fix(models): validate engine protocol budgets and freeze release acceptance inputs

This commit is contained in:
Agent Workbench Dev
2026-10-31 23:05:36 +08:00
parent 31ed219477
commit a72dc0fbc1
49 changed files with 21491 additions and 45 deletions
+8
View File
@@ -23,3 +23,11 @@ E界面已构建,正在操作验收;F独立发行与正式部署未执行。
目视截图发现并修复:片段同批到达后上游停顿,节流需要定时补发最新状态;选池后主窗口可能仍显示离线演示,旧提交校验还错误要求未选中的原连接模型名。现在用公开选路身份同步主窗口,刷新仍保留实际池名,原连接配置不被改写;新UI流程明确等待选路并刷新后发送。下载直接读取工件字节,畸形UTF8也不再被文本解码改写。37项流式/请求计划/升级、20项旧模型中心/API兼容和26项原字节/连接专项通过(重叠范围不累计)。
原UI定位失败、外部API增加连接后未刷新界面的夹具失败、真实节流缺陷、错误mobile选择器和原首次完整UI运行都保留。首次历史UI全量运行的Purge来源传成打包目录,修正为原source/upstream;原日志与阶段结果单独保存,重跑使用新顶层日志。完整回归早于最后修复启动,属于开发中诊断;最终结论以冻结后的独立源码整轮为准。
## F:工程门槛和发行冻结前回顾
固定原Node/React/Python工程通过实际Responses SSE、ModelHub、受控Harness、原审批、原检查、父工程合并和本地Git,共13节点;父工程8/8、9/9、10/10,原测试和用户暂存/未暂存字节保持。原失败cf832704及成功c0121328目录均保留,真实模型请求0。失败发现引擎完成核验只支持body.max_tokens,已逐Chat/Responses实际变体验证原输出预留、原输入SHA及归属,未略过预算核对。新增预算失配回归和协议14/14、Runtime/引擎36/36分别通过,范围重叠不累加。
完整历史UI25类191组通过(model-protocols-all-ui-validation.json)。开发中整套回归553项552通过/1失败,原日志保留;旧测试把破损JSON预期为工具内错误,现按完整响应契约改为合法JSON的语义参数错误,并新增两个协议整组不执行/不重放回归。最终验收须来自冻结后的独立源码整轮,不把开发中结果当最终发行通过。
新原生观察已封存protocol-native-before,正式仍1.16;用户期间新增的项目/Task以正式部署前新快照为准,不沿用旧计数、不重放原任务。私有发行执行器只复制到新路径;正式公开模型中心的新默认能力字段将逐项校验,存储行、导出、配置和原工件必须严格保持。封存脚本初次替换顺序拒绝、构建误用未安装的本地npm路径失败均保留;改为限定顺序和固定Node附带npm后构建通过。
+6
View File
@@ -15,3 +15,9 @@
单看控件存在会遗漏主任务问题。截图中主窗口还显示离线演示,导致发现选池/关闭窗口时的外部状态同步与旧legacy模型校验缺陷;现在选择和刷新都保留实际池名,再由同一后端选路执行。流式首批事件合并时曾只显示0字符,增加定时补发最终片段,停止时清除计时器,专门检查上游不再发送任何事件的情形。
桌面/390px和真实TLS配对观察窗口5组完整流程通过并目视回看。手机原生Safari、信任/PWA已有1.16实机记录;1.17新增流式尚无新实机结论。工程回归继续使用固定原测试和真实Node/React/Python执行,增加同一原工程算法通过Responses SSE与受控Harness的独立门槛,不能拿文本fixture结束当工程完成。
## F:执行成功还要经过交付证明
三个真实工程检查通过时,Responses子任务最初仍暂停。原因是旧证据核验把max_tokens当唯一输出预留字段;新请求变体本身和实际执行正确,但核验不兼容。修复后逐变体核对原native.maxTokens、完整请求指标和归属,原审批/失败/成果没有重放,重新独立工程完成。这样的暂停有价值,不能把它当成理由放松交付证明。
破损JSON整组拒绝与合法JSON参数校验是两个边界,旧Runtime测试现在保留后者,新增前者分别覆盖Chat和Responses及池不重放。完整历史UI191组和原工程通过不替代独立源码发行门槛;正式升级前重新捕获全部用户状态,允许公开能力字段的已知默认增量,禁止把其它差异统一忽略。
+209
View File
@@ -0,0 +1,209 @@
{
"success": true,
"version": "1.17.0",
"at": "2026-10-31T14:54:40.155Z",
"groups": 191,
"results": [
{
"script": "verify-model-protocols-ui.mjs",
"success": true,
"groups": 5,
"durationMs": 22412,
"evidence": "docs/model-protocols-model-protocols-ui-validation.json",
"log": ".qa/model-protocols-verify-model-protocols-ui.log"
},
{
"script": "verify-companion-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 24040,
"evidence": "docs/model-protocols-companion-ui-validation.json",
"log": ".qa/model-protocols-verify-companion-ui.log"
},
{
"script": "verify-controlled-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 88501,
"evidence": "docs/model-protocols-controlled-final-ui-validation.json",
"log": ".qa/model-protocols-verify-controlled-ui.log"
},
{
"script": "verify-purge-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 32355,
"evidence": "docs/model-protocols-purge-final-ui-validation.json",
"log": ".qa/model-protocols-verify-purge-ui.log"
},
{
"script": "verify-workers-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 173264,
"evidence": "docs/model-protocols-workers-ui-validation.json",
"log": ".qa/model-protocols-verify-workers-ui.log"
},
{
"script": "verify-task-plans-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 17386,
"evidence": "docs/model-protocols-task-ui-validation.json",
"log": ".qa/model-protocols-verify-task-plans-ui.log"
},
{
"script": "verify-browser-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 27875,
"evidence": "docs/model-protocols-browser-ui-validation.json",
"log": ".qa/model-protocols-verify-browser-ui.log"
},
{
"script": "verify-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 24543,
"evidence": "docs/model-protocols-basic-ui-validation.json",
"log": ".qa/model-protocols-verify-ui.log"
},
{
"script": "verify-diagnostics-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 23892,
"evidence": "docs/model-protocols-diagnostics-ui-validation.json",
"log": ".qa/model-protocols-verify-diagnostics-ui.log"
},
{
"script": "verify-execution-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 32631,
"evidence": "docs/model-protocols-execution-ui-validation.json",
"log": ".qa/model-protocols-verify-execution-ui.log"
},
{
"script": "verify-delivery-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 56215,
"evidence": "docs/model-protocols-delivery-ui-validation.json",
"log": ".qa/model-protocols-verify-delivery-ui.log"
},
{
"script": "verify-index-ui.mjs",
"success": true,
"groups": 8,
"durationMs": 8665,
"evidence": "docs/model-protocols-index-ui-validation.json",
"log": ".qa/model-protocols-verify-index-ui.log"
},
{
"script": "verify-change-sets-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 16725,
"evidence": "docs/model-protocols-change-sets-ui-validation.json",
"log": ".qa/model-protocols-verify-change-sets-ui.log"
},
{
"script": "verify-context-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 25214,
"evidence": "docs/model-protocols-context-ui-validation.json",
"log": ".qa/model-protocols-verify-context-ui.log"
},
{
"script": "verify-workspaces-ui.mjs",
"success": true,
"groups": 9,
"durationMs": 30360,
"evidence": "docs/model-protocols-workspaces-ui-validation.json",
"log": ".qa/model-protocols-verify-workspaces-ui.log"
},
{
"script": "verify-python-ui.mjs",
"success": true,
"groups": 7,
"durationMs": 36071,
"evidence": "docs/model-protocols-python-ui-validation.json",
"log": ".qa/model-protocols-verify-python-ui.log"
},
{
"script": "verify-react-delivery.mjs",
"success": true,
"groups": 6,
"durationMs": 62073,
"evidence": "docs/model-protocols-react-delivery-validation.json",
"log": ".qa/model-protocols-verify-react-delivery.log"
},
{
"script": "verify-research-ui.mjs",
"success": true,
"groups": 11,
"durationMs": 39718,
"evidence": "docs/model-protocols-research-ui-validation.json",
"log": ".qa/model-protocols-verify-research-ui.log"
},
{
"script": "verify-engines-ui.mjs",
"success": true,
"groups": 10,
"durationMs": 18470,
"evidence": "docs/model-protocols-engines-ui-validation.json",
"log": ".qa/model-protocols-verify-engines-ui.log"
},
{
"script": "verify-model-center-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 14851,
"evidence": "docs/model-protocols-model-center-ui-validation.json",
"log": ".qa/model-protocols-verify-model-center-ui.log"
},
{
"script": "verify-project-memory-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 9629,
"evidence": "docs/model-protocols-project-memory-ui-validation.json",
"log": ".qa/model-protocols-verify-project-memory-ui.log"
},
{
"script": "verify-task-checkpoints-ui.mjs",
"success": true,
"groups": 3,
"durationMs": 10062,
"evidence": "docs/model-protocols-task-checkpoints-ui-validation.json",
"log": ".qa/model-protocols-verify-task-checkpoints-ui.log"
},
{
"script": "verify-skills-ui.mjs",
"success": true,
"groups": 4,
"durationMs": 9400,
"evidence": "docs/model-protocols-skills-ui-validation.json",
"log": ".qa/model-protocols-verify-skills-ui.log"
},
{
"script": "verify-mcp-ui.mjs",
"success": true,
"groups": 6,
"durationMs": 12386,
"evidence": "docs/model-protocols-mcp-ui-validation.json",
"log": ".qa/model-protocols-verify-mcp-ui.log"
},
{
"script": "verify-mcp-recovery-ui.mjs",
"success": true,
"groups": 2,
"durationMs": 7948,
"evidence": "docs/model-protocols-mcp-recovery-ui-validation.json",
"log": ".qa/model-protocols-verify-mcp-recovery-ui.log"
}
],
"scope": "Every verifier owns an independent port and synthetic data directory. Synthetic provider fixtures verify protocols; configured-model acceptance is separate. No production service or real key read/copied."
}
@@ -0,0 +1,27 @@
{
"success": true,
"url": "http://127.0.0.1:62053",
"browser": "Microsoft Edge 156.0.4314.50",
"date": "2026-10-31T14:47:44.485Z",
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\ui-64a4aaa1-6579-409f-88da-70e034ec84fb\\ui-project",
"viewports": [
1440,
780,
390
],
"passed": [
"project selection and real file preview",
"real command consent, execution and stale snapshot rejection",
"diff review and verified file application",
"manual editor creates a reviewable proposal",
"file responses stay with the current selection",
"denial, session selection, reload, stale response rejection and export",
"project inventory responses cannot replace another project",
"780 and 390 px: project drawer, file, diff and trace controls, no page overflow",
"unified and detailed research reports render",
"model list, ephemeral key, compatible fixture tool loop and return to offline mode"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; no real model"
}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:50:03.375Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/model-protocols-batch-desktop-review.png",
".qa/screenshots/model-protocols-batch-desktop-conflict.png",
".qa/screenshots/model-protocols-batch-desktop-recovery.png",
".qa/screenshots/model-protocols-batch-mobile-review.png",
".qa/screenshots/model-protocols-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-40c92fcb-1295-4f58-80f8-fbd6efcaff0c",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,175 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:47:19.835Z",
"directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-358841cd-bd07-4cde-9eff-0622bd53b2f1",
"passed": [
"actual step editor seals the chosen build, viewport and three CSS interactions without opening the page",
"review shows exact build identity and planned assertions; cancelling executes no browser work",
"real inner Edge clicks the intended element and the two counted assertions display with original Task/Run/build identity",
"original large JSON is paged in the UI and downloads the complete hash-identical result",
"the original screenshot renders at its actual resolution and downloads identical PNG bytes",
"a real failed assertion retains actual count one and requires a newly reviewed plan instead of replaying",
"390px forms and result records remain usable and the inner browser captures its real 390px layout",
"stopping an actual in-flight assertion closes its owned browser and preserves prior successful and failed jobs",
"a delayed original-record failure stays with its source and does not appear in a newly selected task",
"actual host restart preserves the four original browser jobs and PNGs without model requests or execution replay"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-358841cd-bd07-4cde-9eff-0622bd53b2f1\\browser-desktop-results.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-358841cd-bd07-4cde-9eff-0622bd53b2f1\\browser-desktop-original-image.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-358841cd-bd07-4cde-9eff-0622bd53b2f1\\browser-mobile-results.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\browser-ui-358841cd-bd07-4cde-9eff-0622bd53b2f1\\browser-mobile-original-image.png"
],
"taskId": "a32f6bf7-5a6a-4a3b-b675-3bf7bb07cc08",
"sessionId": "b0266472-8582-4fe4-9bf7-364c0e968c83",
"jobs": [
{
"id": "0a10a4b2-814f-46ad-bb39-c6363270746b",
"status": "passed",
"planId": "ff4c8e21-5ace-4e40-a79f-ba3f0b13fb7e",
"assertions": {
"total": 2,
"passed": 2,
"failed": 0
},
"resultSha256": "95db2e4c3107cb6a2f9cacf63e79857f64a1e9e49be438a8ef53befb40253e93",
"cleanup": {
"pid": 32508,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-10-31T14:46:59.993Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "23f0e58c-b208-4ecd-a998-8f744c326ab0",
"sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef",
"bytes": 101061,
"width": 1280,
"height": 900,
"label": "initial"
},
{
"artifactId": "39c484dd-afdf-40f5-a804-f609ba8505b6",
"sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7",
"bytes": 85261,
"width": 1280,
"height": 900,
"label": "final"
}
]
},
{
"id": "08e97273-09d1-4ae3-b61e-ee2dbc75989e",
"status": "failed",
"planId": "1d9361b2-c74c-405f-8c32-a87f5d75d6e0",
"assertions": {
"total": 2,
"passed": 1,
"failed": 1
},
"resultSha256": "4853092c9b85e0d4d7768e5d26f88d11a494b6eab18ab4043efbf16bda618c65",
"cleanup": {
"pid": 12784,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-10-31T14:47:07.343Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "f5fedd02-bf03-4933-9743-3658e53d699c",
"sha256": "74f2387b837f5f74bd7e8eef7631865a3b5bb24601c4bbaa93b2478a9e94c6ef",
"bytes": 101061,
"width": 1280,
"height": 900,
"label": "initial"
},
{
"artifactId": "4cad830b-c171-425c-b34e-d719423b3dd5",
"sha256": "b1de525bcf042bc1724e8a9c6670042ab3035bed394ff76cf2a934a443ae98f7",
"bytes": 85261,
"width": 1280,
"height": 900,
"label": "failure"
}
]
},
{
"id": "ebe899f1-66c1-456f-85ae-5a41c82b75f0",
"status": "passed",
"planId": "1c193b34-df7f-4b99-94c1-272e31cd2cd5",
"assertions": {
"total": 2,
"passed": 2,
"failed": 0
},
"resultSha256": "ecb8b9a9aedb31373fcf335d0e573a4d368cdac981615677bbc58725b3ad80bb",
"cleanup": {
"pid": 34296,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-10-31T14:47:11.189Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "f52b25da-c226-4180-b15d-1f47c67f651c",
"sha256": "93969f1954eec1f7fa4736d7a3035631c6066b6727132ff1179180eadb745602",
"bytes": 11011,
"width": 390,
"height": 844,
"label": "initial"
},
{
"artifactId": "d1ba441f-599c-4c33-85f7-bfa4dd495a27",
"sha256": "a6908ecfcfd239721ec6bbb916a5054d2f61183b6dea3f014db89216d371d0e3",
"bytes": 18832,
"width": 390,
"height": 844,
"label": "final"
}
]
},
{
"id": "d5483e7a-3283-453c-9b2d-db645c359edf",
"status": "interrupted",
"planId": "54f5fed3-d482-4ad8-a66e-87c8a271ab98",
"assertions": {
"total": 3,
"passed": 2,
"failed": 1
},
"resultSha256": "8668100df79ec25574a67bf0d1538ec5b7dd46d959a5c85c05f59dbd037f9109",
"cleanup": {
"pid": 38520,
"exited": true,
"exitCode": 0,
"signal": null,
"finishedAt": "2026-10-31T14:47:15.955Z",
"previewClosed": true,
"snapshotDisposed": true
},
"screenshots": [
{
"artifactId": "aaaa0da4-16a2-4124-b475-a8aa15ef8502",
"sha256": "93969f1954eec1f7fa4736d7a3035631c6066b6727132ff1179180eadb745602",
"bytes": 11011,
"width": 390,
"height": 844,
"label": "initial"
}
]
}
],
"scope": "Actual independent Workbench UI plus real Edge static-build executions. The configured production Provider, other projects and keys are not accessed."
