docs: seal 1.10.1 upgrade and actual browser task outcome
This commit is contained in:
+5
-1
@@ -4,7 +4,11 @@
|
||||
|
||||
1.10.0候选20261030004653739完成274/274独立源码回归、离线构建6份一致和170份冻结输入核对;随包REA三操作、DeepSeek六方法及1280px/390px浏览器通过,见[browser源码](browser-engine-source-package-validation.json)、[便携](browser-engine-release-validation.json)和[归档](browser-engine-archives-validation.json)。正式4318保留PID23080/原Provider升级至1.10.0,14项目及23会话(含7归档)完整核对,见[原进程升级](browser-engine-upgrade-initial-validation.json)。
|
||||
|
||||
真实配置模型的首轮页面Task发现此前SQLite宿主保留旧ArtifactStore,新增readBytes不可用;原错误与模型失败保存在[首轮实模失败](browser-engine-live-model-initial-failure.json)。1.10.1改为在升级时用当前API重新打开同一工件目录,失败恢复原对象,不迁移或改写原字节;真实1.9对象回归修复前1/2、修复后2/2,包含实际浏览器PNG和失败回滚。1.10.1独立源码、不可变发行及实模复验继续执行,未完成项目不登记为成功。验收器也修正为只续接paused/step_limit的原Task,不把completed后的内容请求误当同Task续接。
|
||||
真实配置模型的首轮页面Task发现此前SQLite宿主保留旧ArtifactStore,新增readBytes不可用;原错误与模型失败保存在[首轮实模失败](browser-engine-live-model-initial-failure.json)。1.10.1改为在升级时用当前API重新打开同一工件目录,失败恢复原对象,不迁移或改写原字节;真实1.9对象回归修复前1/2、修复后2/2,包含实际浏览器PNG和失败回滚。验收器只续接paused/step_limit的原Task,不把completed后的内容请求误当同Task续接。
|
||||
|
||||
1.10.1最终独立源码276/276通过、离线安装和6份构建一致,174份冻结输入与源码/便携逐字节核对;实际随包REA三操作、DeepSeek六方法、1280px/390px Edge及归档、便携检查通过,见[修复源码](browser-hotfix-source-package-validation.json)、[修复便携](browser-hotfix-release-validation.json)和[修复归档](browser-hotfix-archives-validation.json)。正式4318保留PID23080/原Provider升级1.10.1,14项目、24会话(含7归档)完整核对,8749份发行输入与独立验收源码一致,调试端口关闭,见[修复升级](browser-hotfix-upgrade-initial-validation.json)。
|
||||
|
||||
修复后新的真实模型页面Task在原210秒验收范围内未完成全部要求,见[实际失败记录](browser-engine-live-model-validation.json)。18次已报告响应、输入150599/输出2238/合计152837tokens;桌面11步和8/8断言实际通过。390px的第4步可见性选择器button:nth-of-type(1)实际匹配三个按钮,3/4断言通过后失败;模型继续读取原字段/工件,验收到时人工停止,原Task为paused/cancelled。桌面通过与手机失败分别保留,不记为整体自主页面验收成功,不增加预算重跑;下一切片补真实DOM唯一定位与任务计划核验。
|
||||
|
||||
12项核心/API/协议/恢复/交付专项通过。真实Edge核对填写、选择、点击与断言,PNG原字节和实际PID结束、同版本复用、失败原值、输入变化、停止、工件损坏、HTTP归属与真实宿主重启均验证。协议夹具证明模型先准备计划、经审批执行、读取同Task原字段;夹具结果不计真实模型成功率。
|
||||
|
||||
|
||||
+1
-1
@@ -2,7 +2,7 @@
|
||||
|
||||
## 1.10.0 / 1.10.1 · 实际页面验收与升级兼容性
|
||||
|
||||
1.10.0完成274/274独立源码、13类118组界面、170份冻结输入及不可变源码/便携验证,正式4318保留PID23080/Provider与全部23会话升级。实模首轮另发现旧SQLite工件对象缺少新增字节读取API,原失败保留;1.10.1修复同目录当前API与回滚,16项升级/浏览器/API/Git专项通过。修复版的独立完整源码及实模页面复验继续执行,见[QA-1.10](QA-1.10.md)。
|
||||
1.10.0完成274/274独立源码、13类118组界面、170份冻结输入及不可变源码/便携验证。实模首轮发现旧SQLite工件对象缺少新增字节读取API,原失败保留;1.10.1修复后最终独立源码276/276、174份冻结输入、实际随包REA/DeepSeek/Edge与便携/归档均通过。正式4318保留PID23080/Provider、14项目和全部24会话升级1.10.1。实模复验桌面8/8断言通过,390px因按钮选择器匹配三个元素而失败,210秒内未完成整体任务;18次响应/152837tokens及人工停止按原结果封存,见[QA-1.10](QA-1.10.md)。
|
||||
|
||||
## 1.6.2 · 工作依据保留与旧发送视图兼容
|
||||
|
||||
|
||||
@@ -0,0 +1,71 @@
|
||||
{
|
||||
"success": false,
|
||||
"version": "1.10.1",
|
||||
"testedAt": "2026-10-30T01:37:13.120Z",
|
||||
"directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\live-browser-6b3d9a18-d4e1-460e-a4f5-320ee5f524a1",
|
||||
"sessionId": "596df050-d490-44da-be1c-bcaf58c88dc0",
|
||||
"taskId": "123d1db4-7a5b-430b-8794-82143229477e",
|
||||
"modelStatus": "paused",
|
||||
"usage": {
|
||||
"requests": 18,
|
||||
"inputTokens": 150599,
|
||||
"outputTokens": 2238,
|
||||
"totalTokens": 152837,
|
||||
"unknownRequests": 0,
|
||||
"estimatedUnknownTokens": 0
|
||||
},
|
||||
"decisions": [
|
||||
{
|
||||
