fix: await owned desktop batch before checking rendered completion

This commit is contained in:
Agent Workbench Dev
2026-11-02 06:50:45 +08:00
parent 324b7ab36d
commit 12d1c7f9cb
61 changed files with 256161 additions and 1 deletions
+1
View File
@@ -3,6 +3,7 @@ docs/embedded-browser-development-evidence/** -text whitespace=blank-at-eol,blan
docs/embedded-browser-release-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
docs/embedded-browser-rejected-candidate-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
docs/embedded-browser-b-rejected-candidate-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
docs/embedded-browser-c-rejected-candidate-evidence/** -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
docs/embedded-browser-*-evidence/**/*.log binary
docs/embedded-browser-*-evidence/**/*.tap binary
docs/embedded-browser-*.json -text whitespace=blank-at-eol,blank-at-eof,space-before-tab,cr-at-eol
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Binary file not shown.

After

Width:  |  Height:  |  Size: 254 KiB

File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
@@ -0,0 +1,438 @@
{
"schemaVersion": 1,
"version": "1.22.0",
"kind": "rejected-candidate-C",
"sourceCommit": "324b7ab36d4836898f629b960f0f8922716eb0a2",
"sourceOverallSuccess": false,
"tests": {
"tests": 683,
"pass": 683,
"fail": 0,
"cancelled": 0,
"skipped": 0,
"todo": 0
},
"sets": [
{
"sessionId": "5e9d42db-3cc7-4572-a379-d2c6ad878177",
"id": "4383d260-eb82-4422-b53a-a573a625a35f",
"status": "completed",
"summary": "整批文件的实际建议字节已核对,全部应用完成。",
"requiresVerification": false,
"attemptedAt": "2026-11-01T22:48:20.417Z",
"finishedAt": "2026-11-01T22:48:21.007Z",
"files": [
{
"path": "src/App.tsx",
"state": "after",
"appliedAt": "2026-11-01T22:48:20.532Z"
},
{
"path": "src/query.ts",
"state": "after",
"appliedAt": "2026-11-01T22:48:20.673Z"
},
{
"path": "src/summary.ts",
"state": "after",
"appliedAt": "2026-11-01T22:48:20.807Z"
},
{
"path": "src/transition.ts",
"state": "after",
"appliedAt": "2026-11-01T22:48:20.957Z"
}
]
},
{
"sessionId": "8ac6c104-a942-44e1-b096-131839a5b87c",
"id": "ef78c4f8-0fa2-44c1-8226-140060663353",
"status": "completed",
"summary": "整批文件的实际建议字节已核对,全部应用完成。",
"requiresVerification": false,
"attemptedAt": "2026-11-01T22:47:32.735Z",
"finishedAt": "2026-11-01T22:47:33.475Z",
"files": [
{
"path": "src/query.ts",
"state": "after",
"appliedAt": "2026-11-01T22:47:32.899Z"
},
{
"path": "src/summary.ts",
"state": "after",
"appliedAt": "2026-11-01T22:47:33.113Z"
},
{
"path": "src/transition.ts",
"state": "after",
"appliedAt": "2026-11-01T22:47:33.276Z"
},
{
"path": "src/App.tsx",
"state": "after",
"appliedAt": "2026-11-01T22:47:33.425Z"
}
]
}
],
"files": [
{
"path": "receipts/code-baseline.json",
"source": ".qa/embedded-browser-c-code-baseline.json",
"bytes": 80766,
"sha256": "f44c1819b34f4ffe3eb1bbcfcb316f16a24f0fd9e670d0f0492b0582abb1b94b"
},
{
"path": "receipts/independent-result.json",
"source": ".qa/embedded-browser-c-independent-result.json",
"bytes": 17804,
"sha256": "f605e59f95ceecb9fa154238fa25c17b08a6197448c7ea6fc737475b4886cba5"
},
{
"path": "receipts/source-original-result.json",
"source": ".qa/embedded-browser-c-source-original-result.json",
"bytes": 97922,
"sha256": "3ae3010a37e0e29b0414ad113a829252b647d994b00beaddeff7cd6a5b6bf1b1"
},
{
"path": "receipts/source-receipt.json",
"source": ".qa/embedded-browser-c-source-receipt.json",
"bytes": 450,
"sha256": "f692d23430bc15b7018a585363a7c916cc6003ddaaff774c17801978112b6fd0"
},
{
"path": "receipts/archives-original-result.json",
"source": ".qa/embedded-browser-c-archives-original-result.json",
"bytes": 932,
"sha256": "65f187b1e65fb8576adcbd4fc1439e703a3331b8845fb2595fc3be191e48c2b7"
},
{
"path": "receipts/source-short-path.json",
"source": ".qa/embedded-browser-c-source-short-path.json",
"bytes": 244,
"sha256": "0611970a1a36ae09a92bd507bf9b1dc21fc6de838487bcf89494bb769a2bd3c8"
},
{
"path": "receipts/orchestration-result.json",
"source": ".qa/embedded-browser-c-orchestration-result.json",
"bytes": 226,
"sha256": "43f43c17fdc747cbe4255d163841293d4df9563992bd7cb76c4df6b48906e083"
},
{
"path": "receipts/inherited-ui.json",
"source": ".qa/embedded-browser-c-inherited-ui.json",
"bytes": 823,
"sha256": "72f0915570cff15e0c9c8ca51f748752cbb2eb8993462fc13ae1111d709a0128"
},
{
"path": "receipts/vendor-runtime-binding.json",
"source": ".qa/embedded-browser-c-vendor-runtime-binding.json",
"bytes": 1049,
"sha256": "8d13297138695804a18d4b4910496e270e7e80d6c3eb9739fef97defe49cdd76"
},
{
"path": "receipts/vendor-runtime-initial-review.json",
"source": ".qa/embedded-browser-c-vendor-runtime-initial-review.json",
"bytes": 756,
"sha256": "bbcd9e401c819a6078c2c0d94a3f88f9bb420bbe9a85a97c2c5c030b8b8f6880"
},
{
"path": "receipts/b-git-evidence.json",
"source": ".qa/embedded-browser-c-b-git-evidence.json",
"bytes": 311,
"sha256": "df4b34eec3d9db548f1ef2a66b850019c3a5e1c33e6aca8d33e65b286df02e5b"
},
{
"path": "receipts/http-fix-result.json",
"source": ".qa/embedded-browser-c-http-fix-result.json",
"bytes": 288,
"sha256": "8e3ddb6664820f0c9ac08aa3f32bcbfd41a172206d9c72c0c276bba317d5a89e"
},
{
"path": "receipts/native-input-binding.json",
"source": ".qa/embedded-browser-c-native-input-binding.json",
"bytes": 911,
"sha256": "0f487ef41f4adc8d80c8e73d06a133949593837bcc4dc70b21cb2db80375e64a"
},
{
"path": "pipeline/independent-console.log",
"source": ".qa/embedded-browser-c-independent-console.log",
"bytes": 15623,
"sha256": "e4d327c0857f3afe8e770e56567001b85942e50acd7c30d38cc8e3cfbab48c76"
},
{
"path": "pipeline/source.log",
"source": ".qa/embedded-browser-c-source.log",
"bytes": 14115,
"sha256": "062ba1d9a0b343c3a5b5be846ffd84d890f4e35b6a11c115603e2347f81a6ab9"
},
{
"path": "pipeline/package.log",
"source": ".qa/embedded-browser-c-package.log",
"bytes": 2876,
"sha256": "e33717f29407f7dcf36dc543a3420c4ac122e0127f1c4b7bad8ccb63d97fd9d1"
},
{
"path": "pipeline/archives.log",
"source": ".qa/embedded-browser-c-archives.log",
"bytes": 815,
"sha256": "376236c4842c79c02f249f87af85fa335a1b826b9334e16e4b481aa9160e3706"
},
{
"path": "source/install.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\install.log",
"bytes": 27,
"sha256": "e952e1633d9e410f7ee0ce51cab04b2ff31d8a8dc54b79394d7ba92119b69521"
},
{
"path": "source/build.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\build.log",
"bytes": 1406,
"sha256": "6606f3afb8bd3ab68633455fefb59ece7fdcd04003b0fc186c58dde92e7da2cb"
},
{
"path": "source/rea.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\rea.log",
"bytes": 842,
"sha256": "627f4d19151fbcd90a691221ed080ce37ba1ffa628c467f041a833942ae61a8f"
},
{
"path": "source/engines.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\engines.log",
"bytes": 315,
"sha256": "1cb3f2e1046d4b26382c8aaa1ae2a31596c20ea39a669549830df14be17f1376"
},
{
"path": "source/browser.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\browser.log",
"bytes": 1170,
"sha256": "66878238274278a0fb6f5d3e38b2873eaa05069ef82b78f923f31708672ec1c0"
},
{
"path": "source/controlled-engine.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\controlled-engine.log",
"bytes": 826,
"sha256": "947f4cf90c0bab5079c294522c229aa7f50dc8887f1e5409c907f26e58b5d4f2"
},
{
"path": "source/companion-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\companion-ui.log",
"bytes": 787,
"sha256": "c229cfe7972e4243a077f56e573f3ea3c3491733feb55273c66537faddc9ed81"
},
{
"path": "source/model-protocols-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\model-protocols-ui.log",
"bytes": 696,
"sha256": "18f1f47e55ce927263cead8112f8b0406284d0ce0a588b942dcd8091c90b60b3"
},
{
"path": "source/vision-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\vision-ui.log",
"bytes": 599,
"sha256": "315bb2588fda225c178e77ec6df90767a87f7c5af3ebe7b89bf1a9550997eae0"
},
{
"path": "source/project-cache-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\project-cache-ui.log",
"bytes": 777,
"sha256": "09b8489f828facc300bc40916f1370b595a2fea094e6b4cfb9324ddf652a7122"
},
{
"path": "source/environment-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\environment-ui.log",
"bytes": 4853,
"sha256": "6e428b54eed4db92cedc3c9681df2e3f59b90cf11781a80a3b13e06d3310c4bc"
},
{
"path": "source/environment-engineering.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\environment-engineering.log",
"bytes": 782,
"sha256": "8a33c98dce469ab2263daf74f0015ef52d8bd3df9734a3822c714e791b71566d"
},
{
"path": "source/embedded-browser.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\embedded-browser.log",
"bytes": 1742,
"sha256": "c1c019c31a67552792edea04e869e4b2f746db90849c4b381553efa9900ff070"
},
{
"path": "source/tests-01.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-01.tap",
"bytes": 12448,
"sha256": "565b550606bb49532b7e72794dc772d11a9a4a6ac3199a4e760073830f1cc657"
},
{
"path": "source/tests-02.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-02.tap",
"bytes": 24302,
"sha256": "dbd0cc415f3f511c47990dab5f4fb525c60d3fb5f9db36ed23311927caade5cf"
},
{
"path": "source/tests-03.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-03.tap",
"bytes": 18544,
"sha256": "11fa799aa9005945b8f217b34fb14abc0d84688c4617e0ba89a2e7a14763d3f9"
},
{
"path": "source/tests-04.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-04.tap",
"bytes": 21928,