}
@@ -0,0 +1,29 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:50:03.375Z",
"cases": [
"Desktop batch scope, per-file diffs, sealed single-write guard and pre-apply bytes",
"Three-file reviewed application preserves exact BOM/CRLF/LF and creates the new file",
"Explicit batch rollback restores exact originals and removes only the reviewed new file",
"A last-file owner conflict blocks the whole batch and shows the real recovery direction",
"Durable partial recovery reads actual hashes and preserves owner content during rollback",
"Changed observation fingerprints reject stale acknowledgement without releasing the project",
"Explicit owner-content acknowledgement ends recovery without claiming successful application",
"Switching projects clears the previous task notification while retaining its durable error and recovery history",
"390px step-limit review, same-task continuation entry, rollback confirmation and keyboard close fit the viewport",
"A delayed preparation response never opens a different project or changes its selected session",
"A failed batch response after its component unmounts cannot display an error in the newly selected project"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/model-protocols-batch-desktop-review.png",
".qa/screenshots/model-protocols-batch-desktop-conflict.png",
".qa/screenshots/model-protocols-batch-desktop-recovery.png",
".qa/screenshots/model-protocols-batch-mobile-review.png",
".qa/screenshots/model-protocols-batch-mobile-rollback.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\batch-ui-40c92fcb-1295-4f58-80f8-fbd6efcaff0c",
"scope": "Real independent demo host and durable batch states; UI fixtures include actual owner conflict/rollback results. No real model credentials or user project were used."
}
@@ -0,0 +1,42 @@
{
"success": true,
"version": "1.17.0",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench",
"nodePath": "D:\\Ai-project\\REA逆向\\tools\\node-v24.22.1-win-x64\\node.exe",
"nodeSha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
"containedRuntime": false,
"passed": [
"desktop explicitly enables HTTPS and downloads the actual public CA without changing OS trust",
"390px real gateway pairing clears fragment, displays scoped task list and registers the same device in desktop",
"phone UI confirms original Task/Run approval and the existing Runtime executes one command",
"original paginated diff and counted check/report display verified content from the same Task",
"disconnect and refresh recover from persistent seq without submitting a new command or Run",
"PWA service worker stores the shell and no API/project response",
"desktop revocation removes mobile project content immediately on the next read while preserving the original completed tool"
],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\desktop-certificate.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\desktop-pairing.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-task-list.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-original-approval.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-original-diff.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-original-report.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-disconnected.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\tablet-task-list.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\desktop-management-narrow.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\companion-ui-f35292a9-e3d2-4433-8d99-f9518b3b48a5\\mobile-revoked.png"
],
"errors": [],
"viewports": [
1440,
390,
768
],
"browser": "Microsoft Edge via Playwright; owned loopback QA relay with actual CA verification",
"nativeSafariTrustCookiePWA": "pending-real-iPhone",
"osTrustChanged": false,
"certificateWarningsBypassed": false,
"realModelRequests": 0,
"taskId": "82c87cf5-c7ef-480f-8a38-4b9158836ebe",
"runId": "60f3e204-241e-4e29-be4c-ed4ad1d5612e"
}
@@ -0,0 +1,34 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:50:27.484Z",
"passed": [
"desktop request estimate, actual usage, complete goal and history identity are visible",
"paged complete history opens actual tool result artifacts without executing tools",
"historical and resumed Runs retain their own request records",
"390px history, original JSON and sent-body dialogs fit and retain close controls",
"late old history failure stays in its original scope after switching projects",
"late old Run failure stays in its original scope after switching projects",
"late old request-body failure stays in its original scope after switching projects",
"context-limit pause explains the intact requirement and explicit continuation",
"390px repeated-read pause explains the cause and explicit continuation retains the same Task",
"desktop working evidence shows actual code, original result provenance and the current Task",
"390px working evidence and sent request stay readable and closing the artifact retains task navigation"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/model-protocols-desktop-plan.png",
".qa/screenshots/model-protocols-desktop-history.png",
".qa/screenshots/model-protocols-mobile-history.png",
".qa/screenshots/model-protocols-mobile-original.png",
".qa/screenshots/model-protocols-mobile-request-body.png",
".qa/screenshots/model-protocols-mobile-read-pause.png",
".qa/screenshots/model-protocols-desktop-working-evidence.png",
".qa/screenshots/model-protocols-mobile-working-evidence.png"
],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-fdfeefbd-01db-42ff-ad26-7c487369cc1c",
"data": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\context-ui-fdfeefbd-01db-42ff-ad26-7c487369cc1c\\data",
"mode": "saved synthetic context evidence; no real model or project commands executed by this UI verifier",
"browser": "156.0.4314.50"
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,31 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:49:37.535Z",
"browser": "156.0.4314.50",
"passed": [
"actual failing tests and four source proposals retain the original project and task",
"reviewed changes continue the same Task through 14 real tests and model-prepared Git review",
"review shows actual paths, diffs, tests, author and policy; cancelling leaves Git unchanged",
"an index change after confirmation preview refuses the stale job and preserves both staged owners",
"390px confirmation keeps file hashes, diffs and actions inside the modal",
"double confirmation creates one four-file commit, retains owner bytes and publishes report with completion",
"report viewing and Markdown/JSON downloads preserve verified artifact bytes and truthful acceptance limits",
"mobile report preview closes cleanly and keeps the task input fixed",
"unknown Git results block new submission and the explicit reconcile action restores the existing commit"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\delivery-ui-befaa1a4-b7b3-4391-bf8d-368558b56414\\四模块交付工程",
"projectId": "adcccec2-db95-4a76-8f5f-34e88d210d81",
"sessionId": "590e7a1c-1018-4950-9101-11ae784b9881",
"taskId": "72602590-91b9-472d-815a-cca3825b37d4",
"commit": "577bb8753846b44e3c71d3dc6668d045f835551b",
"recoveryCommit": "de88c98edbb6c802133d24efa0e32fe67405fde3",
"testCounts": {
"baselineFailed": 13,
"passed": 14
},
"model": "controlled local HTTP fixture",
"confirmations": 2
}
@@ -0,0 +1,20 @@
{
"success": true,
"version": "1.17.0",
"url": "http://127.0.0.1:65507",
"date": "2026-10-31T14:48:08.720Z",
"passed": [
"model response validation checks the tentative connection before saving",
"a model failure after successful tools shows source, attempts and local runtime diagnosis",
"explicit retry preserves the completed tool result without replaying the task",
"an error question receives the actual session diagnosis and formatted answer",
"review state exposes the review action and prevents application during a running request",
"approved Unicode commands execute in the declared shell and retain Chinese output",
"authentication errors do not retry and error/diagnostic controls fit a 390 px viewport",
"stop cancels pending retry and clears running model state",
"a transient service failure recovers within the bounded retry policy"
],
"pageErrors": [],
"requestFailures": [],
"modelValidation": "controlled local HTTP fixture; actual configured model is verified separately"
}
@@ -0,0 +1,232 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:53:35.280Z",
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326",
"browser": "156.0.4314.50",
"passed": [
"independent desktop engine entry detects the declared installation and clearly separates connection from project execution",
"missing installations and edited directories cannot launch a check until detection succeeds",
"UI launch seals the selected installation into the current Task/Run and renders actual startup and process-close facts",
"original record paging, full download SHA256 and nested-dialog keyboard close preserve the exact evidence",
"an explicit new check creates a different process and record while retaining the original check unchanged",
"declared pending-initialize fixture stops its owned process and explicit retry preserves the stopped result",
"the same product UI verifies the actual installed DeepSeek SDK without a prompt or configured-model call",
"390px installation paths, source chain, original record, paging and keyboard close remain readable without page overflow",
"late detection failure from a closed panel cannot appear in a different task or reveal its prior engine records",
"actual host restart preserves all native and declared-fixture records with no protocol replay or project modification"
],
"pageErrors": [],
"requestFailures": [],
"expectedRequestFailures": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\screenshots\\engines-native-desktop.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\screenshots\\engines-record-mobile.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\screenshots\\engines-native-mobile.png"
],
"starts": [
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\本地 SDK #",
"identitySha256": "b347cc276b525b570cf86db8a7f0fc26a1006a41e88c1777517db59715c5f85f"
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\本地 SDK #",
"retry": true
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\本地 SDK #",
"identitySha256": "b347cc276b525b570cf86db8a7f0fc26a1006a41e88c1777517db59715c5f85f"
},
{
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\engines-ui-2c53bb6f-73ae-430d-8e02-619431880326\\本地 SDK #",
"retry": true
},
{
"root": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness",
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3"
}
],
"nativeJob": {
"schemaVersion": 1,
"id": "a3084ece-f45c-40c8-b130-4d221b73b4f5",
"sessionId": "f2ea193c-90b1-44ee-b48b-11746b6639e7",
"projectId": "1f0114fb-5cf6-4d70-ae5c-9983dfa2388e",
"taskId": "ce73a541-54ed-4d57-a35e-a731eb6c584b",
"runId": "6c9eef36-dedb-41c7-9855-ef6391316380",
"engineId": "deepseek-harness",
"scope": "deepseek-sdk-connection-probe",
"source": "user",
"installation": {
"engineId": "deepseek-harness",
"name": "DeepSeek Harness",
"profile": "sdk-minimal",
"expectedVersion": "0.2.1-rc.2",
"root": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness",
"capabilities": {
"connectionProbe": true,
"projectExecution": false,
"prompt": false,
"singleSessionCancel": false,
"protocolVersionNegotiation": false,
"cancellationUnit": "owned-process",
"tokenStreaming": false
},
"limitations": [
"当前接入核验启动、会话目录、协议错误和关闭;工程执行接入开发中。",
"SDK没有单会话cancel或close;停止以所属独立进程为单位。",
"SDK serverInfo.version与发行包版本分别核对,没有有效协议版本协商。",
"SDK事件覆盖运行时会话树,idle事件不能直接判项目交付完成。"
],
"status": "available",
"version": "0.2.1-rc.2",
"entry": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\lib\\bin.js",
"inputs": [
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\package.json",
"bytes": 8138,
"sha256": "d42efe9f3ff424f602f11598af8805ad25039953ebbbd3c163d67875f7e8658b",
"relative": "apps/cli/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\apps\\cli\\lib\\bin.js",
"bytes": 11772,
"sha256": "80112efe368efb1a39720c7ada0af00442e5131fb2744edaaff8a3e8bb499e6f",
"relative": "apps/cli/lib/bin.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\boot\\cmdline\\lib\\index.js",
"bytes": 6973,
"sha256": "7253190611566485f8b6f836fae6e0f2a7abbc59bb807c42e874844016e6d3a0",
"relative": "packages/boot/cmdline/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-app\\lib\\index.js",
"bytes": 1921,
"sha256": "cc7e6c38b0b38c0e92a0dffb45210c1dac6ef518547436e805e84b772f91a475",
"relative": "packages/bundle/sdk-app/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-minimal\\package.json",
"bytes": 2920,
"sha256": "0e177cbca85148207343db5afd7f12829723cf3f2afedfa8e85a5c5dcd58f604",
"relative": "packages/bundle/sdk-minimal/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\bundle\\sdk-minimal\\cordis.patch.yml",
"bytes": 5636,
"sha256": "464ea07c03d3639c2c387fa3a684f5d4001e7ca39f8257b361c604f19487af66",
"relative": "packages/bundle/sdk-minimal/cordis.patch.yml"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\server\\package.json",
"bytes": 2155,
"sha256": "2690f99763c3e1e7bd57f680f26e53010c2a3d7c4dffe06ff64a07ae3928cb17",
"relative": "packages/sdk/server/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\server\\lib\\index.js",
"bytes": 16454,
"sha256": "55412923f9f7c279f7e0b2a1e2853eaf238f390b3d84046cb9c94dc5f22a1e4a",
"relative": "packages/sdk/server/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\protocol\\package.json",
"bytes": 1237,
"sha256": "b030b0431d69723b5424dc2519cd4b381ec91acd22b73e0b30d6b8a19f1f2f94",
"relative": "packages/sdk/protocol/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\protocol\\lib\\index.js",
"bytes": 7336,
"sha256": "371c38ca3514797d86df5f4bb78a56c40a2637294b83aababe8145bec6a20253",
"relative": "packages/sdk/protocol/lib/index.js"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\packages\\sdk\\client\\package.json",
"bytes": 1325,
"sha256": "ff33f2ecec2d48bb8a24397cc664fc2dd50ba49d5288eb11fea1cb12931e5d5f",
"relative": "packages/sdk/client/package.json"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\pnpm-lock.yaml",
"bytes": 1090222,
"sha256": "4637cca3b89c4c8d5a147321710e597aa62ec2444a3772ab542be5690893dfe4",
"relative": "pnpm-lock.yaml"
},
{
"path": "D:\\Ai-project\\DeepSeek-Harness-Desktop\\deepseek-harness\\vendor\\cordis\\lib\\index.js",
"bytes": 60361,
"sha256": "6a9394c0877ff45218818c6e815edd038f8057e1a1deb390a8d43ec81c57691e",
"relative": "vendor/cordis/lib/index.js"
}
],
"node": {
"path": "D:\\Ai-project\\REA逆向\\tools\\node-v24.22.1-win-x64\\node.exe",
"bytes": 93915464,
"sha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
"version": "24.22.1"
},
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"serverInfo": {
"name": "deepseek-harness-sdk-runtime",
"version": "0.0.1"
},
"message": "已找到匹配版本,可验证原程序的连接与停止。"
},
"sdkSessionId": "93a36095-7405-471d-8a6e-696f6ca89285",
"directory": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\a3084ece-f45c-40c8-b130-4d221b73b4f5",
"status": "completed",
"startedAt": "2026-10-31T14:53:29.560Z",
"finishedAt": "2026-10-31T14:53:30.923Z",
"requiresVerification": false,
"verification": {
"verified": true,
"installationSha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"readySignal": "appReady",
"sdkSessionId": "93a36095-7405-471d-8a6e-696f6ca89285",
"connectionId": "074fc526-5f82-49dc-a11d-316dc91b7c96",
"rootExited": true,
"modelRequests": 0
},
"summary": "连接通过,启动、协议返回、会话目录与进程结束均已核对。",
"contractArtifactId": "09fb69d8-4737-4b70-a0ef-dedfbad1cc56",
"contractSha256": "fc060f625a81bc3b43fc71e538401af63086cebcd3624cf2f95dc233feed66de",
"eventId": "24be7482-e8be-4c71-a124-f57115ff2f3a",
"pid": 38116,
"connectionId": "074fc526-5f82-49dc-a11d-316dc91b7c96",
"readiness": {
"schemaVersion": 1,
"nonce": "32055bd4-2c67-4c12-beec-d68d13cd3c07",
"pid": 38116,
"signal": "appReady",
"readyAt": "2026-10-31T14:53:30.592Z",
"artifact": {
"path": "C:\\Users\\wangy\\AppData\\Local\\Temp\\AgentWorkbench-Engines\\a3084ece-f45c-40c8-b130-4d221b73b4f5\\ready.json",
"bytes": 135,
"sha256": "9e199be29f0d3e3fa7f36c9e0c112e25070291a80b9bf9e31de64c1b0809f6cd"
}
},
"serverInfo": {
"name": "deepseek-harness-sdk-runtime",
"version": "0.0.1"
},
"reportArtifactId": "c3721b77-e08a-4922-8860-8c91ec74639e",
"reportSha256": "11f3b35c0806c931e692eb35273826b5cecf1761ef316dd6f16b47f09a9c1dfc",
"reportSummary": {
"status": "verified",
"modelRequests": 0,
"providerRequests": 0,
"observedResponses": 6,
"rootExited": true
}
},
"actualSdk": {
"version": "0.2.1-rc.2",
"identitySha256": "65483d7f8aa644d890100a22bc52555ce91c009ba2d213b510f3da1a9ede7ff3",
"nativeMethods": 6,
"modelRequests": 0,
"rootExited": true
},
"stopScope": "declared private SDK pending-initialize fixture",
"scope": "Independent service and data. Original 4318 Provider, tasks and credentials were not accessed."