"id": "a45047a9-1cb4-4c20-957b-103b451e0d88",
|
||||
"taskId": "123d1db4-7a5b-430b-8794-82143229477e",
|
||||
"planId": "02d5e86b-c5d9-4864-881c-d335e5be4bf8",
|
||||
"fingerprint": "4b20b5bcadcfe8ab2fee2c63c253d2d289f9db3506351f4e7d7447e5137fae88",
|
||||
"viewport": {
|
||||
"width": 1280,
|
||||
"height": 900
|
||||
},
|
||||
"steps": 0
|
||||
},
|
||||
{
|
||||
"id": "7e856e8b-056c-4c18-8980-0f85e1e69d3f",
|
||||
"taskId": "123d1db4-7a5b-430b-8794-82143229477e",
|
||||
"planId": "46ca717f-394b-4f90-8c2e-25d9fcda6de6",
|
||||
"fingerprint": "44dd4ff7182f493b6c4956227584010fe1e47d2cd2911ef60f658825368f44d4",
|
||||
"viewport": {
|
||||
"width": 1280,
|
||||
"height": 900
|
||||
},
|
||||
"steps": 11
|
||||
},
|
||||
{
|
||||
"id": "0a6f79c0-3ca6-446a-8b44-61e65293f096",
|
||||
"taskId": "123d1db4-7a5b-430b-8794-82143229477e",
|
||||
"planId": "581b9db0-7bdf-4466-9902-20fa56fb2e89",
|
||||
"fingerprint": "b3ee149b7b38353fc06562f949037ab013bf7b5559e59c3cba0f21e0ff83f316",
|
||||
"viewport": {
|
||||
"width": 390,
|
||||
"height": 844
|
||||
},
|
||||
"steps": 0
|
||||
},
|
||||
{
|
||||
"id": "94a6b416-14d7-4af3-926a-4d623019d423",
|
||||
"taskId": "123d1db4-7a5b-430b-8794-82143229477e",
|
||||
"planId": "f608c1b0-5697-478e-8fc2-2bead0d5045e",
|
||||
"fingerprint": "1b47ed5f208d0b087b35d0784ca21ec6209957ff5c409b4c72f0b47d59b414f3",
|
||||
"viewport": {
|
||||
"width": 390,
|
||||
"height": 844
|
||||
},
|
||||
"steps": 7
|
||||
}
|
||||
],
|
||||
"continuations": [
|
||||
{
|
||||
"previousRunId": "8d074a41-12fc-4504-a73b-9fcc2a2cb1a8",
|
||||
"reason": "step_limit",
|
||||
"at": "2026-10-30T01:36:18.243Z"
|
||||
}
|
||||
],
|
||||
"error": "AssertionError [ERR_ASSERTION]: Actual model task exceeded the acceptance time bound.\n+ actual - expected\n\n+ 'running'\n- 'completed'\n\n at file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/verify-live-browser.mjs:77:10"
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"success": true,
|
||||
"version": "1.10.1",
|
||||
"testedAt": "2026-10-30T01:15:09.844237+00:00",
|
||||
"archives": [
|
||||
{
|
||||
"kind": "portable",
|
||||
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64.zip",
|
||||
"files": 10978,
|
||||
"crcPassed": true,
|
||||
"manifestAndDirectoryMatch": true,
|
||||
"sha256": "79282d19126916e4267233b6db7dd2b646b8fdf545af90cb0c6d6b14ffb9110d"
|
||||
},
|
||||
{
|
||||
"kind": "source",
|
||||
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-source.zip",
|
||||
"files": 9213,
|
||||
"crcPassed": true,
|
||||
"manifestAndDirectoryMatch": true,
|
||||
"sha256": "1ffd99d2d984d9ed5ac29adc88ef6fbcce8d3925f3098bfeeffc95c246a9f636"
|
||||
}
|
||||
],
|
||||
"extractionRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\source-check-b25790b942b14f14ab7f0f478f18e4cf\\Agent-Workbench-1.10.1-source"
|
||||
}
|
||||
@@ -0,0 +1,139 @@
|
||||
{
|
||||
"success": true,
|
||||
"date": "2026-10-30T01:19:36.377Z",
|
||||
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64",
|
||||
"version": "1.10.1",
|
||||
"nodeVersion": "v24.22.1",
|
||||
"verifiedFiles": 10978,
|
||||
"url": "http://127.0.0.1:51311",
|
||||
"reusedPid": 10512,
|
||||
"checks": {
|
||||
"jobId": "5741ea6e-f7b5-4c91-b7c0-70b2fb35780b",
|
||||
"status": "passed",
|
||||
"tests": {
|
||||
"total": 4,
|
||||
"passed": 4,
|
||||
"failed": 0,
