branch' +# Subtest: source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD +ok 90 - source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD + --- + duration_ms: 15857.6832 + type: 'test' + ... +# Switched to a new branch 'delivery-branch' +# Subtest: a later Git metadata change keeps matching source evidence valid but a real source edit requires checks +ok 91 - a later Git metadata change keeps matching source evidence valid but a real source edit requires checks + --- + duration_ms: 6981.636 + type: 'test' + ... +# Subtest: a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence +ok 92 - a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence + --- + duration_ms: 4383.163 + type: 'test' + ... +# HEAD is now at b64a84e Sealed delivery fixture baseline +# Subtest: Git filters, merge state, detached HEAD and old task ownership are explicitly rejected +ok 93 - Git filters, merge state, detached HEAD and old task ownership are explicitly rejected + --- + duration_ms: 17192.4247 + type: 'test' + ... +# Subtest: local snapshot commits disable repository hooks and signing and isolate the Git child environment +ok 94 - local snapshot commits disable repository hooks and signing and isolate the Git child environment + --- + duration_ms: 6167.8228 + type: 'test' + ... +# Subtest: stopping before publication cancels safely; stopping after publication preserves the actual completed commit +ok 95 - stopping before publication cancels safely; stopping after publication preserves the actual completed commit + --- + duration_ms: 11394.8979 + type: 'test' + ... +# Subtest: delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart +ok 96 - delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart + --- + duration_ms: 7853.6085 + type: 'test' + ... +# Subtest: the model can prepare an owned Git review and evidence report while publishing remains a separate user action +ok 97 - the model can prepare an owned Git review and evidence report while publishing remains a separate user action + --- + duration_ms: 8898.0194 + type: 'test' + ... +# Subtest: HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved +ok 98 - HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved + --- + duration_ms: 8365.8757 + type: 'test' + ... +# Subtest: a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task +ok 99 - a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task + --- + duration_ms: 7685.6487 + type: 'test' + ... +# Subtest: a question about the previous workbench error receives local error context and current change states +ok 100 - a question about the previous workbench error receives local error context and current change states + --- + duration_ms: 1607.3419 + type: 'test' + ... +# Subtest: a transient model failure after an approved command retries only the model request +ok 101 - a transient model failure after an approved command retries only the model request + --- + duration_ms: 2266.1555 + type: 'test' + ... +# Subtest: exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay +ok 102 - exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay + --- + duration_ms: 2703.0818 + type: 'test' + ... +# Subtest: stopping during model backoff cancels further requests and clears the running request state +ok 103 - stopping during model backoff cancels further requests and clears the running request state + --- + duration_ms: 1731.8035 + type: 'test' + ... +# Subtest: HTTP authentication errors are classified, redacted and never automatically retried +ok 104 - HTTP authentication errors are classified, redacted and never automatically retried + --- + duration_ms: 21.3029 + type: 'test' + ... +# Subtest: temporary HTTP service errors retry and recover with recorded attempt counts +ok 105 - temporary HTTP service errors retry and recover with recorded attempt counts + --- + duration_ms: 14.3301 + type: 'test' + ... +# Subtest: invalid and oversized protocol responses fail once with a useful response-format diagnosis +ok 106 - invalid and oversized protocol responses fail once with a useful response-format diagnosis + --- + duration_ms: 3.8211 + type: 'test' + ... +# Subtest: HTTP rate limits expose their source and obey the service retry interval before recovery +ok 107 - HTTP rate limits expose their source and obey the service retry interval before recovery + --- + duration_ms: 1020.1336 + type: 'test' + ... +# Subtest: Windows commands preserve Chinese through a PowerShell pipeline into Node +ok 108 - Windows commands preserve Chinese through a PowerShell pipeline into Node + --- + duration_ms: 939.5668 + type: 'test' + ... +# Subtest: Windows shell syntax errors stay readable and native command exit codes are retained +ok 109 - Windows shell syntax errors stay readable and native command exit codes are retained + --- + duration_ms: 1025.0694 + type: 'test' + ... +# Subtest: review and completed states do not turn a generic continue click into a new model request +ok 110 - review and completed states do not turn a generic continue click into a new model request + --- + duration_ms: 638.0906 + type: 'test' + ... +# Subtest: old session data receives a truthful historical connection diagnosis without rewriting history +ok 111 - old session data receives a truthful historical connection diagnosis without rewriting history + --- + duration_ms: 692.7762 + type: 'test' + ... +# Subtest: engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart +ok 112 - engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart + --- + duration_ms: 3163.9146 + type: 'test' + ... +# Subtest: HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session +ok 113 - HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session + --- + duration_ms: 3547.371 + type: 'test' + ... +# Subtest: engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch +ok 114 - engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch + --- + duration_ms: 787.697 + type: 'test' + ... +# Subtest: owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence +ok 115 - owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence + --- + duration_ms: 1662.8023 + type: 'test' + ... +# Subtest: an invalid startup nonce is rejected before initialize and preserves the process close and partial report +ok 116 - an invalid startup nonce is rejected before initialize and preserves the process close and partial report + --- + duration_ms: 1316.0304 + type: 'test' + ... +# Subtest: SDK identity and session directory mismatches retain raw responses and never become verified +ok 117 - SDK identity and session directory mismatches retain raw responses and never become verified + --- + duration_ms: 4961.6783 + type: 'test' + ... +# Subtest: cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation +ok 118 - cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation + --- + duration_ms: 1439.6641 + type: 'test' + ... +# Subtest: cancel before readiness sends no protocol request and a user retry creates a different process and record +ok 119 - cancel before readiness sends no protocol request and a user retry creates a different process and record + --- + duration_ms: 2178.4069 + type: 'test' + ... +# Subtest: source or scratch changes and unexpected model traffic fail after preserving the actual observed result +ok 120 - source or scratch changes and unexpected model traffic fail after preserving the actual observed result + --- + duration_ms: 5718.5258 + type: 'test' + ... +# Subtest: unowned idle notifications stay quarantined and server requests receive a rejection without granting operations +ok 121 - unowned idle notifications stay quarantined and server requests receive a rejection without granting operations + --- + duration_ms: 3605.3818 + type: 'test' + ... +# Subtest: engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths +ok 122 - engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths + --- + duration_ms: 1681.2995 + type: 'test' + ... +# Subtest: foreign sessions and altered reports or task bindings cannot reuse verified engine evidence +ok 123 - foreign sessions and altered reports or task bindings cannot reuse verified engine evidence + --- + duration_ms: 1549.1958 + type: 'test' + ... +# Subtest: restart never replays an active engine check or stops a historical PID, and keeps prior task state +ok 124 - restart never replays an active engine check or stops a historical PID, and keeps prior task state + --- + duration_ms: 2204.3541 + type: 'test' + ... +# Subtest: model argument validation and runtime activity do not grant external engine prompt or project execution +ok 125 - model argument validation and runtime activity do not grant external engine prompt or project execution + --- + duration_ms: 778.062 + type: 'test' + ... +# Subtest: a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged +ok 126 - a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged + --- + duration_ms: 3355.8688 + type: 'test' + ... +# Subtest: JSON migration survives process exit before commit and retains exact legacy backups +ok 127 - JSON migration survives process exit before commit and retains exact legacy backups + --- + duration_ms: 2490.8025 + type: 'test' + ... +# Subtest: process exit after_state rolls back state, event and outbox together +ok 128 - process exit after_state rolls back state, event and outbox together + --- + duration_ms: 2336.9199 + type: 'test' + ... +# Subtest: process exit after_event rolls back state, event and outbox together +ok 129 - process exit after_event rolls back state, event and outbox together + --- + duration_ms: 2455.5947 + type: 'test' + ... +# Subtest: crash recovery at accepted retains execution identity and never replays side effects +ok 130 - crash recovery at accepted retains execution identity and never replays side effects + --- + duration_ms: 2115.1994 + type: 'test' + ... +# Subtest: crash recovery at queued retains execution identity and never replays side effects +ok 131 - crash recovery at queued retains execution identity and never replays side effects + --- + duration_ms: 3053.2959 + type: 'test' + ... +# Subtest: crash recovery at approval_wait retains execution identity and never replays side effects +ok 132 - crash recovery at approval_wait retains execution identity and never replays side effects + --- + duration_ms: 3814.747 + type: 'test' + ... +# Subtest: crash recovery at approved retains execution identity and never replays side effects +ok 133 - crash recovery at approved retains execution identity and never replays side effects + --- + duration_ms: 3719.3888 + type: 'test' + ... +# Subtest: crash recovery at effect_unrecorded retains execution identity and never replays side effects +ok 134 - crash recovery at effect_unrecorded retains execution identity and never replays side effects + --- + duration_ms: 4448.2953 + type: 'test' + ... +# Subtest: crash recovery at result_committed retains execution identity and never replays side effects +ok 135 - crash recovery at result_committed retains execution identity and never replays side effects + --- + duration_ms: 4615.9029 + type: 'test' + ... +# Subtest: crash recovery at before_next_model retains execution identity and never replays side effects +ok 136 - crash recovery at before_next_model retains execution identity and never replays side effects + --- + duration_ms: 4659.9746 + type: 'test' + ... +# Subtest: state and event failures publish no success and preserve the last committed memory snapshot +ok 137 - state and event failures publish no success and preserve the last committed memory snapshot + --- + duration_ms: 938.3503 + type: 'test' + ... +# Subtest: tool result artifacts and event cursors retain project ownership across restart +ok 138 - tool result artifacts and event cursors retain project ownership across restart + --- + duration_ms: 2339.6394 + type: 'test' + ... +# Subtest: token budgets pause before tools execute and continuation keeps original task and accumulated usage +ok 139 - token budgets pause before tools execute and continuation keeps original task and accumulated usage + --- + duration_ms: 2843.753 + type: 'test' + ... +# Subtest: a time budget interrupts an unresponsive model and persists a resumable run +ok 140 - a time budget interrupts an unresponsive model and persists a resumable run + --- + duration_ms: 2138.6124 + type: 'test' + ... +# Subtest: a corrupted large result artifact cannot become a recovered success +ok 141 - a corrupted large result artifact cannot become a recovered success + --- + duration_ms: 2474.837 + type: 'test' + ... +# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes +ok 142 - proposals preserve project bytes until review; apply backs up the exact original bytes + --- + duration_ms: 1072.4934 + type: 'test' + ... +# Subtest: new nested files are created only on apply and unchanged content creates no proposal +ok 143 - new nested files are created only on apply and unchanged content creates no proposal + --- + duration_ms: 1062.1359 + type: 'test' + ... +# Subtest: stale reads and changed baselines are rejected without overwriting external edits +ok 144 - stale reads and changed baselines are rejected without overwriting external edits + --- + duration_ms: 938.3584 + type: 'test' + ... +# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions +ok 145 - file paths reject traversal, absolute paths, credentials and outside junctions + --- + duration_ms: 721.7323 + type: 'test' + ... +# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files +ok 146 - read and search expose bounded text scopes and reject non UTF-8 / oversized files + --- + duration_ms: 990.3144 + type: 'test' + ... +# Subtest: project-local junctions cannot expose or create protected Git and credential files +ok 147 - project-local junctions cannot expose or create protected Git and credential files + --- + duration_ms: 857.6853 + type: 'test' + ... +# Subtest: Windows trailing-dot and trailing-space path aliases cannot bypass protected paths +ok 148 - Windows trailing-dot and trailing-space path aliases cannot bypass protected paths + --- + duration_ms: 1088.8754 + type: 'test' + ... +# Subtest: MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup +ok 149 - MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup + --- + duration_ms: 2371.28 + type: 'test' + ... +# Subtest: MCP probe holds the project operation lock until its owned process and report are settled +ok 150 - MCP probe holds the project operation lock until its owned process and report are settled + --- + duration_ms: 2109.9564 + type: 'test' + ... +# Subtest: MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch +ok 151 - MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch + --- + duration_ms: 4.0689 + type: 'test' + ... +# Subtest: actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets +ok 152 - actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets + --- + duration_ms: 5756.9784 + type: 'test' + ... +# Subtest: denying an MCP call never starts another process or executes the external tool +ok 153 - denying an MCP call never starts another process or executes the external tool + --- + duration_ms: 6944.909 + type: 'test' + ... +# Subtest: actual handshake drift rejects tools/call even if program entry hash is unchanged +ok 154 - actual handshake drift rejects tools/call even if program entry hash is unchanged + --- + duration_ms: 5639.9721 + type: 'test' + ... +# Subtest: cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen +ok 155 - cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen + --- + duration_ms: 4077.7528 + type: 'test' + ... +# Subtest: changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch +ok 156 - changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch + --- + duration_ms: 2214.9448 + type: 'test' + ... +# Subtest: registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests +ok 157 - registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests + --- + duration_ms: 2711.5883 + type: 'test' + ... +# Subtest: unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay +ok 158 - unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay + --- + duration_ms: 7371.5241 + type: 'test' + ... +# Subtest: MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged +ok 159 - MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged + --- + duration_ms: 6050.5168 + type: 'test' + ... +# Subtest: actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call +ok 160 - actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call + --- + duration_ms: 5415.6469 + type: 'test' + ... +# Subtest: changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source +ok 161 - changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source + --- + duration_ms: 2336.109 + type: 'test' + ... +# Subtest: stdio preserves split UTF-8 frames and final replies drained after process exit +ok 162 - stdio preserves split UTF-8 frames and final replies drained after process exit + --- + duration_ms: 2090.1011 + type: 'test' + ... +# Subtest: server-initiated model requests are refused instead of inheriting provider privileges +ok 163 - server-initiated model requests are refused instead of inheriting provider privileges + --- + duration_ms: 1078.7613 + type: 'test' + ... +# Subtest: invalid or over-budget protocol invalid closes only its owned process and is not retried +ok 164 - invalid or over-budget protocol invalid closes only its owned process and is not retried + --- + duration_ms: 938.5023 + type: 'test' + ... +# Subtest: invalid or over-budget protocol oversized closes only its owned process and is not retried +ok 165 - invalid or over-budget protocol oversized closes only its owned process and is not retried + --- + duration_ms: 1012.833 + type: 'test' + ... +# Subtest: cancel and timeout do not resend a dispatched request and pre-cancel has no request trace +ok 166 - cancel and timeout do not resend a dispatched request and pre-cancel has no request trace + --- + duration_ms: 1025.279 + type: 'test' + ... +# Subtest: startup failure remains undispatched and has no process PID to terminate +ok 167 - startup failure remains undispatched and has no process PID to terminate + --- + duration_ms: 605.7334 + type: 'test' + ... +# Subtest: REA launch filters a fixture credential canary and rejects changed entry identity before a new connection +ok 168 - REA launch filters a fixture credential canary and rejects changed entry identity before a new connection + --- + duration_ms: 807.6087 + type: 'test' + ... +# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart +ok 169 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart + --- + duration_ms: 1402.482 + type: 'test' + ... +# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts +ok 170 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts + --- + duration_ms: 1003.651 + type: 'test' + ... +# Subtest: real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity +ok 171 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity + --- + duration_ms: 3087.9676 + type: 'test' + ... +# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests +ok 172 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests + --- + duration_ms: 4120.1118 + type: 'test' + ... +# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes +ok 173 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes + --- + duration_ms: 2006.6005 + type: 'test' + ... +# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request +ok 174 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request + --- + duration_ms: 1373.4907 + type: 'test' + ... +# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model +ok 175 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model + --- + duration_ms: 1449.3932 + type: 'test' + ... +# Subtest: model registry disk failures restore routing, pool profiles and credential references without partial updates +ok 176 - model registry disk failures restore routing, pool profiles and credential references without partial updates + --- + duration_ms: 946.893 + type: 'test' + ... +# Subtest: model selection and saved configuration commit together and failures preserve the original mode and endpoint +ok 177 - model selection and saved configuration commit together and failures preserve the original mode and endpoint + --- + duration_ms: 972.953 + type: 'test' + ... +# Subtest: configuration imports roll back the entire batch and retain one usable preview after validation or commit failure +ok 178 - configuration imports roll back the entire batch and retain one usable preview after validation or commit failure + --- + duration_ms: 721.6298 + type: 'test' + ... +# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply +ok 179 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply + --- + duration_ms: 1043.9031 + type: 'test' + ... +# Subtest: several patches are matched against one original snapshot in any input order and keep LF +ok 180 - several patches are matched against one original snapshot in any input order and keep LF + --- + duration_ms: 1106.1002 + type: 'test' + ... +# Subtest: mixed line endings require exact anchors and preserve untouched formatting +ok 181 - mixed line endings require exact anchors and preserve untouched formatting + --- + duration_ms: 907.6439 + type: 'test' + ... +# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write +ok 182 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write + --- + duration_ms: 740.8398 + type: 'test' + ... +# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts +ok 183 - stale original hashes and changes before apply preserve owner edits and mark conflicts + --- + duration_ms: 899.8181 + type: 'test' + ... +# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes +ok 184 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes + --- + duration_ms: 706.8626 + type: 'test' + ... +# Subtest: an actual shell command keeps Node and UTF-8 output while omitting host-only credentials +ok 185 - an actual shell command keeps Node and UTF-8 output while omitting host-only credentials + --- + duration_ms: 1438.8403 + type: 'test' + ... +# Subtest: real npm tests and build do not inherit arbitrary host credentials or Node injection settings +ok 186 - real npm tests and build do not inherit arbitrary host credentials or Node injection settings + --- + duration_ms: 2155.8417 + type: 'test' + ... +# Subtest: real Python tests and compilation keep their sealed inputs without host credentials +ok 187 - real Python tests and compilation keep their sealed inputs without host credentials + --- + duration_ms: 2727.0762 + type: 'test' + ... +# Subtest: JS/TS/React AST indexes actual declarations, exports, imports and verified source lines +ok 188 - JS/TS/React AST indexes actual declarations, exports, imports and verified source lines + --- + duration_ms: 1054.8858 + type: 'test' + ... +# Subtest: default expressions, named default exports and declared functions retain their AST evidence +ok 189 - default expressions, named default exports and declared functions retain their AST evidence + --- + duration_ms: 722.7019 + type: 'test' + ... +# Subtest: incremental refresh invalidates changed/deleted symbols and recalculates reused import targets +ok 190 - incremental refresh invalidates changed/deleted symbols and recalculates reused import targets + --- + duration_ms: 920.2505 + type: 'test' + ... +# Subtest: Python candidates exclude comments and multiline strings and declare limited evidence +ok 191 - Python candidates exclude comments and multiline strings and declare limited evidence + --- + duration_ms: 948.7316 + type: 'test' + ... +# Subtest: indexes isolate project identity and root and evict bounded caches without sharing results +ok 192 - indexes isolate project identity and root and evict bounded caches without sharing results + --- + duration_ms: 766.5273 + type: 'test' + ... +# Subtest: Git ignore, credential paths and links stay outside the index and no project files are executed +ok 193 - Git ignore, credential paths and links stay outside the index and no project files are executed + --- + duration_ms: 1920.7926 + type: 'test' + ... +# Subtest: malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable +ok 194 - malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable + --- + duration_ms: 1077.7783 + type: 'test' + ... +# Subtest: index query rejects invalid limits/types and does not imply reference or alias resolution +ok 195 - index query rejects invalid limits/types and does not imply reference or alias resolution + --- + duration_ms: 817.7519 + type: 'test' + ... +# Subtest: read-only engineering inspection disables configured Git clean filters and preserves index bytes +ok 196 - read-only engineering inspection disables configured Git clean filters and preserves index bytes + --- + duration_ms: 2050.2349 + type: 'test' + ... +# Subtest: Python multiline declarations retain candidate scope without interpreting expressions as declarations +ok 197 - Python multiline declarations retain candidate scope without interpreting expressions as declarations + --- + duration_ms: 765.1967 + type: 'test' + ... +# Subtest: TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit +ok 198 - TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit + --- + duration_ms: 849.3212 + type: 'test' + ... +# Subtest: actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart +ok 199 - actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart + --- + duration_ms: 2492.1928 + type: 'test' + ... +# Subtest: actual HTTP request excludes archived, timed-out and foreign-project memories +ok 200 - actual HTTP request excludes archived, timed-out and foreign-project memories + --- + duration_ms: 3874.2009 + type: 'test' + ... +# Subtest: actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool +ok 201 - actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool + --- + duration_ms: 2714.3865 + type: 'test' + ... +# Subtest: incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots +ok 202 - incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots + --- + duration_ms: 3010.2786 + type: 'test' + ... +# Subtest: corrupt original artifact expires its memory and cannot reach an HTTP model request +ok 203 - corrupt original artifact expires its memory and cannot reach an HTTP model request + --- + duration_ms: 2248.0346 + type: 'test' + ... +# Subtest: memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values +ok 204 - memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values + --- + duration_ms: 2875.1254 + type: 'test' + ... +# Subtest: optional memory yields to the complete goal and original code evidence under the whole-request budget +ok 205 - optional memory yields to the complete goal and original code evidence under the whole-request budget + --- + duration_ms: 1409.9916 + type: 'test' + ... +# Subtest: changed sealed memory artifacts or binding fields fail verification while the original request remains immutable +ok 206 - changed sealed memory artifacts or binding fields fail verification while the original request remains immutable + --- + duration_ms: 1960.9692 + type: 'test' + ... +# Subtest: a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service +ok 207 - a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service + --- + duration_ms: 2245.4055 + type: 'test' + ... +# Subtest: an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure +ok 208 - an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure + --- + duration_ms: 1302.3923 + type: 'test' + ... +# Subtest: project memories persist across restart, keep source provenance, and are visible across tasks +ok 209 - project memories persist across restart, keep source provenance, and are visible across tasks + --- + duration_ms: 1393.4647 + type: 'test' + ... +# Subtest: source changes expire current project memories and keep the original evidence +ok 210 - source changes expire current project memories and keep the original evidence + --- + duration_ms: 861.0853 + type: 'test' + ... +# Subtest: incomplete source scans mark current memories unverified without expiring or reusing them +ok 211 - incomplete source scans mark current memories unverified without expiring or reusing them + --- + duration_ms: 1069.1974 + type: 'test' + ... +# Subtest: explicit file provenance is rechecked even when the inventory excludes that path +ok 212 - explicit file provenance is rechecked even when the inventory excludes that path + --- + duration_ms: 1028.3443 + type: 'test' + ... +# Subtest: execution snapshots do not expose project memories before their source scope is validated +ok 213 - execution snapshots do not expose project memories before their source scope is validated + --- + duration_ms: 1009.2993 + type: 'test' + ... +# Subtest: project memory records stay isolated and archive requires the owning session +ok 214 - project memory records stay isolated and archive requires the owning session + --- + duration_ms: 1174.2839 + type: 'test' + ... +# Subtest: project memory HTTP API exposes read-only source status and explicit writes +ok 215 - project memory HTTP API exposes read-only source status and explicit writes + --- + duration_ms: 1528.4338 + type: 'test' + ... +# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart +ok 216 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart + --- + duration_ms: 8275.7499 + type: 'test' + ... +# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls +ok 217 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls + --- + duration_ms: 35048.0684 + type: 'test' + ... +# Subtest: Python static inspection does not import project code or probe a project interpreter before approval +ok 218 - Python static inspection does not import project code or probe a project interpreter before approval + --- + duration_ms: 1014.8676 + type: 'test' + ... +# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence +ok 219 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence + --- + duration_ms: 4443.443 + type: 'test' + ... +# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names +ok 220 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names + --- + duration_ms: 2512.5446 + type: 'test' + ... +# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task +ok 221 - unittest empty, skipped, expected failure and class initialization errors never verify a task + --- + duration_ms: 7369.9009 + type: 'test' + ... +# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector +ok 222 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector + --- + duration_ms: 2958.573 + type: 'test' + ... +# Subtest: compilation reads actual Python source bytes without executing top-level project code +ok 223 - compilation reads actual Python source bytes without executing top-level project code + --- + duration_ms: 2706.943 + type: 'test' + ... +# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection +ok 224 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection + --- + duration_ms: 2533.5846 + type: 'test' + ... +# Subtest: changed project interpreters and forged Python plan bindings execute no check +ok 225 - changed project interpreters and forged Python plan bindings execute no check + --- + duration_ms: 1689.129 + type: 'test' + ... +# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope +ok 226 - malformed TOML and invalid Python test paths are reported without expanding npm check scope + --- + duration_ms: 1083.3414 + type: 'test' + ... +# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled +ok 227 - stopping a real Python check terminates its child and keeps the completed result as cancelled + --- + duration_ms: 1754.2432 + type: 'test' + ... +# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes +ok 228 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes + --- + duration_ms: 13411.8681 + type: 'test' + ... +# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check +ok 229 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check + --- + duration_ms: 11798.9089 + type: 'test' + ... +# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass +ok 230 - a missing interpreter and repeated pytest item objects cannot create a false verification pass + --- + duration_ms: 2777.0955 + type: 'test' + ... +# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause +ok 231 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause + --- + duration_ms: 2.0127 + type: 'test' + ... +# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget +ok 232 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget + --- + duration_ms: 0.683 + type: 'test' + ... +# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters +ok 233 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters + --- + duration_ms: 10.0018 + type: 'test' + ... +# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress +ok 234 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress + --- + duration_ms: 0.404 + type: 'test' + ... +# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools +ok 235 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools + --- + duration_ms: 3918.1902 + type: 'test' + ... +# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly +ok 236 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly + --- + duration_ms: 4212.5138 + type: 'test' + ... +# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay +ok 237 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay + --- + duration_ms: 4250.4618 + type: 'test' + ... +# Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs +ok 238 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs + --- + duration_ms: 2026.2053 + type: 'test' + ... +# Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification +ok 239 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification + --- + duration_ms: 2160.5884 + type: 'test' + ... +# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget +ok 240 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget + --- + duration_ms: 2121.2197 + type: 'test' + ... +# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments +ok 241 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments + --- + duration_ms: 4937.8835 + type: 'test' + ... +# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests +ok 242 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests + --- + duration_ms: 970.2084 + type: 'test' + ... +# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window +ok 243 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window + --- + duration_ms: 2201.6607 + type: 'test' + ... +# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix +ok 244 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix + --- + duration_ms: 1743.672 + type: 'test' + ... +# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived +ok 245 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived + --- + duration_ms: 1334.6931 + type: 'test' + ... +# Subtest: invalid orphan result is rejected before archive or network preparation +ok 246 - invalid orphan result is rejected before archive or network preparation + --- + duration_ms: 1221.7584 + type: 'test' + ... +# Subtest: invalid missing result is rejected before archive or network preparation +ok 247 - invalid missing result is rejected before archive or network preparation + --- + duration_ms: 869.8454 + type: 'test' + ... +# Subtest: invalid wrong result is rejected before archive or network preparation +ok 248 - invalid wrong result is rejected before archive or network preparation + --- + duration_ms: 971.3225 + type: 'test' + ... +# Subtest: invalid duplicate call is rejected before archive or network preparation +ok 249 - invalid duplicate call is rejected before archive or network preparation + --- + duration_ms: 1283.8283 + type: 'test' + ... +# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON +ok 250 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON + --- + duration_ms: 2196.6299 + type: 'test' + ... +# Subtest: changed or missing archived evidence stops reuse and is never silently recreated +ok 251 - changed or missing archived evidence stops reuse and is never silently recreated + --- + duration_ms: 1275.8367 + type: 'test' + ... +# Subtest: transaction failure prevents publishing a plan and any corresponding model request +ok 252 - transaction failure prevents publishing a plan and any corresponding model request + --- + duration_ms: 1304.2969 + type: 'test' + ... +# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP +ok 253 - the Provider rejects body mutation after a sealed plan before calling HTTP + --- + duration_ms: 1127.5397 + type: 'test' + ... +# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command +ok 254 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command + --- + duration_ms: 9347.1563 + type: 'test' + ... +# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request +ok 255 - a real process exit after plan persistence marks interruption and never issues an automatic model request + --- + duration_ms: 1919.2966 + type: 'test' + ... +# Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence +ok 256 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence + --- + duration_ms: 2855.6642 + type: 'test' + ... +# Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity +ok 257 - user research registration creates an owned Task without model requests and seals the exact artifact identity + --- + duration_ms: 1153.2515 + type: 'test' + ... +# Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload +ok 258 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload + --- + duration_ms: 2679.3548 + type: 'test' + ... +# Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses +ok 259 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses + --- + duration_ms: 3591.4304 + type: 'test' + ... +# Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history +ok 260 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history + --- + duration_ms: 3257.8679 + type: 'test' + ... +# Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID +ok 261 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID + --- + duration_ms: 2270.1069 + type: 'test' + ... +# Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed +ok 262 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed + --- + duration_ms: 2578.9883 + type: 'test' + ... +# Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts +ok 263 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts + --- + duration_ms: 1376.1183 + type: 'test' + ... +# Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay +ok 264 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay + --- + duration_ms: 5111.7067 + type: 'test' + ... +# Subtest: file identity rejects directory and invalid formats without running a target +ok 265 - file identity rejects directory and invalid formats without running a target + --- + duration_ms: 924.3837 + type: 'test' + ... +# Subtest: a stop from the event loop interrupts immediate model replies before later tools +ok 266 - a stop from the event loop interrupts immediate model replies before later tools + --- + duration_ms: 1916.498 + type: 'test' + ... +# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group +ok 267 - a stop after the first tool preserves a complete interrupted multi-call protocol group + --- + duration_ms: 2276.4477 + type: 'test' + ... +# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands +ok 268 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands + --- + duration_ms: 5991.6293 + type: 'test' + ... +# Subtest: denial prevents command execution and produces a paired denied result +ok 269 - denial prevents command execution and produces a paired denied result + --- + duration_ms: 2623.8084 + type: 'test' + ... +# Subtest: stopping during approval interrupts pending calls without executing or replaying them +ok 270 - stopping during approval interrupts pending calls without executing or replaying them + --- + duration_ms: 2191.3831 + type: 'test' + ... +# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state +ok 271 - stopping a running fixture command terminates its own process tree and retains uncertain state + --- + duration_ms: 2440.9388 + type: 'test' + ... +# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment +ok 272 - command output decodes split UTF-8 and excludes the workbench key from child environment + --- + duration_ms: 1189.4219 + type: 'test' + ... +# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors +ok 273 - model-list testing uses a tentative key without changing the saved connection and redacts service errors + --- + duration_ms: 9.7987 + type: 'test' + ... +# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities +ok 274 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities + --- + duration_ms: 3354.5681 + type: 'test' + ... +# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history +ok 275 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history + --- + duration_ms: 1461.675 + type: 'test' + ... +# Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project +ok 276 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project + --- + duration_ms: 1194.661 + type: 'test' + ... +# Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code +ok 277 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code + --- + duration_ms: 865.4275 + type: 'test' + ... +# Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing +ok 278 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing + --- + duration_ms: 3149.9829 + type: 'test' + ... +# Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay +ok 279 - source edits after a catalog request prevent the read and appear as changed on the next request without replay + --- + duration_ms: 3275.4453 + type: 'test' + ... +# Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project +ok 280 - disabled and foreign skills cannot be read by guessing their IDs from another project + --- + duration_ms: 3259.6768 + type: 'test' + ... +# Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code +ok 281 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code + --- + duration_ms: 1496.029 + type: 'test' + ... +# Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact +ok 282 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact + --- + duration_ms: 4299.4469 + type: 'test' + ... +# Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network +ok 283 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network + --- + duration_ms: 1469.8986 + type: 'test' + ... +# Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs +ok 284 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs + --- + duration_ms: 2922.269 + type: 'test' + ... +# Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls +ok 285 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls + --- + duration_ms: 2511.3845 + type: 'test' + ... +# Subtest: JSON state keeps an atomic backup and preserves corrupt primary files +ok 286 - JSON state keeps an atomic backup and preserves corrupt primary files + --- + duration_ms: 935.0563 + type: 'test' + ... +# Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results +ok 287 - tool-pair recovery fills missing results and drops orphan or duplicate results + --- + duration_ms: 0.3002 + type: 'test' + ... +# Subtest: restart pauses unfinished work, retains proposals and never replays a command +ok 288 - restart pauses unfinished work, retains proposals and never replays a command + --- + duration_ms: 1131.555 + type: 'test' + ... +# Subtest: public snapshots carry increasing revisions without the private provider transcript or config key +ok 289 - public snapshots carry increasing revisions without the private provider transcript or config key + --- + duration_ms: 1518.4805 + type: 'test' + ... +# Subtest: a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay +ok 290 - a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay + --- + duration_ms: 4810.2196 + type: 'test' + ... +# Subtest: checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact +ok 291 - checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact + --- + duration_ms: 3220.9915 + type: 'test' + ... +# Subtest: unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work +ok 292 - unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work + --- + duration_ms: 3460.77 + type: 'test' + ... +# Subtest: checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt +ok 293 - checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt + --- + duration_ms: 3465.9114 + type: 'test' + ... +# Subtest: checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes +ok 294 - checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes + --- + duration_ms: 2979.2158 + type: 'test' + ... +# Subtest: Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state +ok 295 - Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state + --- + duration_ms: 3653.6123 + type: 'test' + ... +# Subtest: checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay +ok 296 - checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay + --- + duration_ms: 2411.1127 + type: 'test' + ... +# Subtest: incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements +ok 297 - incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements + --- + duration_ms: 2065.2799 + type: 'test' + ... +# Subtest: oversized recovery evidence is refused before reading or publishing the checkpoint +ok 298 - oversized recovery evidence is refused before reading or publishing the checkpoint + --- + duration_ms: 2331.9765 + type: 'test' + ... +# Subtest: compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation +ok 299 - compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation + --- + duration_ms: 5010.9138 + type: 'test' + ... +# Subtest: actual process exit before checkpoint commit retains only durable records without replay +ok 300 - actual process exit before checkpoint commit retains only durable records without replay + --- + duration_ms: 2140.4072 + type: 'test' + ... +# Subtest: actual process exit after checkpoint commit retains only durable records without replay +ok 301 - actual process exit after checkpoint commit retains only durable records without replay + --- + duration_ms: 2339.2436 + type: 'test' + ... +# Subtest: task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart +ok 302 - task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart + --- + duration_ms: 3206.9773 + type: 'test' + ... +# Subtest: concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan +ok 303 - concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan + --- + duration_ms: 2417.4555 + type: 'test' + ... +# Subtest: a real escaped long-file tool message keeps its proof identity within a tight request budget +ok 304 - a real escaped long-file tool message keeps its proof identity within a tight request budget + --- + duration_ms: 1546.4012 + type: 'test' + ... +# Subtest: task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies +ok 305 - task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies + --- + duration_ms: 0.5261 + type: 'test' + ... +# Subtest: sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools +ok 306 - sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools + --- + duration_ms: 1300.3361 + type: 'test' + ... +# Subtest: proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes +ok 307 - proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes + --- + duration_ms: 2208.8731 + type: 'test' + ... +# Subtest: new user requirements invalidate current proofs and reseal the same original operations in a new revision +ok 308 - new user requirements invalidate current proofs and reseal the same original operations in a new revision + --- + duration_ms: 2246.2847 + type: 'test' + ... +# Subtest: applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits +ok 309 - applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits + --- + duration_ms: 2277.7446 + type: 'test' + ... +# Subtest: actual npm checks are verified by original counted logs and current source, with failure history retained +ok 310 - actual npm checks are verified by original counted logs and current source, with failure history retained + --- + duration_ms: 7196.8404 + type: 'test' + ... +# Subtest: real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds +ok 311 - real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds + --- + duration_ms: 12218.9312 + type: 'test' + ... +# Subtest: Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit +ok 312 - Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit + --- + duration_ms: 10583.6008 + type: 'test' + ... +# Subtest: the runtime supplies owned read IDs and completes a plan only after original step evidence verification +ok 313 - the runtime supplies owned read IDs and completes a plan only after original step evidence verification + --- + duration_ms: 3437.1424 + type: 'test' + ... +# Subtest: premature model completion pauses the original Task and resume preserves the existing plan without replay +ok 314 - premature model completion pauses the original Task and resume preserves the existing plan without replay + --- + duration_ms: 5057.1178 + type: 'test' + ... +# Subtest: plan operations participate in project activity and orderly shutdown +ok 315 - plan operations participate in project activity and orderly shutdown + --- + duration_ms: 887.8747 + type: 'test' + ... +# Subtest: actual process exit before plan save restores only committed plan evidence without replay +ok 316 - actual process exit before plan save restores only committed plan evidence without replay + --- + duration_ms: 2209.024 + type: 'test' + ... +# Subtest: actual process exit after plan save restores only committed plan evidence without replay +ok 317 - actual process exit after plan save restores only committed plan evidence without replay + --- + duration_ms: 1517.1418 + type: 'test' + ... +# Subtest: actual process exit before proof save restores only committed plan evidence without replay +ok 318 - actual process exit before proof save restores only committed plan evidence without replay + --- + duration_ms: 1555.6062 + type: 'test' + ... +# Subtest: actual process exit after proof save restores only committed plan evidence without replay +ok 319 - actual process exit after proof save restores only committed plan evidence without replay + --- + duration_ms: 2446.8172 + type: 'test' + ... +# Subtest: the latest oversized session result reaches the next request together with already read source modules +ok 320 - the latest oversized session result reaches the next request together with already read source modules + --- + duration_ms: 2741.8347 + type: 'test' + ... +# Subtest: every call in a large latest group keeps its actual outcome, including denied and unknown results +ok 321 - every call in a large latest group keeps its actual outcome, including denied and unknown results + --- + duration_ms: 1615.1143 + type: 'test' + ... +# Subtest: a small complete latest tool group is sent once and needs no duplicate feedback view +ok 322 - a small complete latest tool group is sent once and needs no duplicate feedback view + --- + duration_ms: 1070.7509 + type: 'test' + ... +# Subtest: real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing +ok 323 - real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing + --- + duration_ms: 2903.1482 + type: 'test' + ... +# Subtest: a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes +ok 324 - a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes + --- + duration_ms: 4159.0799 + type: 'test' + ... +# Subtest: failed upgrade restores the original artifact object, provider and request handler +ok 325 - failed upgrade restores the original artifact object, provider and request handler + --- + duration_ms: 961.2097 + type: 'test' + ... +# Subtest: hot upgrade refreshes retained model and importer methods while preserving credential and routing objects +ok 326 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects + --- + duration_ms: 1023.3738 + type: 'test' + ... +# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails +ok 327 - hot upgrade refuses active probes and restores retained model methods if installation fails + --- + duration_ms: 1047.1487 + type: 'test' + ... +# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider +ok 328 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider + --- + duration_ms: 3179.4364 + type: 'test' + ... +# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection +ok 329 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection + --- + duration_ms: 12106.7432 + type: 'test' + ... +# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit +ok 330 - small code and actual failed command stay visible when their original multi-tool group cannot fit + --- + duration_ms: 1641.2226 + type: 'test' + ... +# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes +ok 331 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes + --- + duration_ms: 2180.9829 + type: 'test' + ... +# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence +ok 332 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence + --- + duration_ms: 2428.9374 + type: 'test' + ... +# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence +ok 333 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence + --- + duration_ms: 1556.1137 + type: 'test' + ... +# Subtest: a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid +ok 334 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid + --- + duration_ms: 4814.5831 + type: 'test' + ... +# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries +ok 335 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries + --- + duration_ms: 4.0731 + type: 'test' + ... +# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening +ok 336 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening + --- + duration_ms: 12050.212 + type: 'test' + ... +# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request +ok 337 - actual HTTP file pagination advances over a long file with each returned page visible in the next request + --- + duration_ms: 3410.4774 + type: 'test' + ... +# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements +ok 338 - later mixed history pages cannot displace the actual module sources and complete requirements + --- + duration_ms: 7373.7702 + type: 'test' + ... +# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation +ok 339 - a later narrow page of the same file revision cannot evict the wider actual observation + --- + duration_ms: 3966.4272 + type: 'test' + ... +# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper +ok 340 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper + --- + duration_ms: 1467.5338 + type: 'test' + ... +# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view +ok 341 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view + --- + duration_ms: 2049.7986 + type: 'test' + ... +# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes +ok 342 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes + --- + duration_ms: 16821.9879 + type: 'test' + ... +# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files +ok 343 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files + --- + duration_ms: 7236.2834 + type: 'test' + ... +# Subtest: isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report +ok 344 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report + --- + duration_ms: 31565.8869 + type: 'test' + ... +# warning: in the working copy of 'src/空 格.mjs', LF will be replaced by CRLF the next time Git touches it +# Subtest: worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion +ok 345 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion + --- + duration_ms: 7894.0116 + type: 'test' + ... +# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation +ok 346 - an ignored external file at checkout is observed and never accepted as pristine creation + --- + duration_ms: 4833.6187 + type: 'test' + ... +# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution +ok 347 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution + --- + duration_ms: 4731.1268 + type: 'test' + ... +# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions +ok 348 - workspace preparation refuses known shared-repository activity and preserves archived child sessions + --- + duration_ms: 5300.9913 + type: 'test' + ... +# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name +ok 349 - compact checkout identities create in deep Unicode source directories while retaining the human branch name + --- + duration_ms: 5440.5868 + type: 'test' + ... +# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes +ok 350 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes + --- + duration_ms: 2485.2391 + type: 'test' + ... +# Subtest: a pending source snapshot participates in shutdown and completes before storage can close +ok 351 - a pending source snapshot participates in shutdown and completes before storage can close + --- + duration_ms: 2006.4079 + type: 'test' + ... +# Subtest: source configuration values stay private and a configuration change invalidates a saved review +ok 352 - source configuration values stay private and a configuration change invalidates a saved review + --- + duration_ms: 2404.6565 + type: 'test' + ... +# Subtest: workspace review rejects excluded dependency before any checkout +ok 353 - workspace review rejects excluded dependency before any checkout + --- + duration_ms: 2350.061 + type: 'test' + ... +# Subtest: workspace review rejects large committed blob before any checkout +ok 354 - workspace review rejects large committed blob before any checkout + --- + duration_ms: 2230.1343 + type: 'test' + ... +# Subtest: workspace review rejects case collision before any checkout +ok 355 - workspace review rejects case collision before any checkout + --- + duration_ms: 2859.0228 + type: 'test' + ... +# Subtest: workspace review rejects committed symbolic link before any checkout +ok 356 - workspace review rejects committed symbolic link before any checkout + --- + duration_ms: 2380.4922 + type: 'test' + ... +# Subtest: workspace review rejects external config include before any checkout +ok 357 - workspace review rejects external config include before any checkout + --- + duration_ms: 2041.6831 + type: 'test' + ... +# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay +ok 358 - actual process exit at workspace intent preserves source and reconciles without creation replay + --- + duration_ms: 4966.0767 + type: 'test' + ... +# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay +ok 359 - actual process exit at workspace git_started preserves source and reconciles without creation replay + --- + duration_ms: 5816.4892 + type: 'test' + ... +# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay +ok 360 - actual process exit at workspace git_finished preserves source and reconciles without creation replay + --- + duration_ms: 5562.692 + type: 'test' + ... +# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay +ok 361 - actual process exit at workspace verifying preserves source and reconciles without creation replay + --- + duration_ms: 5708.721 + type: 'test' + ... +# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay +ok 362 - actual process exit at workspace registering preserves source and reconciles without creation replay + --- + duration_ms: 6096.653 + type: 'test' + ... +# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay +ok 363 - actual process exit at workspace project_registered preserves source and reconciles without creation replay + --- + duration_ms: 6602.502 + type: 'test' + ... +# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay +ok 364 - actual process exit at workspace session_registered preserves source and reconciles without creation replay + --- + duration_ms: 6482.765 + type: 'test' + ... +# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay +ok 365 - actual process exit at workspace ready preserves source and reconciles without creation replay + --- + duration_ms: 5099.8905 + type: 'test' + ... +# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity +ok 366 - outside changes at project registration remain unknown and preserve the already registered child identity + --- + duration_ms: 4846.2468 + type: 'test' + ... +# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity +ok 367 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity + --- + duration_ms: 4767.7338 + type: 'test' + ... +# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation +ok 368 - stale review, branch/path collisions and forged ownership do not run worktree creation + --- + duration_ms: 3336.2073 + type: 'test' + ... +# Subtest: workspace project verification is read-only and rejects physical Git identity changes +ok 369 - workspace project verification is read-only and rejects physical Git identity changes + --- + duration_ms: 4389.6571 + type: 'test' + ... +1..369 +# tests 369 +# suites 0 +# pass 368 +# fail 1 +# cancelled 0 +# skipped 0 +# todo 0 +# duration_ms 643373.065 diff --git a/docs/milestone-audit-index-ui-validation.json b/docs/milestone-audit-index-ui-validation.json new file mode 100644 index 00000000..a8d01641 --- /dev/null +++ b/docs/milestone-audit-index-ui-validation.json @@ -0,0 +1,19 @@ +{ + "checkedAt": "2026-10-30T15:34:52.601Z", + "version": "1.12.1", + "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-f4472e28-4c3b-4c00-8715-904242dd0e02", + "primaryProjectId": "cb91ac22-dd97-4ece-99ad-98dd00baa327", + "otherProjectId": "f9ba3e33-0898-477e-a070-c1c48482bcef" +} diff --git a/docs/milestone-audit-mcp-recovery-ui-validation.json b/docs/milestone-audit-mcp-recovery-ui-validation.json new file mode 100644 index 00000000..2ad963ee --- /dev/null +++ b/docs/milestone-audit-mcp-recovery-ui-validation.json @@ -0,0 +1,16 @@ +{ + "success": true, + "assertions": [ + "actual host crash with no result report exposes its original verified input and unknown status", + "390px original-input review clears the job and invocation gates while retaining unknown, no