}
@@ -0,0 +1,19 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:48:41.628Z",
"browser": "156.0.4314.50",
"passed": [
"model-selected checks wait for approval and display actual counted results",
"verified artifact preview shows the real check log and hash",
"changed source invalidates old checks and manual confirmation runs the new plan",
"390px task drawer, log preview, close controls and fixed composer remain operable",
"reconnection synchronizes missed session changes in other projects",
"budget controls pause before tools and preserve the goal across recorded runs",
"applied proposals continue the original task into actual engineering verification"
],
"pageErrors": [],
"requestFailures": [],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\execution-ui-d0bf0c10-0ed2-450b-be09-aadd74848307\\project",
"model": "controlled local HTTP fixture"
}
@@ -0,0 +1,24 @@
✔ saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance (592.287ms)
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (710.0598ms)
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (1527.7255ms)
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (1797.027ms)
▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (994.4985ms)
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (1145.3472ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (1076.7906ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (1121.9989ms)
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (4339.4911ms)
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
✔ chat-completions (1174.9831ms)
✔ responses (1170.1157ms)
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (2345.4991ms)
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.2085ms)
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (678.5131ms)
ℹ tests 14
ℹ suites 0
ℹ pass 14
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 12110.7319
@@ -0,0 +1,46 @@
✔ native text and call IDs preserve original result pairing while unsupported content fails closed (1.1259ms)
✔ one engine child freezes real installation identity before creating tasks and rejects a changed source (13098.4525ms)
✔ owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs (40251.2521ms)
✔ forged native scope cannot change a parent file and a final completion claim cannot replace worker proof (20308.5425ms)
✔ duplicate native IDs are rejected without replaying a saved tool (16562.3545ms)
✔ native input exceeding the context budget is retained and sends no model request (15352.2075ms)
✔ stop retains a late reported model usage once and executes no tool from that output (18454.3389ms)
✔ a source change after the original model intent stops before native tools execute (11914.2429ms)
✔ an engine source change while approval is pending invalidates the old permission before any check starts (20706.4131ms)
✔ missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text (0.6475ms)
✔ closed root with an original live descendant remains unknown and retains its process tree (0.2834ms)
✔ host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes (19007.1945ms)
✔ corrupted model reservation cannot reduce recovered budget or permit a new engine request (16877.8397ms)
✔ owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched (3234.3774ms)
✔ Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes (6488.5999ms)
✔ mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools (4370.0093ms)
▶ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
✔ Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial" (3630.0169ms)
✔ Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal (2948.9085ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal (3278.7186ms)
✔ Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte (3321.5086ms)
✔ Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool (13180.1108ms)
▶ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
✔ chat-completions (3471.3136ms)
✔ responses (2630.7028ms)
✔ invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay (6102.4523ms)
✔ wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint (0.187ms)
✔ connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions (1186.2766ms)
✔ a stop from the event loop interrupts immediate model replies before later tools (3385.4454ms)
✔ a stop after the first tool preserves a complete interrupted multi-call protocol group (4073.0285ms)
✔ the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands (10411.9691ms)
✔ denial prevents command execution and produces a paired denied result (5347.8428ms)
✔ stopping during approval interrupts pending calls without executing or replaying them (3917.6167ms)
✔ stopping a running fixture command terminates its own process tree and retains uncertain state (3065.8461ms)
✔ command output decodes split UTF-8 and excludes the workbench key from child environment (1458.0358ms)
✔ model-list testing uses a tentative key without changing the saved connection and redacts service errors (6.6736ms)
✔ truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities (4921.9888ms)
✔ request projection keeps exact tool pairs and complete recent user instructions while preserving disk history (2627.5789ms)
ℹ tests 36
ℹ suites 0
ℹ pass 36
ℹ fail 0
ℹ cancelled 0
ℹ skipped 0
ℹ todo 0
ℹ duration_ms 192697.2863
@@ -0,0 +1,19 @@
{
"checkedAt": "2026-10-31T14:49:46.758Z",
"version": "1.17.0",
"passed": [
"工程索引可独立于任务使用,实际覆盖范围与损坏文件显示明确",
"真实AST查询打开原文件第181行并仅滚动代码容器,输入区和顶部保持可见",
"查询词保留;过期SHA不高亮旧位置,增量刷新后正确定位第184行",
"切换项目时延迟返回的旧索引不覆盖新项目结果",
"Python候选、字符串误报排除和局部导入文件候选保留真实证据标签",
"两处唯一锚点成为待审核提案,真实界面应用后BOM/CRLF和未选择原字节保留",
"390px索引查询、范围和完整指纹可读且无横向溢出,实际文件行定位通过",
"索引刷新失败保留归属和解释,旧结果禁用并可重试恢复"
],
"pageErrors": [],
"requestFailures": [],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\index-ui-cf2562c0-c35a-4fda-83fd-b65f844c79f1",
"primaryProjectId": "f07c27ba-6e41-4eb8-a5d6-6364dbd93acd",
"otherProjectId": "e62ad02d-c9c6-4d39-9837-92a99842cfc9"
}
@@ -0,0 +1,16 @@
{
"success": true,
"assertions": [
"actual host crash with no result report exposes its original verified input and unknown status",
"390px original-input review clears the job and invocation gates while retaining unknown, no report and no automatic model replay"
],
"viewportWidths": [
1440,
390
],
"pageErrors": [],
"requestFailures": [],
"localFixtureModelRequests": 1,
"realModelRequests": 0,
"jobId": "0b90a4df-d7dd-42d3-bb07-7f6efe6c7e7e"
}
@@ -0,0 +1,24 @@
{
"success": true,
"assertions": [
"MCP registration stays disabled and shows the hashed local executable and Node entry",
"actual stdio tools/list schema is visible; only the reviewed echo tool is enabled",
"an enabled program whose source changes can be disabled immediately without executing the changed entry",
"approved external call interrupted after dispatch remains unknown and does not replay",
"TaskPanel exposes Task/Run source, original report, and human acknowledgement without marking unknown as success",
"390px MCP registry, long executable paths, controls, and operation history have no horizontal overflow"
],
"viewportWidths": [
1440,
390
],
"pageErrors": [],
"requestFailures": [],
"localFixtureModelRequests": 1,
"realModelRequests": 0,
"unknownJobId": "377d19d0-0c5d-4f9d-bb5c-21db2c39fc88",
"screenshots": [
"desktop-mcp-registry.png",
"mobile-mcp-registry.png"
]
}
@@ -0,0 +1,23 @@
{
"url": "http://127.0.0.1:58898",
"viewportWidths": [
1440,
390
],
"assertions": [
"connection form stores only the volatile credential and renders configured status without exposing it",
"pool editor saves weighted members and binds selection for new Runs",
"schema-bound import preview, opt-in automatic sync, revision update and sync shutdown keep credentials hidden",
"real historical pagination detects the owned corrupted older artifact, retains its identity and leaves original bytes unchanged",
"local inspection shows real database and artifact checks and emits zero model requests",
"390px model-center modal and connection cards remain operable without horizontal page overflow"
],
"pageErrors": [],
"requestFailures": [],
"modelRequests": 0,
"screenshots": [
"desktop-operations.png",
"mobile-operations.png",
"mobile-connections.png"
]
}
@@ -0,0 +1,41 @@
{
"success": true,
"version": "1.17.0",
"appRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench",
"nodePath": "D:\\Ai-project\\REA逆向\\tools\\node-v24.22.1-win-x64\\node.exe",
"containedRuntime": false,
"nodeSha256": "d702daa815eabbff763c7d3808e235cf031cf2ca70211b56847bc72f51e240e5",
"passed": [
"actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable",
"separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts",
"actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE",
"desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay",
"truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution"
],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\desktop-editor.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\narrow-editor.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\desktop-capabilities.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\narrow-capabilities.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\desktop-ledger.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\desktop-streaming.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\narrow-streaming.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\mobile-streaming.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\mobile-stopped.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\narrow-stopped.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\desktop-incomplete.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\model-protocols-ui-4d113382-58d9-41f4-882e-380cadb7338d\\narrow-incomplete.png"
],
"pageErrors": [],
"requestFailures": [],
"fixtureModelRequests": 7,
"realModelRequests": 0,
"osTrustChanged": false,
"nativeIPhone": "not exercised; paired Edge viewport uses CA-verifying owned relay",
"taskId": "5bef2fcc-77cf-4756-b458-02609ebaad18",
"runIds": [
"55a3fb7d-395f-422a-b5f8-f262a37d8ea1",
"dab7b7fb-b25b-4dd6-9f37-8371ae1fcf9f",
"0b5ddad4-20da-49d5-8752-72de133fde4a"
]
}
@@ -0,0 +1,24 @@
{
"success": true,
"url": "http://127.0.0.1:51638",
"viewportWidths": [
1440,
390
],
"assertions": [
"source hashes remain visible and a changed file is explicitly expired with retained provenance",
"incomplete inventory marks existing facts unverified and blocks new saves",
"390px memory review stays within the viewport with the incomplete-scan warning visible",
"desktop and 390px request records expose the exact memory snapshot used by one owned local HTTP request"
],
"pageErrors": [],
"requestFailures": [],
"localFixtureModelRequests": 1,
"realModelRequests": 0,
"screenshots": [
"desktop-expired-memory.png",
"mobile-incomplete-memory.png",
"desktop-sent-memory.png",
"mobile-sent-memory.png"
]
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,35 @@
{
"success": true,
"version": "1.17.0",
"at": "2026-10-31T14:51:34.926Z",
"browser": "156.0.4314.50",
"passed": [
"mixed projects retain npm defaults and explicitly seal the selected Python checks",
"the confirmation shows the actual interpreter and cancellation executes no checks",
"actual unittest failures and the separately passed compilation display their counted results",
"the log and original structured result are independently viewable and hash-bound",
"a reviewed three-file repair runs new checks while retaining the original failed job and protected files",
"390px checks, interpreter paths, original result dialog and composer remain operable without page overflow",
"Git confirmation and the Python execution report deliver only the three reviewed sources and preserve owner changes"
],
"pageErrors": [],
"requestFailures": [],
"checks": {
"before": {
"total": 6,
"passed": 1,
"failed": 5,
"skipped": 0,
"cancelled": 0
},
"after": {
"total": 6,
"passed": 6,
"failed": 0,
"skipped": 0,
"cancelled": 0
}
},
"commit": "a18a17bb02741c5105db0591cabf58fb102b3151",
"scope": "Independent host and owned fixture. Real Python processes, reviewed API repairs and actual local Git. No configured model requests or production credentials."
}
@@ -0,0 +1,76 @@
{
"success": true,
"version": "1.17.0",
"at": "2026-10-31T14:52:36.680Z",
"browser": "156.0.4314.50",
"passed": [
"the sealed React TypeScript project builds but its real domain tests first expose the functional failures",
"a real browser separately observes that the broken pending filter wrongly shows all three tasks",
"the four-file reviewed repair passes all nine domain tests, actual TypeScript checking and the Vite production build",
"the production React app passes real filtering, search, single-task toggling and updated statistics",
"the same built React app remains operable at 390px without horizontal overflow",
"Workbench Git commits only the four reviewed files and binds the actual checks while preserving tests, configuration and owner changes"
],
"pageErrors": [],
"requestFailures": [],
"originalTests": {
"total": 9,
"passed": 2,
"failed": 7,
"cancelled": 0,
"skipped": 0
},
"repairedTests": {
"total": 9,
"passed": 9,
"failed": 0,
"cancelled": 0,
"skipped": 0
},
"beforePending": 3,
"checks": [
{
"name": "test",
"status": "passed",
"exitCode": 0,
"tests": {
"total": 9,
"passed": 9,
"failed": 0,
"cancelled": 0,
"skipped": 0
}
},
{
"name": "typecheck",
"status": "passed",
"exitCode": 0,
"tests": null
},
{
"name": "build",
"status": "passed",
"exitCode": 0,
"tests": null
}
],
"commit": "5783f9cec7f1ce54c43bc9e3ddefc9d6c12dd058",
"changes": [
"src/App.tsx",
"src/query.ts",
"src/summary.ts",
"src/transition.ts"
],
"protectedFiles": {
"package.json": "db3c6bfd79d1ebb1f5692727715e2b48d3f09e0314d9f1d455d335774f5e7db8",
"package-lock.json": "48c138a05408667bbd332000731598415c9ae281d5072daa18544025ad89f7ff",
"tsconfig.json": "9dcf064d622cb31ae94ef348655f4f7af84076241601148929232314ef1b0c8a",
"vite.config.mjs": "0ea84b4e2909b04e4c1cb1b92392a9f85bcb46605472763b15935d3498ba8ed3",
"index.html": "37e9fd3172422ecca3902378c567331363dc1277ac749dd9f6bdf74f04540787",
"test/domain.test.mjs": "3fbd155cfc4919f3d0570a7ee26ff5ff4243e3e94250f3d0dbebe93c2b925ec0",
"src/types.ts": "d2bbcac2cb175e7bcafe087915f02c3cf2e0ea4b65235d6231bbcd4c3a682246",
"src/main.tsx": "c9a5787f5544788757ab654e1dfd83b5bc51495144e17aa078c2ee2f4412a302",
"src/styles.css": "60bcb8f7f73f4328274096132a3d73b7ef1fc9e6fbf6a3a3477fb9d519f2c25c"
},
"scope": "Owned frozen React TypeScript project with offline-installed fixed dependencies, real npm/typecheck/build/browser and Workbench review/Git/report. API fixtures supply repairs; configured-model success is separate."