"sha256": "2b0881290084d1ab9dbb6135f2220df3f8d8f196d1827af7ce3d1b4235738cea"
},
{
"path": "source/tests-05.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-05.tap",
"bytes": 22375,
"sha256": "cd93467af5cf34825da059f67b23d08064247b12c19b3961939dd66cb79abae4"
},
{
"path": "source/tests-06.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-06.tap",
"bytes": 12964,
"sha256": "b76274f52c3bc8ab933c5fac201aff8f19f59938975048e9be528d3c99199d46"
},
{
"path": "source/tests-07.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-07.tap",
"bytes": 18854,
"sha256": "54bde42a3c65bba2093ae387139c4bd30cac0bdf959bb49e785a67f2a0084970"
},
{
"path": "source/tests-08.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-08.tap",
"bytes": 18239,
"sha256": "bd4004a84f45113759fba8aee271b89f03ace53bd9569af0588fe58b17a2f3c9"
},
{
"path": "source/tests-09.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-09.tap",
"bytes": 15649,
"sha256": "e13bf227a3ad5f88a0d9ca02e36bcdc4a18109b93190df658cdd2971b58fe81c"
},
{
"path": "source/tests-10.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-10.tap",
"bytes": 19399,
"sha256": "bf3b7a9e8646177ef0876eaaeab786bf27a5944633a9f530c19222c6b821dfe8"
},
{
"path": "source/tests-11.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\tests-11.tap",
"bytes": 884,
"sha256": "44af914ffb4419258ffaee40b7854c52e56f007717c9fd2b71f4ae1aa69e2447"
},
{
"path": "source/upgrade-tests.tap",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\upgrade-tests.tap",
"bytes": 713,
"sha256": "0df85724c0d62322bee42c2475d819cf5501dad32eb380336d42497759e7c2cf"
},
{
"path": "source/task-control-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\task-control-ui.log",
"bytes": 2283,
"sha256": "0d70fa67f6a9df920face4396c4792a77485ccdfda24a06ede49b8555fda54e6"
},
{
"path": "source/desktop-window.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\desktop-window.log",
"bytes": 443,
"sha256": "cee441de460c225f3f95d86edc53baa9bffc1c60b4d8756145138d28002cd2e1"
},
{
"path": "source/desktop-controlled-ui.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\desktop-controlled-ui.log",
"bytes": 1203,
"sha256": "859d2b384e31e138d05194bfab6036e87342ed611bc66417769c9ba931cc67db"
},
{
"path": "source/desktop-projects.log",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\desktop-projects.log",
"bytes": 11569,
"sha256": "2f77d8078fc28238a8e87ab7254a1431a2eb96d79185533678774d5b0c169ac8"
},
{
"path": "source/test-plan.json",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\package-validation-c68c7146-945f-4f7a-90ff-b860e6aa1360\\test-plan.json",
"bytes": 3733,
"sha256": "f5cda56cb4e941e427159b7c77c0d1f6c31e64bff4b3b7d0610c6992c7616b70"
},
{
"path": "desktop/result.json",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c/result.json",
"bytes": 1334336,
"sha256": "497edabe14cb97c1606377cc5e4309f846090282fe92492ef43e67a44ddd1a3d"
},
{
"path": "desktop/react-result.json",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c/react/result.json",
"bytes": 1360408,
"sha256": "3b089a6196c721a0ff2f28f0793b377827a183492694a08502aa2188bc91a24d"
},
{
"path": "desktop/react-failure.png",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c/react/react-desktop-failure.png",
"bytes": 260409,
"sha256": "ad92287941bdcc293bc25f5ed7bcf66244408db013d0dfd34b156961b5a690a4"
},
{
"path": "desktop/react-failure.html",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c/react/react-desktop-failure.html",
"bytes": 52457,
"sha256": "6f59a1c114649e020c3deae15f15d8848ca7ea5fe12fdcd4291963aa468a1f99"
},
{
"path": "desktop/react-failure.json",
"source": "D:\\AWQA22\\s-1fca8c0c\\.qa\\desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c/react/react-desktop-failure.json",
"bytes": 15665,
"sha256": "f4788c0ad63fda834e65beb2443d217332ba21ffbb942d722e979462a12555a7"
},
{
"path": "review/original-desktop-project-qa.mjs",
"source": "scripts/desktop-project-qa.mjs",
"bytes": 12345,
"sha256": "31c49f507b9e3768319837500707a76a297706e8e2c57358b35b5e625ca6c7a3"
},
{
"path": "review/original-source-verifier.mjs",
"source": "scripts/verify-source-package.mjs",
"bytes": 27853,
"sha256": "f760a628fb2968e3983476afb72f2bf5514bf096992777ad316c2abd43a216c0"
},
{
"path": "review/sealer.mjs",
"source": ".qa/seal-embedded-browser-c-rejected.mjs",
"bytes": 4959,
"sha256": "751869c392eb25dd0cec6a4d84ce033645fcd16bf7c5ddc0eee84bdb1d29fb37"
},
{
"path": "release.json",
"source": "releases/latest.json",
"bytes": 2875,
"sha256": "13885a687deca2f005f3cb0fed4196b296475c059efcb6718fec00a2bdf31adf"
},
{
"path": "portable-manifest.json",
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355\\MANIFEST.json",
"bytes": 4184945,
"sha256": "e5e863348681a900aaf30ecd3f79b4981c031693c415a02fe66750802d90af74"
},
{
"path": "source-manifest.json",
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355\\MANIFEST.json",
"bytes": 4246208,
"sha256": "078781e7d56396059894dd621dc42f4f0104e1fe35d5d092902d67bbcda9cb0f"
}
],
"unexecuted": [
"remaining desktop engineering cases",
"Responses/screenshot/cache/fixed evaluation engineering gates",
"portable acceptance",
"same-payload install",
"formal deployment"
],
"realModelRequests": 0,
"reason": "Original desktop React parent review timed out at the default Playwright matcher deadline. Retained failure DOM/PNG and original persisted sets show actual completed write results; source suite 683/683 remains a separate passing stage. Overall C stays failed. No formal phase executed."
}
@@ -0,0 +1 @@
{"success": true, "version": "1.22.0", "testedAt": "2026-11-01T22:01:14.619968+00:00", "archives": [{"kind": "portable", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355.zip", "files": 20902, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "741a016fc41a9d2413ba9ace3fa75c2b1d196f893ade92ae03cf87fe3bab3879"}, {"kind": "source", "path": "D:\\Ai-project\\REA\u9006\u5411\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355.zip", "files": 21267, "crcPassed": true, "manifestAndDirectoryMatch": true, "sha256": "7cf06e037d86637e15332512f16c5bbd37315e81d1c3dcb4cf298b53143e0fcb"}], "extractionRoot": "D:\\AWQA22\\source-check-900e3e229c914be89dd9879f7359da29\\Agent-Workbench-1.22.0-source-20261101215608355"}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,70 @@
{
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355",
"portable": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355.zip",
"bytes": 696779292,
"sha256": "741a016fc41a9d2413ba9ace3fa75c2b1d196f893ade92ae03cf87fe3bab3879"
},
"source": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355.zip",
"bytes": 697009125,
"sha256": "7cf06e037d86637e15332512f16c5bbd37315e81d1c3dcb4cf298b53143e0fcb"
},
"installer": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355-Setup.exe",
"bytes": 655093646,
"sha256": "4c2b969c09e7cf3e7182aa95e3a77bdd7b18865af01df17f82fc95e56efa28d2",
"compiler": {
"version": "6.3.1",
"sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf"
},
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-c57accc9-6844-4293-959d-7a981e7d129d\\installer.iss",
"version": "1.22.0",
"candidateDirectory": "Agent-Workbench-1.22.0-win-x64-20261101215608355",
"qaFixture": null
},
"desktopRuntime": {
"version": "45.2.0",
"sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab",
"bytes": 249810432,
"executable": "desktop/AgentWorkbench.exe",
"scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged."
},
"nativeLauncher": {
"bytes": 12288,
"sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463",
"inputs": {
"compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00",
"source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5",
"icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c"
},
"compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim."
},
"nodeVersion": "v24.22.1",
"reaRuntime": {
"version": "6.8.0",
"protocolVersion": "2025-03-26",
"packages": 149,
"files": 8413,
"bytes": 142395402,
"lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e"
},
"portableFiles": 20902,
"licenseTexts": 135,
"browserRuntime": {
"playwrightVersion": "1.64.1",
"packages": [
{
"name": "playwright",
"version": "1.64.1",
"files": 60
},
{
"name": "playwright-core",
"version": "1.64.1",
"files": 115
}
]
}
}
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,24 @@
{
"success": true,
"version": "1.22.0",
"testedAt": "2026-11-01T22:01:14.619968+00:00",
"archives": [
{
"kind": "portable",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355.zip",
"files": 20902,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "741a016fc41a9d2413ba9ace3fa75c2b1d196f893ade92ae03cf87fe3bab3879"
},
{
"kind": "source",
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355.zip",
"files": 21267,
"crcPassed": true,
"manifestAndDirectoryMatch": true,
"sha256": "7cf06e037d86637e15332512f16c5bbd37315e81d1c3dcb4cf298b53143e0fcb"
}
],
"extractionRoot": "D:\\AWQA22\\source-check-900e3e229c914be89dd9879f7359da29\\Agent-Workbench-1.22.0-source-20261101215608355"
}
@@ -0,0 +1,6 @@
{
"success": true,
"exactBlobs": 257,
"manifestSha256": "c7873d476b1b546e5498db98f91f8714ec13e0cdb9d008cc81e5cf1e1b929546",
"scope": "Every original rejected B evidence file and manifest is present in local Git with exact bytes, including ignored logs. Original source overall result remains failed."