report and no automatic model replay" + ], + "viewportWidths": [ + 1440, + 390 + ], + "pageErrors": [], + "requestFailures": [], + "localFixtureModelRequests": 1, + "realModelRequests": 0, + "jobId": "1d497864-4449-41e1-bc4b-6e8bf82c2d78" +} \ No newline at end of file diff --git a/docs/milestone-audit-mcp-ui-validation.json b/docs/milestone-audit-mcp-ui-validation.json new file mode 100644 index 00000000..1e7177d7 --- /dev/null +++ b/docs/milestone-audit-mcp-ui-validation.json @@ -0,0 +1,24 @@ +{ + "success": true, + "assertions": [ + "MCP registration stays disabled and shows the hashed local executable and Node entry", + "actual stdio tools/list schema is visible; only the reviewed echo tool is enabled", + "an enabled program whose source changes can be disabled immediately without executing the changed entry", + "approved external call interrupted after dispatch remains unknown and does not replay", + "TaskPanel exposes Task/Run source, original report, and human acknowledgement without marking unknown as success", + "390px MCP registry, long executable paths, controls, and operation history have no horizontal overflow" + ], + "viewportWidths": [ + 1440, + 390 + ], + "pageErrors": [], + "requestFailures": [], + "localFixtureModelRequests": 1, + "realModelRequests": 0, + "unknownJobId": "d8b9dea0-9abd-4026-93d4-3666b7f24bf0", + "screenshots": [ + "desktop-mcp-registry.png", + "mobile-mcp-registry.png" + ] +} \ No newline at end of file diff --git a/docs/milestone-audit-model-center-ui-validation.json b/docs/milestone-audit-model-center-ui-validation.json new file mode 100644 index 00000000..c9a19b38 --- /dev/null +++ b/docs/milestone-audit-model-center-ui-validation.json @@ -0,0 +1,22 @@ +{ + "url": "http://127.0.0.1:56571", + "viewportWidths": [ + 1440, + 390 + ], + "assertions": [ + "connection form stores only the volatile credential and renders configured status without exposing it", + "pool editor saves weighted members and binds selection for new Runs", + "schema-bound import preview, opt-in automatic sync, revision update and sync shutdown keep credentials hidden", + "local inspection shows real database and artifact checks and emits zero model requests", + "390px model-center modal and connection cards remain operable without horizontal page overflow" + ], + "pageErrors": [], + "requestFailures": [], + "modelRequests": 0, + "screenshots": [ + "desktop-operations.png", + "mobile-operations.png", + "mobile-connections.png" + ] +} \ No newline at end of file diff --git a/docs/milestone-audit-model-save-initial-repro.json b/docs/milestone-audit-model-save-initial-repro.json new file mode 100644 index 00000000..f1a75f50 --- /dev/null +++ b/docs/milestone-audit-model-save-initial-repro.json @@ -0,0 +1,17 @@ +{ + "directory": "C:\\Users\\wangy\\AppData\\Local\\Temp\\awb-model-save-audit-h1AQcD", + "error": "fixture-disk-failure", + "before": { + "enabled": true, + "revision": 1 + }, + "memory": { + "enabled": false, + "revision": 2 + }, + "disk": { + "enabled": true, + "revision": 1 + }, + "modelRequests": 0 +} diff --git a/docs/milestone-audit-npm-audit.json b/docs/milestone-audit-npm-audit.json new file mode 100644 index 00000000..c5f79658 --- /dev/null +++ b/docs/milestone-audit-npm-audit.json @@ -0,0 +1,22 @@ +{ + "auditReportVersion": 2, + "vulnerabilities": {}, + "metadata": { + "vulnerabilities": { + "info": 0, + "low": 0, + "moderate": 0, + "high": 0, + "critical": 0, + "total": 0 + }, + "dependencies": { + "prod": 13, + "dev": 141, + "optional": 79, + "peer": 0, + "peerOptional": 0, + "total": 153 + } + } +} diff --git a/docs/milestone-audit-path-initial-repro.json b/docs/milestone-audit-path-initial-repro.json new file mode 100644 index 00000000..1f7d0664 --- /dev/null +++ b/docs/milestone-audit-path-initial-repro.json @@ -0,0 +1,34 @@ +{ + "root": "C:\\Users\\wangy\\AppData\\Local\\Temp\\awb-path-audit-BHnvFn", + "platform": "win32", + "results": [ + { + "path": ".git/config", + "allowed": false, + "error": "该路径不在可读取的项目范围内。" + }, + { + "path": "git-alias/config", + "allowed": true, + "protectedContentRead": true + }, + { + "path": "credential-alias/config.txt", + "allowed": true, + "protectedContentRead": true + }, + { + "path": "git-alias/new.txt", + "allowed": true, + "protectedContentRead": false + }, + { + "path": ".git./config", + "allowed": true, + "protectedContentRead": false + }, + { + "inventoryAliases": 0 + } + ] +} diff --git a/docs/milestone-audit-project-memory-ui-validation.json b/docs/milestone-audit-project-memory-ui-validation.json new file mode 100644 index 00000000..f160cc5a --- /dev/null +++ b/docs/milestone-audit-project-memory-ui-validation.json @@ -0,0 +1,24 @@ +{ + "success": true, + "url": "http://127.0.0.1:58686", + "viewportWidths": [ + 1440, + 390 + ], + "assertions": [ + "source hashes remain visible and a changed file is explicitly expired with retained provenance", + "incomplete inventory marks existing facts unverified and blocks new saves", + "390px memory review stays within the viewport with the incomplete-scan warning visible", + "desktop and 390px request records expose the exact memory snapshot used by one owned local HTTP request" + ], + "pageErrors": [], + "requestFailures": [], + "localFixtureModelRequests": 1, + "realModelRequests": 0, + "screenshots": [ + "desktop-expired-memory.png", + "mobile-incomplete-memory.png", + "desktop-sent-memory.png", + "mobile-sent-memory.png" + ] +} \ No newline at end of file diff --git a/docs/milestone-audit-python-ui-validation.json b/docs/milestone-audit-python-ui-validation.json new file mode 100644 index 00000000..31c1cc5c --- /dev/null +++ b/docs/milestone-audit-python-ui-validation.json @@ -0,0 +1,35 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T15:35:57.032Z", + "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": "3dba6ed970b8f9f792e5683d87c64e6ad728e711", + "scope": "Independent host and owned fixture. Real Python processes, reviewed API repairs and actual local Git. No configured model requests or production credentials." +} diff --git a/docs/milestone-audit-react-delivery-validation.json b/docs/milestone-audit-react-delivery-validation.json new file mode 100644 index 00000000..52557904 --- /dev/null +++ b/docs/milestone-audit-react-delivery-validation.json @@ -0,0 +1,76 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T15:36:17.052Z", + "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": "44d9f56dbf9d0ce3c9c2cd457dcfa006749d01e5", + "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." +} diff --git a/docs/milestone-audit-research-ui-validation.json b/docs/milestone-audit-research-ui-validation.json new file mode 100644 index 00000000..d56ab1ce --- /dev/null +++ b/docs/milestone-audit-research-ui-validation.json @@ -0,0 +1,138 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T15:36:38.025Z", + "browser": "156.0.4314.50", + "passed": [ + "independent desktop research entry detects the installed fixed REA version", + "UI registration seals the artifact identity in the current project and creates no model request", + "actual REA ASAR analysis renders the verified source chain and downloads the exact original Bundle", + "original field selection, paging and limitations retain exact bytes; Escape closes only the top dialog", + "raw responses and connection records are readable; repeat analysis reuses the verified original without dispatch", + "UI PE operation selection performs actual import and resource analysis with independently verified target hashes", + "changed artifact versions refuse dispatch, retain the stale record and require a separately registered version", + "390px research, long identities and original evidence dialogs fit the viewport and retain usable close controls", + "a real host restart preserves exact target/job identities and serves sealed Evidence without producer replay", + "a delayed evidence response cannot reopen a closed research panel or change another task", + "declared owned stdio fault fixture stops its root process and explicit retry adds a new record without changing history" + ], + "pageErrors": [], + "requestFailures": [], + "expectedRequestFailures": [], + "root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\research-ui-620b3e88-3c53-4077-b4e9-8a56541c5eed", + "actualRea": { + "version": "6.8.0", + "operations": [ + "javascript", + "pe-imports", + "pe-resources" + ], + "jobs": [ + { + "id": "e75e35da-cf81-4f99-8264-a91b629c3a8d", + "status": "completed", + "evidenceId": "ev_2f04a55fd2f8b4d38ed986bfb50d4f2599f94b256a58371a496409498927b22e" + }, + { + "id": "74b3f1a5-8738-432c-9e6c-9f41a5c97a22", + "status": "completed", + "evidenceId": "ev_2f04a55fd2f8b4d38ed986bfb50d4f2599f94b256a58371a496409498927b22e" + }, + { + "id": "21a3902f-7cfe-4c43-9c03-808c59e8eb0f", + "status": "completed", + "evidenceId": "ev_92454ab0585d1ebbd2d89928228e1d2c1a14d8f67ace457ff54a59cadc8603ab" + }, + { + "id": "114c223f-400e-4f2e-99ef-bc8fa36b88d6", + "status": "completed", + "evidenceId": "ev_d940b75287a3a711cef82cb8307b9673d7cb3ea27b5bc1d2759b3477580c4fb0" + }, + { + "id": "48cd341e-dea6-4bb6-ab9a-bd5541e0fc9e", + "status": "stale" + }, + { + "id": "a55450a8-378e-45ee-a2c1-3bb0af3832e3", + "status": "completed", + "evidenceId": "ev_ae449670ce6b68ae3b714a1d01777490144a22f5ee58eda5865ab0e4aba4bc1c" + } + ], + "targetExecution": false, + "modelRequests": 0 + }, + "stopScope": "explicitly declared private stdio handshake fault fixture", + "screenshots": [ + ".qa/screenshots/milestone-audit-research-desktop.png", + ".qa/screenshots/milestone-audit-research-mobile.png", + ".qa/screenshots/milestone-audit-research-evidence-mobile.png", + ".qa/screenshots/milestone-audit-research-stop-desktop.png" + ], + "analysisRequests": [ + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "70838a70-475d-413d-b12e-fc0b262726c0", + "operation": "javascript", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "70838a70-475d-413d-b12e-fc0b262726c0", + "operation": "javascript", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "51c4f866-1141-42ce-9d12-baf3cbb49400", + "operation": "pe-imports", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "51c4f866-1141-42ce-9d12-baf3cbb49400", + "operation": "pe-resources", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "70838a70-475d-413d-b12e-fc0b262726c0", + "operation": "javascript", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:52066/api/sessions/0288d57f-1388-4dbd-b750-6d15d2ab07b8/research/jobs", + "input": { + "targetId": "61434dfe-2501-4f27-8204-c8b5599a8b29", + "operation": "javascript", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:60891/api/sessions/58255c34-c4f1-4416-9ebd-90c08ea059ca/research/jobs", + "input": { + "targetId": "56cd82b8-68ea-4a9f-9988-41b6e40dea7a", + "operation": "javascript", + "refresh": false + } + }, + { + "url": "http://127.0.0.1:60891/api/sessions/58255c34-c4f1-4416-9ebd-90c08ea059ca/research/jobs", + "input": { + "targetId": "56cd82b8-68ea-4a9f-9988-41b6e40dea7a", + "operation": "javascript", + "refresh": true + } + } + ], + "scope": "Independent ports/data and self-owned inert artifacts. No production service, configured-model request or real key read/copied." +} diff --git a/docs/milestone-audit-security-ui-initial-failure.json b/docs/milestone-audit-security-ui-initial-failure.json new file mode 100644 index 00000000..2c38267a --- /dev/null +++ b/docs/milestone-audit-security-ui-initial-failure.json @@ -0,0 +1,12 @@ +{ + "success": false, + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-100d0d0e-d705-44a4-a6ae-0d1571541714", + "error": "AssertionError [ERR_ASSERTION]: Missing expected rejection.\n at process.processTicksAndRejections (node:internal/process/task_queues:104:5)\n at async file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/milestone-security-ui.mjs:63:5", + "assertions": [ + "real original 1.12.0 renders the workbench inside an independently hosted cross-origin iframe", + "an actual original 1.12.0 process upgrades in place with initialized ModelHub/Importer, unchanged PID, connection metadata and original session" + ], + "pageErrors": [], + "expectedPolicyMessages": [], + "stderr": "Debugger listening on ws://127.0.0.1:9229/76b23bcc-01d1-47d4-b8cb-fddee85a2b15\r\nFor help, see: https://nodejs.org/learn/getting-started/debugging\r\nDebugger attached.\r\nDebugger ending on ws://127.0.0.1:9229/76b23bcc-01d1-47d4-b8cb-fddee85a2b15\r\nFor help, see: https://nodejs.org/learn/getting-started/debugging\r\n" +} \ No newline at end of file diff --git a/docs/milestone-audit-security-ui-validation.json b/docs/milestone-audit-security-ui-validation.json new file mode 100644 index 00000000..20157cb9 --- /dev/null +++ b/docs/milestone-audit-security-ui-validation.json @@ -0,0 +1,83 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T14:42:10.496Z", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd", + "oldReleaseId": "20261030124454517", + "oldHeaders": { + "cache-control": "no-store", + "connection": "keep-alive", + "content-type": "text/html; charset=utf-8", + "date": "Fri, 30 Oct 2026 14:42:06 GMT", + "keep-alive": "timeout=5", + "transfer-encoding": "chunked", + "x-content-type-options": "nosniff" + }, + "newHeaders": { + "cache-control": "no-store", + "connection": "keep-alive", + "content-security-policy": "default-src 'self'; script-src 'self'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; connect-src 'self'; object-src 'none'; base-uri 'none'; frame-ancestors 'none'; form-action 'self'", + "content-type": "text/html; charset=utf-8", + "date": "Fri, 30 Oct 2026 14:42:07 GMT", + "keep-alive": "timeout=5", + "referrer-policy": "no-referrer", + "transfer-encoding": "chunked", + "x-content-type-options": "nosniff", + "x-frame-options": "DENY" + }, + "assertions": [ + "real original 1.12.0 renders the workbench inside an independently hosted cross-origin iframe", + "an actual original 1.12.0 process upgrades in place with initialized ModelHub/Importer, unchanged PID, connection metadata and original session", + "retained importer now rolls back an actual partially invalid batch and keeps the original preview usable after failure", + "both volatile fixture credentials still route correctly after the real process upgrade and are absent from persisted configuration", + "real Edge refuses the cross-origin iframe after the patch instead of exposing the approval interface", + "1280px workbench and model center remain usable under the new response policy", + "390px workbench and model center remain usable under the new response policy", + "policy permits PNG Blob image loading and blocks fetching/executing an independently hosted script" + ], + "pageErrors": [], + "expectedPolicyMessages": [ + "Framing 'http://127.0.0.1:56118/' violates the following Content Security Policy directive: \"frame-ancestors 'none'\". The request has been blocked.