}
@@ -0,0 +1,138 @@
{
"success": true,
"version": "1.17.0",
"at": "2026-10-31T14:53:16.856Z",
"browser": "156.0.4314.50",
"passed": [
"independent desktop research entry detects the installed fixed REA version",
"UI registration seals the artifact identity in the current project and creates no model request",
"actual REA ASAR analysis renders the verified source chain and downloads the exact original Bundle",
"original field selection, paging and limitations retain exact bytes; Escape closes only the top dialog",
"raw responses and connection records are readable; repeat analysis reuses the verified original without dispatch",
"UI PE operation selection performs actual import and resource analysis with independently verified target hashes",
"changed artifact versions refuse dispatch, retain the stale record and require a separately registered version",
"390px research, long identities and original evidence dialogs fit the viewport and retain usable close controls",
"a real host restart preserves exact target/job identities and serves sealed Evidence without producer replay",
"a delayed evidence response cannot reopen a closed research panel or change another task",
"declared owned stdio fault fixture stops its root process and explicit retry adds a new record without changing history"
],
"pageErrors": [],
"requestFailures": [],
"expectedRequestFailures": [],
"root": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\research-ui-bdd74198-8ae0-4701-8715-1915a610da36",
"actualRea": {
"version": "6.8.0",
"operations": [
"javascript",
"pe-imports",
"pe-resources"
],
"jobs": [
{
"id": "d4c49997-06b6-4e98-a169-ee79811f8fbb",
"status": "completed",
"evidenceId": "ev_c1ad800281e4666c02bcc6f7d283254e7d3e044b8190c377f075c4b159ba8eba"
},
{
"id": "083be29e-01af-428a-8141-0d0f54ab0e63",
"status": "completed",
"evidenceId": "ev_c1ad800281e4666c02bcc6f7d283254e7d3e044b8190c377f075c4b159ba8eba"
},
{
"id": "80fe088b-da0b-403e-8862-a120af56a6bc",
"status": "completed",
"evidenceId": "ev_372977a118d2703e195c0611636df0a6fe9cf1d37bc07a2465cecfb69b9587d1"
},
{
"id": "d5e745d2-aed1-44e7-8b28-dca59f973d3d",
"status": "completed",
"evidenceId": "ev_d4d6c9b5c355eb84e69c1b8ead12cce214dc83ed178bacf1dafcc5afbc2e23f7"
},
{
"id": "9f222679-32bb-4339-8937-079a8e77fa97",
"status": "stale"
},
{
"id": "2d95a873-0c43-445c-b2ad-89d6397c8cbc",
"status": "completed",
"evidenceId": "ev_6180816e4b9cee0e16668fe0f31a0a8ab281fbad173e445f5b968de9a33d8f70"
}
],
"targetExecution": false,
"modelRequests": 0
},
"stopScope": "explicitly declared private stdio handshake fault fixture",
"screenshots": [
".qa/screenshots/model-protocols-research-desktop.png",
".qa/screenshots/model-protocols-research-mobile.png",
".qa/screenshots/model-protocols-research-evidence-mobile.png",
".qa/screenshots/model-protocols-research-stop-desktop.png"
],
"analysisRequests": [
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "7747b8a5-7f73-402f-847c-0b6fb8d09ed0",
"operation": "javascript",
"refresh": false
}
},
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "7747b8a5-7f73-402f-847c-0b6fb8d09ed0",
"operation": "javascript",
"refresh": false
}
},
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "83779f93-92a7-4052-9afe-b032515f9f7d",
"operation": "pe-imports",
"refresh": false
}
},
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "83779f93-92a7-4052-9afe-b032515f9f7d",
"operation": "pe-resources",
"refresh": false
}
},
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "7747b8a5-7f73-402f-847c-0b6fb8d09ed0",
"operation": "javascript",
"refresh": false
}
},
{
"url": "http://127.0.0.1:61139/api/sessions/7b4c6388-afbe-4292-8407-ba39b4e9f10d/research/jobs",
"input": {
"targetId": "b3e0df51-5c49-4f94-ac13-7ae9bb3811bb",
"operation": "javascript",
"refresh": false
}
},
{
"url": "http://127.0.0.1:56627/api/sessions/6bfae6ec-0181-4790-b76a-50e87f6a16e3/research/jobs",
"input": {
"targetId": "e4c3871d-2001-4e80-b451-fc6fef517d2a",
"operation": "javascript",
"refresh": false
}
},
{
"url": "http://127.0.0.1:56627/api/sessions/6bfae6ec-0181-4790-b76a-50e87f6a16e3/research/jobs",
"input": {
"targetId": "e4c3871d-2001-4e80-b451-fc6fef517d2a",
"operation": "javascript",
"refresh": true
}
}
],
"scope": "Independent ports/data and self-owned inert artifacts. No production service, configured-model request or real key read/copied."
}
@@ -0,0 +1,22 @@
{
"success": true,
"viewportWidths": [
1440,
390
],
"assertions": [
"desktop registers a disabled skill, reviews original UTF-8 instructions and explicitly enables it with no model calls",
"source edit blocks activation until a new reviewed revision is registered; original revision remains available",
"390px review and activation retain readable paths, revision history and visible source state without horizontal overflow",
"actual local HTTP task reads precisely revision 2 and exposes its SHA-bound sent catalog in task evidence"
],
"pageErrors": [],
"requestFailures": [],
"localFixtureModelRequests": 2,
"realModelRequests": 0,
"screenshots": [
"desktop-skill-source.png",
"mobile-skill-source.png",
"desktop-sent-skill-catalog.png"
]
}
@@ -0,0 +1,20 @@
{
"success": true,
"passed": [
"desktop saves and inspects the full original Task and tool provenance without another model request",
"an outside source change is visible and removes the checkpoint continuation action",
"390px explicit continuation keeps the same Task and one original read; a second resume of the old checkpoint is blocked"
],
"viewportWidths": [
1440,
390
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
"desktop-original-checkpoint.png",
"mobile-checkpoint-ready.png"
],
"localFixtureModelRequests": 3,
"realModelRequests": 0
}
@@ -0,0 +1,31 @@
{
"success": true,
"version": "1.17.0",
"testedAt": "2026-10-31T14:46:51.918Z",
"directory": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4",
"passed": [
"structured editor seals two real steps and their dependency without running tools",
"original owned read verifies the prerequisite and opens its hashed proof without replay",
"real two-test and build job supplies the current-source proof and completes the sealed plan",
"outside source edits invalidate the current proof, retain the rejection and block a passed delivery report",
"390px immutable revision adds a mobile step, preserves old criteria and keeps evidence dialogs operable",
"a delayed plan-read failure stays with the original task after selection changes",
"controlled tab unmount during a delayed successful save retains the original task result without restoring the closed editor",
"real host restart retains all plan revisions, accepted/rejected proofs and the original operations without replay"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-desktop-editor.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-desktop-verified.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-mobile-editor.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-mobile-artifact.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-mobile-steps.png",
"D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\task-plan-ui-24c9339b-ab4c-4753-8c41-d4399457fbe4\\task-plan-mobile-overview.png"
],
"taskId": "5d46257a-0bb7-407a-8740-a5cb277f4fb6",
"sessionId": "95869a68-3b50-4e02-a2ac-d48ba9e393c4",
"planRevisions": 3,
"proofs": 4,
"scope": "Independent real Edge desktop/390px Workbench UI, actual npm checks and owned read fixture. No real model credentials or production service access; semantic project acceptance is separate."
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,28 @@
{
"success": true,
"version": "1.17.0",
"at": "2026-10-31T14:50:58.841Z",
"browser": "156.0.4314.50",
"passed": [
"desktop preview seals the committed version and shows existing staged/unstaged/untracked source changes",
"repeated create clicks execute once and preserve the exact source index and owner files",
"opening the child, returning to the source and reloading retain stable project/session identity",
"a record owned by another session navigates to that saved owner instead of accepting its actions",
"explicit recovery preserves outside content and acknowledgement does not report successful creation",
"390×844 preview/create/open/return stays within viewport and preserves source ownership",
"late-failure stays with the original session after project switching",
"late-success stays with the original session after project switching",
"a delayed bootstrap cannot navigate after the task panel has unmounted"
],
"pageErrors": [],
"requestFailures": [],
"screenshots": [
".qa/screenshots/model-protocols-workspaces-review-desktop.png",
".qa/screenshots/model-protocols-workspaces-ready-desktop.png",
".qa/screenshots/model-protocols-workspaces-recovery-desktop.png",
".qa/screenshots/model-protocols-workspaces-review-mobile.png",
".qa/screenshots/model-protocols-workspaces-child-mobile.png"
],
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\workspace-ui-06d1865c-a007-4814-bf4a-d8461d8e7220",
"scope": "Independent synthetic Git projects and real browser flows. Desktop/390×844, actual worktree creation, source preservation, explicit external recovery, ownership navigation, delayed success/error/navigation. No production service or real model credential used."
}
+2 -2
View File
@@ -1,12 +1,12 @@
{
"name": "local-agent-workbench",
"version": "1.16.0",
"version": "1.17.0",
"lockfileVersion": 3,
"requires": true,
"packages": {
"": {
"name": "local-agent-workbench",
"version": "1.16.0",
"version": "1.17.0",
"dependencies": {
"@babel/parser": "7.29.11",
"@peculiar/x509": "3.1.0",
+3 -2
View File
@@ -1,6 +1,6 @@
{
"name": "local-agent-workbench",
"version": "1.16.0",
"version": "1.17.0",
"private": true,
"type": "module",
"description": "A local coding workbench with explicit tool execution, reviewable changes and recoverable sessions.",
@@ -38,7 +38,8 @@
"verify:desktop-projects": "node scripts/verify-controlled-projects.mjs --desktop",
"verify:desktop-lifecycle": "node scripts/verify-controlled-ui.mjs --desktop",
"verify:desktop-install": "node scripts/verify-desktop-install.mjs",
"verify:companion": "node scripts/verify-companion-ui.mjs"
"verify:companion": "node scripts/verify-companion-ui.mjs",
"verify:model-protocols": "node scripts/verify-model-protocols-ui.mjs"
},
"dependencies": {
"@babel/parser": "7.29.11",
+3
View File
@@ -826,3 +826,6 @@ A已提交578cf88。B/C/D新增协议、请求变体、SSE及能力选路,恢
1.17 E真实操作5组通过,原result与13张截图保持在.qa/model-protocols-ui-5c599342-cbbd-4019-8865-ee1d7b4570e4;主窗口池名、手机接收/停止、390px未知账本已目视核对。补修select明确可访问名称、完成外部API新增后刷新UI夹具、mobile-stream实际选择器、上游停顿的延迟进展、主窗口legacy误判/快速关闭同步、原工件下载字节;37/37、20/20及26/26相关专项分别通过。一次精确替换误命中凭据callback,立即rg核对定位并修正,未执行或部署该中间版本。
第一次历史全量UI运行误将Purge打包目录当源码目录,原结果/日志逐字节复制到protocol-first-ui-environment-failure后,以source/upstream重新整轮,session82022;早于最终修复启动的full-tests session80218仅作开发中诊断。响应协议真实工程新门槛使用同一受控Node/React/Python算法、原测试、审批与Git,但走实际Responses SSE+ModelHub。当前session64602执行,结果尚未判定。只读路径version/gateway误猜后已用rg定位diagnostics.mjs与server/companion-gateway.mjs,无数据写入。
1.17 F诊断:开发整套回归的旧Runtime夹具发送{invalid,现有完整JSON组校验先拒绝,导致旧等待审批断言超时;保留原TAP,旧语义错误用例改为合法JSON/无效query类型,另加Chat/Responses整组无工具/无池重放回归。新Responses真实Harness工程第一次失败原件保留cf832704目录:检查8/8已通过,但worker原输入核验仍只读body.max_tokens;新路由封存的是协议变体。修复为逐变体核对原native.maxTokens与实际输出预留及原预算,不略过SHA、归属或任一线路。此前几个只读大输出截断已改短投影;误猜core/workers路径已按rg定位core/tasks。
F冻结前:Responses三工程13节点和父8/8/9/9/10/10、25类191组历史UI通过;相关36/36及新增预算/协议14/14。开发中完整553项552过/1失败原TAP保留,不作为最终结论。私有wrapper替换顺序首次拒绝已修正且保留原脚本;首次build因误用仓库node_modules/npm不存在而失败,固定Node附带npm的retry构建通过。准备提交全部执行输入、冻结并开始最终不可变独立验收。
+1
View File
@@ -9,6 +9,7 @@ const prefixes = Object.freeze({
'1.14.0': 'controlled-engine',
'1.15.0': 'desktop-host',
'1.16.0': 'mobile-companion',
'1.17.0': 'model-protocols',
});
export function releaseEvidencePrefix(version) {
const prefix = prefixes[version];
+1 -1
View File
@@ -64,7 +64,7 @@ export async function upgradeRunning({ url, pid, currentRoot, newRoot, handlerRo
if (!fs.existsSync(originalScript) || !fs.existsSync(upgradeScript) || !fs.existsSync(path.join(next, 'dist-client', 'index.html'))) throw new Error('Upgrade bundles are incomplete.');
if (!Number.isInteger(pid) || pid < 1 || pid === process.pid) throw new Error('Invalid target process.');
const before = await readUpgradeJson(origin + '/api/bootstrap', 5000, 'Read original Workbench');
if (!before.token || !['0.1.0', '1.0.0', '1.1.0', '1.2.0', '1.3.0', '1.4.0', '1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(before.version)) throw new Error('This migration accepts a supported existing Workbench.');
if (!before.token || !['0.1.0', '1.0.0', '1.1.0', '1.2.0', '1.3.0', '1.4.0', '1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(before.version)) throw new Error('This migration accepts a supported existing Workbench.');
if (before.sessions.some(session => ['running', 'awaiting_approval', 'stopping'].includes(session.status))) throw new Error('Wait for existing tasks and approvals before upgrading.');
let protocol, socket, enabledHere = false, paused = false;
const breakpoints = [];
+12 -11
View File
@@ -9,27 +9,28 @@ import { randomUUID } from 'node:crypto';
if (process.argv.slice(2).some(value => value !== '--help')) throw new Error('Unsupported argument; use --help.');
if (process.argv.includes('--help')) { console.log('node scripts/verify-all-ui.mjs - run serial desktop/390px checks in independent local hosts; use explicit QA Python/Harness/Purge source paths for 1.15.'); process.exit(0); }
const version = JSON.parse(fs.readFileSync('package.json', 'utf8')).version;
assert.ok(['1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version), 'Review evidence paths when introducing the next release.');
assert.ok(['1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version), 'Review evidence paths when introducing the next release.');
const prefix = releaseEvidencePrefix(version), resultFile = `.qa/${prefix}-all-ui-validation.json`, results = [];
const qaEnvironment = Object.fromEntries(['AGENT_WORKBENCH_TEST_PYTHON', 'AGENT_WORKBENCH_DEEPSEEK_ROOT', 'AGENT_WORKBENCH_PURGE_178_ROOT', 'AGENT_WORKBENCH_PURGE_181_ROOT']
.filter(name => process.env[name]).map(name => [name, process.env[name]]));
for (const [name, value] of Object.entries(qaEnvironment)) assert.ok(path.isAbsolute(value) && fs.existsSync(value), 'Use an existing absolute QA runtime/source path: ' + name);
const cases = [
...(version === '1.16.0' ? [['verify-companion-ui.mjs', null]] : []),
...(['1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-controlled-ui.mjs', null], ['verify-purge-ui.mjs', null]] : []),
...(['1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-workers-ui.mjs', null]] : []),
...(['1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-task-plans-ui.mjs', `docs/${prefix}-task-ui-validation.json`]] : []),
...(['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-browser-ui.mjs', `docs/${prefix}-browser-ui-validation.json`]] : []),
...(version === '1.17.0' ? [['verify-model-protocols-ui.mjs', null]] : []),
...(['1.16.0', '1.17.0'].includes(version) ? [['verify-companion-ui.mjs', null]] : []),
...(['1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-controlled-ui.mjs', null], ['verify-purge-ui.mjs', null]] : []),
...(['1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-workers-ui.mjs', null]] : []),
...(['1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-task-plans-ui.mjs', `docs/${prefix}-task-ui-validation.json`]] : []),
...(['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-browser-ui.mjs', `docs/${prefix}-browser-ui-validation.json`]] : []),
['verify-ui.mjs', '.qa/ui-validation.json'], ['verify-diagnostics-ui.mjs', '.qa/diagnostics-ui-validation.json'],
['verify-execution-ui.mjs', '.qa/execution-ui-validation.json'], ['verify-delivery-ui.mjs', '.qa/delivery-ui-validation.json'],