|
||||
"cancelled": 0,
|
||||
"skipped": 0
|
||||
}
|
||||
},
|
||||
"actualRea": [
|
||||
{
|
||||
"operation": "javascript",
|
||||
"jobId": "1d9a11f1-a561-462a-9771-9f8f421bf861",
|
||||
"evidenceId": "ev_d51b3510ae32682774301354ddbf2435fc9a6c72591748b741d7c8a814a7d077",
|
||||
"targetSha256": "d17bffad8f693003a12d6f5267cedd4092b7d0a69b88db7d3db492c3f41a05ef",
|
||||
"bundleSha256": "4a69f23e1828823939426ef6dc1bf48fc3530b6c1bcb85d0f634501e190ac440",
|
||||
"rootExited": true,
|
||||
"reusedJobId": "68702c8c-6603-4f91-b4a7-43c967709932"
|
||||
},
|
||||
{
|
||||
"operation": "pe-imports",
|
||||
"jobId": "6b3adcea-64e6-40c7-a183-95cf2a017a91",
|
||||
"evidenceId": "ev_38f48d25f87a2165276579ac393813cc403df5b4ee01e831b7bc1c1f9cdd4e10",
|
||||
"targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973",
|
||||
"bundleSha256": "e0f2eccbc32ff09daf2ac077a39a2063a8f716f70f40e14f90d8d7cec062e25b",
|
||||
"rootExited": true,
|
||||
"reusedJobId": "5eda3c73-1b92-4351-adae-68be300f405d"
|
||||
},
|
||||
{
|
||||
"operation": "pe-resources",
|
||||
"jobId": "3b11a229-c42c-4d40-9f3d-7bd01f32dbf8",
|
||||
"evidenceId": "ev_369efbccc1976b37cdc6b07b35bcbcb70154c121c19c559039a1497f9be35e71",
|
||||
"targetSha256": "7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973",
|
||||
"bundleSha256": "2b036c47434c47e0842eabf8049c6c6a7ed5fd177ffa413644efcca8d1e3b494",
|
||||
"rootExited": true,
|
||||
"reusedJobId": "89b4bb41-516b-42e8-b9ee-d70b0d21596e"
|
||||
}
|
||||
],
|
||||
"actualEngine": {
|
||||
"packageVersion": "0.2.1-rc.2",
|
||||
"profile": "sdk-minimal",
|
||||
"installationSha256": "dda058a12d3a39afd3a07690316f790fa1721e65db07b80d76a9ffd806c0443d",
|
||||
"reportSha256": "e7713daa6a08bb5dbaaeeb05fe9a6f585623a3eedb6559407506325040e6bedf",
|
||||
"rootExited": true,
|
||||
"modelRequests": 0,
|
||||
"nativeMethods": [
|
||||
"initialize",
|
||||
"session/working-directory/get",
|
||||
"session/wait",
|
||||
"session/resume",
|
||||
"session/cancel",
|
||||
"shutdown"
|
||||
],
|
||||
"node": {
|
||||
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64\\runtime\\node.exe",
|
||||
"bytes": 93915464,
|
||||
"sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
|
||||
"version": "24.22.1"
|
||||
}
|
||||
},
|
||||
"actualBrowser": {
|
||||
"success": true,
|
||||
"installation": {
|
||||
"status": "available",
|
||||
"engine": "Microsoft Edge",
|
||||
"playwrightVersion": "1.64.1"
|
||||
},
|
||||
"results": [
|
||||
{
|
||||
"jobId": "0b2876f8-bb11-4c1c-bb3b-be10c9ee98d3",
|
||||
"taskId": "fa21d44b-90f0-4b65-bd9d-95d0bcc68913",
|
||||
"viewport": {
|
||||
"width": 1280,
|
||||
"height": 900
|
||||
},
|
||||
"status": "passed",
|
||||
"assertions": {
|
||||
"total": 3,
|
||||
"passed": 3,
|
||||
"failed": 0
|
||||
},
|
||||
"resultSha256": "65eadeebba852847365071fb2bcec4b26fe0149d8df94193cbcd684c327dd1b4",
|
||||
"buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd",
|
||||
"screenshotSha256": "a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54",
|
||||
"browserExited": true,
|
||||
"reusedOriginalJob": true
|
||||
},
|
||||
{
|
||||
"jobId": "6c52f2a4-4e2f-4849-befa-47254b922135",
|
||||
"taskId": "fa21d44b-90f0-4b65-bd9d-95d0bcc68913",
|
||||
"viewport": {
|
||||
"width": 390,
|
||||
"height": 844
|
||||
},
|
||||
"status": "passed",