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,12 @@
{
"success": true,
"exitCode": 0,
"args": [
"--test",
"--test-reporter=tap",
"tests/workers-http.test.mjs"
],
"log": ".qa/embedded-browser-c-http-fix.tap",
"logSha256": "4dcb806ba45b83d63ae47acfac119557ad02ce6c176fd0a91eab33aa7d26a477",
"realModelRequests": 0
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,15 @@
{
"success": true,
"sourceCommit": "324b7ab36d4836898f629b960f0f8922716eb0a2",
"inheritedSourceCommit": "50bcdbd0459ec9df3c4ec1fc33c2661b7fabfc66",
"changedInputs": [
".gitattributes",
"tests/workers-http.test.mjs"
],
"exactRuntimeFiles": 207,
"scripts": 33,
"groups": 250,
"originalResultSha256": "2676ac9448b823115de2b2937b062201f15e4fd0e764c74d34de76f11e0a1a58",
"rejectedManifestSha256": "c7873d476b1b546e5498db98f91f8714ec13e0cdb9d008cc81e5cf1e1b929546",
"scope": "Reuse the original B serial UI run after exact identity checks for every product/runtime/script/fixture/public/example input and four directly served reports. Only HTTP test synchronization and evidence Git attributes changed. The failed B source test is not inherited as passing; the new source suite must run in full."
}
@@ -0,0 +1,20 @@
{
"success": true,
"sourceCommit": "324b7ab36d4836898f629b960f0f8922716eb0a2",
"originalInputs": ".qa/embedded-browser-c84756dc-2f5a-4517-8ad0-accd26f68424/inputs.json",
"exactRuntimeFiles": 207,
"screenshots": [
{
"path": ".qa/embedded-browser-c84756dc-2f5a-4517-8ad0-accd26f68424/windows-native-desktop.jpg",
"bytes": 137674,
"sha256": "5909f5ba42bd9ea1c42264ddc18e6e633f9f93c7e6e7adbebeb09a5e44f758dc"
},
{
"path": ".qa/embedded-browser-c84756dc-2f5a-4517-8ad0-accd26f68424/windows-native-mobile.jpg",
"bytes": 54692,
"sha256": "13abaf0123e8917b3c84b471358445cd14fc72d9252a576dcd6ac4a0f621a385"
}
],
"differences": [],
"scope": "Bind already observed Windows native complete-window development screenshots to exact original source and compiled runtime bytes of the frozen release; verifier scripts and deployment remain separate checks."
}
@@ -0,0 +1,11 @@
{
"success": false,
"completed": [
{
"name": "independent",
"exitCode": 1,
"output": ".qa/embedded-browser-c-independent-console.log"
}
],
"requiresDiffReviewLocalCommitAndFinalAudit": true
}
File diff suppressed because one or more lines are too long
@@ -0,0 +1,13 @@
{
"name": "source",
"exitCode": 1,
"finishedAt": "2026-11-01T22:48:22.866Z",
"logPath": ".qa/embedded-browser-c-source.log",
"logBytes": 14115,
"logSha256": "062ba1d9a0b343c3a5b5be846ffd84d890f4e35b6a11c115603e2347f81a6ab9",
"evidence": {
"path": ".qa/source-package-validation.json",
"sha256": "3ae3010a37e0e29b0414ad113a829252b647d994b00beaddeff7cd6a5b6bf1b1"
},
"codeCommit": "324b7ab36d4836898f629b960f0f8922716eb0a2"
}
@@ -0,0 +1,5 @@
{
"from": "D:\\AWQA22\\source-check-900e3e229c914be89dd9879f7359da29\\Agent-Workbench-1.22.0-source-20261101215608355",
"to": "D:\\AWQA22\\s-1fca8c0c",
"reason": "Same-volume owned extraction; short Windows paths for source validation"
}
@@ -0,0 +1,17 @@
{
"success": true,
"files": 10778,
"bytes": 648400168,
"beforeManifestSha256": "0e7f9cb33359fcc9cb8bda0db7d6e3e4f5dcfc10a58f41ba29715eedeb3e4aae",
"afterManifestSha256": "e5e863348681a900aaf30ecd3f79b4981c031693c415a02fe66750802d90af74",
"exactFiles": 10777,
"onlyDescriptorDifference": {
"path": "runtime/REA-RUNTIME.json",
"field": "builtAt",
"before": "2026-11-01T21:08:04.148Z",
"after": "2026-11-01T21:56:06.679Z",
"beforeSha256": "be8c61439c0d21bbbfb96c76e4c80fa0173825f18c0fc2a7831ff627bbadf3eb",
"afterSha256": "dba54499c665b946550dc9402bce7d7ba59f1ecc99c18152bff020e2697b0fbe"
},
"scope": "B and C validated portable manifests declare identical runtime/vendor, compiled, script, asset, example, benchmark, research and license files except the exact builtAt timestamp bytes of the REA descriptor. All other descriptor bytes, including every dependency hash, are identical. This supplements input/UI binding, not B source failure. Changed milestone documents/evidence are outside the comparison."
}
@@ -0,0 +1,19 @@
{
"originalExactComparisonPassed": false,
"differences": [
{
"before": {
"path": "runtime/REA-RUNTIME.json",
"bytes": 1627668,
"sha256": "be8c61439c0d21bbbfb96c76e4c80fa0173825f18c0fc2a7831ff627bbadf3eb"
},
"after": {
"path": "runtime/REA-RUNTIME.json",
"bytes": 1627668,
"sha256": "dba54499c665b946550dc9402bce7d7ba59f1ecc99c18152bff020e2697b0fbe"
}
}
],
"originalVerifierSha256": "691ba6737be69acbd26e0ad7453a038e6c0188d9911ca03c572cf21588fd09d6",
"scope": "Additional verifier first rejected raw manifests because the REA descriptor differs. Original B source failure and C independent suite are unaffected. Narrow field analysis follows; no formal phase ran."
}
@@ -0,0 +1,70 @@
{
"portableRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355",
"sourceRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355",
"portable": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355.zip",
"bytes": 696779292,
"sha256": "741a016fc41a9d2413ba9ace3fa75c2b1d196f893ade92ae03cf87fe3bab3879"
},
"source": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-source-20261101215608355.zip",
"bytes": 697009125,
"sha256": "7cf06e037d86637e15332512f16c5bbd37315e81d1c3dcb4cf298b53143e0fcb"
},
"installer": {
"path": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\releases\\Agent-Workbench-1.22.0-win-x64-20261101215608355-Setup.exe",
"bytes": 655093646,
"sha256": "4c2b969c09e7cf3e7182aa95e3a77bdd7b18865af01df17f82fc95e56efa28d2",
"compiler": {
"version": "6.3.1",
"sha256": "3b22d36fc7e7c421d8caf780008ecdb42b14b3f0371b9bafe3cad64e6648d9cf"
},
"source": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\installer-build-c57accc9-6844-4293-959d-7a981e7d129d\\installer.iss",
"version": "1.22.0",
"candidateDirectory": "Agent-Workbench-1.22.0-win-x64-20261101215608355",
"qaFixture": null
},
"desktopRuntime": {
"version": "45.2.0",
"sha256": "010ea51bfb528c8143513439aa93fb40754403daa2023f9decd4517da71706ab",
"bytes": 249810432,
"executable": "desktop/AgentWorkbench.exe",
"scope": "Fixed original Windows Electron runtime, full license texts, isolated application loader and native bootstrap; original executable hash unchanged."
},
"nativeLauncher": {
"bytes": 12288,
"sha256": "e3d31cb7ce5009d3ca5a96d04dc16b1add0bd1f5cde7e1304461de6713d37463",
"inputs": {
"compiler": "46809206887326d2d24db1eff1f3064de972c3451abe766b49111450a5e08e00",
"source": "1c8e7d7ee5c383897bec48e9aadb8051b47c09686f74bbf34e0b6b695cd01ae5",
"icon": "f1879074e45f01c480ad9bf50b818637cc60ad56526056c886f808a4812d7b0c"
},
"compiler": "Windows .NET Framework C# compiler; source-bound cached original output, no deterministic-build claim."
