From 24b8341ad5b01727ddc5a12edf048b3f4728d607 Mon Sep 17 00:00:00 2001 From: Agent Workbench Dev Date: Sat, 31 Oct 2026 03:33:14 +0800 Subject: [PATCH] docs: preserve independent 404-test source acceptance and raw evidence --- .gitattributes | 1 + CHANGELOG.md | 3 +- README.md | 2 +- docs/QA-1.13.md | 14 +- docs/RETROSPECTIVE-1.13.md | 4 +- docs/VALIDATION.md | 4 +- docs/workers-source-browser-log.txt | 1 + docs/workers-source-build-log.txt | 14 + ...-source-candidate-archives-validation.json | 24 + docs/workers-source-engines-log.txt | 1 + docs/workers-source-inputs-comparison.json | 68 + docs/workers-source-install-log.txt | 7 + docs/workers-source-package-validation.json | 1316 +++++++++ docs/workers-source-rea-log.txt | 1 + docs/workers-source-tested-candidate.json | 40 + docs/workers-source-tests.tap | 2441 +++++++++++++++++ findings.md | 2 + progress.md | 2 + task_plan.md | 2 +- 19 files changed, 3936 insertions(+), 11 deletions(-) create mode 100644 docs/workers-source-browser-log.txt create mode 100644 docs/workers-source-build-log.txt create mode 100644 docs/workers-source-candidate-archives-validation.json create mode 100644 docs/workers-source-engines-log.txt create mode 100644 docs/workers-source-inputs-comparison.json create mode 100644 docs/workers-source-install-log.txt create mode 100644 docs/workers-source-package-validation.json create mode 100644 docs/workers-source-rea-log.txt create mode 100644 docs/workers-source-tested-candidate.json create mode 100644 docs/workers-source-tests.tap diff --git a/.gitattributes b/.gitattributes index be6b09b8..952a6936 100644 --- a/.gitattributes +++ b/.gitattributes @@ -8,3 +8,4 @@ tests/fixtures/legacy-workbench-0.1/dist-server/server.mjs binary docs/workers-*.tap binary docs/workers-*.log binary docs/workers-*-log.txt binary +docs/workers-*.json -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol diff --git a/CHANGELOG.md b/CHANGELOG.md index e32300e0..a9ad5fc5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,11 +1,12 @@ # Agent Workbench 更新记录 -## 1.13.0 · 验收中 · 2026-10-31 +## 1.13.0 · 2026-10-31 - 新增固定父目标和两个受限子任务,各自使用独立Git工作区、稳定任务/运行身份和封存范围;子检查需审批,完成以实际文件及当前检查为准。 - 父任务停止等待所属请求和检查进程树,迟到/未知用量纳入累计预算,续接保持原总时限;宿主退出后先核对原记录与现场,不重放工具或补造成功。 - 归集原文件、检查日志与来源链,显示重叠路径/父已有修改冲突;父工程使用新封存变更集,重新检查和本地Git后才能完成。 - 桌面和390px协作控制台可处理子审查、父合并、停止及显式恢复,历史迟到错误按原记录隔离。[三功能样本](benchmarks/workers-delivery-v1/README.md)分别验证Node/React/Python,真实模型语义独立待验。最终结果见[1.13验收](docs/QA-1.13.md)。 +- 独立源码404/404、完整UI21类160组和三工程13节点通过;原失败日志保持,修正后的宿主崩溃实际心跳及资源清理也在新完整回归通过。安装与正式升级按1.13验收记录单独判定。 ## 1.12.1 · 2026-10-30 diff --git a/README.md b/README.md index 930ca337..3e198197 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ Agent Workbench 将 Claude Code 与 Cursor 的机制研究整合为独立的本地 AI 编程工作台,并内置模型池、项目记忆、Skills/MCP、REA 工件研究、本地DeepSeek Harness连接核验、实际页面验收和有依赖的执行计划。工程索引、精确补丁、多文件整批审查、Node/Python实际检查、浏览器交互、本地Git提交及交付报告可以在同一个Task中完成。 -1.13.0候选新增[隔离协作](docs/WORKERS.md):父目标与两个受限Git工作区、累计预算/停止恢复、当前成果核对、具体冲突和父工程审查/检查/Git交付。三个真实功能工程已通过,父Node8/8、React9/9、Python10/10及构建/编译/Git,React内置Edge两视口各10项断言;完整界面和独立发行继续验收,正式服务保持1.12.1。最终状态见[1.13记录](docs/QA-1.13.md)。 +1.13.0新增[隔离协作](docs/WORKERS.md):父目标与两个受限Git工作区、累计预算/停止恢复、当前成果核对、具体冲突和父工程审查/检查/Git交付。独立源码404/404、完整界面21类160组与三个真实功能工程通过,父Node8/8、React9/9、Python10/10及构建/编译/Git,React内置Edge两视口各10项断言。实际安装/服务版本以页面和[1.13验收与部署记录](docs/QA-1.13.md)为准。 模型中心支持多连接、轮询/权重、故障冷却与请求账本,并可预览导入已验证的CCSwitch/工作台配置。项目记忆按来源复核后进入有界上下文;任务检查点保留全部要求和原工具结果;Skills按版本读取,MCP按实际契约和逐次确认执行。运行中心提供不发送模型请求的本地巡检,发行验收与限制见[1.12记录](docs/QA-1.12.md)。 diff --git a/docs/QA-1.13.md b/docs/QA-1.13.md index dd8ec4e9..402d1ace 100644 --- a/docs/QA-1.13.md +++ b/docs/QA-1.13.md @@ -1,6 +1,6 @@ -# 1.13 开发与验收记录 +# 1.13 验收与发行记录 -2026-10-31。本阶段尚未发行,正式服务仍保持不可变1.12.1。这里记录切片结果,不将局部测试或夹具成功计为真实模型交付。 +2026-10-31。新独立源码404/404、完整UI21类160组及三工程13节点通过。最终便携运行与保留正式状态升级待验,正式服务仍为不可变1.12.1。以下保留各切片和原失败,不将夹具成功计为真实模型推理或自主完成率。 ## 切片一:父子记录与受限执行 @@ -16,7 +16,7 @@ 停止等待所属请求及检查进程,迟到/未报告响应保留累计用量;续接不重置token、步数、工具次数和原总时限。部分创建、未知写入及宿主崩溃先核对原输入/SHA和现场,再显式继续或保留现场结束;历史unknown和原工件保留,不补造完成结果。Windows按原创建身份记录和核对进程树,仍存活时拒绝解除核对,恢复不会根据历史PID自动终止进程。 -最新整合原轮64/65,唯一失败是QA清理漏掉快照后新生后代,产品正确拒绝存活PID;修正自有夹具清理并等待结束后,真实宿主崩溃专项1/1通过。未将两轮拼成65/65。原失败TAP和成功专项分别保留,最终独立源码完整回归仍待验。 +整合切片原轮64/65,唯一失败是QA清理漏掉快照后新生后代,产品正确拒绝存活PID;修正自有夹具清理并等待结束后,真实宿主崩溃专项1/1通过。未将两轮拼成65/65。原失败TAP和成功专项分别保留;当前新独立源码404/404已包含强化后的宿主崩溃场景。 控制台第三轮桌面/390px完整10节点通过,0页面异常/请求失败;计划、独立工作区、子审批/真实检查、父批次/检查/Git、具体冲突、停止、迟到历史错误隔离和原证据核对/保留现场均已操作。原目录workers-ui-c912d9ca-869f-4bf3-a2c3-d7a7b8765236;前两次验收器文案/异步弹窗等待失败保留,不改写结果。桌面截图已目视检查。 @@ -38,4 +38,10 @@ QA补强91cdd45后重新冻结232份输入、6份构建及40份基准,三个 随后串行完整UI21类160组全部通过,0页面异常/请求失败,原报告和21份日志副本以workers-all-ui-validation及workers-final-ui-logs封存。新控制台c4ae46be桌面/390px截图已目视核对,通道/预算/范围/父审查与具体冲突清楚,窄屏无横向溢出。全程源码与构建冻结,正式4318不参与夹具;下一步新不可变源码/便携及保留状态正式升级,不复用修正前候选来宣称最终通过。 -待完成:新候选独立源码/便携与保留正式状态发行。正式服务只读复核为1.12.1/PID23172、无忙任务、2连接/1池、hasKey=true;不读取原Key,不发送模型请求。原Provider和全部历史升级后逐行/全导出复核。 +## 新独立源码通过,最终安装验收待完成 + +新候选20261030190844003归档通过:便携11232/源码9532文件,独立解压至D:/awb/source-check-ab4af9d650d0426ba58562fe29927139。使用固定Node24.22.1、Python3.10.11/pytest8.4.2,离线安装及6份构建、随包REA三操作、实际DeepSeek六方法探针和Edge两视口通过;完整TAP404/404,0失败/取消/跳过/todo。此前失败的第354项在这一整轮也通过,不能与旧403/404轮拼接。 + +232份源码输入与冻结基线全程一致,40份基准保持;原报告、完整TAP及五份阶段日志保存为workers-source-*。原403/404候选与每一轮界面/工程失败保留;最终包只补证据与文档,不改测试过的代码或运行包。 + +待完成:最终不可变便携运行与保留正式状态发行。正式服务升级前重新读取实际PID、公开模型中心和全部历史;原Provider/Key不复制,数据库四表每行及全部会话导出升级后逐项复核,本轮0真实模型请求。 diff --git a/docs/RETROSPECTIVE-1.13.md b/docs/RETROSPECTIVE-1.13.md index a1c4462a..982380c4 100644 --- a/docs/RETROSPECTIVE-1.13.md +++ b/docs/RETROSPECTIVE-1.13.md @@ -11,7 +11,7 @@ | 父成果/合并 | 当前源码、HEAD/index/config、提案链、原检查/用量核对;重叠/父已有修改显示具体冲突,应用前重新核对,父检查/Git完成后收尾 | 合并5项与HTTP、控制台原记录;三个父工程只提交审查过的文件 | | 控制台 | 桌面/390px计划、两个真实通道、审批、原证据、冲突、停止和恢复,迟到历史错误不污染当前记录 | 10节点真实界面;原文案/异步弹窗等待及网络失败保留 | | 功能工程 | Node父8/8、React父9/9、Python父10/10及构建/编译/Git;React内置Edge两视口各10项断言,原owner修改保持 | workers-projects-validation:13节点、原失败测试、9会话导出及完整自有工件 | -| 独立发行 | 新232份输入/6构建/40基准冻结,完整UI21类160组及三工程13节点通过;首独立源码403/404被拒绝,修正后新源码/便携/升级继续验收 | code-baseline、final-ui-logs及QA-1.13,只有最终成功报告才接受发行 | +| 独立发行 | 232份输入/6构建/40基准保持;新独立源码404/404、全UI21类160组及三工程13节点通过,原403/404候选拒绝并保留;最终便携/升级待验 | source-package、code-baseline、final-ui-logs及QA-1.13 | ## 已修复的关键问题 @@ -31,7 +31,7 @@ React统计在1280px内联数字/单位,在390px分行。最终按固定CSS分 并行源码与界面验收曾产生一次ERR_NO_BUFFER_SPACE。协作功能10节点完成,但错误门槛仍将整轮判失败;保留原请求失败,后续按资源诊断/串行完整验收处理,不忽略错误或改变OS配置。 -首个独立源码最终403/404,宿主崩溃用例的清理钩子EPERM使候选拒绝。修正夹具为两个实际心跳PID均有原创建身份记录后再崩溃;资源清理采用onCleanup,先于目录删除,有界异步重试保留持久失败。停止与显式确认后原心跳不再变化的新增断言已在真实宿主退出专项1/1通过,最终完整新候选仍需重新验收,不能将两轮拼为一次通过。 +首个独立源码403/404,宿主崩溃用例的清理钩子EPERM使候选拒绝。修正夹具为两个实际心跳PID均有原创建身份记录后再崩溃;资源清理采用onCleanup,先于目录删除,有界异步重试保留持久失败。停止与显式确认后原心跳不再变化的新增断言在专项1/1及当前新独立完整404/404轮都通过,原失败不改写,不将两轮拼为一次通过。 ## 后续门槛 diff --git a/docs/VALIDATION.md b/docs/VALIDATION.md index 7606810d..c56ee1c2 100644 --- a/docs/VALIDATION.md +++ b/docs/VALIDATION.md @@ -1,8 +1,8 @@ # Agent Workbench 验收记录 -## 1.13 · 隔离协作开发验收,发行进行中 +## 1.13 · 隔离协作独立源码与界面通过,安装验收进行中 -父目标与两个受限worker、独立Git工作区、累计预算/停止恢复、来源复核/具体冲突、父工程审查/检查/Git已实现。新三功能工程13节点及父Node8/8、React9/9、Python10/10与构建/编译/Git通过,React内置Edge两视口各10项断言通过;完整UI21类160组通过,0页面/请求异常。91cdd45补强两份实际心跳PID归属和清理顺序,232份输入/6构建/40基准冻结;首个独立源码403/404失败及六份日志保留,新独立源码/便携及保留状态正式升级待验,正式仍1.12.1。真实模型0请求,见[1.13验收](QA-1.13.md)、[回顾](RETROSPECTIVE-1.13.md)及[1.14计划](PLAN-1.14.md)。 +父目标与两个受限worker、独立Git工作区、累计预算/停止恢复、来源复核/具体冲突、父工程审查/检查/Git已实现。新三功能工程13节点及父Node8/8、React9/9、Python10/10与构建/编译/Git通过,React内置Edge两视口各10项断言通过;完整UI21类160组通过,0页面/请求异常。91cdd45补强两份实际心跳PID归属和清理顺序,232份输入/6构建/40基准保持;新候选20261030190844003完整独立源码404/404、REA/DeepSeek/Edge及归档通过,首个403/404失败及六份原日志保留。最终便携与保留状态正式升级待验,本轮真实模型0请求。见[1.13验收](QA-1.13.md)、[回顾](RETROSPECTIVE-1.13.md)及[1.14计划](PLAN-1.14.md)。 ## 1.12.1 · 里程碑审查与确认问题修复 diff --git a/docs/workers-source-browser-log.txt b/docs/workers-source-browser-log.txt new file mode 100644 index 00000000..e296c7d4 --- /dev/null +++ b/docs/workers-source-browser-log.txt @@ -0,0 +1 @@ +{"success":true,"version":"1.13.0","directory":"D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\browser-native-1a1f20d0-a9a9-451f-9cd0-0843cbb755ee","results":[{"jobId":"2b3fa3c2-b312-408d-99ff-9fadc049fb02","taskId":"f9254215-3554-48a2-be7e-a6fbf0b96103","viewport":{"width":1280,"height":900},"status":"passed","assertions":{"total":3,"passed":3,"failed":0},"resultSha256":"b464587681f4b3da6d68003006b0c3421e115e3d15bc31eb2e9d58262b767cd0","buildSha256":"1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd","screenshotSha256":"a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54","browserExited":true,"reusedOriginalJob":true},{"jobId":"85078cee-545b-4635-a07d-c33f4aac0ef0","taskId":"f9254215-3554-48a2-be7e-a6fbf0b96103","viewport":{"width":390,"height":844},"status":"passed","assertions":{"total":3,"passed":3,"failed":0},"resultSha256":"9f65da2317bd34136431eed0a35beb9a143c118eb3a57eadbae4df73673d2ab3","buildSha256":"1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd","screenshotSha256":"590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f","browserExited":true,"reusedOriginalJob":true}],"modelRequests":0,"rootExited":true} diff --git a/docs/workers-source-build-log.txt b/docs/workers-source-build-log.txt new file mode 100644 index 00000000..bb9a8461 --- /dev/null +++ b/docs/workers-source-build-log.txt @@ -0,0 +1,14 @@ + +> local-agent-workbench@1.13.0 build +> tsc --noEmit && vite build && node scripts/build-server.mjs + +vite v7.3.7 building client environment for production... +transforming... +✓ 1712 modules transformed. +rendering chunks... +computing gzip size... +dist-client/index.html  0.50 kB │ gzip: 0.37 kB +dist-client/assets/index-Ck6k2AkM.css 122.54 kB │ gzip: 23.73 kB +dist-client/assets/index-Cxe0yWpO.js 471.04 kB │ gzip: 139.56 kB +✓ built in 1.38s +Server bundle built. diff --git a/docs/workers-source-candidate-archives-validation.json b/docs/workers-source-candidate-archives-validation.json new file mode 100644 index 00000000..f089d5b3 --- /dev/null +++ b/docs/workers-source-candidate-archives-validation.json @@ -0,0 +1,24 @@ +{ + "success": true, + "version": "1.13.0", + "testedAt": "2026-10-30T19:09:59.187471+00:00", + "archives": [ + { + "kind": "portable", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-win-x64-20261030190844003.zip", + "files": 11232, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "4767b7775dd082c8a396066f8689a87efdc8a662eba1261009fd164aa500aead" + }, + { + "kind": "source", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-source-20261030190844003.zip", + "files": 9532, + "crcPassed": true, + "manifestAndDirectoryMatch": true, + "sha256": "41daee87775ef237d123ffbb427344f51a8db15f295aceced91b4b7c04005582" + } + ], + "extractionRoot": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003" +} \ No newline at end of file diff --git a/docs/workers-source-engines-log.txt b/docs/workers-source-engines-log.txt new file mode 100644 index 00000000..c8ea0d35 --- /dev/null +++ b/docs/workers-source-engines-log.txt @@ -0,0 +1 @@ +{"success":true,"version":"1.13.0","directory":"D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\native-engine-408fd97a-c574-43cc-a11b-267aa558fc7f","sdkVersion":"0.2.1-rc.2","nativeMethods":["initialize","session/working-directory/get","session/wait","session/resume","session/cancel","shutdown"],"modelRequests":0,"rootExited":true} diff --git a/docs/workers-source-inputs-comparison.json b/docs/workers-source-inputs-comparison.json new file mode 100644 index 00000000..5cacce6a --- /dev/null +++ b/docs/workers-source-inputs-comparison.json @@ -0,0 +1,68 @@ +{ + "success": true, + "version": "1.13.0", + "testedAt": "2026-10-30T19:28:36.998Z", + "codeCommit": "91cdd454ed9fed484a67b4f909aae4bb75e05161", + "commit": "be02e99b7db9ce13c4487eb90d479c4333f98a85", + "finalSourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-source-20261030190844003", + "finalPortableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-win-x64-20261030190844003", + "independentSourceRoot": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003", + "tests": { + "tests": 404, + "pass": 404, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "inputFiles": 232, + "exactBytes": 228, + "normalized": [ + { + "path": "scripts/verify-ui.mjs", + "sourceSha256": "d9e7b3e8eb0ff80168acfd5d320685db6d4e1f53827cac4b96cffd5e54c758b6", + "gitBlobSha256": "cd57dd67aada66f667a4e62b7a8f76a79d3c09acd7ba7c658b89e6d38dc6be9f", + "difference": "Previously