|
||||
"assertions": {
|
||||
"total": 3,
|
||||
"passed": 3,
|
||||
"failed": 0
|
||||
},
|
||||
"resultSha256": "239860af593dd6e476977dcd031fa80cef240ad3a435b5a823d3252f8f9deb0d",
|
||||
"buildSha256": "1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd",
|
||||
"screenshotSha256": "590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f",
|
||||
"browserExited": true,
|
||||
"reusedOriginalJob": true
|
||||
}
|
||||
],
|
||||
"modelRequests": 0,
|
||||
"scope": "Actual API, locked browser runtime, two isolated Edge processes, CSS interactions, original DOM and PNG bytes. The task is created through the offline demonstration; no remote model is used."
|
||||
},
|
||||
"steps": [
|
||||
"manifest hashes",
|
||||
"bundled Node launch",
|
||||
"same-service reuse",
|
||||
"packaged example and static page",
|
||||
"explicit command consent",
|
||||
"actual bundled Node version",
|
||||
"actual bundled npm check without system Node/npm",
|
||||
"check log artifact",
|
||||
"contained REA installation and Node identity",
|
||||
"actual ASAR/imports/resources",
|
||||
"original Bundle and target hash binding",
|
||||
"verified reuse without producer replay",
|
||||
"report availability",
|
||||
"graceful stop"
|
||||
],
|
||||
"realModel": false
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,180 @@
|
||||
{
|
||||
"success": true,
|
||||
"testedAt": "2026-10-30T01:32:55.996Z",
|
||||
"version": "1.10.1",
|
||||
"pid": 23080,
|
||||
"hasKey": true,
|
||||
"projects": 14,
|
||||
"sessions": 24,
|
||||
"appDirectory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64",
|
||||
"verified": true,
|
||||
"connectionPreserved": true,
|
||||
"url": "http://127.0.0.1:4318",
|
||||
"previousVersion": "1.10.0",
|
||||
"model": "gpt-6.1-sol",
|
||||
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64",
|
||||
"dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench",
|
||||
"projectsPreserved": true,
|
||||
"preservedSessionSnapshots": [
|
||||
{
|
||||
"id": "03d6acd3-01ee-46fb-aa1c-90483307737e",
|
||||
"session": "ce12fab8fa32c200b16851a66d7af6eea99ddb4783aa5c2ebd2211f7fbbfcb4b",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "0c9601a4-cc20-476c-aa28-ea010c222f70",
|
||||
"session": "ed40337c7e51140540dfc7fbbae065e04cf9b49d8bad1e02f61aa922859eeba7",
|
||||
"project": "8de47871c83677c90f046ab4ef11b10f2bf6602e4e7683a68034f91665f18ae7",
|
||||
"execution": "32346c10d95f71e2b5a82ac06d8bc76c9c45af5b9798815ea9ba13d578e1a0d8"
|
||||
},
|
||||
{
|
||||
"id": "0f3ace68-4988-4370-bf22-aac01f33a8ab",
|
||||
"session": "462ab9235f6132141aab9b6fc9c03966d256970c8e19b98a17a38d1a0812b4b4",
|
||||
"project": "b62f016403188e605f211acf90e6435af951fa772e339f5a967078dc49341dc9",
|
||||
"execution": "889846e378aa03c9e26f57ba6a818e2d4762690d1c6524ae3af5adb7a6435294"
|
||||
},
|
||||
{
|
||||
"id": "1102be26-9799-4f0f-9a28-7a4ce552f3a9",
|
||||
"session": "3303bc0113392be74ba3091f133a247b86acf7fdd935a9d3d7692a12a555f928",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "1cf22a27-ac13-4c95-a878-9b4356ccb5b3",
|
||||
"session": "519eea1e103fd081279a82d4b4e72d17857a18b027eb0b156972855c90349552",
|
||||
"project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1",
|
||||
"execution": "bd26cba0a2cffcbbb32bb6f36bbd914b266c57d2d2e7c7edc505cdedbf5a68fa"
|
||||