},
"nodeVersion": "v24.22.1",
"reaRuntime": {
"version": "6.8.0",
"protocolVersion": "2025-03-26",
"packages": 149,
"files": 8413,
"bytes": 142395402,
"lockSha256": "687fb3fa3089a12f239dd5e87d9fa07df55a87df4935931d495a92600a1b0f6e"
},
"portableFiles": 20902,
"licenseTexts": 135,
"browserRuntime": {
"playwrightVersion": "1.64.1",
"packages": [
{
"name": "playwright",
"version": "1.64.1",
"files": 60
},
{
"name": "playwright-core",
"version": "1.64.1",
"files": 115
}
]
}
}
@@ -0,0 +1,130 @@
import assert from 'node:assert/strict';
import fs from 'node:fs';
import path from 'node:path';
import http from 'node:http';
import { randomUUID, createHash } from 'node:crypto';
import { _electron, expect } from 'playwright/test';
import { createRequestHandler, createSessionPublisher } from '../src/server/app.mjs';
import { hostAuthority } from '../src/core/desktop/host-authority.mjs';
import { desktopExecutableIdentity } from '../src/core/desktop/app-installation.mjs';
import { projectEnvironment } from '../src/core/process-environment.mjs';
const hash = bytes => createHash('sha256').update(bytes).digest('hex');
export async function desktopProjectQa({ store, provider, runtime, sample, kind }) {
const appRoot = path.resolve(process.env.AGENT_WORKBENCH_DESKTOP_QA_APP_ROOT || process.cwd()), server = http.createServer(), clients = new Set(), token = randomUUID();
runtime.appDirectory = appRoot; store.claimRuntime(); store.on('update', createSessionPublisher(clients));
server.on('request', createRequestHandler({ appDirectory: appRoot, server, store, provider, runtime, token, clients, started: Date.now(), getPort: () => server.address().port, shutdown: () => {} }));
await new Promise(resolve => server.listen(0, '127.0.0.1', resolve));
const authority = hostAuthority({ appDirectory: appRoot, server, store, provider, runtime }); authority.initialize();
let application, page, selected; const events = [], errors = [], screenshots = [];
async function launch() {
const executable = desktopExecutableIdentity(appRoot).path, packaged = executable.toLowerCase().endsWith('agentworkbench.exe');
application = await _electron.launch({ executablePath: executable,
args: [...(packaged ? [] : [path.join(appRoot, 'dist-desktop/main.cjs')]), '--app-root', appRoot, '--data-root', store.directory, '--node', process.execPath, '--port', String(server.address().port), '--hidden-window'],
cwd: appRoot, env: projectEnvironment(), timeout: 60000 });
page = await application.firstWindow(); page.on('pageerror', error => errors.push(error.message));
await page.locator('.connection.connected').waitFor({ timeout: 30000 });
if (selected) await select(selected);
}
async function select(session) {
selected = session;
const project = page.getByRole('combobox', { name: '当前项目', exact: true });
if (!await project.isVisible()) await page.getByRole('button', { name: '展开项目栏', exact: true }).click();
await project.selectOption(session.projectId);
await expect.poll(() => page.evaluate(() => localStorage.getItem('awb-session')), { timeout: 20000 }).toBe(session.id);
}
async function closeInspector() { const close = page.getByRole('button', { name: '关闭检视区', exact: true }); if (await close.isVisible().catch(() => false)) await close.click(); }
async function review(session, ids) {
await select(session); await closeInspector();
const prepared = [...store.core.change_set.values()].find(value => value.sessionId === session.id && value.status === 'prepared' && JSON.stringify(value.files.map(file => file.changeId).sort()) === JSON.stringify(ids.slice().sort()));
if (prepared) {
await page.getByRole('button', { name: '隔离协作', exact: true }).click();
await page.getByRole('button', { name: '打开父工程变更集审查', exact: true }).click();
await page.getByRole('button', { name: '审查变更集', exact: true }).click();
} else {
if (await page.getByRole('button', { name: '查看改动', exact: true }).isVisible()) await page.getByRole('button', { name: '查看改动', exact: true }).click();
else await page.locator('.inspector-tabs').getByRole('button', { name: /^改动/ }).click();
await page.getByRole('button', { name: '组合审查', exact: true }).click();
await page.getByRole('dialog', { name: '选择要一起审查的提案', exact: true }).getByRole('button', { name: '封存审查范围', exact: true }).click();
}
const dialog = page.getByRole('dialog', { name: '多文件变更集审查', exact: true });
const confirm = dialog.getByRole('button', { name: '确认应用全部 ' + ids.length + ' 项', exact: true }); await confirm.waitFor();
const matching = [...store.core.change_set.values()].filter(value => value.sessionId === session.id && value.status !== 'completed' && JSON.stringify(value.files.map(file => file.changeId).sort()) === JSON.stringify(ids.slice().sort()));
assert.equal(matching.length, 1); const set = matching[0];
await confirm.click(); await expect(dialog).toContainText('全部应用完成'); await page.keyboard.press('Escape');
assert.equal(set.status, 'completed'); events.push({ action: 'actual-desktop-file-review', taskId: session.taskId, changeSetId: set.id, fingerprint: set.fingerprint, paths: set.files.map(value => value.path) }); return set;
}
async function approve(session, approval) {
await select(session); await closeInspector();
const button = page.getByRole('button', { name: '确认执行', exact: true }); await button.waitFor({ timeout: 20000 });
assert.equal(session.approvals.filter(value => value.status === 'pending').length, 1); assert.equal(session.approvals.find(value => value.status === 'pending').id, approval.id);
await button.click(); await expect.poll(() => approval.status).toBe('approved'); events.push({ action: 'actual-desktop-original-approval', approvalId: approval.id, taskId: session.taskId });
}
async function cycle(session, label) {
await select(session); const identity = authority.identity(), eventSeq = session.eventSeq, taskId = session.taskId, runId = session.runId;
const originalEvents = () => {
const events = []; let cursor = 0;
while (cursor < eventSeq) {
const chunk = store.eventsAfter(cursor, { sessionId: session.id, limit: 500 });
events.push(...chunk.events.filter(value => value.seq <= eventSeq));
if (!chunk.hasMore || chunk.nextCursor >= eventSeq) break;
assert.ok(chunk.nextCursor > cursor); cursor = chunk.nextCursor;
}
return events;
};
const retainedEvents = originalEvents(); assert.equal(retainedEvents.at(-1).seq, eventSeq);
const completed = () => [...store.core.tool.values()].filter(value => value.sessionId === session.id && value.state === 'completed');
const prior = hash(Buffer.from(JSON.stringify(completed()))), approvals = session.approvals.map(value => ({ id: value.id, status: value.status }));
await application.close(); application = null;
assert.equal(runtime.isActive(session.id), true); assert.equal(authority.identity().instanceId, identity.instanceId); assert.equal(process.pid, identity.pid);
await launch(); assert.equal(session.taskId, taskId); assert.equal(session.runId, runId); assert.ok(session.eventSeq >= eventSeq); assert.deepEqual(originalEvents(), retainedEvents);
const replay = await page.evaluate(async ({ sessionId, cursor }) => {
const bootstrap = await (await fetch('/api/bootstrap')).json();
const response = await fetch('/api/events/history?session=' + encodeURIComponent(sessionId) + '&after=' + cursor + '&limit=500', { headers: { 'x-workbench-token': bootstrap.token } });
if (!response.ok) throw Error('Original desktop event replay failed (' + response.status + ')'); return response.json();
}, { sessionId: session.id, cursor: eventSeq - 1 });
assert.deepEqual(replay.events[0], retainedEvents.at(-1)); assert.ok(replay.events.every((value, index) => !index || value.seq > replay.events[index - 1].seq));
assert.equal(hash(Buffer.from(JSON.stringify(completed()))), prior); assert.deepEqual(session.approvals.map(value => ({ id: value.id, status: value.status })), approvals);
events.push({ action: label, hostPid: process.pid, taskId, runId, eventSeq, reopenedEventSeq: session.eventSeq, replayCursor: replay.nextCursor,
retainedEvents: retainedEvents.length, retainedEventsSha256: hash(Buffer.from(JSON.stringify(retainedEvents))), instanceId: identity.instanceId, completedToolSha256: prior, approvals });
}
async function capture(session, label) {
await select(session); await closeInspector(); await page.getByRole('button', { name: '隔离协作', exact: true }).click();
for (const width of [1440, 390]) {
const native = await application.browserWindow(page); await native.evaluate((value, width) => { value.showInactive(); value.setContentSize(width, 900); }, width);
await expect.poll(() => page.evaluate(() => innerWidth)).toBe(width);
const filename = path.join(sample, kind + '-' + label + '-' + width + '.png'); await page.screenshot({ path: filename }); fs.writeFileSync(filename + '.html', await page.content());
assert.equal(await page.evaluate(() => document.documentElement.scrollWidth > innerWidth), false); screenshots.push({ file: filename, width, sha256: hash(fs.readFileSync(filename)) });
}
await (await application.browserWindow(page)).evaluate(value => value.setContentSize(1440, 1000));
// Electron resize and React's responsive state settle independently.
// Await both before querying a control whose accessible name changes.
await expect.poll(() => page.evaluate(() => innerWidth)).toBe(1440);
await expect(page.getByRole('button', { name: '关闭检视区', exact: true })).toBeHidden();
await page.keyboard.press('Escape'); await expect(page.getByRole('dialog', { name: '隔离协作', exact: true })).toBeHidden();
await closeInspector();
}
await launch();
return { select, review, approve, cycle, capture, events, screenshots, errors, get page() { return page; },
async resize(width, height) { await (await application.browserWindow(page)).evaluate((value, size) => { value.showInactive(); value.setContentSize(size.width, size.height); }, { width, height }); await expect.poll(() => page.evaluate(() => innerWidth)).toBe(width); },
async download(filename, trigger) {
const id = randomUUID();
await application.evaluate(({ session }, { id, filename }) => {
globalThis.workbenchQaDownloads ??= {};
globalThis.workbenchQaDownloads[id] = { state: 'waiting' };
session.defaultSession.once('will-download', (_event, item) => {
const value = globalThis.workbenchQaDownloads[id]; value.suggestedFilename = item.getFilename(); value.state = 'started';
item.setSavePath(filename); // Actual Electron DownloadItem; only the owned destination selection is a QA fixture.