\n", + "Loading the script 'http://127.0.0.1:56121/forbidden.js' violates the following Content Security Policy directive: \"script-src 'self'\". Note that 'script-src-elem' was not explicitly set, so 'script-src' is used as a fallback. The action has been blocked." + ], + "unexpectedRequests": [], + "pid": 36724, + "processExited": true, + "syntheticModelRequests": 2, + "realModelRequests": 0, + "files": [ + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\buttons-1280.json", + "sha256": "ac701db35c9e4f392512f538843511c69ec57f6e8ddce660910b19c4c198d746" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\buttons-390.json", + "sha256": "a8cd5c189a51fb9f990f93a5f86b66e8116edc67b33ee0096f7c1aa8b173f0a3" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\model-center-1280.png", + "sha256": "e5110517113d81c9ff7a80294e1d9e0c28a487202ebb650a6e2acebd4c48f77f" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\model-center-390.png", + "sha256": "e0fb690d0d92bb4da2565af70d9f507af05f701014ce7ca3c2e64f617439ca27" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\new-blocked-iframe.png", + "sha256": "66ca379556d77ef1d88203acc3374643bda5896ca6846e79c61c6377769b61f4" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\old-embedded.png", + "sha256": "001b1dfde3310ae50467e6091791a2769518784f4c063506c2d9e874b65e4c07" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\old-frame.html", + "sha256": "af4c18ef5c86a7ef356580b2cf194822fe4ed55d6dd7ed950cacef3ddce77b64" + }, + { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd\\owned-import.json", + "sha256": "5efc64fd7e5c88e1c6c0c8572f9ef6b52a91643d3232a02f7152ad9c5fa442c5" + } + ], + "scope": "Owned projects, credentials, independent ports and original immutable 1.12.0 process; no production service affected." +} diff --git a/docs/milestone-audit-security-ui-verifier.mjs b/docs/milestone-audit-security-ui-verifier.mjs new file mode 100644 index 00000000..e75b9543 --- /dev/null +++ b/docs/milestone-audit-security-ui-verifier.mjs @@ -0,0 +1,119 @@ +import fs from 'node:fs'; +import path from 'node:path'; +import http from 'node:http'; +import assert from 'node:assert/strict'; +import { spawn } from 'node:child_process'; +import { randomUUID, createHash } from 'node:crypto'; +import { chromium, expect } from 'playwright/test'; +import { fixture, until, compatibleFixture, completion, workspace } from '../tests/helpers.mjs'; +import { gitEnvironment } from '../src/core/git-process.mjs'; +import { upgradeRunning } from '../scripts/upgrade-running.mjs'; + +const directory = path.resolve('.qa/milestone-security-ui-' + randomUUID()); fs.mkdirSync(directory); +const original = JSON.parse(fs.readFileSync('docs/model-center-release-identity.json', 'utf8')); +const oldRoot = original.release.portableRoot; +const disposers = [], t = { after: action => disposers.push(action) }, f = fixture(t); f.store.close(); +const assertions = [], pageErrors = [], expectedPolicyMessages = [], unexpectedRequests = []; +const record = value => { assertions.push(value); console.log('PASS ' + value); }; +const fakeModel = await compatibleFixture(t, () => completion([], 'owned model probe response')); +const child = spawn(process.execPath, [path.join(oldRoot, 'dist-server/server.mjs')], { cwd: oldRoot, env: gitEnvironment({ + AGENT_WORKBENCH_APP_DIR: oldRoot, AGENT_WORKBENCH_DATA_DIR: f.data, AGENT_WORKBENCH_PORT: '0' }), windowsHide: true, stdio: ['ignore', 'pipe', 'pipe'] }); +let url = '', stdout = '', stderr = '', browser, external; +child.stdout.on('data', bytes => { stdout += bytes.toString(); for (const line of stdout.split('\n')) { try { const item = JSON.parse(line); if (item.ready) url = item.url; } catch {} } }); +child.stderr.on('data', bytes => { stderr += bytes.toString(); }); +let bootstrap; +async function api(route, input) { + const response = await fetch(url + '/api' + route, { method: input === undefined ? 'GET' : 'POST', headers: { + 'Content-Type': 'application/json', 'X-Workbench-Token': bootstrap.token, Connection: 'close' }, ...(input === undefined ? {} : { body: JSON.stringify(input) }) }); + const value = await response.json(); if (!response.ok) throw Object.assign(new Error(value.error), { status: response.status }); return value; +} +try { + await until(() => url || child.exitCode !== null); assert.ok(url, stderr); assert.notEqual(new URL(url).port, '4318'); + bootstrap = await (await fetch(url + '/api/bootstrap')).json(); assert.equal(bootstrap.version, '1.12.0'); assert.equal(bootstrap.config.hasKey, false); + const oldHeaders = Object.fromEntries((await fetch(url)).headers); assert.equal(oldHeaders['x-frame-options'], undefined); + external = http.createServer((request, response) => { + if (request.url === '/forbidden.js') { unexpectedRequests.push('external script fetched'); response.writeHead(200, { 'Content-Type': 'text/javascript' }); response.end('window.ownedExternalScriptExecuted=true;'); } + else { response.writeHead(200, { 'Content-Type': 'text/html' }); response.end('Owned embedding fixture

External fixture

'); } + }); + await new Promise(resolve => external.listen(0, '127.0.0.1', resolve)); const externalUrl = 'http://127.0.0.1:' + external.address().port; + browser = await chromium.launch({ channel: 'msedge', headless: true }); + const page = await browser.newPage({ viewport: { width: 1280, height: 1000 } }); + page.on('pageerror', error => pageErrors.push(error.message)); + page.on('console', message => { if (message.type() === 'error' && /frame|Content Security Policy|script-src/i.test(message.text())) expectedPolicyMessages.push(message.text()); }); + await page.goto(externalUrl); await page.waitForLoadState('networkidle'); + await expect(page.frameLocator('#workbench').getByRole('button', { name: '打开模型中心', exact: true })).toBeVisible(); + fs.writeFileSync(path.join(directory, 'old-frame.html'), await page.content()); await page.screenshot({ path: path.join(directory, 'old-embedded.png') }); + record('real original 1.12.0 renders the workbench inside an independently hosted cross-origin iframe'); + + await api('/config', { mode: 'compatible', model: 'owned-legacy', baseUrl: fakeModel.baseUrl, apiKey: 'owned-legacy-upgrade-marker' }); + const connection = await api('/model-center/connections', { name: 'Retained owned connection', baseUrl: fakeModel.baseUrl, model: 'owned-reserve', apiKey: 'owned-connection-upgrade-marker' }); + const importFile = path.join(directory, 'owned-import.json'); + fs.writeFileSync(importFile, JSON.stringify({ schema: 1, connections: [ + { name: 'First valid imported entry', baseUrl: fakeModel.baseUrl, model: 'owned-first', apiKey: 'owned-import-marker' }, + { name: 'Second invalid imported entry', baseUrl: fakeModel.baseUrl, model: 'owned-invalid', apiKey: 'x'.repeat(16001) }, + ] })); + const preview = await api('/model-center/import-preview', { source: 'workbench-json', path: importFile }); + const beforeCenter = await api('/model-center'), beforeSession = await api('/sessions/' + f.session.id), beforeConfig = (await api('/bootstrap')).config; + const upgraded = await upgradeRunning({ url, pid: child.pid, currentRoot: oldRoot, newRoot: workspace }); + assert.equal(upgraded.verified, true); assert.equal(upgraded.version, '1.12.1'); assert.equal(upgraded.pid, child.pid); assert.equal(upgraded.hasKey, true); + bootstrap = await api('/bootstrap'); assert.deepEqual(bootstrap.config, beforeConfig); + assert.deepEqual(await api('/model-center'), beforeCenter); assert.deepEqual(await api('/sessions/' + f.session.id), beforeSession); + record('an actual original 1.12.0 process upgrades in place with initialized ModelHub/Importer, unchanged PID, connection metadata and original session'); + for (let attempt = 0; attempt < 2; attempt++) { + await assert.rejects(api('/model-center/import-apply', { previewId: preview.id }), error => error.status === 400 && !/预览已过期/.test(error.message)); + assert.deepEqual(await api('/model-center'), beforeCenter); + } + record('retained importer now rolls back an actual partially invalid batch and keeps the original preview usable after failure'); + assert.equal((await api('/model-center/probe', { id: connection.id })).ok, true); + assert.equal(fakeModel.requests.at(-1).headers.authorization, 'Bearer owned-connection-upgrade-marker'); + await api('/config/models', {}); assert.equal(fakeModel.requests.at(-1).headers.authorization, 'Bearer owned-legacy-upgrade-marker'); + assert.ok(!fs.readFileSync(path.join(f.data, 'config.json'), 'utf8').includes('owned-legacy-upgrade-marker')); + record('both volatile fixture credentials still route correctly after the real process upgrade and are absent from persisted configuration'); + + const newHeaders = Object.fromEntries((await fetch(url)).headers); assert.equal(newHeaders['x-frame-options'], 'DENY'); + assert.match(newHeaders['content-security-policy'], /frame-ancestors 'none'/); assert.equal(newHeaders['referrer-policy'], 'no-referrer'); + await page.goto(externalUrl); await page.waitForLoadState('networkidle'); + assert.equal(await page.frameLocator('#workbench').locator('#root').count(), 0); + assert.ok(expectedPolicyMessages.some(value => /frame-ancestors|frame/i.test(value))); + await page.screenshot({ path: path.join(directory, 'new-blocked-iframe.png') }); + record('real Edge refuses the cross-origin iframe after the patch instead of exposing the approval interface'); + + await page.addInitScript(({ projectId, sessionId }) => { localStorage.setItem('awb-project', projectId); localStorage.setItem('awb-session', sessionId); }, { projectId: f.project.id, sessionId: f.session.id }); + for (const width of [1280, 390]) { + await page.setViewportSize({ width, height: 1000 }); await page.goto(url); await page.waitForLoadState('networkidle'); + fs.writeFileSync(path.join(directory, 'buttons-' + width + '.json'), JSON.stringify(await page.locator('button').evaluateAll(nodes => nodes.map(node => ({ text: node.textContent, label: node.getAttribute('aria-label'), title: node.title }))), null, 2)); + await page.getByRole('button', { name: '打开模型中心', exact: true }).click(); + const dialog = page.getByRole('dialog', { name: '模型中心', exact: true }); await expect(dialog).toBeVisible(); + await expect(dialog).toContainText('Retained owned connection'); + const bounds = await dialog.boundingBox(); assert.ok(bounds.x >= 0 && bounds.x + bounds.width <= width + 1); + await page.screenshot({ path: path.join(directory, 'model-center-' + width + '.png') }); await page.keyboard.press('Escape'); + assert.equal(await page.evaluate(() => document.documentElement.scrollWidth <= innerWidth), true); + record(width + 'px workbench and model center remain usable under the new response policy'); + } + const blobImage = await page.evaluate(async () => { + const bytes = Uint8Array.from(atob('iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mP8/x8AAwMCAO+/lWQAAAAASUVORK5CYII='), value => value.charCodeAt(0)); + const url = URL.createObjectURL(new Blob([bytes], { type: 'image/png' })), image = document.createElement('img'); + try { const loaded = await new Promise(resolve => { image.onload = () => resolve(image.naturalWidth); image.onerror = () => resolve(0); image.src = url; document.body.append(image); }); return loaded; } + finally { image.remove(); URL.revokeObjectURL(url); } + }); + assert.equal(blobImage, 1); + await assert.rejects(page.addScriptTag({ url: externalUrl + '/forbidden.js' })); + assert.equal(await page.evaluate(() => window.ownedExternalScriptExecuted === true), false); assert.deepEqual(unexpectedRequests, []); + record('policy permits PNG Blob image loading and blocks fetching/executing an independently hosted script'); + assert.deepEqual(pageErrors, []); await browser.close(); browser = null; + await api('/shutdown', {}); await until(() => child.exitCode !== null); assert.equal(child.exitCode, 0); + await assert.rejects(fetch('http://127.0.0.1:9229/json/list', { signal: AbortSignal.timeout(500) })); + const hash = filename => createHash('sha256').update(fs.readFileSync(filename)).digest('hex'); + const files = fs.readdirSync(directory).map(name => ({ path: path.join(directory, name), sha256: hash(path.join(directory, name)) })); + const result = { success: true, version: '1.12.1', at: new Date().toISOString(), directory, oldReleaseId: original.releaseId, + oldHeaders, newHeaders, assertions, pageErrors, expectedPolicyMessages, unexpectedRequests, pid: child.pid, processExited: true, + syntheticModelRequests: fakeModel.requests.length, realModelRequests: 0, files, scope: 'Owned projects, credentials, independent ports and original immutable 1.12.0 process; no production service affected.' }; + fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify(result, null, 2) + '\n'); + fs.writeFileSync('.qa/milestone-security-ui-result.json', JSON.stringify(result, null, 2) + '\n'); console.log('EVIDENCE ' + directory); +} catch (error) { + fs.writeFileSync(path.join(directory, 'failure.json'), JSON.stringify({ success: false, directory, error: error.stack, assertions, pageErrors, expectedPolicyMessages, stderr }, null, 2)); throw error; +} finally { + await browser?.close(); if (external) await new Promise(resolve => external.close(resolve)); + if (child.exitCode === null && child.signalCode === null) { try { await api('/shutdown', {}); await until(() => child.exitCode !== null, 5000); } catch { child.kill(); } } + for (const dispose of disposers.reverse()) await dispose(); +} diff --git a/docs/milestone-audit-service-preflight.json b/docs/milestone-audit-service-preflight.json new file mode 100644 index 00000000..ad077dcf --- /dev/null +++ b/docs/milestone-audit-service-preflight.json @@ -0,0 +1,21 @@ +{ + "observedAt": "2026-10-30T15:34:04.6420682Z", + "version": "1.12.0", + "pid": 23172, + "registeredPid": 23172, + "appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "runtimeRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517", + "dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench", + "processExecutable": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.12.0-win-x64-20261030124454517\\runtime\\node.exe", + "processCreatedAt": "2026-10-30T14:33:10.3641640Z", + "hasKey": true, + "mode": "compatible", + "model": "gpt-6.1-sol", + "visibleProjects": 16, + "visibleSessions": 20, + "busySessions": 0, + "historicalReleasePid": 19084, + "historicalPidIsCurrent": false, + "realModelRequests": 0, + "scope": "Read-only current host identity; public hasKey only. Upgrade must preserve this current process and freshly snapshot every persisted row/export, rather than use historical release counts." +} diff --git a/docs/milestone-audit-skills-ui-validation.json b/docs/milestone-audit-skills-ui-validation.json new file mode 100644 index 00000000..4dfb839b --- /dev/null +++ b/docs/milestone-audit-skills-ui-validation.json @@ -0,0 +1,22 @@ +{ + "success": true, + "viewportWidths": [ + 1440, + 390 + ], + "assertions": [ + "desktop registers a disabled skill, reviews original UTF-8 instructions and explicitly enables it with no model calls", + "source edit blocks activation until a new reviewed revision is registered; original revision remains available", + "390px review and activation retain readable paths, revision history and visible source state without horizontal overflow", + "actual local HTTP task reads precisely revision 2 and exposes its SHA-bound sent catalog in task evidence" + ], + "pageErrors": [], + "requestFailures": [], + "localFixtureModelRequests": 2, + "realModelRequests": 0, + "screenshots": [ + "desktop-skill-source.png", + "mobile-skill-source.png", + "desktop-sent-skill-catalog.png" + ] +} \ No newline at end of file diff --git a/docs/milestone-audit-targeted-tests-validation.json b/docs/milestone-audit-targeted-tests-validation.json new file mode 100644 index 00000000..46f62f8c --- /dev/null +++ b/docs/milestone-audit-targeted-tests-validation.json @@ -0,0 +1,35 @@ +{ + "success": true, + "version": "1.12.1", + "startedAt": "2026-10-30T14:33:49.472Z", + "finishedAt": "2026-10-30T14:35:40.420Z", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-targeted-673244ae-32ef-46d2-9719-63d73d92598d", + "files": [ + "tests/files.test.mjs", + "tests/patch.test.mjs", + "tests/code-tools.test.mjs", + "tests/model-center.test.mjs", + "tests/upgrade-model-center.test.mjs", + "tests/api.test.mjs", + "tests/upgrade.test.mjs", + "tests/process-environment.test.mjs", + "tests/checks.test.mjs", + "tests/python-checks.test.mjs", + "tests/runtime.test.mjs" + ], + "code": 0, + "tests": { + "tests": 80, + "pass": 80, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "log": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\milestone-targeted-673244ae-32ef-46d2-9719-63d73d92598d\\tests.tap", + "bytes": 20775, + "sha256": "11fa9751969c13d1c1544c4b9eda460ecfbf19de13319d3def71e9b5043cef74" + }, + "realModelRequests": 0 +} diff --git a/docs/milestone-audit-targeted-tests.tap b/docs/milestone-audit-targeted-tests.tap new file mode 100644 index 00000000..91689ee8 --- /dev/null +++ b/docs/milestone-audit-targeted-tests.tap @@ -0,0 +1,490 @@ +TAP version 13 +# Subtest: the bundled local service enforces host, origin, token and JSON object contracts +ok 1 - the bundled local service enforces host, origin, token and JSON object contracts + --- + duration_ms: 1140.4923 + type: 'test' + ... +# Subtest: an in-flight connection probe prevents configuration changes and another probe until its actual result returns +ok 2 - an in-flight connection probe prevents configuration changes and another probe until its actual result returns + --- + duration_ms: 1150.652 + type: 'test' + ... +# Subtest: API review applies verified content, detects conflicts, exports sessions and keeps keys in memory +ok 3 - API review applies verified content, detects conflicts, exports sessions and keeps keys in memory + --- + duration_ms: 2027.8642 + type: 'test' + ... +# Subtest: a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume +ok 4 - a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume + --- + duration_ms: 7285.0082 + type: 'test' + ... +# Subtest: runtime diagnostics and model-response validation use actual records and preserve the saved connection +ok 5 - runtime diagnostics and model-response validation use actual records and preserve the saved connection + --- + duration_ms: 1269.4122 + type: 'test' + ... +# Subtest: persistent event replay is read-only and keeps run/artifact identity across reconnects +ok 6 - persistent event replay is read-only and keeps run/artifact identity across reconnects + --- + duration_ms: 6534.977 + type: 'test' + ... +# Subtest: engineering inspection preserves a dirty Git baseline and treats project rules as data +ok 7 - engineering inspection preserves a dirty Git baseline and treats project rules as data + --- + duration_ms: 2489.6531 + type: 'test' + ... +# Subtest: real npm tests and build produce counted results, log artifacts and persistent verification +ok 8 - real npm tests and build produce counted results, log artifacts and persistent verification + --- + duration_ms: 2266.4572 + type: 'test' + ... +# Subtest: an actual failing test retains the nonzero exit code and failed count +ok 9 - an actual failing test retains the nonzero exit code and failed count + --- + duration_ms: 2121.7752 + type: 'test' + ... +# Subtest: zero tests, skipped tests and unrecognized stdout cannot become verification passes +ok 10 - zero tests, skipped tests and unrecognized stdout cannot become verification passes + --- + duration_ms: 7113.8357 + type: 'test' + ... +# Subtest: a successful build with no selected tests does not verify the task +ok 11 - a successful build with no selected tests does not verify the task + --- + duration_ms: 1743.1807 + type: 'test' + ... +# Subtest: stale check plans and forged script names execute no project commands +ok 12 - stale check plans and forged script names execute no project commands + --- + duration_ms: 1443.4315 + type: 'test' + ... +# Subtest: applying a later proposal invalidates the prior passed engineering snapshot +ok 13 - applying a later proposal invalidates the prior passed engineering snapshot + --- + duration_ms: 2744.2162 + type: 'test' + ... +# Subtest: stopping an actual check terminates its child process and blocks concurrent jobs +ok 14 - stopping an actual check terminates its child process and blocks concurrent jobs + --- + duration_ms: 1834.6345 + type: 'test' + ... +# Subtest: check timeout records a failure with its actual termination result +ok 15 - check timeout records a failure with its actual termination result + --- + duration_ms: 2097.9352 + type: 'test' + ... +# Subtest: source edits during a successful check make the result stale +ok 16 - source edits during a successful check make the result stale + --- + duration_ms: 3248.9389 + type: 'test' + ... +# Subtest: bounded large logs retain the test footer and readable artifact instead of inventing counts +ok 17 - bounded large logs retain the test footer and readable artifact instead of inventing counts + --- + duration_ms: 2239.0116 + type: 'test' + ... +# Subtest: model-selected checks require a run-bound decision and denial creates no check job +ok 18 - model-selected checks require a run-bound decision and denial creates no check job + --- + duration_ms: 3607.9929 + type: 'test' + ... +# Subtest: check APIs expose owned plans and jobs and preserve the authoritative results across restart +ok 19 - check APIs expose owned plans and jobs and preserve the authoritative results across restart + --- + duration_ms: 4102.6016 + type: 'test' + ... +# Subtest: reviewed changes continue the original task without reopening a generic completed run +ok 20 - reviewed changes continue the original task without reopening a generic completed run + --- + duration_ms: 3861.4867 + type: 'test' + ... +# Subtest: concurrent review-continuation API requests accept one run and retain the goal after restart +ok 21 - concurrent review-continuation API requests accept one run and retain the goal after restart + --- + duration_ms: 7416.1113 + type: 'test' + ... +# Subtest: the model reads owned failure logs without running the check again +ok 22 - the model reads owned failure logs without running the check again + --- + duration_ms: 4454.8987 + type: 'test' + ... +# Subtest: process exit at check queued preserves results and never replays commands +ok 23 - process exit at check queued preserves results and never replays commands + --- + duration_ms: 1548.6213 + type: 'test' + ... +# Subtest: process exit at check result_committed preserves results and never replays commands +ok 24 - process exit at check result_committed preserves results and never replays commands + --- + duration_ms: 2832.095 + type: 'test' + ... +# Subtest: model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery +ok 25 - model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery + --- + duration_ms: 4625.6807 + type: 'test' + ... +# Subtest: bundled code APIs isolate project results, validate queries and create review-only patches with conflicts +ok 26 - bundled code APIs isolate project results, validate queries and create review-only patches with conflicts + --- + duration_ms: 2189.429 + type: 'test' + ... +# Subtest: code tool arguments reject malformed ownership-independent inputs before side effects +ok 27 - code tool arguments reject malformed ownership-independent inputs before side effects + --- + duration_ms: 0.4268 + type: 'test' + ... +# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes +ok 28 - proposals preserve project bytes until review; apply backs up the exact original bytes + --- + duration_ms: 861.7613 + type: 'test' + ... +# Subtest: new nested files are created only on apply and unchanged content creates no proposal +ok 29 - new nested files are created only on apply and unchanged content creates no proposal + --- + duration_ms: 1087.478 + type: 'test' + ... +# Subtest: stale reads and changed baselines are rejected without overwriting external edits +ok 30 - stale reads and changed baselines are rejected without overwriting external edits + --- + duration_ms: 746.7513 + type: 'test' + ... +# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions +ok 31 - file paths reject traversal, absolute paths, credentials and outside junctions + --- + duration_ms: 699.1052 + type: 'test' + ... +# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files +ok 32 - read and search expose bounded text scopes and reject non UTF-8 / oversized files + --- + duration_ms: 812.157 + type: 'test' + ... +# Subtest: project-local junctions cannot expose or create protected Git and credential files +ok 33 - project-local junctions cannot expose or create protected Git and credential files + --- + duration_ms: 804.7499 + type: 'test' + ... +# Subtest: Windows trailing-dot and trailing-space path aliases cannot bypass protected paths +ok 34 - Windows trailing-dot and trailing-space path aliases cannot bypass protected paths + --- + duration_ms: 796.5457 + type: 'test' + ... +# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart +ok 35 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart + --- + duration_ms: 1482.7296 + type: 'test' + ... +# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts +ok 36 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts + --- + duration_ms: 1057.5669 + type: 'test' + ... +# Subtest: real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity +ok 37 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity + --- + duration_ms: 2746.5494 + type: 'test' + ... +# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests +ok 38 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests + --- + duration_ms: 6161.3018 + type: 'test' + ... +# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes +ok 39 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes + --- + duration_ms: 2059.4583 + type: 'test' + ... +# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request +ok 40 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request + --- + duration_ms: 1265.7207 + type: 'test' + ... +# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model +ok 41 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model + --- + duration_ms: 1422.0311 + type: 'test' + ... +# Subtest: model registry disk failures restore routing, pool profiles and credential references without partial updates +ok 42 - model registry disk failures restore routing, pool profiles and credential references without partial updates + --- + duration_ms: 1023.5952 + type: 'test' + ... +# Subtest: model selection and saved configuration commit together and failures preserve the original mode and endpoint +ok 43 - model selection and saved configuration commit together and failures preserve the original mode and endpoint + --- + duration_ms: 1023.7873 + type: 'test' + ... +# Subtest: configuration imports roll back the entire batch and retain one usable preview after validation or commit failure +ok 44 - configuration imports roll back the entire batch and retain one usable preview after validation or commit failure + --- + duration_ms: 683.1714 + type: 'test' + ... +# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply +ok 45 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply + --- + duration_ms: 855.5786 + type: 'test' + ... +# Subtest: several patches are matched against one original snapshot in any input order and keep LF +ok 46 - several patches are matched against one original snapshot in any input order and keep LF + --- + duration_ms: 914.334 + type: 'test' + ... +# Subtest: mixed line endings require exact anchors and preserve untouched formatting +ok 47 - mixed line endings require exact anchors and preserve untouched formatting + --- + duration_ms: 802.8502 + type: 'test' + ... +# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write +ok 48 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write + --- + duration_ms: 973.8542 + type: 'test' + ... +# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts +ok 49 - stale original hashes and changes before apply preserve owner edits and mark conflicts + --- + duration_ms: 1050.0935 + type: 'test' + ... +# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes +ok 50 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes + --- + duration_ms: 675.0859 + type: 'test' + ... +# Subtest: an actual shell command keeps Node and UTF-8 output while omitting host-only credentials +ok 51 - an actual shell command keeps Node and UTF-8 output while omitting host-only credentials + --- + duration_ms: 1124.9693 + type: 'test' + ... +# Subtest: real npm tests and build do not inherit arbitrary host credentials or Node injection settings +ok 52 - real npm tests and build do not inherit arbitrary host credentials or Node injection settings + --- + duration_ms: 2274.3652 + type: 'test' + ... +# Subtest: real Python tests and compilation keep their sealed inputs without host credentials +ok 53 - real Python tests and compilation keep their sealed inputs without host credentials + --- + duration_ms: 2404.7429 + type: 'test' + ... +# Subtest: Python static inspection does not import project code or probe a project interpreter before approval +ok 54 - Python static inspection does not import project code or probe a project interpreter before approval + --- + duration_ms: 1216.2853 + type: 'test' + ... +# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence +ok 55 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence + --- + duration_ms: 4902.4376 + type: 'test' + ... +# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names +ok 56 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names + --- + duration_ms: 3427.6883 + type: 'test' + ... +# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task +ok 57 - unittest empty, skipped, expected failure and class initialization errors never verify a task + --- + duration_ms: 8458.5265 + type: 'test' + ... +# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector +ok 58 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector + --- + duration_ms: 3386.228 + type: 'test' + ... +# Subtest: compilation reads actual Python source bytes without executing top-level project code +ok 59 - compilation reads actual Python source bytes without executing top-level project code + --- + duration_ms: 3085.9532 + type: 'test' + ... +# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection +ok 60 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection + --- + duration_ms: 2593.428 + type: 'test' + ... +# Subtest: changed project interpreters and forged Python plan bindings execute no check +ok 61 - changed project interpreters and forged Python plan bindings execute no check + --- + duration_ms: 1784.3921 + type: 'test' + ... +# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope +ok 62 - malformed TOML and invalid Python test paths are reported without expanding npm check scope + --- + duration_ms: 1434.1686 + type: 'test' + ... +# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled +ok 63 - stopping a real Python check terminates its child and keeps the completed result as cancelled + --- + duration_ms: 2354.4609 + type: 'test' + ... +# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes +ok 64 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes + --- + duration_ms: 13021.3619 + type: 'test' + ... +# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check +ok 65 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check + --- + duration_ms: 5243.031 + type: 'test' + ... +# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass +ok 66 - a missing interpreter and repeated pytest item objects cannot create a false