},
|
||||
{
|
||||
"id": "4442eee6-8b68-4bb5-a39c-9cafbaeb9eb8",
|
||||
"session": "7c45225f6ace5f5397584a92e5303db762acdb2bfa311cc3d16e8fd6aaeb5253",
|
||||
"project": "5ec499d561c29586cc0f4d4237d361d144bcbee14c1fc262479172a77d93b1a1",
|
||||
"execution": "4ce5df2162054e94de1468a70bf40efad9216e749ec25920ca95d7294537755d"
|
||||
},
|
||||
{
|
||||
"id": "4abc4201-549e-46e0-947c-3d3f5b53ffae",
|
||||
"session": "7f76d7f6ea57b3b842b8289b0fbba5d196df03df7cdc8ae0c6594816f103ae4d",
|
||||
"project": "91f80e1c4cec343d0b632ad7e0b9eb8f732ca39c8290e40a8dc085f113339ffd",
|
||||
"execution": "ce1831ebe9eb59cc3784d4803f574e29cf1c356967330e5589cb9d69036261a6"
|
||||
},
|
||||
{
|
||||
"id": "50c279be-66ad-48b8-a483-4e11c814db47",
|
||||
"session": "9abdcf0865de6578dbfda995836e7e913f4f65ee38c0f40af90f7bb8a9f0ae87",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "569c9457-d399-46e6-b53e-4b1fdbb02109",
|
||||
"session": "11614934261d3c1c7b2134d9ffaf70bcca207876b2e8dff76e596afe48c1be3c",
|
||||
"project": "91f80e1c4cec343d0b632ad7e0b9eb8f732ca39c8290e40a8dc085f113339ffd",
|
||||
"execution": "390674ad40f55fd0ed37cbcf087d1c0f1c992480e7b8d8b3cb7282575a10ac5f"
|
||||
},
|
||||
{
|
||||
"id": "72d3d22f-14d9-4bca-bb6a-ab686bc96b26",
|
||||
"session": "1ba568d537e40edf8400dbb0c6bdce5a13ed4e71a3634c38a563b468b8a309aa",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "1d57f5926ec3e1e47ccfbf6db301fe3519b3b26f10359850df984cd91d2525cd"
|
||||
},
|
||||
{
|
||||
"id": "776d488f-18a7-41aa-96a4-91dd1f19d374",
|
||||
"session": "dc9824b3cd6e7203e6e805ab7291bd6c4b514c7524637a937e487c32853aab1d",
|
||||
"project": "bcaad9ff6ce07b52fbe8f23009bc72f8928c2f2a4859099bfbd3121d52d0bca3",
|
||||
"execution": "d65517746df52b6c0be3e2e08dba5f2ba969e48fff28c94b66cd2971650d24b5"
|
||||
},
|
||||
{
|
||||
"id": "77f7237d-b7b4-4725-b82b-0781a669740b",
|
||||
"session": "27f35a1b6db0905f20b758abc68c79286a703c6557eeef7bcb95bc17c13eafa0",
|
||||
"project": "d881bf752b0e14b37c0325d077a459b08be741605aef0db775195d2de66c4595",
|
||||
"execution": "fbb3b475561fac29ac8ac793f91176254b5b1a3fce476f3e2a70d13182e273f8"
|
||||
},
|
||||
{
|
||||
"id": "87a48440-804e-4ac4-8a9f-5ba38a55c082",
|
||||
"session": "b4e9c835232835730d601c1a327795602c5bc21bf330d30b67acd0f5b57720fa",
|
||||
"project": "3b83f6c68b0af564e8732559ff71514f738252a0fd2d097db61c9a023f179d79",
|
||||
"execution": "c4a01832f3c963bba8282d9b585de2429a9f2aff2ebf89914cac067ec35cb6a5"
|
||||
},
|
||||
{
|
||||
"id": "997213e9-ccd7-485e-a099-ad348b626610",
|
||||
"session": "7edddb9135e4c0694e9e375d00d0db38f889b47c3cd8ce9c118873e3ab17c9a8",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "af2827eb-b31c-456e-b9ab-6f34ab8f600e",
|
||||
"session": "8b5fcd43f63f2dcb5a2bf65c9503b02147f3e0a76ca5da6c84cb588b53b1714c",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "b045829c-377b-4f69-ad0b-513fe797b421",
|
||||
"session": "44040c046fd23053228a203745112b277acfcb191ae5a5ce957dd7090c983a2f",
|
||||
"project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1",
|
||||
"execution": "a83ff26c46d72d5f4bc11716fb5073fcd1685dcf5a30740d9becddb78e273d19"
|
||||
},
|
||||
{
|
||||
"id": "c25669d5-9c3b-4548-80d5-51c58a3c5e73",
|
||||
"session": "e662f26079c573528662fe5a144142fc938f8a316a74afea9a4eaffd4fa25e69",
|
||||
