docs: preserve independent 404-test source acceptance and raw evidence

This commit is contained in:
Agent Workbench Dev
2026-10-31 03:33:14 +08:00
parent be02e99b7d
commit 24b8341ad5
19 changed files with 3936 additions and 11 deletions
+10 -4
View File
@@ -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。
+2 -2
View File
@@ -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
+2 -2
View File
@@ -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
+1
View File
@@ -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}
+14
View File
@@ -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.
@@ -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"
}
+1
View File
@@ -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}
@@ -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."
}
+7
View File
@@ -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 <pkg>` to allow.
File diff suppressed because it is too large Load Diff
+1
View File
@@ -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}]}
+40
View File
@@ -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
}
]
}
}
File diff suppressed because it is too large Load Diff