['verify-index-ui.mjs', '.qa/index-ui-result.json'], ['verify-change-sets-ui.mjs', `docs/${prefix}-batch-ui-validation.json`],
['verify-context-ui.mjs', `.qa/${version === '1.6.0' ? 'workspaces-context' : prefix}-ui-validation.json`],
['verify-workspaces-ui.mjs', `docs/${prefix === 'workspaces' ? prefix : prefix + '-workspaces'}-ui-validation.json`],
...(['1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-python-ui.mjs', `docs/${prefix}-python-ui-validation.json`]] : []),
...(['1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-react-delivery.mjs', version === '1.7.0' ? 'docs/react-engine-delivery-validation.json' : `docs/${prefix}-react-delivery-validation.json`]] : []),
...(['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-research-ui.mjs', `docs/${prefix}-research-ui-validation.json`]] : []),
...(['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? [['verify-engines-ui.mjs', version === '1.9.0' ? 'docs/engines-ui-validation.json' : `docs/${prefix}-engines-ui-validation.json`]] : []),
...(['1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(version) ? ['model-center', 'project-memory', 'task-checkpoints', 'skills', 'mcp', 'mcp-recovery'].map(name => [`verify-${name}-ui.mjs`, null]) : []),
...(['1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-python-ui.mjs', `docs/${prefix}-python-ui-validation.json`]] : []),
...(['1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-react-delivery.mjs', version === '1.7.0' ? 'docs/react-engine-delivery-validation.json' : `docs/${prefix}-react-delivery-validation.json`]] : []),
...(['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-research-ui.mjs', `docs/${prefix}-research-ui-validation.json`]] : []),
...(['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? [['verify-engines-ui.mjs', version === '1.9.0' ? 'docs/engines-ui-validation.json' : `docs/${prefix}-engines-ui-validation.json`]] : []),
...(['1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(version) ? ['model-center', 'project-memory', 'task-checkpoints', 'skills', 'mcp', 'mcp-recovery'].map(name => [`verify-${name}-ui.mjs`, null]) : []),
];
fs.mkdirSync('.qa', { recursive: true });
const externalHost = new Set(['verify-ui.mjs', 'verify-diagnostics-ui.mjs', 'verify-execution-ui.mjs', 'verify-index-ui.mjs']);
+1 -1
View File
@@ -34,7 +34,7 @@ child.stdout.on('data', value => { output += value; for (const line of output.sp
child.stderr.on('data', value => { errors += value; });
const wait = async predicate => { const deadline = Date.now() + 15000; while (!await predicate()) { if (Date.now() > deadline) throw new Error('UI fixture timed out: ' + errors); await new Promise(resolve => setTimeout(resolve, 40)); } };
await wait(() => url); const bootstrap = await (await fetch(url + '/api/bootstrap')).json();
assert.ok(['1.4.0', '1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(bootstrap.version)); assert.equal(bootstrap.config.mode, 'demo'); assert.equal(bootstrap.config.hasKey, false);
assert.ok(['1.4.0', '1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(bootstrap.version)); assert.equal(bootstrap.config.mode, 'demo'); assert.equal(bootstrap.config.hasKey, false);
const proofPrefix = releaseEvidencePrefix(bootstrap.version) + '-batch';
const screenshotPrefix = bootstrap.version === '1.4.0' ? '1.4-batch' : proofPrefix;
const api = async (route, input) => { const response = await fetch(url + '/api' + route, { method: input === undefined ? 'GET' : 'POST', headers: { 'Content-Type': 'application/json', 'X-Workbench-Token': bootstrap.token, Connection: 'close' },
+1 -1
View File
@@ -77,7 +77,7 @@ child.stderr.on('data', bytes => { errors += bytes.toString('utf8'); });
const until = async predicate => { const deadline = Date.now() + 20000; while (!await predicate()) { if (Date.now() > deadline) throw new Error('Context UI fixture timeout: ' + errors); await new Promise(resolve => setTimeout(resolve, 40)); } };
await until(() => url || child.exitCode !== null); assert.ok(url, errors);
const bootstrap = await (await fetch(url + '/api/bootstrap', { headers: { Connection: 'close' } })).json();
assert.ok(['1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(bootstrap.version)); assert.equal(bootstrap.config.mode, 'demo'); assert.equal(bootstrap.config.hasKey, false);
assert.ok(['1.5.0', '1.5.1', '1.6.0', '1.6.1', '1.6.2', '1.7.0', '1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(bootstrap.version)); assert.equal(bootstrap.config.mode, 'demo'); assert.equal(bootstrap.config.hasKey, false);
const api = async route => { const response = await fetch(url + '/api' + route, { headers: { 'X-Workbench-Token': bootstrap.token, Connection: 'close' } }); const value = await response.json(); assert.ok(response.ok, value.error); return value; };
const proofPrefix = bootstrap.version === '1.6.0' ? 'workspaces-context' : releaseEvidencePrefix(bootstrap.version);
const browser = await chromium.launch({ channel: 'msedge', headless: true }), page = await browser.newPage({ viewport: { width: 1440, height: 1000 } });
+20 -6
View File
@@ -13,13 +13,15 @@ import { resolvePurgeSource, assertPurgeModelInput, nativeSystemTexts, PURGE_DEF
import { deliveryGit as git, writeDeliveryFile as write } from '../tests/fixtures/delivery-project.mjs';
import { ownerBytes } from '../tests/fixtures/workers-project.mjs';
import { desktopProjectQa } from './desktop-project-qa.mjs';
import { responsesEngineeringHttp } from '../tests/fixtures/responses-engineering-http.mjs';
const args = process.argv.slice(2);
assert.ok(args.every(value => ['--help', '--purge-comparison', '--desktop'].includes(value)), 'Unknown option; use --help.');
assert.ok(args.every(value => ['--help', '--purge-comparison', '--desktop', '--responses'].includes(value)), 'Unknown option; use --help.');
if (args.includes('--help')) {
console.log('node scripts/verify-controlled-projects.mjs [--purge-comparison | --desktop] — actual pinned Harness and owned HTTP model fixture; default verifies Node/React/Python with approvals, Edge and Git. Comparison verifies eight independent Node projects: two Purge versions, two repetitions, enabled/disabled. Set AGENT_WORKBENCH_DEEPSEEK_ROOT; default also requires AGENT_WORKBENCH_TEST_PYTHON, comparison requires AGENT_WORKBENCH_PURGE_178_ROOT / AGENT_WORKBENCH_PURGE_181_ROOT. No configured-model requests.'); process.exit(0);
console.log('node scripts/verify-controlled-projects.mjs [--purge-comparison | --desktop] [--responses] — actual pinned Harness and owned HTTP model fixture; default verifies Node/React/Python with approvals, Edge and Git. --responses uses actual Responses SSE and ModelHub routing with the same engineering algorithm. Comparison verifies eight independent Node projects. Set AGENT_WORKBENCH_DEEPSEEK_ROOT and AGENT_WORKBENCH_TEST_PYTHON; comparison requires both Purge source roots. No configured-model requests.'); process.exit(0);
}
const comparisonMode = args.includes('--purge-comparison'), desktopMode = args.includes('--desktop');
const responsesMode = args.includes('--responses'); assert.ok(!responsesMode || !comparisonMode, 'Protocol acceptance and Purge comparison remain separate.');
assert.ok(!comparisonMode || !desktopMode, 'Desktop engineering and prompt comparison are separate acceptance runs.');
const version = JSON.parse(fs.readFileSync('package.json', 'utf8')).version;
const directory = path.resolve('.qa', (desktopMode ? 'desktop-projects-' : comparisonMode ? 'controlled-purge-' : 'controlled-projects-') + randomUUID()), results = [], cases = [];
@@ -93,7 +95,7 @@ async function runSample(kind, { sampleName = kind, strategy = null, comparison
};
if (kind === 'react') install(f.projectRoot, 'parent');
let phase = 'new';
const model = await compatibleFixture(t, async (route, input) => {
const model = await (responsesMode ? responsesEngineeringHttp : compatibleFixture)(t, async (route, input) => {
assert.equal(route, '/v1/chat/completions'); assert.equal(input.model, 'owned-controlled-engineering');
assertToolPairs(input.messages);
const worker = [...f.store.core.worker.values()][0], session = f.store.session(worker.sessionId);
@@ -116,7 +118,13 @@ async function runSample(kind, { sampleName = kind, strategy = null, comparison
finish_reason: calls.length ? 'tool_calls' : 'stop' }], usage: { prompt_tokens: 123, completion_tokens: 45, total_tokens: 168 } };
});
f.store.saveConfig({ mode: 'compatible', model: 'owned-controlled-engineering', baseUrl: model.baseUrl, contextLimit: 64000 });
const provider = new Provider(); provider.setKey('self-owned-controlled-model-fixture'); runtime = new Runtime(f.store, provider); f.onCleanup(() => runtime.stopAll());
const provider = new Provider(); provider.setKey('self-owned-controlled-model-fixture');
if (responsesMode) {
const hub = provider.modelHub(f.store), connection = hub.upsert({ name: 'Owned Responses engineering', protocol: 'responses', model: 'owned-controlled-engineering', baseUrl: model.baseUrl,
requiresKey: false, contextLimit: 64000, streaming: true, capabilityDeclarations: { streaming: 'supported' } });
hub.select({ type: 'connection', id: connection.id });
}
runtime = new Runtime(f.store, provider); f.onCleanup(() => runtime.stopAll());
runtime.controlledEngines = new EngineRunner(f.store, provider, { directoryRoot: path.join(f.root, 'owned-engine-runs') });
runtime.checkRunner().pythonExecutable = python; const manager = runtime.workerManager();
if (desktopMode) desktopQa = await desktopProjectQa({ store: f.store, provider, runtime, sample, kind });
@@ -169,6 +177,12 @@ async function runSample(kind, { sampleName = kind, strategy = null, comparison
}
assert.equal(f.store.core.task.get(child.taskId).usage.requests, modelRequests.length);
assert.equal(f.store.core.task.get(child.taskId).usage.totalTokens, modelRequests.length * 168);
if (responsesMode) {
const attempts = provider.modelHub(f.store).attempts;
assert.equal(attempts.length, model.requests.length); assert.ok(attempts.every(value => value.protocol === 'responses' && value.stream?.terminal && value.responseArtifactId));
fs.writeFileSync(path.join(sample, 'original-responses-requests.json'), JSON.stringify(model.requests, null, 2));
fs.writeFileSync(path.join(sample, 'original-responses-attempts.json'), JSON.stringify(attempts, null, 2));
}
mark(label + ': actual Harness uses owned model/tool bridges, retains failing tests, and completes reviewed repairs with one accounting entry per HTTP request');
await (await manager.collect(f.session, group.id, group.fingerprint)).promise; assert.equal(group.status, 'collected', group.summary);
const collection = await manager.readCollection(f.session, group); assert.deepEqual(collection.conflicts, []); assert.deepEqual(collection.paths, writable);
@@ -252,7 +266,7 @@ try {
assert.equal(results.length, 8); assert.equal(comparisons.length, 4);
} else for (const kind of ['node', 'react', 'python']) results.push(await runSample(kind));
assert.deepEqual(inputs(), frozen);
report = { success: true, targetVersion: version, testedVersion: version, directory, installation, cases, results, comparisons, sources, inputs: frozen, realModelRequests: 0,
report = { success: true, targetVersion: version, testedVersion: version, protocol: responsesMode ? 'responses-stream' : 'chat-completions', directory, installation, cases, results, comparisons, sources, inputs: frozen, realModelRequests: 0,
scope: 'Pinned actual Harness and workbench execution with an owned HTTP model fixture. Checks, approvals, failures, parent merges, Edge and Git are real. Model reasoning and Purge benefit remain separate.' };
} catch (error) { report = { success: false, targetVersion: version, testedVersion: version, directory, installation, cases, results, inputs: frozen, error: error.stack, realModelRequests: 0 }; process.exitCode = 1; }
finally { fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify(report, null, 2)); fs.writeFileSync('.qa/' + (desktopMode ? 'desktop-projects' : comparisonMode ? 'controlled-purge' : 'controlled-projects') + '-location.json', JSON.stringify({ directory, result: path.join(directory, 'result.json') })); console.log('EVIDENCE ' + directory); console.log(JSON.stringify({ success: report.success, cases: cases.length, directory, realModelRequests: 0, error: report.error ?? null })); }
finally { fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify(report, null, 2)); fs.writeFileSync('.qa/' + (responsesMode ? 'responses-engineering' : desktopMode ? 'desktop-projects' : comparisonMode ? 'controlled-purge' : 'controlled-projects') + '-location.json', JSON.stringify({ directory, result: path.join(directory, 'result.json') })); console.log('EVIDENCE ' + directory); console.log(JSON.stringify({ success: report.success, cases: cases.length, directory, realModelRequests: 0, error: report.error ?? null })); }
+1 -1
View File
@@ -22,7 +22,7 @@ export async function verifyControlledApi({ api, url, token, directory, appRoot,
const origin = new URL(url);
assert.equal(origin.hostname, '127.0.0.1'); assert.notEqual(origin.port, '4318');
const expectedVersion = JSON.parse(fs.readFileSync(path.join(appRoot, fs.existsSync(path.join(appRoot, 'MANIFEST.json')) ? 'MANIFEST.json' : 'package.json'), 'utf8')).version;
assert.ok(['1.14.0', '1.15.0', '1.16.0'].includes(expectedVersion));
assert.ok(['1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(expectedVersion));
const bootstrap = await api('/bootstrap'); assert.equal(bootstrap.version, expectedVersion);
assert.equal(bootstrap.config.mode, 'demo'); assert.equal(bootstrap.config.hasKey, false);
const root = path.join(directory, 'compiled-controlled-node'), hooks = path.join(directory, 'disabled-hooks');
+159
View File
@@ -0,0 +1,159 @@
import fs from 'node:fs';
import path from 'node:path';
import http from 'node:http';
import https from 'node:https';
import assert from 'node:assert/strict';
import { createHash, randomUUID, X509Certificate } from 'node:crypto';
import { chromium, expect } from 'playwright/test';
import { fixture, launchWorkbench, until } from '../tests/helpers.mjs';
if (process.argv.includes('--help')) { console.log('node scripts/verify-model-protocols-ui.mjs [--app-root <absolute-package>] — owned HTTP Responses/SSE, connection persistence, scoped detection, pool rejection, original stream download and desktop/mobile stop. Explicit package uses contained Node/server. No real model calls or OS trust changes.'); process.exit(0); }
const args = process.argv.slice(2); assert.ok(!args.length || args.length === 2 && args[0] === '--app-root' && path.isAbsolute(args[1]));
const appRoot = fs.realpathSync.native(args.length ? args[1] : process.cwd()), nodePath = args.length ? path.join(appRoot, 'runtime/node.exe') : process.execPath;
const directory = path.resolve('.qa', 'model-protocols-ui-' + randomUUID()); fs.mkdirSync(directory, { recursive: true });
const disposers = [], t = { after: action => disposers.push(action) }, f = fixture(t); f.store.close();
const requests = [], sockets = new Set(), held = new Set(); let mode = 'success', closedStreams = 0;
const item = text => ({ type: 'message', id: 'msg_owned', status: 'completed', role: 'assistant', content: [{ type: 'output_text', text }] });
const responseBody = output => ({ id: 'resp_owned', status: 'completed', output, usage: { input_tokens: 60, output_tokens: 20, total_tokens: 80 } });
const modelServer = http.createServer(async (request, response) => {
try {
const parts = []; for await (const part of request) parts.push(part);
const body = JSON.parse(Buffer.concat(parts)); requests.push({ route: request.url, body });
assert.equal(request.url, '/v1/responses');
const prompt = body.input.findLast(value => value.role === 'user')?.content ?? '';