"project": "e5048b792e2681faf68f83b4cd35a7e321dce4ac0dafd07d8b6007d430db66bf",
|
||||
"execution": "5f08a4c7a4c2209c10a1e540ea4873cae70a501f0a5dd05b2d8f3a79da9fcc31"
|
||||
},
|
||||
{
|
||||
"id": "c32c9c87-8239-4606-a4c0-783529603bc7",
|
||||
"session": "5a9d028a1054136e85c2037d4151709c3d835d9edb2e67476e3dd9becb493e83",
|
||||
"project": "6b00a6786f0a47fc81edbcdb39300b0d486deea338d1c4c327395da64238f331",
|
||||
"execution": "7035206125b8fbd14a6b6e2450c4be439fd43a6557e07ed7e3a5cfeb74f26a15"
|
||||
},
|
||||
{
|
||||
"id": "c52d620a-dbaa-4bbd-9039-0eabe53ba03d",
|
||||
"session": "019799045a657a75bf74f2cb659ca00aa31e55a8c1609df64ac007ee4b1a9c61",
|
||||
"project": "4eaa22c28bc011f866c6fd49ad44169d8c6eb14e3e3a6a23e916d25545d5e3fa",
|
||||
"execution": "2a60abba8cfa47818937fe733170500bbedc448248e600d6d55b1e951ecf9582"
|
||||
},
|
||||
{
|
||||
"id": "dccf608f-44c9-4031-a58c-5ba87fe3b3f8",
|
||||
"session": "00018e8b18ba8311b139cce9ab5c5414c26b8893b3234efd8f54804711978ed1",
|
||||
"project": "844f1c9a520e159edb9e76a169d674484386ca30a141e47de720a8c2ec4d4acd",
|
||||
"execution": "544d05e27c12bf22ece5cff61642f2d62ca210935473fbeb8db010bba55f238a"
|
||||
},
|
||||
{
|
||||
"id": "e8846c6e-1ba2-497e-b0db-ca5778181eb0",
|
||||
"session": "81477eeefcdf965fdd9091e05670df99e3817f7cbc6ab56605c215262ec3cd5c",
|
||||
"project": "0a1d247fb4e3fc9dfc35ec2e4902e107c8ccc8efcc33e61e556cd5230e4777d1",
|
||||
"execution": "4154c4490e5ed0ff19004f5c95cce946620aeefdc4402db7aef149888abfa62e"
|
||||
},
|
||||
{
|
||||
"id": "ea5ec3cb-b074-41ac-989c-34c6515bd742",
|
||||
"session": "983e92750affa53234ea805de39889e58c5a2a1b4e016e8a84d1ff15d83bb918",
|
||||
"project": "3b83f6c68b0af564e8732559ff71514f738252a0fd2d097db61c9a023f179d79",
|
||||
"execution": "6f811eaed0dc1cf0af7d9568dfea7a94a745e05f57e820802806918dc5269ba9"
|
||||
},
|
||||
{
|
||||
"id": "f8a5a714-183d-4d6c-af27-ed56c60225b2",
|
||||
"session": "cff80cd569d20f8294703ad3fce75555a21b911e07339220a5bb2a31c01eb78d",
|
||||
"project": "d3025c877b071c0815d63323d883f68be4e778ba4392ab2bae91cf24cd34e29f",
|
||||
"execution": "e708ce8a2e1ff83110818db1bac7180483da9dd92801facb0652ee77fd64e0be"
|
||||
},
|
||||
{
|
||||
"id": "fc87c3f6-a108-4095-ae41-4ef56bc789c3",
|
||||
"session": "49dbf09c02b74d867df47a65185c60f5fac173ed114ccd6e7adf261a93e71b1f",
|
||||
"project": "72cc4e0235d860965503c3b4f7d0a59f5f8a8720592e10578c4da7ab36bf1af1",
|
||||
"execution": "96b629b8b3c9a22e3a67ad97f6fabea1c1d077aa64c618dab2329645b3827043"
|
||||
}
|
||||
],
|
||||
"inspectorClosed": true,
|
||||
"comparedFiles": 8749,
|
||||
"allSessionCount": 24,
|
||||
"activeSessionCount": 17,
|
||||
"archivedSessionCount": 7,
|
||||
"independentSourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\source-check-b25790b942b14f14ab7f0f478f18e4cf\\Agent-Workbench-1.10.1-source",
|
||||
"independentSourceTests": {
|
||||
"tests": 276,
|
||||
"pass": 276,
|
||||
"fail": 0,
|
||||
"cancelled": 0,
|
||||
"skipped": 0,
|
||||
"todo": 0
|
||||
},
|
||||
"comparison": "Canonical JSON order; only missing execution.engineJobs=[], browserPlans=[] and browserJobs=[] are projected. Every existing session/project/execution field and public model budget is compared.",
|
||||
"credentialsHandling": "The original Provider keeps the original model connection in memory; no model key was read, copied, printed or saved."