verification pass + --- + duration_ms: 2624.9358 + type: 'test' + ... +# Subtest: a stop from the event loop interrupts immediate model replies before later tools +ok 67 - a stop from the event loop interrupts immediate model replies before later tools + --- + duration_ms: 1907.2383 + type: 'test' + ... +# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group +ok 68 - a stop after the first tool preserves a complete interrupted multi-call protocol group + --- + duration_ms: 1833.902 + type: 'test' + ... +# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands +ok 69 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands + --- + duration_ms: 5221.645 + type: 'test' + ... +# Subtest: denial prevents command execution and produces a paired denied result +ok 70 - denial prevents command execution and produces a paired denied result + --- + duration_ms: 1901.2261 + type: 'test' + ... +# Subtest: stopping during approval interrupts pending calls without executing or replaying them +ok 71 - stopping during approval interrupts pending calls without executing or replaying them + --- + duration_ms: 1527.4161 + type: 'test' + ... +# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state +ok 72 - stopping a running fixture command terminates its own process tree and retains uncertain state + --- + duration_ms: 2435.5711 + type: 'test' + ... +# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment +ok 73 - command output decodes split UTF-8 and excludes the workbench key from child environment + --- + duration_ms: 1223.7402 + type: 'test' + ... +# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors +ok 74 - model-list testing uses a tentative key without changing the saved connection and redacts service errors + --- + duration_ms: 6.7258 + type: 'test' + ... +# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities +ok 75 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities + --- + duration_ms: 2285.6172 + type: 'test' + ... +# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history +ok 76 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history + --- + duration_ms: 1324.0526 + type: 'test' + ... +# Subtest: hot upgrade refreshes retained model and importer methods while preserving credential and routing objects +ok 77 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects + --- + duration_ms: 745.7607 + type: 'test' + ... +# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails +ok 78 - hot upgrade refuses active probes and restores retained model methods if installation fails + --- + duration_ms: 694.9354 + type: 'test' + ... +# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider +ok 79 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider + --- + duration_ms: 2795.3936 + type: 'test' + ... +# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection +ok 80 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection + --- + duration_ms: 9319.3218 + type: 'test' + ... +1..80 +# tests 80 +# suites 0 +# pass 80 +# fail 0 +# cancelled 0 +# skipped 0 +# todo 0 +# duration_ms 110897.8839 diff --git a/docs/milestone-audit-task-checkpoints-ui-validation.json b/docs/milestone-audit-task-checkpoints-ui-validation.json new file mode 100644 index 00000000..6704345c --- /dev/null +++ b/docs/milestone-audit-task-checkpoints-ui-validation.json @@ -0,0 +1,20 @@ +{ + "success": true, + "passed": [ + "desktop saves and inspects the full original Task and tool provenance without another model request", + "an outside source change is visible and removes the checkpoint continuation action", + "390px explicit continuation keeps the same Task and one original read; a second resume of the old checkpoint is blocked" + ], + "viewportWidths": [ + 1440, + 390 + ], + "pageErrors": [], + "requestFailures": [], + "screenshots": [ + "desktop-original-checkpoint.png", + "mobile-checkpoint-ready.png" + ], + "localFixtureModelRequests": 3, + "realModelRequests": 0 +} \ No newline at end of file diff --git a/docs/milestone-audit-task-ui-validation.json b/docs/milestone-audit-task-ui-validation.json new file mode 100644 index 00000000..cd8fa684 --- /dev/null +++ b/docs/milestone-audit-task-ui-validation.json @@ -0,0 +1,31 @@ +{ + "success": true, + "version": "1.12.1", + "testedAt": "2026-10-30T15:32:43.531Z", + "directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349", + "passed": [ + "structured editor seals two real steps and their dependency without running tools", + "original owned read verifies the prerequisite and opens its hashed proof without replay", + "real two-test and build job supplies the current-source proof and completes the sealed plan", + "outside source edits invalidate the current proof, retain the rejection and block a passed delivery report", + "390px immutable revision adds a mobile step, preserves old criteria and keeps evidence dialogs operable", + "a delayed plan-read failure stays with the original task after selection changes", + "controlled tab unmount during a delayed successful save retains the original task result without restoring the closed editor", + "real host restart retains all plan revisions, accepted/rejected proofs and the original operations without replay" + ], + "pageErrors": [], + "requestFailures": [], + "screenshots": [ + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-desktop-editor.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-desktop-verified.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-mobile-editor.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-mobile-artifact.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-mobile-steps.png", + "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-848a1079-5b4b-4e62-a5e0-9fc48401d349\\task-plan-mobile-overview.png" + ], + "taskId": "e2113ef4-37ea-496f-be05-ae8a6c0f6489", + "sessionId": "00623235-588b-44c8-a204-5737529075c2", + "planRevisions": 3, + "proofs": 4, + "scope": "Independent real Edge desktop/390px Workbench UI, actual npm checks and owned read fixture. No real model credentials or production service access; semantic project acceptance is separate." +} diff --git a/docs/milestone-audit-workspaces-ui-validation.json b/docs/milestone-audit-workspaces-ui-validation.json new file mode 100644 index 00000000..77de1825 --- /dev/null +++ b/docs/milestone-audit-workspaces-ui-validation.json @@ -0,0 +1,28 @@ +{ + "success": true, + "version": "1.12.1", + "at": "2026-10-30T15:35:39.766Z", + "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/milestone-audit-workspaces-review-desktop.png", + ".qa/screenshots/milestone-audit-workspaces-ready-desktop.png", + ".qa/screenshots/milestone-audit-workspaces-recovery-desktop.png", + ".qa/screenshots/milestone-audit-workspaces-review-mobile.png", + ".qa/screenshots/milestone-audit-workspaces-child-mobile.png" + ], + "projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\workspace-ui-ab0158d6-f5bb-4f31-9804-410aa327a027", + "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." +} diff --git a/findings.md b/findings.md index c0b18976..96c66cd1 100644 --- a/findings.md +++ b/findings.md @@ -404,3 +404,56 @@ Claude Code 报告已验证工具输入校验、权限决定、队列并发屏 - 正式服务已是1.12.0/PID19084,原Provider和公开hasKey=true状态保持;15项目/26全部会话/2505执行记录/4476事件逐行散列与导出一致。部署后8个桌面/390px页面状态只读复验通过,四类数据库仍不变。物理service-info.appRoot保留最初启动目录,实际runtimeRoot和健康版本才标识已升级运行代码。 - 最终包与测试输入逐份核对,REA-RUNTIME.json仅builtAt不同,其余JSON字段及全部依赖散列严格一致;未广泛忽略清单。209份输入与Git原字节一致,4份旧文件仅CRLF/LF差异且规范化后逐字节相同,未为凑散列改写原文件。 - 6阶段原日志与13份报告散列封存在docs/model-center-release-identity.json;真实模型请求为0,既有用户选择继续有效。桌面壳、手机配对、隔离worker、多协议/多模态和真实工程成功率均为后续独立开发或验收范围。 + +## 2026-10-30 里程碑审查启动 + +- 用户要求在推进后续新功能前记录计划、逐里程碑审查和修复漏洞;基线ca9042e/3f6797b、1.12.0独立发行与原证据保留,正式服务不普通重启、不使用真实Key或付费模型。 +- 初读发现docs/PRODUCT-PLAN.md开头仍有“1.12源码尚未部署、正式1.11单连接”和“动态MCP未实现”的旧概括,需按最终发行事实更新,同时保留真实模型、WorkBuddy未知格式、OS隔离和桌面/手机等未完成边界。 +- 第一份合并补丁因findings.md占位锚点不匹配被拒绝,没有写入;改用实际末段锚点保存。本阶段报告为docs/MILESTONE-AUDIT.md。 + +- A01已在Windows临时项目实际复现:git-alias/config与credential-alias/config.txt通过内部junction读取受保护夹具,git-alias/new.txt也通过创建预检;直接.git/config被拒绝,说明仅检查词法路径不够。原结果保存.qa/milestone-path-initial-repro.json,未接触用户项目/真实凭据。 +- 修复统一safePath:校验已解析真实路径、受限凭据目录后缀和Windows尾点/空格别名;仍允许指向普通项目内文档的链接,未知副作用和原提案核验流程保持。新增真实junction读/列举/提案及Windows路径别名专项验证。 + +- A02在真实SQLite故障注入中复现:toggle返回磁盘保存失败,但内存enabled=false/revision2,磁盘仍enabled=true/revision1。修复ModelHub保存失败恢复已提交状态;模型选择/运行模式同事务,批量配置导入全部连接、来源与内存凭据统一回滚;原连接设置在成功提交后才更新Key引用。 +- npm audit --json --ignore-scripts已完成,153项依赖元数据中0已知漏洞;原输出与散列保存.qa/milestone-dependency-audit。此检查不证明未存在漏洞,也不代替随包REA等依赖身份验证。 +- 一次只读查询使用不存在的validate-source-package.mjs,已通过rg确认实际verify-source-package.mjs;没有运行错误的验收器或改写发行证据。 + +- A03审查热升级发现Provider保留的ModelHub/ConfigImporter对象未更新方法,补丁源码可能无法作用到已初始化模型中心。升级现保留原对象/凭据引用并更新原型,安装失败恢复旧原型;实际在途模型探针/排队会阻止改配置与热升级。新增原对象保留/失败回滚专项。 +- A04工作台静态响应原来无frame-ancestors/X-Frame-Options,任意页面可以嵌入带审批能力的本地工作台。补充禁止嵌入、同源脚本/API与no-referrer策略;React仅已有动态布局允许内联style,模型文字仍经安全React文本渲染。实际Edge对照另行验收。 +- 首次构建显式调用Node24的npm,但npm脚本仍由原PATH找到Node16,Vite在构建前拒绝;改用本次进程PATH前置Node24,保留失败记录,不更改系统PATH或正式服务。一次不存在Markdown.tsx查询改用实际components.tsx。 + +- 新接口探针专项首轮19/20,唯一失败在探针成功之后:测试只传mode,违反既有/config完整地址/模型契约导致Invalid URL。前面的并发请求409/0新增派发均已通过;测试改为提交完整配置,不降低原接口验证。模型保存/导入10/10、升级原对象/回滚及两种实际编译宿主升级均通过。 + +- 接续时复用上一轮源码和原证据,未重复运行初始复现;最后一次版本正则查询因PowerShell引号形成无效正则,改为rg -F明确字符串查询,实际匹配包括verify-change-sets-ui.mjs也需增加1.12.1。一次多份长文读取被限额截断,后续缩小段落/输出。 +- 后续顺序已封存docs/NEXT-STEPS.md:先完成审查补丁,再隔离worker、受控引擎及Purge同题对照、Windows桌面、可撤销手机配对、跨协议/多模态、隔离自我迭代。更新总计划的正式1.12与stdio MCP状态,同时保留尚未完成边界。 + +- A05在隔离子进程中以3个自有环境标记实际复现:PowerShell终端、npm检查及Python检查全部继承宿主未知凭据变量。原证据.qa/milestone-environment-initial-repro.json,未读真实Key。新增projectEnvironment只传系统/运行路径和内核明确字段,三条执行链路统一使用;原Python隔离选项保留。实际shell/npm/Python行为测试验证凭据不继承且UTF-8、测试/构建与结构化证据可用。 + +- 1.12.1首次完整相关专项80/80、0失败/取消/跳过,原TAP/散列保存.qa/milestone-targeted-673244ae-32ef-46d2-9719-63d73d92598d;修正后的探针API、路径`.`兼容和新增三条真实执行检查均通过。 +- 实际旧1.12发行已证明可被外部夹具iframe加载、同进程升级后原ModelHub/Importer、公开配置和会话保持。随后导入故障测试错误地选用无效URL,来源解析按契约预先跳过该项,导致“应拒绝”断言失败;改用预览保留但提交拒绝的超长夹具Key,不改变产品契约。原失败保留.qa/milestone-security-ui-100d0d0e-d705-44a4-a6ae-0d1571541714。 + +- 修正后真实旧1.12→1.12.1进程、失败批量回滚/预览保留、两类夹具凭据、Edge iframe/外部脚本拒绝、1280/390模型中心和Blob PNG8组通过;所属PID退出、9229关闭,原结果目录9f38a7ec保留。额外配置HTTP磁盘提交故障/非法Key/成功重试检查通过,真实模型请求0。 +- 一次task_plan/progress合并补丁使用错误progress首行锚点导致全批拒绝;只读确认两个文件未写入后按实际首行修正,不将补丁失败当作完成。后续冻结前只规范本次修改的代码/测试/脚本LF,原未修改输入不改写。 + +- 完整UI验收器原gitEnvironment过滤也丢掉独立QA Python路径,现仅额外显式传入该绝对路径,仍不继承模型凭据;完整20类流程进行中。 +- 查询归档/便携验收器--help时发现旧脚本未实现帮助分支,实际执行了一次旧1.12独立验收(端口51528、夹具4/4、REA/Edge通过并停止,真实模型0)。只覆盖.qa临时指针,未修改docs历史报告或正式服务。为归档/源码/便携三个入口增加先行帮助和未知参数拒绝;原误运行证据另存,不计为1.12.1验收。 + +- A01追加静态别名复核实际发现硬链接绕过:AGENTS.md与.secrets/owned.txt共享文件,nlink=2,普通读取和自动项目规则均暴露自有受保护标记。原证据.qa/milestone-hardlink-initial-repro.json,不含真实凭据。realpath无法找出所有硬链接名称,新增常规文件nlink=1保护并在清单跳过多路径文件;普通项目junction仍可用,独立复制文件可正常读取。 +- 正在运行的首个独立源码候选20261030150404738保持其原输入,仅作为硬链接补强前基线。新增修复只在工作仓库,不改该解压目录;最终发行需使用追加修复后的新源码/构建/UI与完整回归,不沿用首次候选通过结果。 + +- 硬链接专项首轮8/9,新增提案测试错误使用proposeFile参数顺序,未达到路径门控即TypeError;已按store/session/args契约修正,原读保护及其余八项通过。未降低保护或改写原失败。 + +- 首个独立源码候选最终368/369、唯一失败为旧批次Windows别名测试:新的safePath在提案入口已经拒绝尾点,旧测试仍假定先生成提案。更新验证同时要求当前提案入口拒绝,以及旧宿主保留的别名提案仍在批次层拒绝;原失败/TAP与冻结源码目录保留,不登记为最终通过。 +- 硬链接读取/提案/清单/规则保护和独立文件副本恢复9/9通过。追加后将重新封存源码及完整UI,首轮150组仅作为补强前基线保存。 + +- 旧别名提案在批次层也由共用safePath更早拒绝,修正测试首轮仍期待旧“路径别名”文案而失败;按实际保护错误“可读取的项目范围”核对,两层的实际拒绝保留。原失败在执行输出/本记录中,不伪造原TAP。 + +## 2026-10-30 追加路径复核收尾 + +- 接续原95492路径/提案/补丁/变更集验证,5文件29/29通过,0失败/取消/跳过;原TAP SHA256为875bc7cebd4893db0468901b4af234b2c684c08a6d52cb5a9d0b53d30ea1176e,副本与原报告保存docs/milestone-audit-path-followup-*。 +- 实际硬链接受保护规则可被读取/自动加载的问题已补强,当前多硬链接明确拒绝、独立副本仍可读取;首个独立候选不包含此补强且368/369,不能发布,下一步重新构建和完整验收。 +- 一次文档组合补丁因findings占位锚点不存在被拒绝,未写入文档;原证据复制已完成,改用准确锚点及追加记录保存。 + +- 正式服务当前只读实测为1.12.0/PID23172(2026-10-30T14:33:10Z创建),service-info/appRoot/runtimeRoot均指向原1.12不可变发行;hasKey=true、compatible/gpt-6.1-sol,16项目/20可见会话,无忙任务。历史1.12交付PID19084不是当前进程,本轮未重启服务;原历史数据计数保持为当时记录。升级驱动已绑定新实际preflight,升级前重新快照全部四表/每行及全部会话导出,保留当前Provider与新增数据,未读取Key/发送模型请求。 + +- 7b1f529新构建完整UI20类150组全部通过、0页面/请求异常,正式4318不参与夹具;当前源码快照218份输入/6份构建已保存.qa/milestone-final-code-baseline.json。首轮候选证据已另存,接下来生成新的不可变包并独立完整回归,不重复开发树全量。 diff --git a/progress.md b/progress.md index 2d11310f..e95f7f1c 100644 --- a/progress.md +++ b/progress.md @@ -1,5 +1,15 @@ # 统一执行进度 +## 2026-10-30 里程碑审查与1.12.1候选 + +- 后续顺序、前置和真实完成门槛已保存docs/NEXT-STEPS.md;docs/MILESTONE-AUDIT.md逐版本对照1.0–1.12,并明确M0–M6哪些只是部分完成。更新PRODUCT-PLAN与VALIDATION的正式1.12/stdio MCP和1.7–1.9索引。 +- A01路径、A02配置事务、A03保留模型原型/活动门控、A04页面策略和A05宿主环境传递已修复;80/80相关专项与额外实际配置HTTP故障检查通过。 +- 原不可变1.12进程的实际升级与Edge8组通过:原PID、初始化Hub/Importer、预览和夹具凭据保留;失败批量不部分导入;第三方iframe/脚本拒绝,1280/390模型中心与Blob PNG仍正常。原证据.qa/milestone-security-ui-9f38a7ec-8649-4260-9c43-375425e6c8dd,两张截图已目视核对。 +- 首轮Edge测试选择无效URL作为提交故障,但预览按契约跳过,原失败目录100d0d0e保留;修正为超长自有凭据后通过。一次含错误progress首行锚点的合并补丁被拒绝,确认所有目标文件未写入,再按实际首行应用。 +- 准备完整UI与独立源码候选验收。正式4318暂未升级、不普通重启、不读取真实Key、真实模型0请求;后续隔离worker等新能力尚未开始。 + +- 完整20类150组UI全部通过,0页面/请求异常;源代码修复已分步提交c1e9575/f4bd0ad。24项能力基线已更新至实际交付1.12,原总计划与历史执行记录分开;后续冻结独立源码回归,期间不修改实现输入。 + ## 2026-10-30 MCP管理与运行记录接续 - 接续 `feat/model-center-1.12` 工作树;Skills/检查点提交已存在,MCP 改动仍未提交且完整保留。 @@ -458,3 +468,13 @@ - 部署后1280px/390px各检查执行计划、模型中心、Skills和MCP,8个实际页面状态通过,0页面异常/请求失败/HTTP错误/写入请求;四类数据库散列仍一致。6阶段日志和13份报告已封存docs/model-center-release-identity.json,调试端口9229关闭,本轮真实模型请求0。 - 升级前首次REA清单时间差使流程在新handler安装前停止;部署后Python环境缺Playwright使检查在浏览器启动前退出,随后使用锁定Node Playwright完成8组只读复验。两次均保留原记录,不修改产品代码、不重放工具或调用模型。 - 本轮收尾仅修正文档中的旧候选/未发布状态,补充最终验收和后续开发顺序。代码已由3f6797b封存;最终报告和规划另作本地文档提交,不推送。下一独立阶段为隔离worker及受控外部引擎,再推进桌面、真实手机配对、多协议/多模态与迭代评测;真实模型验收继续按用户选择暂缓。 + +## 2026-10-30 追加路径复核收尾 + +- 接续原95492路径/提案/补丁/变更集验证,5文件29/29通过,0失败/取消/跳过;原TAP SHA256为875bc7cebd4893db0468901b4af234b2c684c08a6d52cb5a9d0b53d30ea1176e,副本与原报告保存docs/milestone-audit-path-followup-*。 +- 实际硬链接受保护规则可被读取/自动加载的问题已补强,当前多硬链接明确拒绝、独立副本仍可读取;首个独立候选不包含此补强且368/369,不能发布,下一步重新构建和完整验收。 +- 一次文档组合补丁因findings占位锚点不存在被拒绝,未写入文档;原证据复制已完成,改用准确锚点及追加记录保存。 + +- 正式服务当前只读实测为1.12.0/PID23172(2026-10-30T14:33:10Z创建),service-info/appRoot/runtimeRoot均指向原1.12不可变发行;hasKey=true、compatible/gpt-6.1-sol,16项目/20可见会话,无忙任务。历史1.12交付PID19084不是当前进程,本轮未重启服务;原历史数据计数保持为当时记录。升级驱动已绑定新实际preflight,升级前重新快照全部四表/每行及全部会话导出,保留当前Provider与新增数据,未读取Key/发送模型请求。 + +- 7b1f529新构建完整UI20类150组全部通过、0页面/请求异常,正式4318不参与夹具;当前源码快照218份输入/6份构建已保存.qa/milestone-final-code-baseline.json。首轮候选证据已另存,接下来生成新的不可变包并独立完整回归,不重复开发树全量。 diff --git a/task_plan.md b/task_plan.md index 63289fbf..4aabae0c 100644 --- a/task_plan.md +++ b/task_plan.md @@ -1,7 +1,19 @@ # Agent Workbench:核心代理能力研究与产品计划 +## 2026-10-30 当前任务:里程碑回顾、漏洞修复与后续计划封存 + +用户要求先回顾审查每个里程碑、修复漏洞并核对计划实现,再推进后续新能力。本阶段暂停新功能切片,不暂停已部署1.12.0服务;真实模型验收继续暂缓。 + +1. [complete] 后续顺序/前置/验收门槛已写docs/NEXT-STEPS.md;1.0–1.12全部节点及M0–M6计划/实现/原证据/遗留项已对照,修正总计划/验证索引过时概括。 +2. [complete] 核对HTTP、路径/Git、执行/取消/恢复、上下文/计划、模型/导入、Skills/MCP/REA/引擎/浏览器;A01/A02/A05真实隔离复现已封存,依赖0已知漏洞另记。 +3. [complete] A01–A05修复及追加硬链接补强完成;80项相关专项、额外配置故障HTTP检查、实际旧1.12→补丁升级/Edge策略8组及路径/提案/变更集29项复验通过;初始复现与失败保留。两张新界面/拒绝嵌入截图已目视核对。 +4. [in_progress] 首轮1.12.1独立源码368/369,唯一失败为Windows尾点已在提案层提前拒绝而旧测试仍期待生成提案;更新当前/旧提案两层断言,29项复验通过。7b1f529与新构建的20类150组UI全部通过,218份输入/6份构建已快照;进入新不可变候选、独立源码冻结回归和保留当前正式Provider/全部历史验收;首失败候选不能部署。 +5. [pending] 交付审查报告、修复与复验结果、未完成能力和后续起点。真实模型请求为0,后续隔离worker等只在本阶段收尾后推进。 + ## 2026-10-30 当前接续:1.12 完整发行与本地交付 +以下按原过程保留历史执行记录;历史中的pending/in_progress不作为新的执行队列。最新阶段状态以本文顶部为准,尚未完成的能力与后续顺序统一见docs/NEXT-STEPS.md。 + 1. [complete] 模型中心/池、来源核对记忆、检查点、Skills已本地实现并分段提交;MCP实际stdio、未知结果门控、人工核对与无报告恢复已补强。 2. [complete] MCP补强后20项专项、6组管理与2组真实中断界面通过;353项旧全量仅作为补强前基线,不替代最终源码结果。 3. [complete] 统一1.12版本/文档/验收脚本;20类150组界面通过,标题栏5组复验及最终MCP6+2组复验通过。修复并实际复验长MCP参数审批上限,20项stdio/注册专项全通过。