const probe = prompt === 'Reply OK.' || prompt.startsWith('Call workbench_capability_echo');
const nonce = prompt.match(/nonce ([a-f0-9-]+)/)?.[1];
const tool = { type: 'function_call', id: 'fc_owned', call_id: 'owned_call', name: nonce ? 'workbench_capability_echo' : 'list_files', arguments: JSON.stringify(nonce ? { nonce } : { path: '', depth: 1 }), status: 'completed' };
const output = probe ? nonce ? [tool] : [item('OK')] : body.input.some(value => value.type === 'function_call_output') ? [item('项目读取完成。')] : [item('正在核对当前项目。'), tool];
if (!body.stream) { response.writeHead(200, { 'Content-Type': 'application/json' }); response.end(JSON.stringify(responseBody(output))); return; }
response.writeHead(200, { 'Content-Type': 'text/event-stream' }); let sequence = 0;
const send = (type, data) => response.write('data: ' + JSON.stringify({ type, sequence_number: sequence++, ...data }) + '\r\n\r\n');
send('response.created', { response: { id: 'resp_owned' } });
if (!probe && mode !== 'success') {
send('response.output_text.delta', { delta: '正在核对当前项目,尚未执行工具。' });
send('response.output_item.added', { item: { ...tool, arguments: '', status: 'in_progress' }, output_index: 1 });
send('response.function_call_arguments.delta', { item_id: tool.id, delta: '{"path":' });
if (mode === 'truncate') response.end();
else { held.add(response); response.on('close', () => { held.delete(response); closedStreams++; }); }
return;
}
for (const value of output) {
if (value.type === 'message') send('response.output_text.delta', { delta: value.content[0].text });
else { send('response.output_item.added', { item: { ...value, arguments: '', status: 'in_progress' }, output_index: 1 }); send('response.function_call_arguments.delta', { item_id: value.id, delta: value.arguments }); send('response.function_call_arguments.done', { item_id: value.id, arguments: value.arguments }); }
}
send('response.completed', { response: responseBody(output) }); response.end();
} catch { response.destroy(); }
});
modelServer.on('connection', socket => { sockets.add(socket); socket.on('close', () => sockets.delete(socket)); });
await new Promise(resolve => modelServer.listen(0, '127.0.0.1', resolve));
const host = await launchWorkbench(t, f.data, {}, { appRoot, nodePath }), browser = await chromium.launch({ channel: 'msedge', headless: true });
assert.equal(fs.realpathSync.native(host.bootstrap.runtimeRoot), appRoot); assert.notEqual(new URL(host.url).port, '4318');
const page = await browser.newPage({ viewport: { width: 1440, height: 1000 } }), errors = [], failures = [], passed = [], screenshots = [];
page.on('pageerror', error => errors.push(error.message)); page.on('requestfailed', request => failures.push(request.url() + ': ' + request.failure()?.errorText));
const mark = text => { passed.push(text); console.log('PASS ' + text); };
async function shot(target, name) { const file = path.join(directory, name + '.png'); await target.screenshot({ path: file, fullPage: false }); screenshots.push(file); assert.ok(await target.locator('body').evaluate(node => node.scrollWidth <= innerWidth), name + ' page overflow'); }
const getSession = () => host.api('/sessions/' + f.session.id);
let mobile, relay, cookie = '', gateway;
try {
await page.addInitScript(({ projectId, sessionId }) => { localStorage.setItem('awb-project', projectId); localStorage.setItem('awb-session', sessionId); }, { projectId: f.project.id, sessionId: f.session.id });
await page.goto(host.url); await page.waitForLoadState('networkidle');
await page.getByRole('button', { name: '打开模型中心', exact: true }).click();
const dialog = page.getByRole('dialog', { name: '模型中心', exact: true });
await dialog.getByRole('button', { name: '添加连接', exact: true }).click();
const form = dialog.getByRole('form', { name: '编辑模型连接', exact: true });
await form.getByLabel('连接名称', { exact: true }).fill('验收 Responses');
await form.getByLabel('接口协议', { exact: true }).selectOption('responses');
await expect(form.getByLabel('使用流式输出', { exact: true })).toBeDisabled();
await form.getByLabel('流式能力', { exact: true }).selectOption('supported'); await form.getByLabel('使用流式输出', { exact: true }).check();
await form.getByLabel('接口根地址', { exact: true }).fill('http://127.0.0.1:' + modelServer.address().port + '/v1');
await form.getByLabel('实际模型名称', { exact: true }).fill('owned-responses'); await form.getByLabel('服务需要 API Key', { exact: true }).uncheck();
await shot(page, 'desktop-editor'); await page.setViewportSize({ width: 390, height: 844 }); await form.scrollIntoViewIfNeeded(); await shot(page, 'narrow-editor');
await form.getByRole('button', { name: '保存模型连接', exact: true }).click(); await expect(form).toHaveCount(0);
await page.reload(); await page.getByRole('button', { name: '打开模型中心', exact: true }).click();
const card = dialog.locator('.mc-connection').filter({ hasText: '验收 Responses' }); await expect(card).toContainText('Responses · 流式开启');
let center = await host.api('/model-center'), connection = center.connections.find(value => value.name === '验收 Responses');
assert.equal(connection.protocol, 'responses'); assert.equal(connection.streaming, true);
mark('actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable');
await page.setViewportSize({ width: 1440, height: 1000 });
for (const [scope, label] of [['text', '文本'], ['tools', '工具'], ['streaming', '流式']]) {
await card.getByLabel('验收 Responses检测范围', { exact: true }).selectOption(scope);
await card.getByRole('button', { name: '验证响应(调用模型)', exact: true }).click();
await expect(dialog.locator('.mc-notice')).toContainText(label + '检测通过');
await expect(card.locator('.mc-capabilities')).toContainText(label + ':已验证');
if (scope === 'text') await expect(card.locator('.mc-capabilities')).toContainText('工具:声明支持');
}
await shot(page, 'desktop-capabilities'); await page.setViewportSize({ width: 390, height: 844 }); await shot(page, 'narrow-capabilities'); await page.setViewportSize({ width: 1440, height: 1000 });
mark('separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts');
const text = await host.api('/model-center/connections', { name: '只支持文本', model: 'text-only', baseUrl: connection.baseUrl, requiresKey: false, capabilityDeclarations: { tools: 'unsupported' } });
const textId = text.connection?.id ?? (await host.api('/model-center')).connections.find(value => value.name === '只支持文本').id;
await page.reload(); await page.getByRole('button', { name: '打开模型中心', exact: true }).click();
await dialog.getByRole('button', { name: '模型池', exact: true }).click(); await dialog.getByRole('button', { name: '新建模型池', exact: true }).click();
const poolForm = dialog.getByRole('form', { name: '编辑模型池', exact: true }); await poolForm.getByLabel('模型池名称', { exact: true }).fill('按能力选择的验收池');
for (const name of ['验收 Responses', '只支持文本']) await poolForm.locator('.mc-member-choice').filter({ hasText: name }).locator('input[type=checkbox]').check();
await poolForm.getByRole('button', { name: '保存模型池', exact: true }).click(); await dialog.locator('.mc-pool').filter({ hasText: '按能力选择的验收池' }).getByRole('button', { name: '使用此模型池', exact: true }).click();
await page.keyboard.press('Escape');
await expect(page.locator('.model-button')).toContainText('按能力选择的验收池');
await page.reload(); await expect(page.locator('.model-button')).toContainText('按能力选择的验收池');
assert.equal((await host.api('/bootstrap')).config.model, '', 'The unselected legacy model remains untouched.');
await page.getByLabel('任务内容', { exact: true }).fill('受控完整流程:读取项目后结束。'); await page.getByRole('button', { name: '发送任务', exact: true }).click();
await until(async () => (await getSession()).status === 'completed', 15000);
const completed = await getSession(); assert.equal(completed.events.filter(value => value.tool === 'list_files' && value.phase === 'completed').length, 1);
center = await host.api('/model-center'); const attempt = center.attempts.find(value => value.runId === completed.runId);
assert.equal(attempt.protocol, 'responses'); assert.ok(attempt.rejections.some(value => value.connectionId === textId && value.capability === 'tools')); assert.ok(requests.every(value => value.body.model !== 'text-only'));
await page.getByRole('button', { name: '打开模型中心', exact: true }).click(); await dialog.getByRole('button', { name: '请求账本', exact: true }).click();
await expect(dialog.locator('.mc-route-rejections').first()).toContainText('只支持文本');
const downloadEvent = page.waitForEvent('download'); await dialog.getByRole('button', { name: '下载已保存的响应', exact: true }).first().click();
const download = await downloadEvent, saved = path.join(directory, 'original-stream.sse'); await download.saveAs(saved);
assert.equal(createHash('sha256').update(fs.readFileSync(saved)).digest('hex'), attempt.responseSha256); await shot(page, 'desktop-ledger');
mark('actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE');
await page.keyboard.press('Escape');
const initial = await host.api('/companion'); assert.ok(initial.addresses.length);
const reservation = http.createServer(); await new Promise(resolve => reservation.listen(0, initial.addresses[0].address, resolve)); const port = reservation.address().port; await new Promise(resolve => reservation.close(resolve));
await host.api('/companion/start', { address: initial.addresses[0].address, port }); gateway = await host.api('/companion');
const cert = await fetch(host.url + '/api/companion/certificate', { headers: { 'X-Workbench-Token': host.bootstrap.token } }); assert.ok(cert.ok);
const ca = new X509Certificate(Buffer.from(await cert.arrayBuffer())).toString(), target = new URL(gateway.origin);
const ticket = await host.api('/companion/pair', { projectIds: [f.project.id], permissions: { observe: true, approve: false, stop: true }, expiresInHours: 1 });
relay = http.createServer((request, response) => {
const forwarded = https.request(new URL(request.url, target), { method: request.method, ca, servername: '', headers: { Host: target.host, Origin: target.origin, Connection: 'close', ...(cookie ? { Cookie: cookie } : {}), ...(request.headers['content-type'] ? { 'Content-Type': request.headers['content-type'] } : {}) } }, incoming => {
if (incoming.headers['set-cookie']?.length) cookie = incoming.headers['set-cookie'][0].split(';')[0]; const headers = { ...incoming.headers }; delete headers['set-cookie']; response.writeHead(incoming.statusCode, headers); incoming.pipe(response);
}); forwarded.on('error', () => response.destroy()); request.pipe(forwarded);
});
await new Promise(resolve => relay.listen(0, '127.0.0.1', resolve));
mobile = await browser.newPage({ viewport: { width: 390, height: 844 }, isMobile: true, hasTouch: true }); mobile.on('pageerror', error => errors.push(error.message));
await mobile.goto('http://127.0.0.1:' + relay.address().port + '/#pair=' + new URLSearchParams(new URL(ticket.url).hash.slice(1)).get('pair'));
await mobile.getByLabel('设备名称', { exact: true }).fill('协议验收观察窗口'); await mobile.getByRole('button', { name: '连接这台电脑', exact: true }).click(); await expect(mobile.getByRole('heading', { name: '项目任务', exact: true })).toBeVisible();
mode = 'hold'; const count = requests.length;
await page.getByLabel('任务内容', { exact: true }).fill('受控停止:保留片段。'); await page.getByRole('button', { name: '发送任务', exact: true }).click();
await expect(page.getByLabel('模型输出片段', { exact: true }).last()).toContainText('正在核对当前项目');
const active = await getSession(); assert.equal(active.events.filter(value => value.kind === 'tool' && value.runId === active.runId).length, 0);
await shot(page, 'desktop-streaming'); await page.setViewportSize({ width: 390, height: 844 }); await shot(page, 'narrow-streaming');
await mobile.getByRole('button', { name: '刷新任务', exact: true }).click(); await mobile.locator('.mobile-task-row').first().click();
await expect(mobile.locator('.mobile-stream')).toContainText('正在核对当前项目'); await mobile.locator('.mobile-stream').scrollIntoViewIfNeeded(); await shot(mobile, 'mobile-streaming');
await mobile.getByRole('button', { name: '停止原任务', exact: true }).click(); await mobile.getByRole('dialog').getByRole('button', { name: '确认', exact: true }).click();
await until(async () => (await getSession()).status === 'paused' && closedStreams === 1, 15000);
await expect(mobile.locator('.mobile-stream')).toContainText('输出未完成');
assert.equal(requests.length, count + 1); await mobile.locator('.mobile-stream').scrollIntoViewIfNeeded(); await shot(mobile, 'mobile-stopped');
await expect(page.getByLabel('模型输出片段', { exact: true }).last()).toContainText('输出未完成'); await shot(page, 'narrow-stopped');
mark('desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay');
await page.setViewportSize({ width: 1440, height: 1000 }); mode = 'truncate';
await page.getByLabel('任务内容', { exact: true }).fill('受控断流:半截参数不得执行。'); await page.getByRole('button', { name: '发送任务', exact: true }).click();
await until(async () => (await getSession()).status === 'failed', 15000);
const broken = await getSession(), latest = (await host.api('/model-center')).attempts.find(value => value.runId === broken.runId);
assert.equal(latest.status, 'unknown'); assert.equal(latest.stream.terminal, false); assert.equal(requests.length, count + 2);
await page.getByRole('button', { name: '打开模型中心', exact: true }).click(); await dialog.getByRole('button', { name: '请求账本', exact: true }).click();
await expect(dialog.locator('.mc-attempts article').first()).toContainText('结果待核对'); await expect(dialog.locator('.mc-attempts article').first()).toContainText('响应未完整'); await shot(page, 'desktop-incomplete');
await page.setViewportSize({ width: 390, height: 844 }); await shot(page, 'narrow-incomplete');
mark('truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution');
assert.deepEqual(errors, []); assert.deepEqual(failures, []);
fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify({ success: true, version: host.bootstrap.version, appRoot, nodePath, containedRuntime: args.length > 0, nodeSha256: createHash('sha256').update(fs.readFileSync(nodePath)).digest('hex'), passed, screenshots, pageErrors: errors, requestFailures: failures, fixtureModelRequests: requests.length, realModelRequests: 0, osTrustChanged: false, nativeIPhone: 'not exercised; paired Edge viewport uses CA-verifying owned relay', taskId: completed.taskId, runIds: [completed.runId, active.runId, broken.runId] }, null, 2));
} catch (error) {
await shot(page, 'failure-desktop').catch(() => {}); if (mobile) await shot(mobile, 'failure-mobile').catch(() => {});
fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify({ success: false, error: error.stack, passed, screenshots, pageErrors: errors, requestFailures: failures }, null, 2)); throw error;
} finally {
console.log('EVIDENCE ' + directory); await browser.close();
if (relay) await new Promise(resolve => { relay.closeAllConnections(); relay.close(resolve); });
if (gateway) await host.api('/companion/close', {});
for (const response of held) response.destroy(); for (const socket of sockets) socket.destroy(); await new Promise(resolve => modelServer.close(resolve));
for (const dispose of disposers.reverse()) await dispose();
}
+7 -7
View File
@@ -34,7 +34,7 @@ for (const name of Object.keys(env)) if (name.toLowerCase() === 'path') delete e
const windowsRoot = process.env.SystemRoot || 'C:\\Windows';
env.PATH = [windowsRoot, path.join(windowsRoot, 'System32'), path.join(windowsRoot, 'System32', 'WindowsPowerShell', 'v1.0')].join(path.delimiter);
let externalGit = null;
if (['1.14.0', '1.15.0', '1.16.0'].includes(manifest.version)) {
if (['1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(manifest.version)) {
// The controlled project requires external Git. Preserve its observed binary
// directory while keeping system Node/npm unavailable to the packaged host.