|
||||
}
|
||||
@@ -1,14 +1,14 @@
|
||||
{
|
||||
"ready": true,
|
||||
"url": "http://127.0.0.1:4318",
|
||||
"version": "1.10.0",
|
||||
"version": "1.10.1",
|
||||
"mode": "compatible",
|
||||
"model": "gpt-6.1-sol",
|
||||
"hasKey": true,
|
||||
"pid": 23080,
|
||||
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.0-win-x64-20261030004653739",
|
||||
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.10.1-win-x64",
|
||||
"originalAppRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-0.1.0-win-x64",
|
||||
"dataRoot": "C:\\Users\\wangy\\AppData\\Local\\AgentWorkbench",
|
||||
"upgradedAt": "2026-10-30T01:03:29.628Z",
|
||||
"upgradedAt": "2026-10-30T01:32:55.996Z",
|
||||
"storage": "sqlite"
|
||||
}
|
||||
|
||||
@@ -285,3 +285,12 @@ Claude Code 报告已验证工具输入校验、权限决定、队列并发屏
|
||||
- 当前REA安装来自父研究目录runtime,149个已安装包、0个dev包、8465文件约136MiB;原发行脚本没有随包复制,必须封存生产依赖并验证发布目录内身份。
|
||||
- 研究面板最终11组、十一类界面98组通过,0页面/请求异常;桌面来源链/表单和390px原字段已目视核对。嵌套证据窗口键盘关闭已修正,长路径可换行,原文在内部滚动。停止按实际PID、finishedAt和关闭结果验证。
|
||||
- 完整源码首轮243项仅重复升级失败:支持版本列表漏了1.8.0,补齐后实际旧进程/重复升级专项1/1通过;原失败TAP/输入与UI首轮resize失败均保留。最终独立源码全量另行验证。
|
||||
|
||||
## 2026-10-30 当前恢复结论
|
||||
|
||||
- 1.10.1修复SQLite宿主升级后保留旧ArtifactStore API的问题;最终独立源码276项、源码/便携实际REA/DeepSeek/Edge均已通过,正式服务仍待从1.10.0升级。
|
||||
- 前轮页面实模的验证脚本错误地在completed后调用resume,产生新Task后触发身份断言;应仅续接paused/step_limit的原Task,其他结果如实封存,不改写原失败。
|
||||
- 已有独立任务计划草稿尚未完成API/UI/验收,不能登记为正式能力。下一切片将计划步骤和依赖绑定Task/Run及原结果,区别自述进度与实际可核验完成。
|
||||
|
||||
- 1.10.1实模实际桌面11步/8断言通过;390px的button:nth-of-type(1)在三个不同article内分别匹配按钮,严格模式正确拒绝。现有控件观察只给出文本/aria/id,没有经实际DOM计数验证的唯一CSS定位;补此证据比默默选第一个元素更能支持模型纠错。
|
||||
- 新实模失败后的原反馈与工件页有完整数据,模型仍反复读取,导致在210秒原边界内未完成。整体收尾需要持久步骤/核验与对专业结果读取的进展判断,不能用增加调用预算掩盖该问题。
|
||||
|
||||
+11
@@ -321,3 +321,14 @@
|
||||
|
||||
- 修复包便携10773份、源码8978份完整归档及便携三项实际REA通过;独立源码实际REA也通过,完整244项为243通过/1失败。唯一失败是新增深目录夹具固定追加4段,在解压源码下让SQLite自身超过路径范围,尚未到REA。改为按实际checkout补足165字符并为SQLite保留余量,保持REA必须走短输出目录的断言;原244项TAP与目录保留,最终源码重新冻结验收。
|
||||