item.once('done', (_event, state) => { value.state = state; value.bytes = item.getReceivedBytes(); value.totalBytes = item.getTotalBytes(); });
});
}, { id, filename });
await trigger(); await expect.poll(() => application.evaluate((_electron, id) => globalThis.workbenchQaDownloads[id].state, id), { timeout: 30000 }).toBe('completed');
const value = await application.evaluate((_electron, id) => globalThis.workbenchQaDownloads[id], id);
assert.equal(value.bytes, value.totalBytes); assert.equal(fs.statSync(filename).size, value.bytes);
events.push({ action: 'actual-electron-native-download', ...value, file: filename, sha256: hash(fs.readFileSync(filename)), scope: 'Actual DownloadItem and transferred bytes; own output path chosen by QA without exercising the Windows save dialog.' });
return value;
},
scope: 'Real Electron renderer and fixed native main/preload; own in-process Node fixture host, actual native Harness/HTTP/check/Git. The whole fixture host is never exited from its desktop UI.',
async failure(error) { if (!page || page.isClosed()) return; const filename = path.join(sample, kind + '-desktop-failure'); fs.writeFileSync(filename + '.html', await page.content()); fs.writeFileSync(filename + '.json', JSON.stringify({ error: error.stack, dialogs: await page.getByRole('dialog').allTextContents(), errors, events }, null, 2)); await (await application.browserWindow(page)).evaluate(value => value.showInactive()); await page.screenshot({ path: filename + '.png' }); },
async close() { await application?.close(); for (const response of clients) response.destroy(); server.closeAllConnections(); await new Promise(resolve => server.close(resolve)); assert.deepEqual(errors, []); } };
}
@@ -0,0 +1,293 @@
import fs from 'node:fs';
import path from 'node:path';
import assert from 'node:assert/strict';
import { createHash, randomUUID } from 'node:crypto';
import { spawn, execFileSync } from 'node:child_process';
if (process.argv.includes('--help')) { console.log('node scripts/verify-source-package.mjs [--native-engines] - validate independently extracted source after verify-archives.py --extract-source; set the absolute QA Python and archive root.'); process.exit(0); }
if (process.argv.slice(2).some(value => value !== '--native-engines')) throw new Error('Unsupported argument; use --help.');
const workspace = process.cwd();
const evidence = JSON.parse(fs.readFileSync('.qa/archives-validation.json', 'utf8'));
assert.equal(evidence.success, true);
assert.ok(evidence.extractionRoot, 'Run python scripts/verify-archives.py --extract-source first.');
const sourceRoot = fs.realpathSync.native(evidence.extractionRoot);
const archiveQaRoot = path.resolve(process.env.AGENT_WORKBENCH_ARCHIVE_QA_ROOT || '.qa');
assert.ok(sourceRoot.startsWith(archiveQaRoot + path.sep));
const npmCli = path.join(path.dirname(process.execPath), 'node_modules/npm/bin/npm-cli.js');
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', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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)));
const inheritedPath = Object.entries(env).find(([key]) => key.toLowerCase() === 'path')?.[1] || '';
for (const key of Object.keys(env)) if (key.toLowerCase() === 'path') delete env[key];
env.PATH = [path.dirname(process.execPath), inheritedPath].filter(Boolean).join(path.delimiter);
const directory = path.join(sourceRoot, '.qa', 'package-validation-' + randomUUID());
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', ...(['1.16.0', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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;
const resultFile = path.join(workspace, '.qa/source-package-validation.json');
const logs = [];
function save(result) {
fs.writeFileSync(path.join(directory, 'result.json'), JSON.stringify(result, null, 2));
fs.writeFileSync(resultFile, JSON.stringify(result, null, 2));
}
function run(args, logName) {
console.log('Source package: ' + stage);
return new Promise((resolve, reject) => {
const logPath = path.join(directory, logName);
const outputFile = fs.createWriteStream(logPath);
const child = spawn(process.execPath, args, { cwd: sourceRoot, env, windowsHide: true, stdio: ['ignore', 'pipe', 'pipe'] });
let tail = '', timedOut = false;
const capture = bytes => { outputFile.write(bytes); tail = (tail + bytes.toString('utf8')).slice(-12000); };
child.stdout.on('data', capture); child.stderr.on('data', capture);
const timer = setTimeout(() => {
timedOut = true;
if (process.platform === 'win32' && child.pid) {
try { execFileSync('taskkill.exe', ['/PID', String(child.pid), '/T', '/F'], { windowsHide: true, timeout: 10000, stdio: 'ignore' }); } catch { child.kill(); }
} else child.kill();
}, 30 * 60 * 1000);
child.once('error', error => { clearTimeout(timer); outputFile.end(); reject(error); });
child.once('close', code => { clearTimeout(timer); outputFile.end(() => {
logs.push({ stage, path: logPath, sha256: digest(logPath), bytes: fs.statSync(logPath).size });
code === 0 && !timedOut ? resolve(tail) : reject(new Error(stage + (timedOut ? ' timed out after 30 minutes' : ' failed (' + code + ')') + ': ' + tail));
}); });
});
}
try {
assert.equal(JSON.parse(fs.readFileSync(path.join(sourceRoot, 'package.json'), 'utf8')).version, evidence.version);
assert.match(process.version, /^v24\./, 'Source package validation requires Node.js 24.');
if (env.AGENT_WORKBENCH_TEST_PYTHON) {
assert.ok(path.isAbsolute(env.AGENT_WORKBENCH_TEST_PYTHON) && fs.existsSync(env.AGENT_WORKBENCH_TEST_PYTHON), 'AGENT_WORKBENCH_TEST_PYTHON must name an existing absolute QA interpreter.');
const executable = fs.realpathSync.native(env.AGENT_WORKBENCH_TEST_PYTHON);
python = JSON.parse(execFileSync(executable, ['-I', '-c', 'import json,sys,pytest; print(json.dumps({"version":sys.version.split()[0],"pytest":pytest.__version__}))'], { env, windowsHide: true, encoding: 'utf8', timeout: 10000 }));
assert.ok(Number(python.version.split('.')[0]) === 3 && Number(python.version.split('.')[1]) >= 10, 'QA Python must be 3.10 or newer.');
assert.equal(python.pytest, '8.4.2', 'Install the fixed QA requirements before validating the source package.');
python.path = executable; env.AGENT_WORKBENCH_TEST_PYTHON = executable;
}
console.log(JSON.stringify({ sourceRoot, directory, nodeVersion: process.version, python }));
stage = 'install';
await run([npmCli, 'ci', '--offline', '--ignore-scripts', '--no-audit', '--no-fund'], 'install.log');
stage = 'build'; await run([npmCli, 'run', 'build'], 'build.log');
const actualFiles = buildFolders.flatMap(folder => files(path.join(sourceRoot, folder)).map(relative => path.join(folder, relative)));
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', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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));
assert.equal(actualRea.success, true); assert.equal(actualRea.version, evidence.version); assert.equal(actualRea.results.length, 3);
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', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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));
assert.equal(actualEngine.success, true); assert.equal(actualEngine.version, evidence.version);
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', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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));
assert.equal(actualBrowser.success, true); assert.equal(actualBrowser.version, evidence.version);
assert.equal(actualBrowser.rootExited, true); assert.equal(actualBrowser.results.length, 2);
assert.ok(actualBrowser.results.every(value => value.status === 'passed' && value.browserExited));
assert.equal(actualBrowser.modelRequests, 0);
}
let actualControlled = null;
if (['1.14.0', '1.15.0', '1.16.0', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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));
assert.equal(actualControlled.success, true); assert.equal(actualControlled.version, evidence.version); assert.equal(actualControlled.rootExited, true);
assert.equal(actualControlled.realModelRequests, 0); assert.equal(actualControlled.cases, 4); assert.ok(actualControlled.fixtureModelRequests > 0);
}
let actualCompanion = null;
if (['1.16.0', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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();
assert.ok(location && path.resolve(location).startsWith(path.join(sourceRoot, '.qa') + path.sep));
actualCompanion = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualCompanion.success, true); assert.equal(actualCompanion.version, evidence.version);
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 (['1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
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?$/gm)].at(-1)?.[1]?.trim();
assert.ok(location && path.resolve(location).startsWith(path.join(sourceRoot, '.qa') + path.sep));
actualProtocols = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualProtocols.success, true); assert.equal(actualProtocols.version, evidence.version);
assert.equal(fs.realpathSync.native(actualProtocols.appRoot), sourceRoot); assert.equal(actualProtocols.containedRuntime, true);
assert.equal(actualProtocols.passed.length, 5); assert.deepEqual(actualProtocols.pageErrors, []); assert.deepEqual(actualProtocols.requestFailures, []);
}
let actualVision = null;
if (['1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'contained screenshot inputs and exact Task budget resume';
const output = await run(['scripts/verify-vision-ui.mjs', '--app-root', sourceRoot], 'vision-ui.log');
const location = [...output.matchAll(/^EVIDENCE (.+)\r?$/gm)].at(-1)?.[1]?.trim();
assert.ok(location && path.resolve(location).startsWith(path.join(sourceRoot, '.qa') + path.sep));
actualVision = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualVision.success, true); assert.equal(actualVision.version, evidence.version);
assert.equal(fs.realpathSync.native(actualVision.appRoot), sourceRoot); assert.equal(actualVision.containedRuntime, true);
assert.equal(actualVision.passed.length, 5); assert.deepEqual(actualVision.pageErrors, []); assert.equal(actualVision.realModelRequests, 0);
}
let actualProjectCache = null;
if (['1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'contained source-verified parsing cache controls';
const output = await run(['scripts/verify-project-cache-ui.mjs', '--app-root', sourceRoot], 'project-cache-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));
actualProjectCache = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualProjectCache.success, true); assert.equal(actualProjectCache.version, evidence.version);
assert.equal(fs.realpathSync.native(actualProjectCache.appRoot), sourceRoot); assert.equal(actualProjectCache.passed.length, 7);
assert.equal(actualProjectCache.realModelRequests, 0); assert.deepEqual(actualProjectCache.pageErrors, []);
}
let actualEnvironment = null, actualEnvironmentEngineering = null;
if (['1.21.0','1.22.0'].includes(evidence.version)) {
stage = 'contained environment approval, stop and recovery UI';
const output = await run(['scripts/verify-environment-ui.mjs', '--app-root', sourceRoot], 'environment-ui.log');
const summary = JSON.parse(output.trim().split(/\r?\n/).findLast(line => line.startsWith('{"success":')));
const relative = path.relative(path.join(sourceRoot, '.qa'), summary.directory);
assert.ok(relative && !relative.startsWith('..') && !path.isAbsolute(relative));
actualEnvironment = JSON.parse(fs.readFileSync(path.join(summary.directory, 'result.json'), 'utf8'));
assert.equal(actualEnvironment.success, true); assert.equal(actualEnvironment.appRoot, sourceRoot);
assert.equal(actualEnvironment.version, evidence.version); assert.equal(actualEnvironment.checks.length, 7);
assert.deepEqual(actualEnvironment.pageErrors, []); assert.deepEqual(actualEnvironment.failures, []); assert.equal(actualEnvironment.realModelRequests, 0);
stage = 'real locked React dependency preparation and Python engineering';
const engineeringOutput = await run(['scripts/verify-environment-projects.mjs'], 'environment-engineering.log');
actualEnvironmentEngineering = JSON.parse(engineeringOutput.trim().split(/\r?\n/).findLast(line => line.startsWith('{"success":')));
assert.equal(actualEnvironmentEngineering.success, true); assert.equal(actualEnvironmentEngineering.reactOriginal, 'failed');
assert.equal(actualEnvironmentEngineering.reactCandidate, 'passed'); assert.equal(actualEnvironmentEngineering.reactTests, 9);
assert.equal(actualEnvironmentEngineering.pythonTests, 2); assert.equal(actualEnvironmentEngineering.realModelRequests, 0);
}
let actualEmbeddedBrowser = null;
if (evidence.version === '1.22.0') {
stage = 'actual embedded Electron, Vite and original mobile observation';
await run(['scripts/verify-embedded-browser.mjs', '--app-root', sourceRoot], 'embedded-browser.log');
actualEmbeddedBrowser = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/embedded-browser-latest.json'), 'utf8'));
assert.equal(actualEmbeddedBrowser.success, true); assert.equal(actualEmbeddedBrowser.version, evidence.version);
assert.equal(fs.realpathSync.native(actualEmbeddedBrowser.appRoot), sourceRoot); assert.equal(actualEmbeddedBrowser.checks.length, 17);
assert.equal(fs.realpathSync.native(actualEmbeddedBrowser.nodePath), path.join(sourceRoot, 'runtime', 'node.exe'));
assert.equal(actualEmbeddedBrowser.realModelRequests, 0); assert.deepEqual(actualEmbeddedBrowser.errors, []);
}
// Only this file opens the fixed inspector port. Run it separately so another
// test's child host can never compete for that port during the full suite.