recorded unchanged file; exact bytes match after CRLF to LF only." + }, + { + "path": "src/client/SkillCenter.tsx", + "sourceSha256": "b227ffdccf1d90ac969f1e4e2a56c592b7c9eac13746bf0c90ee9d9e702e9f10", + "gitBlobSha256": "de7a4426aef468a73a9522da9883592ab0cc29a1f2b3786b764cd51a304347b2", + "difference": "Previously recorded unchanged file; exact bytes match after CRLF to LF only." + }, + { + "path": "src/client/styles.css", + "sourceSha256": "2712f7bb0a0145a6945ea904ba95a1a189831fef40108bdc4300400cd4d20218", + "gitBlobSha256": "734193e1a166024f1418c021bbd56255412d49268386c2c688e5766ef118e438", + "difference": "Previously recorded unchanged file; exact bytes match after CRLF to LF only." + }, + { + "path": "tests/skills.test.mjs", + "sourceSha256": "c7228c190337bb5f2b9ab5a85ad34b78fd03541854e83197d7c4d2506bb3c6c6", + "gitBlobSha256": "977e987ccdeab5bf07fd3dd1788d8ba866a3dc3715c9dd947982a9abfbab7e06", + "difference": "Previously recorded unchanged file; exact bytes match after CRLF to LF only." + } + ], + "buildMatchedFiles": 6, + "comparedFiles": 8815, + "comparedFolders": [ + "src", + "tests", + "scripts", + "public", + "benchmarks", + "runtime" + ], + "repackedMetadata": [], + "logsVerified": 6, + "validationNode": { + "path": "C:\\Program Files\\nodejs\\node.exe", + "version": "v24.22.1", + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5" + }, + "portableNode": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-win-x64-20261030190844003\\runtime\\node.exe", + "sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5" + }, + "scope": "All frozen inputs/builds and native source runtime compared with independently validated source. Git exceptions limited to four previously recorded unchanged CRLF/LF files." +} diff --git a/docs/workers-source-install-log.txt b/docs/workers-source-install-log.txt new file mode 100644 index 00000000..33c40a28 --- /dev/null +++ b/docs/workers-source-install-log.txt @@ -0,0 +1,7 @@ + +added 78 packages in 7s +npm warn install-scripts 2 packages have install scripts not yet covered by allowScripts: +npm warn install-scripts esbuild@0.25.12 (postinstall: node install.js) +npm warn install-scripts esbuild@0.28.2 (postinstall: node install.js) +npm warn install-scripts +npm warn install-scripts Run `npm install-scripts ls` to review, or `npm install-scripts approve ` to allow. diff --git a/docs/workers-source-package-validation.json b/docs/workers-source-package-validation.json new file mode 100644 index 00000000..e16156a0 --- /dev/null +++ b/docs/workers-source-package-validation.json @@ -0,0 +1,1316 @@ +{ + "success": true, + "version": "1.13.0", + "testedAt": "2026-10-30T19:27:10.874Z", + "sourceRoot": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003", + "directory": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67", + "nodeVersion": "v24.22.1", + "python": { + "version": "3.10.11", + "pytest": "8.4.2", + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\dev-task-plans\\.qa\\python-3.10\\Scripts\\python.exe" + }, + "offlineInstall": true, + "inputs": [ + { + "path": "index.html", + "bytes": 411, + "sha256": "893c264c5c1293d6af54a6ca65280cf637b5afffee3cd2156ff88e4a44c370c5" + }, + { + "path": "package-lock.json", + "bytes": 79507, + "sha256": "54cdcf0680390a842734cbfced4fabfd993dc4b0038b7d5a888520ad87c752ba" + }, + { + "path": "package.json", + "bytes": 2140, + "sha256": "6a5ac13790ac78cca237c3cb1f7d4d73888415efc9e54829407475c7ba3ceea3" + }, + { + "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": 702, + "sha256": "257e828d9725de0955eb904cd924874fc07210923940281bf983093aca6c5c1c" + }, + { + "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": 12314, + "sha256": "51928f911fe71bfffc8cdfe917daaece85269f4dd6e702bd5a2422096359ca52" + }, + { + "path": "scripts/verify-all-ui.mjs", + "bytes": 8969, + "sha256": "1ff53abdb41e4a5ead21ec10069d6bae9db446597550c1f566073422621921ac" + }, + { + "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": 16126, + "sha256": "8482868f522bc3d59ae0b0220930e412a6a83ad42c27877f52a108365f4abec4" + }, + { + "path": "scripts/verify-context-ui.mjs", + "bytes": 18455, + "sha256": "ce2f507ace0231f5275618ce7a9dab4f89269452883f55ef13ec2676f4a663be" + }, + { + "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": 14643, + "sha256": "fadfffed82aebbc67208dab5de686a63b34059d5e4e6521e3a262016fb9a4c49" + }, + { + "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": 10206, + "sha256": "c351194c237ec265f532793c90f5c4fbbb802b7256fe5033f513b92a9df8821e" + }, + { + "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-workers-projects.mjs", + "bytes": 24099, + "sha256": "9fe0cf44540a9739fdba28741c02e826f89e8504c7165b5587a10e598e5b30c5" + }, + { + "path": "scripts/verify-workers-ui.mjs", + "bytes": 18594, + "sha256": "0630855581368c708ad71489449d440798e13fbc7a6ec4235770fb7d584b7b0d" + }, + { + "path": "scripts/verify-workspaces-ui.mjs", + "bytes": 15427, + "sha256": "fdf5900e0936b681d030f18a7a5245beacf8ab091b79a495ca823df65e8bb4a7" + }, + { + "path": "src/client/App.tsx", + "bytes": 63016, + "sha256": "8f3fc2b126e2507c1fb9ce61075c8b407d23c0854832d941fea5d53f138d28f1" + }, + { + "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/WorkerPanel.css", + "bytes": 6849, + "sha256": "d3015e518db15d8b70f222b01e2feaeecdbb1cb1778dd7f8704b8daac5f6d7f4" + }, + { + "path": "src/client/WorkerPanel.tsx", + "bytes": 19856, + "sha256": "3400ab04a97117c95b8b8d97ffb6cf7d4c3081a64c8e77252c4992cf46af95d5" + }, + { + "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": 26469, + "sha256": "1f911158c3b271f52e2ec77c7ec75f67ce8a3bb54211fd597d85190242159c2d" + }, + { + "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": 24896, + "sha256": "e5038a223039686e35838366c0a23ea5055b2da8c843a255101b137e1106e752" + }, + { + "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": 41256, + "sha256": "106d7f6384f69ecff0cd68ba89f0a45876d37cc0bce537b75490e78e1aae8ca6" + }, + { + "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/owned-process-tree.mjs", + "bytes": 3010, + "sha256": "b1742eb2b3db3f661815cd5b3d806197082bcadb7b0ba20a91837590b2a394f4" + }, + { + "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/tasks/worker-manager.mjs", + "bytes": 65799, + "sha256": "66f5ff323eaa745e58c23e50e3defce5f32cfe9061c4ecf11913fc2bf52a0576" + }, + { + "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": 26778, + "sha256": "c5a9e2886d7ea586f3f4290b167b8aa7d941009a1fd930af1b20c018cbcebc66" + }, + { + "path": "src/core/workspaces/git-workspaces.mjs", + "bytes": 37508, + "sha256": "0276d2b877acdb065717f7c93154d6999d56a9358b93e50bae7e2c7afc191806" + }, + { + "path": "src/server/app.mjs", + "bytes": 54259, + "sha256": "be19dab9e2652f914c9fd266b8186c424fd8154b2f55fcbc4dcbf9d6ab36e606" + }, + { + "path": "src/server/diagnostics.mjs", + "bytes": 7965, + "sha256": "a5b0166904bb7015e65ac7de614e684e9f83c38f711cbac69ac865f68cf06032" + }, + { + "path": "src/server/files.mjs", + "bytes": 15787, + "sha256": "2a51d87311c896e4adbae9f59f26ce9a4eb70fa1d68e5bb31193069380846816" + }, + { + "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": 60174, + "sha256": "288f322b40db5f3a0815061bcb6bcc151f9364c72f0864f8b52b94293e5667d5" + }, + { + "path": "src/server/store.mjs", + "bytes": 45174, + "sha256": "e3e67e9cb5f64e70545bfa7be76fbf3ff6afb50c039d580a51bff24db59ac90b" + }, + { + "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": 5062, + "sha256": "49ba58f91c967c0ae77318be024c227e6db9bf31333e8d9de4947053e10efbfa" + }, + { + "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/workers.mjs", + "bytes": 10564, + "sha256": "4b87565f528dea9b3fe19bfab02586fcdb9e17c6cd230085a47cab65dc929453" + }, + { + "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/workers-crash.mjs", + "bytes": 1723, + "sha256": "16ad1b0b3e491c9ffcba95793a743036a96dafdfc6f17b8546d3eaa9803a84fd" + }, + { + "path": "tests/fixtures/workers-http.mjs", + "bytes": 1999, + "sha256": "95d9dc5b7d9747050f169522cf28734e728aa58567a369bc9632d021edf6e5be" + }, + { + "path": "tests/fixtures/workers-project.mjs", + "bytes": 4752, + "sha256": "fab9ea26a01fc9fb4d06a6aa4f45ea1ef9057645a959363f755599e0d24b88d7" + }, + { + "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": 6413, + "sha256": "386beaafeabd9bdb15741165291db980502bd232dc4c877bfc4bf1c87d14ade7" + }, + { + "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/workers-http.test.mjs", + "bytes": 5288, + "sha256": "bbf6ac90935c717bd59fcfbb6a83c99a83aa7856cd05bd1351e450aa27c29daf" + }, + { + "path": "tests/workers-merge.test.mjs", + "bytes": 6047, + "sha256": "d2d82965abd621ebb67838c49b1ef32b4c7cc83c05b166d7f252e33effddf0ea" + }, + { + "path": "tests/workers-recovery.test.mjs", + "bytes": 30461, + "sha256": "537f780f5854c9de12ca24513efc7ce8aceed74bc1057ca5065bb4e5461425b4" + }, + { + "path": "tests/workers.test.mjs", + "bytes": 7824, + "sha256": "33e83ba2c9f611ddf1c86faa46c5846da562b86d36022186954408196dac14e2" + }, + { + "path": "tests/working-set.test.mjs", + "bytes": 23492, + "sha256": "b5a163c4d441c49b68a906508156f1e0792d2f0a5a6fe76ebe4429970c432d76" + }, + { + "path": "tests/workspace-api.test.mjs", + "bytes": 9444, + "sha256": "b1dd1ed7a2b14cdd8851a6ff6e15b8f5f9dce85a4e70f1314dcfce98e66d8dd8" + }, + { + "path": "tests/workspace-policy.test.mjs", + "bytes": 12247, + "sha256": "ff8cc7ea014bb630951ae61e7fdda80d5333155823a91986f52f998d011d010c" + }, + { + "path": "tests/workspace-recovery.test.mjs", + "bytes": 5382, + "sha256": "7aeaf03ae89a7de7641d260704aafca4a330b532e46d2d0468a64932c1ab057c" + }, + { + "path": "tests/workspaces.test.mjs", + "bytes": 5490, + "sha256": "4118e9208fed31b3ea2ab55276ed1477291c2daf83809753764a5f17dee7bc60" + }, + { + "path": "tsconfig.json", + "bytes": 398, + "sha256": "aca51bc97061d8ee755197b432ce24f70eb37e02cf8c60445edcfe35305d0510" + }, + { + "path": "vite.config.ts", + "bytes": 247, + "sha256": "6ad3b1bd9d5390876535ba189200fa08e46e5fb481f3f57581376859998e63f4" + } + ], + "inputFiles": 232, + "logs": [ + { + "stage": "install", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\install.log", + "sha256": "d004705f9743512ff45730927b3cc7f185b3c61eb38e5412e95df8d0843125a2", + "bytes": 401 + }, + { + "stage": "build", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\build.log", + "sha256": "84780203409c4107b09f82f987321b62c2e8b81bb86931ddcedc6318e207d6b4", + "bytes": 685 + }, + { + "stage": "contained REA", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\rea.log", + "sha256": "8704be816c5e004ddc609de655175895261a366d84e228aca1bfa6253d264399", + "bytes": 923 + }, + { + "stage": "native DeepSeek SDK", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\engines.log", + "sha256": "122d1171202b24d69c07bf5f37ce67d6292a0d2d73eb31b6e2262afa0f961220", + "bytes": 396 + }, + { + "stage": "contained browser runtime", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\browser.log", + "sha256": "dd2b7323855ab15ddcd8be42116bccd7d8a8108a953419bc3d71d1f1eb8485c5", + "bytes": 1251 + }, + { + "stage": "tests", + "path": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\package-validation-8debdb95-532f-4eec-95dd-7830b92c5c67\\tests.tap", + "sha256": "9c285c57c4827d0d32ddd632f43eaed3a36977d042bb83b57039b232e979ce6d", + "bytes": 109600 + } + ], + "buildMatchedFiles": 6, + "tests": { + "tests": 404, + "pass": 404, + "fail": 0, + "cancelled": 0, + "skipped": 0, + "todo": 0 + }, + "actualRea": { + "success": true, + "version": "1.13.0", + "directory": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\rea-integration-0ff6fd87-d1c4-45a6-b4ba-31572c3822a2", + "results": [ + { + "operation": "javascript", + "evidenceId": "ev_47c4996b37ae6eda067ff771706ab02dd41c60d82d1615ad20398e7c0083e2bb", + "targetSha256": "d17eee2327720cce413dab7dac8151c06f22d9b4d58908fead931f475b2ff37d", + "advertisedTools": 229, + "rootExited": true + }, + { + "operation": "pe-imports", + "evidenceId": "ev_d9d39ec6945300d8ebfc3682a23646b9f95da75457512aa2d51acc57582417c0", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "advertisedTools": 229, + "rootExited": true + }, + { + "operation": "pe-resources", + "evidenceId": "ev_9791a88843caf08b6cfc5df674b108f9acaf794731de592e4f2723dd6b8b2798", + "targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973", + "advertisedTools": 