- DeepSeek SDK首次实际initialize到20秒无响应,所属进程退出已核对,未发送prompt/模型请求;CLI版本0.2.1-rc.2与真实sdk-minimal默认配置已读取,继续定位启动与服务注入。OpenAI官方文档网页首次返回403,搜索只限定官方域;继续按可用官方页面核对,不能用空搜索或403当文档依据。
|
||||
|
||||
## 2026-10-30 接续1.10.1及任务计划
|
||||
|
||||
- 实际恢复HEAD 6bc3ce4,主仓库仅保留一份未跟踪的前轮实模页面失败记录;正式4318仍为1.10.0/PID23080。此前阶段旧日志不当作当前部署状态。
|
||||
- .qa/source-package-validation.json确认1.10.1最终独立源码276/276通过、离线构建6份一致;实际随包REA三操作、DeepSeek六方法和1280/390px Edge均通过,所属进程结束。完整TAP为526.963秒,验收已完成,不重复执行。
|
||||
- .qa/dev-task-plans是已存在的独立Git工作区,含未提交任务计划/契约/Runtime草稿,继续复用。现有研究worker均已完成,没有新建或重新委派。
|
||||
- 首次恢复批量输出及嵌套node_modules排除错误造成截断;改为明确文件/结构化摘要。下一步封存1.10.1证据、原连接升级、补实模页面验收及下一核心能力。
|
||||
|
||||
- 1.10.1专用源码/便携/归档/完整回归证据封存,174份冻结输入及8749份发行文件与独立源码一致;正式4318已保留PID23080/Provider及14项目/24会话升级,调试端口关闭。
|
||||
- 修复后的实模页面Task保存桌面8/8实际通过和390px3/4失败,原因是button:nth-of-type(1)匹配三个按钮;210秒到时停止,18响应/152837tokens,整体未完成。原1.10.0错误与新失败分别保留。
|
||||
- 1.11草稿接入持久计划/证明、HTTP身份、Git预览/发布时核对和JSON/Markdown报告;执行计划界面已编译。首轮TypeScript可选execution字段错误修正;首次专项日志重定向因独立工作区尚无.qa目录而未启动测试,创建目录后执行。
|
||||
|
||||
@@ -288,3 +288,15 @@
|
||||
本轮恢复错误:父研究目录不是Git仓库,已切换独立产品目录。批量源码/文档输出触发截断后改为短段和结构化摘要;Windows rg通配文件名失败改为目录加-g,未把截断内容作为完整核对。所有验收使用自有工件、独立端口和数据目录。
|
||||
|
||||
恢复时的只读搜索一次错误使用Windows通配路径和不存在的types文件,改为实际目录加glob;先前大输出截断不作为完整读取证据。session-catchup未发现额外记录。
|
||||
|
||||
## 2026-10-30 当前接续:1.10.1交付与持久任务计划
|
||||
|
||||
用户继续授权全量推进,沿用HEAD 6bc3ce4及.qa/dev-task-plans独立工作区的未提交草稿。正式4318实测1.10.0/PID23080;原Provider及仅内存Key保持。
|
||||
|
||||
1. [complete] 恢复1.10.1独立源码276/276、离线构建6份一致、实际随包REA/DeepSeek/Edge和便携/归档通过的原记录;不重复已完成的完整回归。
|
||||
2. [complete] 174份冻结输入及8749份发行输入与独立验收源码一致;专用证据封存、PID23080/Provider及14项目/24会话保留升级1.10.1。
|
||||
3. [complete] 同Task续接判定已修正,实模复验已执行并保存失败:桌面8/8,390px选择器匹配三个按钮;18响应/152837tokens、210秒后停止,不把部分通过算整体成功。
|
||||
4. [in_progress] 接续独立工作区的持久任务计划草稿;完成依赖、真实证据、续接/失效和确定性交付判定,接入模型/API/桌面及390px界面。
|
||||
5. [pending] 相关行为/API/恢复/真实界面和工程交付验收,审查diff并按小步本地提交;完成不可变下一发行的独立验收与部署。
|
||||
|
||||
恢复读文件时一次rg排除模式没有排除嵌套node_modules,输出过大;后续限定已知根文件及目录,不将截断清单作为核对结果。无新worker启动,不触碰其他项目。
|
||||
|
||||
Reference in New Issue
Block a user