const testFiles = files(path.join(sourceRoot, 'tests')).filter(file => !file.includes(path.sep) && file.endsWith('.test.mjs'));
const ordinaryTests = testFiles.filter(file => file !== 'upgrade.test.mjs');
const testGroups = [];
// Keep the per-process deadline, while letting the growing suite complete in
// bounded batches. A slow worker recovery file must not consume the deadline
// of every preceding, unrelated file. Every discovered file runs exactly once.
for (let offset = 0; offset < ordinaryTests.length; offset += 8) testGroups.push(ordinaryTests.slice(offset, offset + 8));
testGroups.push(['upgrade.test.mjs']);
assert.deepEqual(testGroups.flat().slice().sort(), testFiles.slice().sort());
assert.equal(new Set(testGroups.flat()).size, testFiles.length);
const testPlan = testGroups.map((group, index) => ({ index, files: group, concurrency: index === testGroups.length - 1 ? 1 : 2, timeoutMs: 30 * 60 * 1000 }));
fs.writeFileSync(path.join(directory, 'test-plan.json'), JSON.stringify(testPlan, null, 2));
const stats = Object.fromEntries(['tests', 'pass', 'fail', 'cancelled', 'skipped', 'todo'].map(key => [key, 0]));
for (const [index, group] of testGroups.entries()) {
assert.ok(group.length > 0);
const exclusiveUpgrade = index === testGroups.length - 1;
stage = exclusiveUpgrade ? 'exclusive retained upgrade tests' : 'full source tests batch ' + (index + 1) + '/' + (testGroups.length - 1);
const logName = exclusiveUpgrade ? 'upgrade-tests.tap' : 'tests-' + String(index + 1).padStart(2, '0') + '.tap';
const output = await run(['--test', '--test-concurrency=' + testPlan[index].concurrency, '--test-reporter=tap', ...group.map(file => path.join('tests', file))], logName);
const groupStats = Object.fromEntries([...output.matchAll(/^# (tests|pass|fail|cancelled|skipped|todo) (\d+)\s*$/gm)].map(match => [match[1], Number(match[2])]));
assert.ok(groupStats.tests > 0); assert.equal(groupStats.pass, groupStats.tests);
for (const key of Object.keys(stats)) { assert.ok(Number.isInteger(groupStats[key])); stats[key] += groupStats[key]; }
for (const key of ['fail', 'cancelled', 'skipped', 'todo']) assert.equal(groupStats[key], 0);
}
let actualTaskControl = null;
if (['1.20.1', '1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'task control desktop and 390px';
await run(['scripts/verify-task-control-ui.mjs', '--app-root', sourceRoot], 'task-control-ui.log');
actualTaskControl = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/task-control-ui-validation.json'), 'utf8'));
assert.equal(actualTaskControl.success, true); assert.equal(actualTaskControl.passed.length, 5); assert.equal(actualTaskControl.realModelRequests, 0);
}
let actualDesktop = null;
if (['1.15.0', '1.16.0', '1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].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);
stage = 'actual contained Electron engine UI'; await run(['scripts/verify-controlled-ui.mjs', '--desktop'], 'desktop-controlled-ui.log');
const uiLocation = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/desktop-controlled-ui-location.json'), 'utf8'));
const ui = JSON.parse(fs.readFileSync(uiLocation.result, 'utf8')); assert.equal(ui.passed, true); assert.equal(ui.testedVersion, evidence.version); assert.equal(ui.assertions.length, 9);
stage = 'actual contained Electron engineering projects'; await run(['scripts/verify-controlled-projects.mjs', '--desktop'], 'desktop-projects.log');
const projectLocation = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/desktop-projects-location.json'), 'utf8'));
const projects = JSON.parse(fs.readFileSync(projectLocation.result, 'utf8')); assert.equal(projects.success, true); assert.equal(projects.testedVersion, evidence.version); assert.equal(projects.cases.length, 16);
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 (['1.17.0', '1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
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]);
}
let actualVisionEngineering = null;
if (['1.18.0', '1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'screenshot Task Node React Python engineering';
await run(['scripts/verify-vision-projects.mjs'], 'vision-engineering.log');
const location = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/vision-engineering-location.json'), 'utf8'));
actualVisionEngineering = JSON.parse(fs.readFileSync(location.result, 'utf8'));
assert.equal(actualVisionEngineering.success, true); assert.equal(actualVisionEngineering.version, evidence.version);
assert.equal(actualVisionEngineering.realModelRequests, 0);
assert.deepEqual(actualVisionEngineering.results.map(value => value.check.results[0].tests.passed), [8, 9, 10]);
}
let actualCacheEngineering = null;
if (['1.19.0', '1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'cached index original requests and Node React Python engineering';
await run(['scripts/verify-project-cache-projects.mjs'], 'project-cache-engineering.log');
const location = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/project-cache-engineering-location.json'), 'utf8'));
actualCacheEngineering = JSON.parse(fs.readFileSync(location.result, 'utf8'));
assert.equal(actualCacheEngineering.success, true); assert.equal(actualCacheEngineering.version, evidence.version);
assert.equal(actualCacheEngineering.realModelRequests, 0); assert.equal(actualCacheEngineering.cases.length, 9);
assert.deepEqual(actualCacheEngineering.results.map(value => value.check.results[0].tests.passed), [8, 9, 10]);
}
let actualEvaluations = null, actualEvaluationEngineering = null;
if (['1.20.0', '1.20.1','1.21.0', '1.22.0'].includes(evidence.version)) {
stage = 'compiled fixed engineering evaluations';
const output = await run(['scripts/verify-evaluations-release.mjs', '--app-root', sourceRoot], 'evaluations-release.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));
actualEvaluations = JSON.parse(fs.readFileSync(path.join(location, 'result.json'), 'utf8'));
assert.equal(actualEvaluations.success, true); assert.equal(actualEvaluations.version, evidence.version);
assert.equal(fs.realpathSync.native(actualEvaluations.appRoot), sourceRoot); assert.equal(actualEvaluations.containedRuntime, true);
assert.equal(actualEvaluations.assertions.length, 5); assert.equal(actualEvaluations.realModelRequests, 0); assert.deepEqual(actualEvaluations.pageErrors, []);
stage = 'fixed Node React Python and source-bound module engineering';
await run(['scripts/verify-evaluations-projects.mjs'], 'evaluations-engineering.log');
const engineeringLocation = JSON.parse(fs.readFileSync(path.join(sourceRoot, '.qa/engineering-evals-projects-location.json'), 'utf8'));
actualEvaluationEngineering = JSON.parse(fs.readFileSync(engineeringLocation.result, 'utf8'));
assert.equal(actualEvaluationEngineering.success, true); assert.equal(actualEvaluationEngineering.version, evidence.version);
assert.equal(actualEvaluationEngineering.assertions.length, 14); assert.equal(actualEvaluationEngineering.realModelRequests, 0);
assert.deepEqual(actualEvaluationEngineering.results.map(row => row.parentCheck.results[0].tests.passed), [8, 9, 10, 9]);
}
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, testPlan, actualEmbeddedBrowser, actualEnvironment, actualEnvironmentEngineering, actualTaskControl, actualRea, actualEngine, actualBrowser, actualControlled, actualDesktop, actualCompanion, actualProtocols, actualProtocolEngineering, actualVision, actualVisionEngineering, actualProjectCache, actualCacheEngineering, actualEvaluations, actualEvaluationEngineering, 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 });