const binary = fs.realpathSync.native(execFileSync('where.exe', ['git.exe'], { env: gitEnvironment(), encoding: 'utf8', windowsHide: true, timeout: 10000 }).trim().split(/\r?\n/)[0]);
@@ -88,7 +88,7 @@ try {
console.log((await launch()).trim());
assert.equal(JSON.parse(fs.readFileSync(path.join(data, 'service-info.json'), 'utf8')).pid, firstInfo.pid);
const example = bootstrap.projects.find(project => project.id === bootstrap.exampleProjectId);
if (['1.15.0', '1.16.0'].includes(manifest.version)) {
if (['1.15.0', '1.16.0', '1.17.0'].includes(manifest.version)) {
assert.equal(path.resolve(example.root).toLowerCase(), path.join(data, 'projects', 'starter-project').toLowerCase());
const compareTemplate = relative => { for (const entry of fs.readdirSync(path.join(appRoot, 'examples/starter-project', relative), { withFileTypes: true })) {
const next = path.join(relative, entry.name); if (entry.isDirectory()) compareTemplate(next);
@@ -114,7 +114,7 @@ try {
const checkLog = await api('/artifacts/' + checked.results[0].logArtifactId + '?session=' + session.id); assert.match(checkLog.content, /tests 4/);
assert.ok(fs.existsSync(path.join(appRoot, 'runtime/node_modules/npm/bin/npm-cli.js')));
const actualRea = [];
if (['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(manifest.version)) {
if (['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(manifest.version)) {
const installation = await api('/research/availability'); assert.equal(installation.status, 'available'); assert.equal(installation.version, '6.8.0');
assert.equal(fs.realpathSync.native(installation.packageRoot), fs.realpathSync.native(path.join(appRoot, 'runtime/node_modules/rea-agents')));
assert.equal(fs.realpathSync.native(installation.node.path), fs.realpathSync.native(path.join(appRoot, 'runtime/node.exe')));
@@ -146,7 +146,7 @@ try {
console.log('PASS actual contained REA: ASAR, PE imports and PE resources; zero target execution/model requests');
}
let actualEngine = null;
if (['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(manifest.version) && process.argv.includes('--native-engines')) {
if (['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(manifest.version) && process.argv.includes('--native-engines')) {
const installation = await api('/engines/deepseek/availability'); assert.equal(installation.status, 'available', installation.message);
assert.equal(fs.realpathSync.native(installation.node.path), fs.realpathSync.native(path.join(appRoot, 'runtime/node.exe')));
const engineRoot = path.join(data, 'engine-project'); fs.mkdirSync(engineRoot); fs.writeFileSync(path.join(engineRoot, 'README.md'), '# Owned portable engine connection\n');
@@ -166,8 +166,8 @@ try {
assert.equal((await api('/research')).length, 4);
const page = await fetch(url); assert.equal(page.status, 200);
assert.match(await page.text(), /Agent Workbench/);
const actualBrowser = ['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(manifest.version) ? await verifyBrowserApi({ api, url, token: bootstrap.token, directory: data, appRoot, contained: true }) : null;
const actualControlled = ['1.14.0', '1.15.0', '1.16.0'].includes(manifest.version) ? await verifyControlledApi({ api, url, token: bootstrap.token, directory: data, appRoot, contained: true }) : null;
const actualBrowser = ['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(manifest.version) ? await verifyBrowserApi({ api, url, token: bootstrap.token, directory: data, appRoot, contained: true }) : null;
const actualControlled = ['1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(manifest.version) ? await verifyControlledApi({ api, url, token: bootstrap.token, directory: data, appRoot, contained: true }) : null;
console.log((await stop()).trim()); started = false;
await until(async () => { try { await fetch(url + '/api/health'); return false; } catch { return true; } });
for (const file of manifest.files) {
@@ -176,7 +176,7 @@ try {
}
const result = { success: true, date: new Date().toISOString(), appRoot, version: manifest.version, nodeVersion: manifest.nodeVersion,
verifiedFiles: manifest.files.length, url, reusedPid: firstInfo.pid, checks: { jobId, status: checked.status, tests: checked.results[0].tests }, actualRea, actualEngine, actualBrowser, actualControlled, externalGit,
steps: ['manifest hashes', 'bundled Node launch', 'same-service reuse', 'packaged example and static page', ...(['1.15.0', '1.16.0'].includes(manifest.version) ? ['starter project copied to owned user data; original template bytes matched'] : []), 'explicit command consent', 'actual bundled Node version', 'actual bundled npm check without system Node/npm', 'check log artifact', ...(actualRea.length ? ['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', 'every original packaged file remains unchanged'], realModel: false };
steps: ['manifest hashes', 'bundled Node launch', 'same-service reuse', 'packaged example and static page', ...(['1.15.0', '1.16.0', '1.17.0'].includes(manifest.version) ? ['starter project copied to owned user data; original template bytes matched'] : []), 'explicit command consent', 'actual bundled Node version', 'actual bundled npm check without system Node/npm', 'check log artifact', ...(actualRea.length ? ['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', 'every original packaged file remains unchanged'], realModel: false };
fs.writeFileSync('.qa/release-validation.json', JSON.stringify(result, null, 2));
console.log(JSON.stringify(result, null, 2));
} finally { if (started) { try { await stop(); } catch {} } }
+30 -9
View File
@@ -19,7 +19,7 @@ assert.ok(fs.existsSync(npmCli), 'Use Node with its bundled npm.');
const files = (root, relative = '') => fs.readdirSync(path.join(root, relative), { withFileTypes: true }).sort((a, b) => a.name.localeCompare(b.name))
.flatMap(entry => entry.isDirectory() ? files(root, path.join(relative, entry.name)) : [path.join(relative, entry.name)]);
const digest = file => createHash('sha256').update(fs.readFileSync(file)).digest('hex');
const buildFolders = ['dist-client', 'dist-server', ...(['1.15.0', '1.16.0'].includes(evidence.version) ? ['dist-desktop'] : [])];
const buildFolders = ['dist-client', 'dist-server', ...(['1.15.0', '1.16.0', '1.17.0'].includes(evidence.version) ? ['dist-desktop'] : [])];
const expected = Object.fromEntries(buildFolders.flatMap(folder => files(path.join(workspace, folder)).map(relative => [path.join(folder, relative), digest(path.join(workspace, folder, relative))])));
const allowedEnv = /^(path|pathext|systemroot|systemdrive|windir|comspec|temp|tmp|userprofile|homedrive|homepath|home|appdata|localappdata|programfiles(?:\(x86\))?|commonprogramfiles(?:\(x86\))?|lang|lc_all|AGENT_WORKBENCH_TEST_PYTHON|AGENT_WORKBENCH_DEEPSEEK_ROOT|AGENT_WORKBENCH_PURGE_ROOT)$/i;
const env = Object.fromEntries(Object.entries(process.env).filter(([key]) => allowedEnv.test(key)));
@@ -30,7 +30,7 @@ const directory = path.join(sourceRoot, '.qa', 'package-validation-' + randomUUI
fs.mkdirSync(directory, { recursive: true });
const inputFolders = ['src', 'tests', 'scripts', ...['benchmarks', 'public', 'examples', 'research'].filter(folder => fs.existsSync(path.join(sourceRoot, folder)))];
const inputNames = [...inputFolders.flatMap(folder => files(path.join(sourceRoot, folder)).map(relative => path.join(folder, relative))),
'package.json', 'package-lock.json', 'vite.config.ts', 'tsconfig.json', 'index.html', ...(evidence.version === '1.16.0' ? ['mobile.html'] : []), ...['.gitattributes', '.gitignore', 'Start-Desktop.cmd', 'Start-Workbench.cmd', 'Stop-Workbench.cmd'].filter(name => fs.existsSync(path.join(sourceRoot, name)))].sort();
'package.json', 'package-lock.json', 'vite.config.ts', 'tsconfig.json', 'index.html', ...(['1.16.0', '1.17.0'].includes(evidence.version) ? ['mobile.html'] : []), ...['.gitattributes', '.gitignore', 'Start-Desktop.cmd', 'Start-Workbench.cmd', 'Stop-Workbench.cmd'].filter(name => fs.existsSync(path.join(sourceRoot, name)))].sort();
const snapshot = () => inputNames.map(relative => ({ path: relative.replaceAll('\\', '/'), bytes: fs.statSync(path.join(sourceRoot, relative)).size, sha256: digest(path.join(sourceRoot, relative)) }));
const inputs = snapshot(); fs.writeFileSync(path.join(directory, 'inputs.json'), JSON.stringify(inputs, null, 2));
let stage = 'environment preflight', python = null;
@@ -83,7 +83,7 @@ try {
assert.deepEqual(actualFiles.slice().sort(), Object.keys(expected).sort());
for (const [relative, sha256] of Object.entries(expected)) assert.equal(digest(path.join(sourceRoot, relative)), sha256, relative);
let actualRea = null;
if (['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(evidence.version)) {
if (['1.8.0', '1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(evidence.version)) {
stage = 'contained REA';
const reaOutput = await run(['scripts/verify-rea.mjs', '--app-root', sourceRoot, '--contained'], 'rea.log');
actualRea = JSON.parse(reaOutput.trim().split('\n').at(-1));
@@ -91,7 +91,7 @@ try {
assert.ok(actualRea.results.every(item => item.rootExited === true));
}
let actualEngine = null;
if (['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(evidence.version) && process.argv.includes('--native-engines')) {
if (['1.9.0', '1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(evidence.version) && process.argv.includes('--native-engines')) {
stage = 'native DeepSeek SDK';
const output = await run(['scripts/verify-engines.mjs'], 'engines.log');
actualEngine = JSON.parse(output.trim().split('\n').at(-1));
@@ -99,7 +99,7 @@ try {
assert.equal(actualEngine.modelRequests, 0); assert.equal(actualEngine.rootExited, true); assert.equal(actualEngine.nativeMethods.length, 6);
}
let actualBrowser = null;
if (['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0'].includes(evidence.version)) {
if (['1.10.0', '1.10.1', '1.11.0', '1.12.0', '1.12.1', '1.13.0', '1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(evidence.version)) {
stage = 'contained browser runtime';
const output = await run(['scripts/verify-browser.mjs', '--app-root', sourceRoot, '--contained'], 'browser.log');
actualBrowser = JSON.parse(output.trim().split('\n').at(-1));
@@ -109,7 +109,7 @@ try {
assert.equal(actualBrowser.modelRequests, 0);
}
let actualControlled = null;
if (['1.14.0', '1.15.0', '1.16.0'].includes(evidence.version)) {
if (['1.14.0', '1.15.0', '1.16.0', '1.17.0'].includes(evidence.version)) {
stage = 'compiled controlled-engine delivery';
const output = await run(['scripts/verify-controlled-release.mjs', '--app-root', sourceRoot], 'controlled-engine.log');
actualControlled = JSON.parse(output.trim().split('\n').at(-1));
@@ -117,7 +117,7 @@ try {
assert.equal(actualControlled.realModelRequests, 0); assert.equal(actualControlled.cases, 4); assert.ok(actualControlled.fixtureModelRequests > 0);
}
let actualCompanion = null;
if (evidence.version === '1.16.0') {
if (['1.16.0', '1.17.0'].includes(evidence.version)) {
stage = 'contained companion gateway and UI';
const output = await run(['scripts/verify-companion-ui.mjs', '--app-root', sourceRoot], 'companion-ui.log');
const location = [...output.matchAll(/^EVIDENCE (.+)\r?$/gm)].at(-1)?.[1]?.trim();
@@ -127,12 +127,23 @@ try {
assert.equal(fs.realpathSync.native(actualCompanion.appRoot), sourceRoot); assert.equal(actualCompanion.containedRuntime, true);
assert.equal(actualCompanion.passed.length, 7); assert.deepEqual(actualCompanion.errors, []); assert.equal(actualCompanion.realModelRequests, 0);
}
let actualProtocols = null;
if (evidence.version === '1.17.0') {
stage = 'contained model protocols and mobile streams';
const output = await run(['scripts/verify-model-protocols-ui.mjs', '--app-root', sourceRoot], 'model-protocols-ui.log');
const location = [...output.matchAll(/^EVIDENCE (.+)\r?$/gm)].at(-1)?.[1]?.trim();
assert.ok(location && path.resolve(location).startsWith(path.join(sourceRoot, '.qa') + path.sep));
actualProtocols = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualProtocols.success, true); assert.equal(actualProtocols.version, evidence.version);
assert.equal(fs.realpathSync.native(actualProtocols.appRoot), sourceRoot); assert.equal(actualProtocols.containedRuntime, true);
assert.equal(actualProtocols.passed.length, 5); assert.deepEqual(actualProtocols.pageErrors, []); assert.deepEqual(actualProtocols.requestFailures, []);
}
stage = 'tests';
const output = await run(['--test', '--test-concurrency=2', '--test-reporter=tap', ...files(path.join(sourceRoot, 'tests')).filter(file => !file.includes(path.sep) && file.endsWith('.test.mjs')).map(file => path.join('tests', file))], 'tests.tap');
const stats = Object.fromEntries([...output.matchAll(/^# (tests|pass|fail|cancelled|skipped|todo) (\d+)\s*$/gm)].map(match => [match[1], Number(match[2])]));
assert.ok(stats.tests > 0); assert.equal(stats.pass, stats.tests); for (const key of ['fail', 'cancelled', 'skipped', 'todo']) assert.equal(stats[key], 0);
let actualDesktop = null;
if (['1.15.0', '1.16.0'].includes(evidence.version)) {
if (['1.15.0', '1.16.0', '1.17.0'].includes(evidence.version)) {
stage = 'actual contained Electron window'; await run(['scripts/verify-desktop-window.mjs'], 'desktop-window.log');
const window = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/desktop-window-latest.json'), 'utf8'));