229, + "rootExited": true + } + ] + }, + "actualEngine": { + "success": true, + "version": "1.13.0", + "directory": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\native-engine-408fd97a-c574-43cc-a11b-267aa558fc7f", + "sdkVersion": "0.2.1-rc.2", + "nativeMethods": [ + "initialize", + "session/working-directory/get", + "session/wait", + "session/resume", + "session/cancel", + "shutdown" + ], + "modelRequests": 0, + "rootExited": true + }, + "actualBrowser": { + "success": true, + "version": "1.13.0", + "directory": "D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\browser-native-1a1f20d0-a9a9-451f-9cd0-0843cbb755ee", + "results": [ + { + "jobId": "2b3fa3c2-b312-408d-99ff-9fadc049fb02", + "taskId": "f9254215-3554-48a2-be7e-a6fbf0b96103", + "viewport": { + "width": 1280, + "height": 900 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "b464587681f4b3da6d68003006b0c3421e115e3d15bc31eb2e9d58262b767cd0", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54", + "browserExited": true, + "reusedOriginalJob": true + }, + { + "jobId": "85078cee-545b-4635-a07d-c33f4aac0ef0", + "taskId": "f9254215-3554-48a2-be7e-a6fbf0b96103", + "viewport": { + "width": 390, + "height": 844 + }, + "status": "passed", + "assertions": { + "total": 3, + "passed": 3, + "failed": 0 + }, + "resultSha256": "9f65da2317bd34136431eed0a35beb9a143c118eb3a57eadbae4df73673d2ab3", + "buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd", + "screenshotSha256": "590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f", + "browserExited": true, + "reusedOriginalJob": true + } + ], + "modelRequests": 0, + "rootExited": true + }, + "credentialsHandling": "Only build/runtime environment paths are inherited; no model configuration or credentials are used." +} \ No newline at end of file diff --git a/docs/workers-source-rea-log.txt b/docs/workers-source-rea-log.txt new file mode 100644 index 00000000..20f676b0 --- /dev/null +++ b/docs/workers-source-rea-log.txt @@ -0,0 +1 @@ +{"success":true,"version":"1.13.0","directory":"D:\\awb\\source-check-ab4af9d650d0426ba58562fe29927139\\Agent-Workbench-1.13.0-source-20261030190844003\\.qa\\rea-integration-0ff6fd87-d1c4-45a6-b4ba-31572c3822a2","results":[{"operation":"javascript","evidenceId":"ev_47c4996b37ae6eda067ff771706ab02dd41c60d82d1615ad20398e7c0083e2bb","targetSha256":"d17eee2327720cce413dab7dac8151c06f22d9b4d58908fead931f475b2ff37d","advertisedTools":229,"rootExited":true},{"operation":"pe-imports","evidenceId":"ev_d9d39ec6945300d8ebfc3682a23646b9f95da75457512aa2d51acc57582417c0","targetSha256":"7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973","advertisedTools":229,"rootExited":true},{"operation":"pe-resources","evidenceId":"ev_9791a88843caf08b6cfc5df674b108f9acaf794731de592e4f2723dd6b8b2798","targetSha256":"7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973","advertisedTools":229,"rootExited":true}]} diff --git a/docs/workers-source-tested-candidate.json b/docs/workers-source-tested-candidate.json new file mode 100644 index 00000000..fa8007bf --- /dev/null +++ b/docs/workers-source-tested-candidate.json @@ -0,0 +1,40 @@ +{ + "portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-win-x64-20261030190844003", + "sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-source-20261030190844003", + "portable": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-win-x64-20261030190844003.zip", + "bytes": 91213769, + "sha256": "4767b7775dd082c8a396066f8689a87efdc8a662eba1261009fd164aa500aead" + }, + "source": { + "path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.13.0-source-20261030190844003.zip", + "bytes": 51739086, + "sha256": "41daee87775ef237d123ffbb427344f51a8db15f295aceced91b4b7c04005582" + }, + "nodeVersion": "v24.22.1", + "reaRuntime": { + "version": "6.8.0", + "protocolVersion": "2025-03-26", + "packages": 149, + "files": 8413, + "bytes": 142395402, + "lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e" + }, + "portableFiles": 11232, + "licenseTexts": 76, + "browserRuntime": { + "playwrightVersion": "1.64.1", + "packages": [ + { + "name": "playwright", + "version": "1.64.1", + "files": 60 + }, + { + "name": "playwright-core", + "version": "1.64.1", + "files": 115 + } + ] + } +} \ No newline at end of file diff --git a/docs/workers-source-tests.tap b/docs/workers-source-tests.tap new file mode 100644 index 00000000..eff7a02b --- /dev/null +++ b/docs/workers-source-tests.tap @@ -0,0 +1,2441 @@ +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: 1301.2217 + 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: 1285.8091 + 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: 1938.3734 + 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: 6883.7683 + 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: 1242.4648 + 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: 5937.3901 + 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: 5319.5262 + 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: 10110.7162 + 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: 3813.0159 + 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: 5746.5104 + 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: 15299.3366 + 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: 7672.2058 + 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: 6300.2744 + 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: 0.4805 + 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: 5058.1419 + 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: 0.8879 + 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: 3254.3674 + 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: 7567.3039 + 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: 1504.0323 + 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: 2864.7402 + 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: 2966.1736 + 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: 2977.3851 + 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: 2404.9717 + 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: 2216.4734 + 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: 5050.3797 + 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: 10715.1823 + 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: 2104.5355 + 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: 1663.1659 + 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: 1598.1261 + 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: 1975.7831 + 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: 2068.3066 + 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: 2175.7091 + 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: 1970.3942 + 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: 2602.3582 + 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: 2840.2157 + 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: 3281.6446 + 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: 3288.3231 + 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: 2701.1835 + 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: 3066.1887 + 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: 2807.0331 + 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: 2537.0194 + 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: 2663.5933 + type: 'test' + ... +# Subtest: duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch +ok 43 - duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch + --- + duration_ms: 1232.7305 + type: 'test' + ... +# 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: 2307.2685 + 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: 1820.7832 + 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: 2129.0747 + 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: 1766.3256 + 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: 1525.5904 + 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: 3323.0427 + 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: 2773.418 + 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: 2006.1099 + 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: 2371.3596 + 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: 2167.7027 + 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: 1897.8129 + 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: 6479.0097 + 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: 1300.7292 + 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: 1071.1625 + 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: 2140.6381 + 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: 1680.1091 + 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: 1851.7114 + 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: 2598.3364 + 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: 1421.6129 + 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: 2244.6901 + 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: 3247.4198 + 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: 1889.8144 + 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: 4987.9032 + 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: 2925.4624 + 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: 1174.648 + 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: 1661.665 + 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: 4473.0693 + 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: 1684.4505 + 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: 0.2871 + 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: 1203.4227 + 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: 9583.6311 + 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: 9346.5806 + 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: 9125.1087 + 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: 9810.6264 + 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: 9479.0445 + 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: 10188.7739 + 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: 7251.2105 + 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: 8172.4346 + 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: 6722.6276 + 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: 6481.6351 + 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: 7285.7794 + 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: 8086.2821 + 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: 6072.081 + 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: 10239.5583 + 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: 9334.7495 + 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: 11990.9719 + 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: 14465.6104 + 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: 7057.0641 + 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: 4210.4195 + type: 'test' + ... +# HEAD is now at e03b287 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: 16756.0687 + 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: 6073.8035 + 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: 11298.0431 + 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: 8072.94 + 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: 7964.4719 + 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: 8250.6161 + 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: 6922.4981 + 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: 1587.4552 + 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: 2442.7089 + 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: 2711.6316 + 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: 1474.3414 + 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: 19.9348 + 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: 22.5123 + 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: 3.7035 + 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: 1013.6254 + 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: 849.4241 + 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: 1045.1165 + 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: 660.12 + 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: 819.6522 + 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: 3061.78 + 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: 3016.2139 + 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: 947.1031 + 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: 1589.2103 + 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: 1542.2332 + 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: 4397.0924 + 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: 1547.0967 + 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: 2244.5057 + 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: 5276.1682 + 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: 3224.3643 + 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: 1600.1262 + 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: 1742.5267 + 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: 1872.0212 + 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: 997.3702 + 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: 2930.5788 + 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: 2818.2352 + 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: 2063.89 + 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: 2279.2269 + 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: 2035.0408 + 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: 2721.1114 + 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: 3145.7916 + 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: 3991.5714 + 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: 3313.6177 + 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: 4263.2265 + 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: 4379.0122 + 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: 831.3573 + 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: 2137.6423 + 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: 1972.0251 + 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: 1433.788 + 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: 1274.4167 + type: 'test' + ... +# Subtest: hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules +ok 142 - hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules + --- + duration_ms: 760.3171 + type: 'test' + ... +# Subtest: ambiguous project hard links are explicit and ordinary independent file copies remain readable +ok 143 - ambiguous project hard links are explicit and ordinary independent file copies remain readable + --- + duration_ms: 715.5899 + type: 'test' + ... +# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes +ok 144 - proposals preserve project bytes until review; apply backs up the exact original bytes + --- + duration_ms: 1092.8682 + type: 'test' + ... +# Subtest: new nested files are created only on apply and unchanged content creates no proposal +ok 145 - new nested files are created only on apply and unchanged content creates no proposal + --- + duration_ms: 876.1877 + type: 'test' + ... +# Subtest: stale reads and changed baselines are rejected without overwriting external edits +ok 146 - stale reads and changed baselines are rejected without overwriting external edits + --- + duration_ms: 921.9115 + type: 'test' + ... +# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions +ok 147 - file paths reject traversal, absolute paths, credentials and outside junctions + --- + duration_ms: 710.3096 + type: 'test' + ... +# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files +ok 148 - read and search expose bounded text scopes and reject non UTF-8 / oversized files + --- + duration_ms: 765.3955 + type: 'test' + ... +# Subtest: project-local junctions cannot expose or create protected Git and credential files +ok 149 - project-local junctions cannot expose or create protected Git and credential files + --- + duration_ms: 1004.6319 + type: 'test' + ... +# Subtest: Windows trailing-dot and trailing-space path aliases cannot bypass protected paths +ok 150 - Windows trailing-dot and trailing-space path aliases cannot bypass protected paths + --- + duration_ms: 937.2276 + type: 'test' + ... +# Subtest: MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup +ok 151 - MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup + --- + duration_ms: 2355.3104 + type: 'test' + ... +# Subtest: MCP probe holds the project operation lock until its owned process and report are settled +ok 152 - MCP probe holds the project operation lock until its owned process and report are settled + --- + duration_ms: 2274.6932 + type: 'test' + ... +# Subtest: MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch +ok 153 - MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch + --- + duration_ms: 0.6107 + 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 154 - actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets + --- + duration_ms: 5421.5215 + type: 'test' + ... +# Subtest: denying an MCP call never starts another process or executes the external tool +ok 155 - denying an MCP call never starts another process or executes the external tool + --- + duration_ms: 4251.5257 + type: 'test' + ... +# Subtest: actual handshake drift rejects tools/call even if program entry hash is unchanged +ok 156 - actual handshake drift rejects tools/call even if program entry hash is unchanged + --- + duration_ms: 4819.2396 + type: 'test' + ... +# Subtest: cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen +ok 157 - cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen + --- + duration_ms: 4580.6471 + type: 'test' + ... +# Subtest: changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch +ok 158 - changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch + --- + duration_ms: 2176.7049 + type: 'test' + ... +# Subtest: registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests +ok 159 - registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests + --- + duration_ms: 3000.2024 + 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 160 - 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: 6957.2293 + type: 'test' + ... +# Subtest: MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged +ok 161 - MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged + --- + duration_ms: 5640.2199 + 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 162 - 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: 4731.8775 + type: 'test' + ... +# Subtest: changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source +ok 163 - changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source + --- + duration_ms: 2162.4587 + type: 'test' + ... +# Subtest: stdio preserves split UTF-8 frames and final replies drained after process exit +ok 164 - stdio preserves split UTF-8 frames and final replies drained after process exit + --- + duration_ms: 1898.2225 + type: 'test' + ... +# Subtest: server-initiated model requests are refused instead of inheriting provider privileges +ok 165 - server-initiated model requests are refused instead of inheriting provider privileges + --- + duration_ms: 911.945 + type: 'test' + ... +# Subtest: invalid or over-budget protocol invalid closes only its owned process and is not retried +ok 166 - invalid or over-budget protocol invalid closes only its owned process and is not retried + --- + duration_ms: 839.0503 + type: 'test' + ... +# Subtest: invalid or over-budget protocol oversized closes only its owned process and is not retried +ok 167 - invalid or over-budget protocol oversized closes only its owned process and is not retried + --- + duration_ms: 1024.0072 + type: 'test' + ... +# Subtest: cancel and timeout do not resend a dispatched request and pre-cancel has no request trace +ok 168 - cancel and timeout do not resend a dispatched request and pre-cancel has no request trace + --- + duration_ms: 933.5984 + type: 'test' + ... +# Subtest: startup failure remains undispatched and has no process PID to terminate +ok 169 - startup failure remains undispatched and has no process PID to terminate + --- + duration_ms: 791.6053 + type: 'test' + ... +# Subtest: REA launch filters a fixture credential canary and rejects changed entry identity before a new connection +ok 170 - REA launch filters a fixture credential canary and rejects changed entry identity before a new connection + --- + duration_ms: 910.1911 + type: 'test' + ... +# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart +ok 171 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart + --- + duration_ms: 1086.0421 + type: 'test' + ... +# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts +ok 172 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts + --- + duration_ms: 1024.8939 + 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 173 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity + --- + duration_ms: 3212.7274 + type: 'test' + ... +# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests +ok 174 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests + --- + duration_ms: 4723.1567 + type: 'test' + ... +# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes +ok 175 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes + --- + duration_ms: 1626.7322 + type: 'test' + ... +# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request +ok 176 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request + --- + duration_ms: 1095.6469 + type: 'test' + ... +# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model +ok 177 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model + --- + duration_ms: 1141.7176 + type: 'test' + ... +# Subtest: model registry disk failures restore routing, pool profiles and credential references without partial updates +ok 178 - model registry disk failures restore routing, pool profiles and credential references without partial updates + --- + duration_ms: 790.6133 + type: 'test' + ... +# Subtest: model selection and saved configuration commit together and failures preserve the original mode and endpoint +ok 179 - model selection and saved configuration commit together and failures preserve the original mode and endpoint + --- + duration_ms: 944.1495 + type: 'test' + ... +# Subtest: configuration imports roll back the entire batch and retain one usable preview after validation or commit failure +ok 180 - configuration imports roll back the entire batch and retain one usable preview after validation or commit failure + --- + duration_ms: 811.9426 + type: 'test' + ... +# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply +ok 181 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply + --- + duration_ms: 810.1709 + type: 'test' + ... +# Subtest: several patches are matched against one original snapshot in any input order and keep LF +ok 182 - several patches are matched against one original snapshot in any input order and keep LF + --- + duration_ms: 990.49 + type: 'test' + ... +# Subtest: mixed line endings require exact anchors and preserve untouched formatting +ok 183 - mixed line endings require exact anchors and preserve untouched formatting + --- + duration_ms: 865.1746 + type: 'test' + ... +# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write +ok 184 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write + --- + duration_ms: 683.0634 + type: 'test' + ... +# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts +ok 185 - stale original hashes and changes before apply preserve owner edits and mark conflicts + --- + duration_ms: 682.8696 + type: 'test' + ... +# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes +ok 186 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes + --- + duration_ms: 583.5327 + type: 'test' + ... +# Subtest: an actual shell command keeps Node and UTF-8 output while omitting host-only credentials +ok 187 - an actual shell command keeps Node and UTF-8 output while omitting host-only credentials + --- + duration_ms: 1524.1101 + type: 'test' + ... +# Subtest: real npm tests and build do not inherit arbitrary host credentials or Node injection settings +ok 188 - real npm tests and build do not inherit arbitrary host credentials or Node injection settings + --- + duration_ms: 2362.596 + type: 'test' + ... +# Subtest: real Python tests and compilation keep their sealed inputs without host credentials +ok 189 - real Python tests and compilation keep their sealed inputs without host credentials + --- + duration_ms: 2370.1345 + type: 'test' + ... +# Subtest: JS/TS/React AST indexes actual