throw error;
}
@@ -0,0 +1,41 @@
import fs from 'node:fs';
import path from 'node:path';
import assert from 'node:assert/strict';
import { createHash } from 'node:crypto';
const read = file => JSON.parse(fs.readFileSync(file)), hash = bytes => createHash('sha256').update(bytes).digest('hex');
const prefix = '.qa/embedded-browser-c-', root = 'docs/embedded-browser-c-rejected-candidate-evidence';
const source = read(prefix + 'source-original-result.json'), independent = read(prefix + 'independent-result.json');
assert.equal(source.success, false); assert.equal(independent.success, false);
assert.equal(source.stage, 'actual contained Electron engineering projects'); assert.equal(fs.existsSync(root), false);
const files = [], pending = [];
function copy(file, target) {
assert.ok(!/\.sqlite(?:-|$)/i.test(file)); const bytes = fs.readFileSync(file);
files.push({ path: target, source: file, bytes: bytes.length, sha256: hash(bytes) }); pending.push({ target: path.join(root, target), bytes });
}
for (const name of ['code-baseline','independent-result','source-original-result','source-receipt','archives-original-result','source-short-path','orchestration-result','inherited-ui','vendor-runtime-binding','vendor-runtime-initial-review','b-git-evidence','http-fix-result','native-input-binding']) copy(prefix + name + '.json','receipts/' + name + '.json');
for (const name of ['independent-console','source','package','archives']) copy(prefix + name + '.log','pipeline/' + name + '.log');
for (const row of source.logs) { assert.equal(hash(fs.readFileSync(row.path)), row.sha256); copy(row.path,'source/' + path.basename(row.path)); }
copy(path.join(source.directory,'test-plan.json'),'source/test-plan.json');
const desktopRoot = path.join(source.sourceRoot,'.qa/desktop-projects-d512f711-bda4-42e0-b29b-193608b73d8c');
copy(desktopRoot + '/result.json','desktop/result.json'); copy(desktopRoot + '/react/result.json','desktop/react-result.json');
for (const ext of ['png','html','json']) copy(desktopRoot + '/react/react-desktop-failure.' + ext,'desktop/react-failure.' + ext);
copy('scripts/desktop-project-qa.mjs','review/original-desktop-project-qa.mjs');
copy('scripts/verify-source-package.mjs','review/original-source-verifier.mjs');
copy('.qa/seal-embedded-browser-c-rejected.mjs','review/sealer.mjs');
const sessions = fs.readdirSync(desktopRoot + '/react').filter(name => /^session-.*\.json$/.test(name)).map(name => read(desktopRoot + '/react/' + name));
const sets = sessions.flatMap(value => (value.execution.changeSets ?? []).map(set => ({ sessionId: value.session.id, id: set.id, status: set.status, summary: set.summary, requiresVerification: set.requiresVerification, attemptedAt: set.attemptedAt, finishedAt: set.finishedAt, files: set.files.map(file => ({ path: file.path, state: file.state, appliedAt: file.appliedAt })) })));
assert.equal(sets.length, 2); assert.ok(sets.every(set => set.status === 'completed' && !set.requiresVerification));
const testRows = source.logs.filter(row => /(?:tests-\d+|upgrade-tests)\.tap$/.test(row.path)).map(row => {
const text = fs.readFileSync(row.path,'utf8');
return Object.fromEntries(['tests','pass','fail','cancelled','skipped','todo'].map(key => [key,Number(text.match(new RegExp('^# '+key+' (\\d+)\\s*$','m'))?.[1])]));
});
const tests = Object.fromEntries(['tests','pass','fail','cancelled','skipped','todo'].map(key => [key,testRows.reduce((sum,row) => sum + row[key],0)]));
assert.deepEqual(tests,{ tests:683,pass:683,fail:0,cancelled:0,skipped:0,todo:0 });
const release = read('releases/latest.json'); assert.equal(path.basename(release.portableRoot),'Agent-Workbench-1.22.0-win-x64-20261101215608355');
copy('releases/latest.json','release.json'); copy(path.join(release.portableRoot,'MANIFEST.json'),'portable-manifest.json'); copy(path.join(release.sourceRoot,'MANIFEST.json'),'source-manifest.json');
const manifest = { schemaVersion:1,version:'1.22.0',kind:'rejected-candidate-C',sourceCommit:independent.codeCommit,sourceOverallSuccess:false,tests,sets,files,
unexecuted:['remaining desktop engineering cases','Responses/screenshot/cache/fixed evaluation engineering gates','portable acceptance','same-payload install','formal deployment'],
realModelRequests:0,reason:'Original desktop React parent review timed out at the default Playwright matcher deadline. Retained failure DOM/PNG and original persisted sets show actual completed write results; source suite 683/683 remains a separate passing stage. Overall C stays failed. No formal phase executed.' };
fs.mkdirSync(root); for (const item of pending) { fs.mkdirSync(path.dirname(item.target),{recursive:true}); fs.writeFileSync(item.target,item.bytes,{flag:'wx'}); }
fs.writeFileSync(root+'/manifest.json',JSON.stringify(manifest,null,2)+'\n',{flag:'wx'});
console.log(JSON.stringify({success:true,files:files.length,tests,sets:sets.map(set => ({status:set.status,writeDurationMs:Date.parse(set.finishedAt)-Date.parse(set.attemptedAt)}))}));
File diff suppressed because it is too large Load Diff
@@ -0,0 +1 @@
{"success":true,"version":"1.22.0","directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\browser-native-3b591915-e673-4ce7-ac22-80ce27cb8182","results":[{"jobId":"5551b6e3-08fd-4ca2-a14b-33f3ae841157","taskId":"47fc0172-3f71-4d2b-8664-69b1ecf3063f","viewport":{"width":1280,"height":900},"status":"passed","assertions":{"total":3,"passed":3,"failed":0},"resultSha256":"8dd43544d68e7a6e0ee439283ab2587ebe801a4123a045f84b4b0a687bb1671b","buildSha256":"1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd","screenshotSha256":"a0b9187034642bb65372f74db669b60f07c0888d7ce86deb60a4a202b505ca54","browserExited":true,"reusedOriginalJob":true},{"jobId":"ad55ddae-40a5-4d1c-aff0-0845aa8e4558","taskId":"47fc0172-3f71-4d2b-8664-69b1ecf3063f","viewport":{"width":390,"height":844},"status":"passed","assertions":{"total":3,"passed":3,"failed":0},"resultSha256":"44cb9ac98c5cc6b1025ced39246d34cd5bd7df08952d4289d953c6e18ec5f3ac","buildSha256":"1128c86f9108e72bc1ada18b7c48c9f865283f46d5e530b99caa04d7507f46cd","screenshotSha256":"590ef1090d857bc7a7eb30ed790f918d76ebabe4d53b54b82948de4db20cfb4f","browserExited":true,"reusedOriginalJob":true}],"modelRequests":0,"rootExited":true}
@@ -0,0 +1,20 @@
> local-agent-workbench@1.22.0 build
> tsc --noEmit && vite build && node scripts/build-mobile.mjs && node scripts/build-server.mjs
vite v7.3.7 building client environment for production...
transforming...
✓ 1743 modules transformed.
rendering chunks...
computing gzip size...
dist-client/.vite/manifest.json  0.55 kB │ gzip: 0.22 kB
dist-client/index.html  0.58 kB │ gzip: 0.39 kB
dist-client/mobile.html  0.82 kB │ gzip: 0.46 kB
dist-client/assets/mobile-CNDnI_ru.css  11.92 kB │ gzip: 3.12 kB
dist-client/assets/desktop-vcA-TXgD.css 157.84 kB │ gzip: 29.95 kB
dist-client/assets/mobile-BewIZSK_.js  26.14 kB │ gzip: 9.09 kB
dist-client/assets/x-BnWsFXbN.js 225.51 kB │ gzip: 70.77 kB
dist-client/assets/desktop-CwBApaLz.js 368.20 kB │ gzip: 104.10 kB
✓ built in 1.16s
Mobile shell built: 3 allowed assets; API and project data are never cached.
Server bundle built.