assert.equal(window.success, true); assert.equal(path.resolve(window.appRoot), sourceRoot); assert.equal(window.results.length, 7);
@@ -145,9 +156,19 @@ try {
assert.deepEqual(projects.results.map(value => value.parentCheck.results[0].tests.passed), [8, 9, 10]);
actualDesktop = { window, ui, projects, scope: 'Independently rebuilt source and its shipped Electron binary; original window/engine/engineering assertions. Own credentials/HTTP fixtures; Windows native picker and complete host crash/stop have separate actual evidence.' };
}
let actualProtocolEngineering = null;
if (evidence.version === '1.17.0') {
stage = 'Responses SSE actual Node React Python engineering';
await run(['scripts/verify-controlled-projects.mjs', '--responses'], 'responses-engineering.log');
const location = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/responses-engineering-location.json'), 'utf8'));
actualProtocolEngineering = JSON.parse(fs.readFileSync(location.result, 'utf8'));
assert.equal(actualProtocolEngineering.success, true); assert.equal(actualProtocolEngineering.testedVersion, evidence.version);
assert.equal(actualProtocolEngineering.protocol, 'responses-stream'); assert.equal(actualProtocolEngineering.realModelRequests, 0);
assert.deepEqual(actualProtocolEngineering.results.map(value => value.parentCheck.results[0].tests.passed), [8, 9, 10]);
}
assert.deepEqual(snapshot(), inputs, 'Source package inputs changed during validation.');
const result = { success: true, version: evidence.version, testedAt: new Date().toISOString(), sourceRoot, directory, nodeVersion: process.version, python, offlineInstall: true,
inputs, inputFiles: inputs.length, logs, buildMatchedFiles: Object.keys(expected).length, buildFiles: Object.entries(expected).map(([path, sha256]) => ({ path: path.replaceAll('\\', '/'), sha256 })), tests: stats, actualRea, actualEngine, actualBrowser, actualControlled, actualDesktop, actualCompanion, credentialsHandling: 'Only build/runtime environment paths are inherited; no configured model credentials are used. The controlled-engine stage supplies a declared owned local response fixture.' };
inputs, inputFiles: inputs.length, logs, buildMatchedFiles: Object.keys(expected).length, buildFiles: Object.entries(expected).map(([path, sha256]) => ({ path: path.replaceAll('\\', '/'), sha256 })), tests: stats, actualRea, actualEngine, actualBrowser, actualControlled, actualDesktop, actualCompanion, actualProtocols, actualProtocolEngineering, credentialsHandling: 'Only build/runtime environment paths are inherited; no configured model credentials are used. The controlled-engine stage supplies a declared owned local response fixture.' };
save(result); console.log(JSON.stringify({ success: true, version: result.version, sourceRoot, directory, tests: stats, nodeVersion: process.version, python, inputFiles: inputs.length, buildMatchedFiles: result.buildMatchedFiles, rea: !!actualRea?.success, engine: !!actualEngine?.success, browser: !!actualBrowser?.success, controlled: !!actualControlled?.success }));
} catch (error) {
save({ success: false, version: evidence.version, testedAt: new Date().toISOString(), stage, error: error.message, sourceRoot, directory, nodeVersion: process.version, python, inputs, logs });
+1 -1
View File
@@ -8,7 +8,7 @@ import { workerHttp } from '../tests/fixtures/workers-http.mjs';
import { workerDefinition, ownerBytes, applyWorkerProposals, approveWorkerChecks } from '../tests/fixtures/workers-project.mjs';
if (process.argv.includes('--help')) { console.log('node scripts/verify-workers-ui.mjs — owned local fixture, real isolated Git/checks/review, desktop/390px, conflicts, stop, recovery and late source errors'); process.exit(0); }
const version = JSON.parse(fs.readFileSync('package.json', 'utf8')).version, prefix = version === '1.16.0' ? 'mobile-companion-workers' : version === '1.15.0' ? 'desktop-host-workers' : version === '1.14.0' ? 'controlled-engine-workers' : version === '1.13.0' ? 'workers' : 'workers-development';
const version = JSON.parse(fs.readFileSync('package.json', 'utf8')).version, prefix = version === '1.17.0' ? 'model-protocols-workers' : version === '1.16.0' ? 'mobile-companion-workers' : version === '1.15.0' ? 'desktop-host-workers' : version === '1.14.0' ? 'controlled-engine-workers' : version === '1.13.0' ? 'workers' : 'workers-development';
const directory = path.resolve('.qa', 'workers-ui-' + randomUUID()); fs.mkdirSync(directory, { recursive: true });
const disposers = [], t = { after: dispose => disposers.push(dispose) }, f = fixture(t), host = await workerHttp(f);
assert.notEqual(new URL(host.url).port, '4318');
+4 -2
View File
@@ -1,5 +1,5 @@
import { engineError, engineCanonicalDigest as controlledDigest } from './engines.mjs';
import { requestMetrics } from './model-request.mjs';
import { requestMetrics, requestVariants, outputReservation } from './model-request.mjs';
export const ENGINE_RUN_ACTIVE = new Set(['queued', 'starting', 'initializing', 'running', 'waiting_tool', 'closing', 'stopping']);
export function selectedEngineInput(input) {
@@ -55,7 +55,9 @@ export function verifyEngineModelInput(store, session, job, request) {
if (input.owner.sessionId !== job.sessionId || input.owner.taskId !== job.taskId || input.owner.runId !== job.runId || input.owner.projectId !== job.projectId
|| controlledDigest(input.native) !== request.sourceSha256 || metrics.sha256 !== request.requestSha256 || metrics.bytes !== request.requestBytes
|| !Number.isSafeInteger(request.maxAttempts) || request.maxAttempts < 1 || request.maxAttempts > 8
|| request.reservedPerAttempt !== metrics.estimatedInputTokens + 128 + input.body.max_tokens) throw engineError('原引擎模型输入、归属或预算核对失败。');
|| !Number.isSafeInteger(input.native.maxTokens) || input.native.maxTokens < 1
|| !requestVariants(input.body).every(body => outputReservation(body) === input.native.maxTokens)
|| request.reservedPerAttempt !== metrics.estimatedInputTokens + 128 + input.native.maxTokens) throw engineError('原引擎模型输入、归属或预算核对失败。');
return input;
}
export function assertEngineWorkerResult(store, session, worker) {
+33
View File
@@ -0,0 +1,33 @@
import http from 'node:http';
import assert from 'node:assert/strict';
import { requestHistory } from '../../src/shared/contracts/model-request.mjs';
// An owned wire fixture only: the original engineering algorithm receives the
// same canonical history. Runtime/Harness/checks/Git still execute for real.
export async function responsesEngineeringHttp(t, algorithm) {
const requests = [], sockets = new Set();
const server = http.createServer(async (request, response) => {
try {
const parts = []; for await (const part of request) parts.push(part);
const wire = JSON.parse(Buffer.concat(parts)); assert.equal(request.url, '/v1/responses'); assert.equal(wire.stream, true);
requests.push(wire);
const input = { ...wire, messages: requestHistory(wire) }, result = await algorithm('/v1/chat/completions', input);
const message = result.choices[0].message;
const output = [...(message.content ? [{ id: 'msg_' + requests.length, type: 'message', role: 'assistant', status: 'completed', content: [{ type: 'output_text', text: message.content }] }] : []),
...(message.tool_calls ?? []).map((call, index) => ({ type: 'function_call', id: 'fc_' + requests.length + '_' + index, call_id: call.id, name: call.function.name, arguments: call.function.arguments, status: 'completed' }))];
const final = { id: 'resp_' + requests.length, status: 'completed', output, usage: { input_tokens: result.usage.prompt_tokens, output_tokens: result.usage.completion_tokens, total_tokens: result.usage.total_tokens } };
response.writeHead(200, { 'Content-Type': 'text/event-stream' }); let sequence = 0;
const send = (type, data) => response.write('data: ' + JSON.stringify({ type, sequence_number: sequence++, ...data }) + '\n\n');
send('response.created', { response: { id: final.id } });
for (const item of output) {
if (item.type === 'message') send('response.output_text.delta', { delta: item.content[0].text });
else { send('response.output_item.added', { item: { ...item, arguments: '', status: 'in_progress' } }); send('response.function_call_arguments.delta', { item_id: item.id, delta: item.arguments }); send('response.function_call_arguments.done', { item_id: item.id, arguments: item.arguments }); }
}
send('response.completed', { response: final }); response.end();
} catch { response.destroy(); }
});
server.on('connection', socket => { sockets.add(socket); socket.on('close', () => sockets.delete(socket)); });
await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
t.after(() => new Promise(resolve => { for (const socket of sockets) socket.destroy(); server.close(resolve); }));
return { baseUrl: 'http://127.0.0.1:' + server.address().port + '/v1', requests };
}
+39
View File
@@ -10,6 +10,28 @@ import { Runtime } from '../src/server/runtime.mjs';
import { verifyPlanEvidence } from '../src/core/context/request-plan.mjs';
import { completionBody, requestMetrics } from '../src/shared/contracts/model-request.mjs';
import { ConfigImporter } from '../src/core/models/config-import.mjs';
import { verifyEngineModelInput } from '../src/shared/contracts/engine-execution.mjs';
import { engineCanonicalDigest } from '../src/shared/contracts/engines.mjs';
test('saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance', t => {
const f = fixture(t), run = f.store.beginRun(f.session, 'Owned engine input proof', false, f.store.config);
const owner = { sessionId: f.session.id, projectId: f.project.id, taskId: run.taskId, runId: run.id };
const native = { messages: [], maxTokens: 512 };
const verify = body => {
const metrics = requestMetrics(body), request = { id: 'owned', bridgeTraceId: 'owned-trace', sourceSha256: engineCanonicalDigest(native),
requestSha256: metrics.sha256, requestBytes: metrics.bytes, estimatedInputTokens: metrics.estimatedInputTokens,
reservedPerAttempt: metrics.estimatedInputTokens + 128 + native.maxTokens, maxAttempts: 1 };
const artifact = f.store.artifactStore.write(f.session, run, { owner, native, body, plan: request }, { kind: 'engine-model-input' });
f.store.core.artifact.set(artifact.id, artifact); request.inputArtifactId = artifact.id; request.inputSha256 = artifact.sha256;
return () => verifyEngineModelInput(f.store, f.session, owner, request);
};
const config = { model: 'owned', maxOutputTokens: 512 };
for (const protocol of ['chat-completions', 'responses']) assert.doesNotThrow(verify(completionBody({ ...config, protocol }, [], [])));
const mixed = completionBody({ ...config, modelRouting: { members: [{ id: 'chat', model: 'owned', protocol: 'chat-completions' },
{ id: 'responses', model: 'owned', protocol: 'responses' }] } }, [], []);
assert.doesNotThrow(verify(mixed)); mixed.variants[1].body.max_output_tokens++;
assert.throws(verify(mixed), /预算核对失败/);
});
test('owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched', t => {
const f = fixture(t), file = path.join(f.root, 'owned-switch.db'), db = new DatabaseSync(file);
@@ -87,6 +109,23 @@ test('Responses incomplete, failed, missing call identity and unsupported hosted
}
});
test('invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay', async t => {
for (const protocol of ['chat-completions', 'responses']) await t.test(protocol, async sub => {
const f = fixture(sub), value = protocol === 'responses' ? response([fn('valid'), fn('broken', 'search_files', '{invalid')])
: { choices: [{ message: { role: 'assistant', content: '', tool_calls: [
{ id: 'valid', type: 'function', function: { name: 'list_files', arguments: '{"path":""}' } },
{ id: 'broken', type: 'function', function: { name: 'search_files', arguments: '{invalid' } },
] }, finish_reason: 'tool_calls' }] };
const server = await compatibleFixture(sub, () => value), unused = await compatibleFixture(sub, () => { throw new Error('Must not replay'); });
const provider = new Provider(), hub = provider.modelHub(f.store), first = connect(hub, server, protocol), second = connect(hub, unused, protocol);
const pool = hub.pool({ name: 'Owned validation boundary', members: [{ connectionId: first.id }, { connectionId: second.id }] });
hub.select({ type: 'pool', id: pool.id }); const runtime = new Runtime(f.store, provider); sub.after(() => runtime.stopAll());
await runUntilIdle(runtime, f.session);
assert.equal(server.requests.length, 1); assert.equal(unused.requests.length, 0); assert.equal(f.store.core.tool.size, 0);
assert.notEqual(f.session.status, 'completed'); assert.equal(hub.view().attempts[0].status, 'failed');
});
});
test('wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint', () => {
const messages = [{ role: 'user', content: 'Inspect' }, { role: 'assistant', content: '', tool_calls: [{ id: 'call_own', type: 'function', function: { name: 'read_file', arguments: '{"path":"README.md"}' } }],
providerState: { protocol: 'responses', endpoint: 'https://owned.invalid/v1', model: 'm', items: [{ type: 'reasoning', encrypted_content: 'owned-private' }] } },
+1 -1
View File
@@ -73,7 +73,7 @@ test('the compatible HTTP loop preserves call IDs, validates errors and waits be
round++;
if (round === 1) return completion([
call('list', 'list_files', { path: '', depth: 2 }),
call('malformed', 'search_files', '{invalid'),
call('malformed', 'search_files', { query: 42 }),
call('unknown', 'unknown_tool', {}),
]);
if (round === 2) {