declarations, exports, imports and verified source lines +ok 190 - JS/TS/React AST indexes actual declarations, exports, imports and verified source lines + --- + duration_ms: 735.9834 + type: 'test' + ... +# Subtest: default expressions, named default exports and declared functions retain their AST evidence +ok 191 - default expressions, named default exports and declared functions retain their AST evidence + --- + duration_ms: 785.0463 + type: 'test' + ... +# Subtest: incremental refresh invalidates changed/deleted symbols and recalculates reused import targets +ok 192 - incremental refresh invalidates changed/deleted symbols and recalculates reused import targets + --- + duration_ms: 1019.203 + type: 'test' + ... +# Subtest: Python candidates exclude comments and multiline strings and declare limited evidence +ok 193 - Python candidates exclude comments and multiline strings and declare limited evidence + --- + duration_ms: 805.7099 + type: 'test' + ... +# Subtest: indexes isolate project identity and root and evict bounded caches without sharing results +ok 194 - indexes isolate project identity and root and evict bounded caches without sharing results + --- + duration_ms: 916.0468 + type: 'test' + ... +# Subtest: Git ignore, credential paths and links stay outside the index and no project files are executed +ok 195 - Git ignore, credential paths and links stay outside the index and no project files are executed + --- + duration_ms: 1468.709 + type: 'test' + ... +# Subtest: malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable +ok 196 - malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable + --- + duration_ms: 832.0618 + type: 'test' + ... +# Subtest: index query rejects invalid limits/types and does not imply reference or alias resolution +ok 197 - index query rejects invalid limits/types and does not imply reference or alias resolution + --- + duration_ms: 1033.6825 + type: 'test' + ... +# Subtest: read-only engineering inspection disables configured Git clean filters and preserves index bytes +ok 198 - read-only engineering inspection disables configured Git clean filters and preserves index bytes + --- + duration_ms: 1954.4108 + type: 'test' + ... +# Subtest: Python multiline declarations retain candidate scope without interpreting expressions as declarations +ok 199 - Python multiline declarations retain candidate scope without interpreting expressions as declarations + --- + duration_ms: 1021.8195 + type: 'test' + ... +# Subtest: TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit +ok 200 - TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit + --- + duration_ms: 867.1896 + type: 'test' + ... +# Subtest: actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart +ok 201 - actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart + --- + duration_ms: 2290.1745 + type: 'test' + ... +# Subtest: actual HTTP request excludes archived, timed-out and foreign-project memories +ok 202 - actual HTTP request excludes archived, timed-out and foreign-project memories + --- + duration_ms: 3301.809 + type: 'test' + ... +# Subtest: actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool +ok 203 - actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool + --- + duration_ms: 2727.2888 + type: 'test' + ... +# Subtest: incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots +ok 204 - incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots + --- + duration_ms: 2945.0554 + type: 'test' + ... +# Subtest: corrupt original artifact expires its memory and cannot reach an HTTP model request +ok 205 - corrupt original artifact expires its memory and cannot reach an HTTP model request + --- + duration_ms: 2042.4237 + type: 'test' + ... +# Subtest: memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values +ok 206 - memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values + --- + duration_ms: 3051.0516 + type: 'test' + ... +# Subtest: optional memory yields to the complete goal and original code evidence under the whole-request budget +ok 207 - optional memory yields to the complete goal and original code evidence under the whole-request budget + --- + duration_ms: 1351.0277 + type: 'test' + ... +# Subtest: changed sealed memory artifacts or binding fields fail verification while the original request remains immutable +ok 208 - changed sealed memory artifacts or binding fields fail verification while the original request remains immutable + --- + duration_ms: 1845.2694 + type: 'test' + ... +# Subtest: a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service +ok 209 - a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service + --- + duration_ms: 1715.9262 + type: 'test' + ... +# Subtest: an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure +ok 210 - an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure + --- + duration_ms: 1203.9166 + type: 'test' + ... +# Subtest: project memories persist across restart, keep source provenance, and are visible across tasks +ok 211 - project memories persist across restart, keep source provenance, and are visible across tasks + --- + duration_ms: 1122.8651 + type: 'test' + ... +# Subtest: source changes expire current project memories and keep the original evidence +ok 212 - source changes expire current project memories and keep the original evidence + --- + duration_ms: 1066.7244 + type: 'test' + ... +# Subtest: incomplete source scans mark current memories unverified without expiring or reusing them +ok 213 - incomplete source scans mark current memories unverified without expiring or reusing them + --- + duration_ms: 990.3598 + type: 'test' + ... +# Subtest: explicit file provenance is rechecked even when the inventory excludes that path +ok 214 - explicit file provenance is rechecked even when the inventory excludes that path + --- + duration_ms: 969.3827 + type: 'test' + ... +# Subtest: execution snapshots do not expose project memories before their source scope is validated +ok 215 - execution snapshots do not expose project memories before their source scope is validated + --- + duration_ms: 880.1625 + type: 'test' + ... +# Subtest: project memory records stay isolated and archive requires the owning session +ok 216 - project memory records stay isolated and archive requires the owning session + --- + duration_ms: 981.6986 + type: 'test' + ... +# Subtest: project memory HTTP API exposes read-only source status and explicit writes +ok 217 - project memory HTTP API exposes read-only source status and explicit writes + --- + duration_ms: 1939.5737 + type: 'test' + ... +# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart +ok 218 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart + --- + duration_ms: 6756.0068 + type: 'test' + ... +# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls +ok 219 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls + --- + duration_ms: 32930.5764 + type: 'test' + ... +# Subtest: Python static inspection does not import project code or probe a project interpreter before approval +ok 220 - Python static inspection does not import project code or probe a project interpreter before approval + --- + duration_ms: 1025.9879 + type: 'test' + ... +# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence +ok 221 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence + --- + duration_ms: 4572.7313 + type: 'test' + ... +# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names +ok 222 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names + --- + duration_ms: 2539.593 + type: 'test' + ... +# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task +ok 223 - unittest empty, skipped, expected failure and class initialization errors never verify a task + --- + duration_ms: 7234.653 + type: 'test' + ... +# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector +ok 224 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector + --- + duration_ms: 2760.9844 + type: 'test' + ... +# Subtest: compilation reads actual Python source bytes without executing top-level project code +ok 225 - compilation reads actual Python source bytes without executing top-level project code + --- + duration_ms: 2797.1933 + type: 'test' + ... +# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection +ok 226 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection + --- + duration_ms: 2328.0864 + type: 'test' + ... +# Subtest: changed project interpreters and forged Python plan bindings execute no check +ok 227 - changed project interpreters and forged Python plan bindings execute no check + --- + duration_ms: 1728.9933 + type: 'test' + ... +# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope +ok 228 - malformed TOML and invalid Python test paths are reported without expanding npm check scope + --- + duration_ms: 969.7434 + type: 'test' + ... +# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled +ok 229 - stopping a real Python check terminates its child and keeps the completed result as cancelled + --- + duration_ms: 1917.2647 + type: 'test' + ... +# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes +ok 230 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes + --- + duration_ms: 13452.6086 + type: 'test' + ... +# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check +ok 231 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check + --- + duration_ms: 11911.2388 + type: 'test' + ... +# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass +ok 232 - a missing interpreter and repeated pytest item objects cannot create a false verification pass + --- + duration_ms: 2702.3064 + type: 'test' + ... +# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause +ok 233 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause + --- + duration_ms: 1.9395 + type: 'test' + ... +# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget +ok 234 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget + --- + duration_ms: 0.6274 + type: 'test' + ... +# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters +ok 235 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters + --- + duration_ms: 9.4589 + type: 'test' + ... +# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress +ok 236 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress + --- + duration_ms: 0.3771 + type: 'test' + ... +# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools +ok 237 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools + --- + duration_ms: 4235.0786 + type: 'test' + ... +# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly +ok 238 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly + --- + duration_ms: 4237.7028 + type: 'test' + ... +# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay +ok 239 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay + --- + duration_ms: 4401.8042 + type: 'test' + ... +# Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs +ok 240 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs + --- + duration_ms: 2053.8844 + type: 'test' + ... +# Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification +ok 241 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification + --- + duration_ms: 1934.9459 + type: 'test' + ... +# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget +ok 242 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget + --- + duration_ms: 2299.367 + type: 'test' + ... +# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments +ok 243 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments + --- + duration_ms: 4304.1063 + type: 'test' + ... +# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests +ok 244 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests + --- + duration_ms: 1090.8752 + type: 'test' + ... +# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window +ok 245 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window + --- + duration_ms: 2258.5298 + type: 'test' + ... +# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix +ok 246 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix + --- + duration_ms: 1614.6147 + type: 'test' + ... +# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived +ok 247 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived + --- + duration_ms: 1406.1221 + type: 'test' + ... +# Subtest: invalid orphan result is rejected before archive or network preparation +ok 248 - invalid orphan result is rejected before archive or network preparation + --- + duration_ms: 773.0041 + type: 'test' + ... +# Subtest: invalid missing result is rejected before archive or network preparation +ok 249 - invalid missing result is rejected before archive or network preparation + --- + duration_ms: 1032.6608 + type: 'test' + ... +# Subtest: invalid wrong result is rejected before archive or network preparation +ok 250 - invalid wrong result is rejected before archive or network preparation + --- + duration_ms: 869.8247 + type: 'test' + ... +# Subtest: invalid duplicate call is rejected before archive or network preparation +ok 251 - invalid duplicate call is rejected before archive or network preparation + --- + duration_ms: 814.5858 + type: 'test' + ... +# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON +ok 252 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON + --- + duration_ms: 2604.1221 + type: 'test' + ... +# Subtest: changed or missing archived evidence stops reuse and is never silently recreated +ok 253 - changed or missing archived evidence stops reuse and is never silently recreated + --- + duration_ms: 1251.8042 + type: 'test' + ... +# Subtest: transaction failure prevents publishing a plan and any corresponding model request +ok 254 - transaction failure prevents publishing a plan and any corresponding model request + --- + duration_ms: 1112.9656 + type: 'test' + ... +# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP +ok 255 - the Provider rejects body mutation after a sealed plan before calling HTTP + --- + duration_ms: 868.4164 + type: 'test' + ... +# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command +ok 256 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command + --- + duration_ms: 8841.3082 + type: 'test' + ... +# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request +ok 257 - a real process exit after plan persistence marks interruption and never issues an automatic model request + --- + duration_ms: 1922.9122 + type: 'test' + ... +# Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence +ok 258 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence + --- + duration_ms: 2690.9289 + type: 'test' + ... +# Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity +ok 259 - user research registration creates an owned Task without model requests and seals the exact artifact identity + --- + duration_ms: 1313.4617 + type: 'test' + ... +# Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload +ok 260 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload + --- + duration_ms: 2740.0633 + type: 'test' + ... +# Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses +ok 261 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses + --- + duration_ms: 3359.3913 + type: 'test' + ... +# Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history +ok 262 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history + --- + duration_ms: 2652.3114 + type: 'test' + ... +# Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID +ok 263 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID + --- + duration_ms: 2024.95 + type: 'test' + ... +# Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed +ok 264 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed + --- + duration_ms: 2351.8423 + type: 'test' + ... +# Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts +ok 265 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts + --- + duration_ms: 1233.0541 + type: 'test' + ... +# Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay +ok 266 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay + --- + duration_ms: 5054.3581 + type: 'test' + ... +# Subtest: file identity rejects directory and invalid formats without running a target +ok 267 - file identity rejects directory and invalid formats without running a target + --- + duration_ms: 797.5602 + type: 'test' + ... +# Subtest: a stop from the event loop interrupts immediate model replies before later tools +ok 268 - a stop from the event loop interrupts immediate model replies before later tools + --- + duration_ms: 1866.2282 + type: 'test' + ... +# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group +ok 269 - a stop after the first tool preserves a complete interrupted multi-call protocol group + --- + duration_ms: 2360.4709 + type: 'test' + ... +# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands +ok 270 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands + --- + duration_ms: 6645.0039 + type: 'test' + ... +# Subtest: denial prevents command execution and produces a paired denied result +ok 271 - denial prevents command execution and produces a paired denied result + --- + duration_ms: 2488.5606 + type: 'test' + ... +# Subtest: stopping during approval interrupts pending calls without executing or replaying them +ok 272 - stopping during approval interrupts pending calls without executing or replaying them + --- + duration_ms: 2174.0062 + type: 'test' + ... +# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state +ok 273 - stopping a running fixture command terminates its own process tree and retains uncertain state + --- + duration_ms: 2696.6541 + type: 'test' + ... +# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment +ok 274 - command output decodes split UTF-8 and excludes the workbench key from child environment + --- + duration_ms: 1426.6613 + type: 'test' + ... +# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors +ok 275 - model-list testing uses a tentative key without changing the saved connection and redacts service errors + --- + duration_ms: 8.794 + type: 'test' + ... +# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities +ok 276 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities + --- + duration_ms: 3062.5419 + type: 'test' + ... +# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history +ok 277 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history + --- + duration_ms: 1655.9246 + type: 'test' + ... +# Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project +ok 278 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project + --- + duration_ms: 1519.0488 + type: 'test' + ... +# Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code +ok 279 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code + --- + duration_ms: 902.3011 + type: 'test' + ... +# Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing +ok 280 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing + --- + duration_ms: 3291.2901 + type: 'test' + ... +# Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay +ok 281 - source edits after a catalog request prevent the read and appear as changed on the next request without replay + --- + duration_ms: 3039.8768 + type: 'test' + ... +# Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project +ok 282 - disabled and foreign skills cannot be read by guessing their IDs from another project + --- + duration_ms: 3192.0602 + type: 'test' + ... +# Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code +ok 283 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code + --- + duration_ms: 1743.1065 + type: 'test' + ... +# Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact +ok 284 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact + --- + duration_ms: 4438.0209 + type: 'test' + ... +# Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network +ok 285 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network + --- + duration_ms: 1380.5452 + type: 'test' + ... +# Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs +ok 286 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs + --- + duration_ms: 2018.4134 + type: 'test' + ... +# Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls +ok 287 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls + --- + duration_ms: 2688.8405 + type: 'test' + ... +# Subtest: JSON state keeps an atomic backup and preserves corrupt primary files +ok 288 - JSON state keeps an atomic backup and preserves corrupt primary files + --- + duration_ms: 905.4257 + type: 'test' + ... +# Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results +ok 289 - tool-pair recovery fills missing results and drops orphan or duplicate results + --- + duration_ms: 0.3613 + type: 'test' + ... +# Subtest: restart pauses unfinished work, retains proposals and never replays a command +ok 290 - restart pauses unfinished work, retains proposals and never replays a command + --- + duration_ms: 882.7797 + type: 'test' + ... +# Subtest: public snapshots carry increasing revisions without the private provider transcript or config key +ok 291 - public snapshots carry increasing revisions without the private provider transcript or config key + --- + duration_ms: 1367.4043 + 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 292 - a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay + --- + duration_ms: 4035.7126 + type: 'test' + ... +# Subtest: checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact +ok 293 - checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact + --- + duration_ms: 3080.6313 + type: 'test' + ... +# Subtest: unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work +ok 294 - unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work + --- + duration_ms: 3093.7229 + type: 'test' + ... +# Subtest: checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt +ok 295 - checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt + --- + duration_ms: 2987.4787 + type: 'test' + ... +# Subtest: checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes +ok 296 - checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes + --- + duration_ms: 3398.0474 + type: 'test' + ... +# Subtest: Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state +ok 297 - Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state + --- + duration_ms: 2916.149 + type: 'test' + ... +# Subtest: checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay +ok 298 - checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay + --- + duration_ms: 2397.1262 + type: 'test' + ... +# Subtest: incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements +ok 299 - incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements + --- + duration_ms: 2758.8204 + type: 'test' + ... +# Subtest: oversized recovery evidence is refused before reading or publishing the checkpoint +ok 300 - oversized recovery evidence is refused before reading or publishing the checkpoint + --- + duration_ms: 1843.9784 + type: 'test' + ... +# Subtest: compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation +ok 301 - compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation + --- + duration_ms: 4924.9504 + type: 'test' + ... +# Subtest: actual process exit before checkpoint commit retains only durable records without replay +ok 302 - actual process exit before checkpoint commit retains only durable records without replay + --- + duration_ms: 1940.0567 + type: 'test' + ... +# Subtest: actual process exit after checkpoint commit retains only durable records without replay +ok 303 - actual process exit after checkpoint commit retains only durable records without replay + --- + duration_ms: 2262.9532 + type: 'test' + ... +# Subtest: task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart +ok 304 - task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart + --- + duration_ms: 2927.4589 + type: 'test' + ... +# Subtest: concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan +ok 305 - concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan + --- + duration_ms: 2312.6796 + type: 'test' + ... +# Subtest: a real escaped long-file tool message keeps its proof identity within a tight request budget +ok 306 - a real escaped long-file tool message keeps its proof identity within a tight request budget + --- + duration_ms: 1553.1241 + type: 'test' + ... +# Subtest: task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies +ok 307 - task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies + --- + duration_ms: 0.4523 + type: 'test' + ... +# Subtest: sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools +ok 308 - sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools + --- + duration_ms: 1054.5093 + type: 'test' + ... +# Subtest: proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes +ok 309 - proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes + --- + duration_ms: 1853.0022 + type: 'test' + ... +# Subtest: new user requirements invalidate current proofs and reseal the same original operations in a new revision +ok 310 - new user requirements invalidate current proofs and reseal the same original operations in a new revision + --- + duration_ms: 2026.9618 + type: 'test' + ... +# Subtest: applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits +ok 311 - applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits + --- + duration_ms: 2503.8817 + type: 'test' + ... +# Subtest: actual npm checks are verified by original counted logs and current source, with failure history retained +ok 312 - actual npm checks are verified by original counted logs and current source, with failure history retained + --- + duration_ms: 7295.0111 + 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 313 - real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds + --- + duration_ms: 11960.1958 + type: 'test' + ... +# Subtest: Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit +ok 314 - Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit + --- + duration_ms: 10643.9477 + type: 'test' + ... +# Subtest: the runtime supplies owned read IDs and completes a plan only after original step evidence verification +ok 315 - the runtime supplies owned read IDs and completes a plan only after original step evidence verification + --- + duration_ms: 3385.8604 + type: 'test' + ... +# Subtest: premature model completion pauses the original Task and resume preserves the existing plan without replay +ok 316 - premature model completion pauses the original Task and resume preserves the existing plan without replay + --- + duration_ms: 4045.42 + type: 'test' + ... +# Subtest: plan operations participate in project activity and orderly shutdown +ok 317 - plan operations participate in project activity and orderly shutdown + --- + duration_ms: 806.4907 + type: 'test' + ... +# Subtest: actual process exit before plan save restores only committed plan evidence without replay +ok 318 - actual process exit before plan save restores only committed plan evidence without replay + --- + duration_ms: 2128.7548 + type: 'test' + ... +# Subtest: actual process exit after plan save restores only committed plan evidence without replay +ok 319 - actual process exit after plan save restores only committed plan evidence without replay + --- + duration_ms: 1424.9785 + type: 'test' + ... +# Subtest: actual process exit before proof save restores only committed plan evidence without replay +ok 320 - actual process exit before proof save restores only committed plan evidence without replay + --- + duration_ms: 1299.04 + type: 'test' + ... +# Subtest: actual process exit after proof save restores only committed plan evidence without replay +ok 321 - actual process exit after proof save restores only committed plan evidence without replay + --- + duration_ms: 2081.9156 + type: 'test' + ... +# Subtest: the latest oversized session result reaches the next request together with already read source modules +ok 322 - the latest oversized session result reaches the next request together with already read source modules + --- + duration_ms: 2343.3047 + type: 'test' + ... +# Subtest: every call in a large latest group keeps its actual outcome, including denied and unknown results +ok 323 - every call in a large latest group keeps its actual outcome, including denied and unknown results + --- + duration_ms: 1696.1368 + type: 'test' + ... +# Subtest: a small complete latest tool group is sent once and needs no duplicate feedback view +ok 324 - a small complete latest tool group is sent once and needs no duplicate feedback view + --- + duration_ms: 960.4731 + type: 'test' + ... +# Subtest: real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing +ok 325 - real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing + --- + duration_ms: 2496.6048 + 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 326 - a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes + --- + duration_ms: 4186.5448 + type: 'test' + ... +# Subtest: failed upgrade restores the original artifact object, provider and request handler +ok 327 - failed upgrade restores the original artifact object, provider and request handler + --- + duration_ms: 1064.8477 + type: 'test' + ... +# Subtest: hot upgrade refreshes retained model and importer methods while preserving credential and routing objects +ok 328 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects + --- + duration_ms: 887.9008 + type: 'test' + ... +# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails +ok 329 - hot upgrade refuses active probes and restores retained model methods if installation fails + --- + duration_ms: 862.1355 + type: 'test' + ... +# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider +ok 330 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider + --- + duration_ms: 2619.171 + type: 'test' + ... +# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection +ok 331 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection + --- + duration_ms: 11351.8356 + type: 'test' + ... +# Subtest: HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source +ok 332 - HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source + --- + duration_ms: 11776.3398 + type: 'test' + ... +# Subtest: HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention +ok 333 - HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention + --- + duration_ms: 15951.2433 + type: 'test' + ... +# Subtest: verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source +ok 334 - verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source + --- + duration_ms: 40801.1167 + type: 'test' + ... +# Subtest: overlapping worker paths are explicit conflicts even if each independent task checks successfully +ok 335 - overlapping worker paths are explicit conflicts even if each independent task checks successfully + --- + duration_ms: 27130.9235 + type: 'test' + ... +# Subtest: source edits after isolated work preserve the owner file and invalidate collection without proposing a merge +ok 336 - source edits after isolated work preserve the owner file and invalidate collection without proposing a merge + --- + duration_ms: 26610.5316 + type: 'test' + ... +# Subtest: changed child bytes after parent preview block the entire batch before any parent write +ok 337 - changed child bytes after parent preview block the entire batch before any parent write + --- + duration_ms: 34105.1023 + type: 'test' + ... +# Subtest: corrupt original check logs cannot become collected outputs or a parent review +ok 338 - corrupt original check logs cannot become collected outputs or a parent review + --- + duration_ms: 26425.35 + type: 'test' + ... +# Subtest: stopping a parent accounts late responses and executes none of their proposed tools +ok 339 - stopping a parent accounts late responses and executes none of their proposed tools + --- + duration_ms: 11218.8832 + type: 'test' + ... +# Subtest: unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume +ok 340 - unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume + --- + duration_ms: 12449.482 + type: 'test' + ... +# Subtest: a response exceeding the cumulative token allocation stops before registering or executing its tools +ok 341 - a response exceeding the cumulative token allocation stops before registering or executing its tools + --- + duration_ms: 11554.3765 + type: 'test' + ... +# Subtest: cumulative tool allocation rejects the entire returned batch before any tool side effect +ok 342 - cumulative tool allocation rejects the entire returned batch before any tool side effect + --- + duration_ms: 11483.6738 + type: 'test' + ... +# Subtest: single response 16 tool ceiling rejects the entire returned batch before any tool side effect +ok 343 - single response 16 tool ceiling rejects the entire returned batch before any tool side effect + --- + duration_ms: 12204.6294 + type: 'test' + ... +# Subtest: consumed request steps remain consumed across explicit worker resumes +ok 344 - consumed request steps remain consumed across explicit worker resumes + --- + duration_ms: 13662.3477 + type: 'test' + ... +# Subtest: a saved completed response with missing usage is conservatively accounted exactly once during recovery +ok 345 - a saved completed response with missing usage is conservatively accounted exactly once during recovery + --- + duration_ms: 10341.6104 + type: 'test' + ... +# Subtest: an unexecuted second workspace plan resumes its original identity without recreating the first checkout +ok 346 - an unexecuted second workspace plan resumes its original identity without recreating the first checkout + --- + duration_ms: 11755.5067 + type: 'test' + ... +# Subtest: a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change +ok 347 - a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change + --- + duration_ms: 39176.8934 + type: 'test' + ... +# Subtest: recovery attaches a sealed parent batch saved before its group reference without creating another batch +ok 348 - recovery attaches a sealed parent batch saved before its group reference without creating another batch + --- + duration_ms: 33521.187 + type: 'test' + ... +# Subtest: explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal +ok 349 - explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal + --- + duration_ms: 36035.4321 + type: 'test' + ... +# Subtest: unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback +ok 350 - unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback + --- + duration_ms: 41870.4064 + type: 'test' + ... +# Subtest: after a restart the batch application lazily reinstates the worker result guard before any parent write +ok 351 - after a restart the batch application lazily reinstates the worker result guard before any parent write + --- + duration_ms: 35464.1483 + type: 'test' + ... +# Subtest: unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact +ok 352 - unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact + --- + duration_ms: 12827.0945 + type: 'test' + ... +# Subtest: a parent stop observes and waits for a manually approved child check and its real descendant process +ok 353 - a parent stop observes and waits for a manually approved child check and its real descendant process + --- + duration_ms: 12520.8424 + type: 'test' + ... +# Subtest: a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool +ok 354 - a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool + --- + duration_ms: 22222.7094 + type: 'test' + ... +# Subtest: a persisted child initialization resumes the original control run after a failure before its worker record +ok 355 - a persisted child initialization resumes the original control run after a failure before its worker record + --- + duration_ms: 11590.2219 + type: 'test' + ... +# Subtest: failed request intent persistence never dispatches a worker request or changes source +ok 356 - failed request intent persistence never dispatches a worker request or changes source + --- + duration_ms: 11196.793 + type: 'test' + ... +# Subtest: failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools +ok 357 - failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools + --- + duration_ms: 11764.8345 + type: 'test' + ... +# Subtest: a child file change after observation prevents acknowledgement even when the tool inputs did not change +ok 358 - a child file change after observation prevents acknowledgement even when the tool inputs did not change + --- + duration_ms: 11912.8607 + type: 'test' + ... +# Subtest: worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow +ok 359 - worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow + --- + duration_ms: 662.4037 + type: 'test' + ... +# Subtest: two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes +ok 360 - two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes + --- + duration_ms: 9604.8389 + type: 'test' + ... +# Subtest: real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims +ok 361 - real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims + --- + duration_ms: 26574.9984 + type: 'test' + ... +# Subtest: forged worker tools cannot execute terminal or Git even when absent from the advertised tool list +ok 362 - forged worker tools cannot execute terminal or Git even when absent from the advertised tool list + --- + duration_ms: 10662.2751 + type: 'test' + ... +# Subtest: a completion-only model pauses each worker without fabricated changes or checks +ok 363 - a completion-only model pauses each worker without fabricated changes or checks + --- + duration_ms: 13078.215 + type: 'test' + ... +# Subtest: restart retains frozen scope and marks interrupted parent and workers unknown without sending requests +ok 364 - restart retains frozen scope and marks interrupted parent and workers unknown without sending requests + --- + duration_ms: 9870.6433 + type: 'test' + ... +# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit +ok 365 - small code and actual failed command stay visible when their original multi-tool group cannot fit + --- + duration_ms: 1386.3179 + type: 'test' + ... +# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes +ok 366 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes + --- + duration_ms: 2666.7078 + type: 'test' + ... +# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence +ok 367 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence + --- + duration_ms: 1827.8384 + type: 'test' + ... +# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence +ok 368 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence + --- + duration_ms: 1098.7602 + 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 369 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid + --- + duration_ms: 4262.5665 + type: 'test' + ... +# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries +ok 370 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries + --- + duration_ms: 4.2119 + type: 'test' + ... +# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening +ok 371 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening + --- + duration_ms: 12663.9268 + type: 'test' + ... +# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request +ok 372 - actual HTTP file pagination advances over a long file with each returned page visible in the next request + --- + duration_ms: 2621.2681 + type: 'test' + ... +# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements +ok 373 - later mixed history pages cannot displace the actual module sources and complete requirements + --- + duration_ms: 6100.1862 + type: 'test' + ... +# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation +ok 374 - a later narrow page of the same file revision cannot evict the wider actual observation + --- + duration_ms: 3150.9011 + type: 'test' + ... +# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper +ok 375 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper + --- + duration_ms: 1128.277 + type: 'test' + ... +# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view +ok 376 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view + --- + duration_ms: 1194.0803 + type: 'test' + ... +# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes +ok 377 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes + --- + duration_ms: 10964.0514 + type: 'test' + ... +# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files +ok 378 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files + --- + duration_ms: 6231.5607 + 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 379 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report + --- + duration_ms: 26187.7784 + 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 380 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion + --- + duration_ms: 5016.7404 + type: 'test' + ... +# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation +ok 381 - an ignored external file at checkout is observed and never accepted as pristine creation + --- + duration_ms: 4164.6762 + type: 'test' + ... +# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution +ok 382 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution + --- + duration_ms: 3895.7778 + type: 'test' + ... +# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions +ok 383 - workspace preparation refuses known shared-repository activity and preserves archived child sessions + --- + duration_ms: 4163.632 + type: 'test' + ... +# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name +ok 384 - compact checkout identities create in deep Unicode source directories while retaining the human branch name + --- + duration_ms: 4839.4182 + type: 'test' + ... +# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes +ok 385 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes + --- + duration_ms: 2565.6687 + type: 'test' + ... +# Subtest: a pending source snapshot participates in shutdown and completes before storage can close +ok 386 - a pending source snapshot participates in shutdown and completes before storage can close + --- + duration_ms: 2056.4165 + type: 'test' + ... +# Subtest: source configuration values stay private and a configuration change invalidates a saved review +ok 387 - source configuration values stay private and a configuration change invalidates a saved review + --- + duration_ms: 2116.455 + type: 'test' + ... +# Subtest: workspace review rejects excluded dependency before any checkout +ok 388 - workspace review rejects excluded dependency before any checkout + --- + duration_ms: 2144.5803 + type: 'test' + ... +# Subtest: workspace review rejects large committed blob before any checkout +ok 389 - workspace review rejects large committed blob before any checkout + --- + duration_ms: 2004.9384 + type: 'test' + ... +# Subtest: workspace review rejects case collision before any checkout +ok 390 - workspace review rejects case collision before any checkout + --- + duration_ms: 2133.2534 + type: 'test' + ... +# Subtest: workspace review rejects committed symbolic link before any checkout +ok 391 - workspace review rejects committed symbolic link before any checkout + --- + duration_ms: 2396.9441 + type: 'test' + ... +# Subtest: workspace review rejects external config include before any checkout +ok 392 - workspace review rejects external config include before any checkout + --- + duration_ms: 1804.9488 + type: 'test' + ... +# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay +ok 393 - actual process exit at workspace intent preserves source and reconciles without creation replay + --- + duration_ms: 3746.1699 + type: 'test' + ... +# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay +ok 394 - actual process exit at workspace git_started preserves source and reconciles without creation replay + --- + duration_ms: 5528.5656 + type: 'test' + ... +# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay +ok 395 - actual process exit at workspace git_finished preserves source and reconciles without creation replay + --- + duration_ms: 5559.8371 + type: 'test' + ... +# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay +ok 396 - actual process exit at workspace verifying preserves source and reconciles without creation replay + --- + duration_ms: 5258.0961 + type: 'test' + ... +# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay +ok 397 - actual process exit at workspace registering preserves source and reconciles without creation replay + --- + duration_ms: 5895.6749 + type: 'test' + ... +# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay +ok 398 - actual process exit at workspace project_registered preserves source and reconciles without creation replay + --- + duration_ms: 6573.9414 + type: 'test' + ... +# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay +ok 399 - actual process exit at workspace session_registered preserves source and reconciles without creation replay + --- + duration_ms: 6422.0501 + type: 'test' + ... +# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay +ok 400 - actual process exit at workspace ready preserves source and reconciles without creation replay + --- + duration_ms: 5657.2141 + type: 'test' + ... +# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity +ok 401 - outside changes at project registration remain unknown and preserve the already registered child identity + --- + duration_ms: 5379.8474 + type: 'test' + ... +# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity +ok 402 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity + --- + duration_ms: 4491.5374 + type: 'test' + ... +# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation +ok 403 - stale review, branch/path collisions and forged ownership do not run worktree creation + --- + duration_ms: 2702.3002 + type: 'test' + ... +# Subtest: workspace project verification is read-only and rejects physical Git identity changes +ok 404 - workspace project verification is read-only and rejects physical Git identity changes + --- + duration_ms: 3747.4732 + type: 'test' + ... +1..404 +# tests 404 +# suites 0 +# pass 404 +# fail 0 +# cancelled 0 +# skipped 0 +# todo 0 +# duration_ms 924786.8274 diff --git a/findings.md b/findings.md index 9ca7a63d..72ab9d65 100644 --- a/findings.md +++ b/findings.md @@ -2,6 +2,8 @@ ## 2026-10-31 1.13 隔离worker接续 +- 新完整独立源码404/404与228份Git原字节、4份旧文件仅既有CRLF/LF差异、6构建及8815份实现/基准/原生资源比较通过。暂存时Git发现Python归档原JSON的CRLF会被自动规范化;本阶段workers-*.json增加-text,只保存原报告字节,不改原文件或旧生产输入。暂存后重新核对报告及日志原字节,最终发行仍仅补文档。 +- 原归档JSON保留CRLF后,git diff --check把CR本身报告为尾部空白;本阶段报告属性明确cr-at-eol,同时保留blank-at-eol/blank-at-eof/space-before-tab检查,原报告不重写。十份新报告/日志与Git索引已逐字节一致,继续发行,不对代码或原测试扩大换行例外。 - 本轮串行控制台截图c4ae46be的桌面/390px已目视核对:两个子通道、真实预算/范围、父成果审查及具体冲突均清楚,窄屏按钮和路径留在面板内,无横向溢出。截图是已滚动的控制台,顶部标题在上方;没有据此声称标题缺失或改动产品布局。当前新三工程187cea09的13节点和输入全部通过,完整UI前11类102组已完成,最终统计仍待整轮退出。 - 首个独立源码实际统计404项、403通过/1失败,唯一失败是原宿主崩溃用例的目录删除hookFailed/EPERM,不能发布或用额外专项拼成全量通过。残留心跳4532字节在1.2秒观察中稳定,当前节点进程清单没有该轮时间窗口仍存活的Node,未按未知PID杀任何程序。夹具原本只等待任一树和任一心跳;现要求两个实际心跳PID均在两份原创建身份记录中,再模拟已建立所属检查后的宿主崩溃。后注册t.after不保证先于fixture删除,改用既有onCleanup生命周期;追加停止后/确认后心跳字节断言并有界异步删除,失败仍保留。 - 本次恢复确认唯一未完成的独立源码exec会话为76537;已有348项原TAP通过、尚无最终统计,不能使用上一轮通用指针冒充本轮结果。96846的界面会话已结束,后续串行重验21类160组并继续要求零页面/请求异常。源码验收与UI曾并行是已知环境条件,尚不能据此确认ERR_NO_BUFFER_SPACE的根因。 diff --git a/progress.md b/progress.md index fcb1f6f4..67652c17 100644 --- a/progress.md +++ b/progress.md @@ -2,6 +2,8 @@ ## 2026-10-31 1.13 隔离执行阶段 +- 新独立源码91264完成404/404,0失败/取消/跳过/todo,原第354项宿主崩溃在同轮通过;232份输入与冻结基线一致,6份构建及REA/DeepSeek/Edge通过。六份原日志及报告/受测候选/归档身份已复制docs/workers-source-*并核对原字节。只补最终文档后重封不可变包;便携、实际Provider/PID及全部历史升级仍待执行,不重复已通过的源码/工程/UI。 +- be02e99封存160组全UI、原日志、三工程与后续方案。新不可变候选20261030190844003便携11232/源码9532文件归档通过,独立解压至D:/awb/source-check-ab4af9d650d0426ba58562fe29927139;源码会话91264已通过离线安装、6份构建、REA/DeepSeek/Edge,完整回归进行中,原403/404候选保留且不采用。当前只有91264执行,不并行运行UI/工程;最终升级/比对/封存明确要求固定404项全部通过及PLAN-1.14原文身份。 - 串行全UI会话70846完成21类160组,0页面异常/请求失败;三工程13节点、全部源码/构建/基准和21份原日志字节核对通过。控制台桌面/390px截图已目视检查并记入findings;更新1.13验收/能力/总计划及PLAN-1.14,下一步生成新不可变候选、独立离线完整回归,不提前升级正式服务。 - 91cdd45提交QA补强及完整原失败证据后重新冻结232份输入/6构建/40基准。新三工程187cea09完整13节点通过,父8/8、9/9、10/10、真实编译/构建/Git及React两视口各10项断言通过;修正前三工程/控制台/基线另存为原证据。现在仅运行串行全UI会话70846,不与独立源码争用浏览器/检查资源。下一阶段PLAN-1.14已记录受控引擎六切片与同题Purge对照,尚未实现。 - 强化后的真实宿主崩溃专项1/1通过,原TAP/4份依赖身份保存workers-crash-cleanup-*;两个实际心跳PID已分别进入原树后再崩溃,存活拒绝、全树结束、停止后/确认后不继续写入、资源先关闭再删除全部实际检查。下一步小步提交QA修正,重新冻结;原三工程报告另存为修正前证据,新完整源码/UI/三工程用新输入判定。 diff --git a/task_plan.md b/task_plan.md index b7b6f095..2ead8944 100644 --- a/task_plan.md +++ b/task_plan.md @@ -9,7 +9,7 @@ 3. [complete] 停止传播、原创建身份的检查进程树、迟到/未知用量与累计预算、部分创建及宿主退出核对已实现。整合原轮64/65,唯一QA清理竞态修正后真实宿主崩溃专项1/1;未拼称同轮65/65,最终独立源码待验。 4. [complete] 原子成果、当前文件/检查原日志、Git及提案链核对、具体路径冲突、父封存批次与应用前复核、父检查/Git完成门槛已接入并实际验证。部分归集封存中断按原绑定恢复,未知不造完成结果。 5. [complete] 桌面/390px协作控制台10节点及Node/React/Python三个真实功能工程完成;父测试8/8、9/9、10/10与实际构建/编译/Git通过,React内置Edge两视口各10项断言通过。13个工程节点、原失败及完整工件保留;UI等待及响应式文本断言已修正,真实模型语义仍单独待验。 -6. [in_progress] 切片回顾后进入最终完整UI/独立源码/不可变源码与便携验收、保留当前Provider/全部历史正式升级;封存1.13报告并更新下一阶段起点。正式服务仍1.12.1/PID23172,不提前登记发行。 +6. [in_progress] 新独立源码404/404、232份输入/6构建/40基准、完整UI21类160组及三工程13节点通过;91264已退出。保存全部原证据后只补文档生成最终不可变包,完成便携、保留当前Provider/全部历史正式升级及1.13封存;下一阶段PLAN-1.14已记录。正式服务未升级,不提前登记交付。 ## 2026-10-30 当前任务:里程碑回顾、漏洞修复与后续计划封存