@@ -0,0 +1,8 @@
PASS desktop explicitly enables HTTPS and downloads the actual public CA without changing OS trust
PASS 390px real gateway pairing clears fragment, displays scoped task list and registers the same device in desktop
PASS phone UI confirms original Task/Run approval and the existing Runtime executes one command
PASS original paginated diff and counted check/report display verified content from the same Task
PASS disconnect and refresh recover from persistent seq without submitting a new command or Run
PASS PWA service worker stores the shell and no API/project response
PASS desktop revocation removes mobile project content immediately on the next read while preserving the original completed tool
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\companion-ui-def22f3b-0b0b-41c7-b094-84dcba61b65d
@@ -0,0 +1,6 @@
PASS compiled host seals actual Harness/source identities and prepares one owned worktree while retaining parent bytes and staging
PASS compiled native execution retains failing tests, requires original check approvals, seals literal prompt/model/receipts/results and accounts each owned HTTP request once
PASS compiled parent review and immutable merge pass the original 8 functional tests and actual ESM build
PASS compiled Git delivery contains only reviewed modules, preserves staged/unstaged/untracked owner bytes and completes the parent with sealed original evidence
EVIDENCE C:\Users\wangy\AppData\Local\Temp\awb-controlled-iT2baN
{"success":true,"version":"1.22.0","directory":"C:\\Users\\wangy\\AppData\\Local\\Temp\\awb-controlled-iT2baN","cases":4,"rootExited":true,"fixtureModelRequests":7,"realModelRequests":0}
@@ -0,0 +1,10 @@
PASS desktop engine selector rejects a missing source, pins the actual installation and seals one original scope without model calls
PASS actual Harness runs the owned bridge and returns reviewable proposals after confirmed process-tree closure
PASS 390px keeps the real single-engine scope, header and a single-line 42px refresh action without horizontal overflow
PASS mobile child run view shows actual counts and closure, pages original inputs and downloads the exact original report bytes
PASS closing a run view ignores an old delayed record failure and keeps the selected task unchanged
PASS explicit child file review and check approval create a new native Run, retain previous evidence and account actual model requests once
PASS parent collection reads the original controlled-worker proof and explicit retention preserves every owner byte
PASS actual native stop closes the owned process tree, preserves one unknown model attempt and dispatches no late tool
PASS 390px recovery requires reading the owned observation before explicit review and preserves original outcome/report and cumulative budget
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\desktop-controlled-ui-ff68b469-3054-40b6-b5ea-15d4508fd562
File diff suppressed because one or more lines are too long
@@ -0,0 +1,7 @@
actual Electron process registered and original host reused: passed
sandboxed renderer and fixed preload: passed
external navigation, requests and popups rejected: passed
offline original task and approval retained across refresh and window close: passed
actual command approval, proposal and project check: passed
current project, task and file desktop entry scope: passed
native stop cancelled, then original host explicitly stopped: passed
@@ -0,0 +1,20 @@
fatal: not a git repository (or any of the parent directories): .git
actual owned React/Vite UI approval, OS listener identity and HTTP readiness: passed
same actual native page, isolated Node/preload and blocked workbench API: passed
drag and keyboard width adjustment, native occlusion during drag and 125% zoom geometry: passed
fixed original-control fill and click operate real React controlled state: passed
actual DOM mutation invalidates previous observation without submitting: passed
actual source update reaches same native WebContents through Vite live reload: passed
390px mobile shell verifies and displays the same actual Electron original PNG through CA-verified TLS: passed
mobile digest mismatch shows failure and never displays unverified screenshot: passed
mobile device revocation removes original browser observation and task content: passed
native page hides for main-window authorization modal and restores: passed
unapproved popup is denied in actual Electron: passed
actual native navigation, back and forward preserve original scoped receipts: passed
explicit exact-URL download keeps original binary artifact and SHA: passed
actual independent temporary/persistent sessions, explicit reuse and selective cookie/storage/cache revocation: passed
390px native geometry, modal occlusion and return-to-task with no horizontal overflow: passed
closing actual view leaves owned development service running: passed
window close retains host and preview; explicit service stop confirms original process tree: passed
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\embedded-browser-5e2fc4f4-5e91-46c8-b2bf-6e314b7d5c73
{"passed":true,"root":"D:\\AWQA22\\s-1fca8c0c\\.qa\\embedded-browser-5e2fc4f4-5e91-46c8-b2bf-6e314b7d5c73","groups":17}
@@ -0,0 +1 @@
{"success":true,"version":"1.22.0","directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\native-engine-73e700d9-f813-4dd1-9bd7-3b6ea443e774","sdkVersion":"0.2.1-rc.2","nativeMethods":["initialize","session/working-directory/get","session/wait","session/resume","session/cancel","shutdown"],"modelRequests":0,"rootExited":true}
@@ -0,0 +1,5 @@
PASS actual React npm ci: e50670c4-49cc-46df-8396-e49aa0f31975
PASS actual React npm ci: 1101d1ab-d528-4cbc-a269-0493fbe88d89
Observed dependency changes: ["node_modules/.vite-temp"]
Observed dependency changes: ["node_modules/.vite-temp"]
{"success":true,"directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-projects-fb4c6798-c6e8-49a5-ac4b-be6f75662a62","reports":5,"reactOriginal":"failed","reactCandidate":"passed","reactTests":9,"pythonTests":2,"requests":138,"originalLockSha256":"48c138a05408667bbd332000731598415c9ae281d5072daa18544025ad89f7ff","ownedLockSha256":"f0faebd3acbc9501a3e52495f6eff4f5e4578ba377b12a3526923b53ffd4a5e2","downloadSource":"local HTTP feed of existing npm tarball bytes by locked SRI; no config/credentials or remote network","realModelRequests":0}
@@ -0,0 +1,8 @@
PASS desktop diagnosis, fixed plan, explicit approval, actual npm, original log and refresh
PASS 390px same real flow and bounded plan modal
PASS explicit script approval and original nonzero install failure
PASS stop kills only owned npm tree and keeps cancelled logs
PASS changed lock rejected before process dispatch
PASS recovered unknown remains original unknown after explicit reconciliation
PASS late plan response cannot replace another project or task
{"success":true,"appRoot":"D:\\AWQA22\\s-1fca8c0c","version":"1.22.0","checks":["desktop diagnosis, fixed plan, explicit approval, actual npm, original log and refresh","390px same real flow and bounded plan modal","explicit script approval and original nonzero install failure","stop kills only owned npm tree and keeps cancelled logs","changed lock rejected before process dispatch","recovered unknown remains original unknown after explicit reconciliation","late plan response cannot replace another project or task"],"screenshots":[{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\desktop-plan.png","sha256":"1a8c3276a2e4fb4ef74a0bd006561357a92348a09ca3b9eb22163012ad1cc9d9"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\desktop-prepared.png","sha256":"7c2d87fb231e754dc9eb40f16b3fa44a59a07d3ffdf87d27b19a0dbf8b172543"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\mobile-plan.png","sha256":"bf81fc71fc7a6eee3d1e0980f5c4d4549fe67b4075a59a64ce5fdbcc5e7dd1c3"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\mobile-prepared.png","sha256":"c2f239fae0f290f6c86635e9fa7b5190a539c56d03457a56ccfd46fc1e7dc400"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\failure-original-log.png","sha256":"23e841a33a56ef47fdf2eacca9993d220de22224dc97b662977efb870588abcc"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\stopped-owned-process.png","sha256":"803d620c441f0011f46f61c1e461ba9076e39def77cb8f83714a43edeadf2984"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\stale-input-rejected.png","sha256":"97fdd35a3c65155b1f54b0637b32106847e6e6b491159cf93ca83e31f34040aa"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250\\recovery-reconciled.png","sha256":"50482f0690bec428d583a287d58f3f96327f411ab2fbd122da551771fe86f560"}],"pageErrors":[],"failures":[],"events":[{"url":"http://127.0.0.1:54656/api/sessions/07adb270-c839-4421-b503-670eacb47fa3/environment-diagnostics","status":201},{"url":"http://127.0.0.1:54656/api/sessions/07adb270-c839-4421-b503-670eacb47fa3/environment-plans","status":201},{"url":"http://127.0.0.1:54656/api/sessions/07adb270-c839-4421-b503-670eacb47fa3/environment-jobs","status":202},{"url":"http://127.0.0.1:54656/api/sessions/84e988e5-b6bb-4423-ab62-5be82536aacb/environment-diagnostics","status":201},{"url":"http://127.0.0.1:54656/api/sessions/84e988e5-b6bb-4423-ab62-5be82536aacb/environment-plans","status":201},{"url":"http://127.0.0.1:54656/api/sessions/84e988e5-b6bb-4423-ab62-5be82536aacb/environment-jobs","status":202},{"url":"http://127.0.0.1:54656/api/sessions/887dd89d-beaf-4dc0-a790-75961d945ede/environment-diagnostics","status":201},{"url":"http://127.0.0.1:54656/api/sessions/887dd89d-beaf-4dc0-a790-75961d945ede/environment-plans","status":201},{"url":"http://127.0.0.1:54656/api/sessions/887dd89d-beaf-4dc0-a790-75961d945ede/environment-jobs","status":202},{"url":"http://127.0.0.1:54656/api/sessions/fdffae81-8fb6-45d3-86eb-4dc85037280d/environment-diagnostics","status":201},{"url":"http://127.0.0.1:54656/api/sessions/fdffae81-8fb6-45d3-86eb-4dc85037280d/environment-plans","status":201},{"url":"http://127.0.0.1:54656/api/sessions/fdffae81-8fb6-45d3-86eb-4dc85037280d/environment-jobs","status":202},{"url":"http://127.0.0.1:54656/api/sessions/fdffae81-8fb6-45d3-86eb-4dc85037280d/environment-jobs/57d416d5-2ea9-4cdf-a90d-a0c82137a672/stop","status":200},{"url":"http://127.0.0.1:54656/api/sessions/52a5acf1-e723-45c6-8258-7ad61e18ea9d/environment-diagnostics","status":201},{"url":"http://127.0.0.1:54656/api/sessions/52a5acf1-e723-45c6-8258-7ad61e18ea9d/environment-plans","status":201},{"url":"http://127.0.0.1:54656/api/sessions/52a5acf1-e723-45c6-8258-7ad61e18ea9d/environment-jobs","status":409},{"url":"http://127.0.0.1:54656/api/sessions/2188885d-fce5-4fa3-8550-345cbffdbf38/environment-jobs/63444253-3926-40dc-a4f0-4b6dcdd6675b/reconcile","status":200},{"url":"http://127.0.0.1:54656/api/sessions/03c9c1b4-566c-40c9-a5f8-57032f99ed30/environment-diagnostics","status":201}],"directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\environment-ui-244f4a14-52ab-4d11-a722-80e8f3c6e250","realModelRequests":0}
@@ -0,0 +1,2 @@
added 137 packages in 11s
@@ -0,0 +1,6 @@
PASS actual form saves Responses and declared stream, refresh preserves both and narrow editor remains operable
PASS separate text, nonce tool and actual SSE probes bind only their requested capability and own attempts
PASS actual pooled task excludes text-only before dispatch, executes original tool once and downloads SHA-matched original SSE
PASS desktop and actual paired gateway show same bounded stream; mobile stops original HTTP with zero fragment tool dispatch or replay
PASS truncated output keeps explicit unknown ledger, partial evidence and no automatic failover or incomplete tool execution
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\model-protocols-ui-199cc210-83ff-4887-a2c4-fdfaca498bf9
@@ -0,0 +1,8 @@
PASS desktop query shows two-pass current SHA verification and real parsing reuse
PASS same-size restored-mtime edit invalidates the actual source and displays the reason
PASS disable persists across page reload and future queries parse current sources
PASS clear removes only derived project material; next query rebuilds while sessions and configuration remain byte-semantically unchanged
PASS failed settings keep actual switch and query state; the same operation can recover
PASS diagnostics displays bounded cache and last project verification without triggering another query
PASS 390px controls support keyboard, 44px targets, readable metrics and no horizontal page/panel overflow
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\project-cache-ui-3cc5d42a-61e1-4a6d-9cf1-8ec27739dd7c
@@ -0,0 +1 @@
{"success":true,"version":"1.22.0","directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\rea-integration-9ef7ad33-3118-404e-ab9c-e5b64fe42a72","results":[{"operation":"javascript","evidenceId":"ev_73fa7937157b2997025b7097b3330506d6f085b25697ad2ba3ce2c68c1d7e5cb","targetSha256":"7ccd88b69f04b043168d70e97f2fa24a6bb94c20e4b4b65f8c89802bd49ccc7c","advertisedTools":229,"rootExited":true},{"operation":"pe-imports","evidenceId":"ev_6226bfc1e973a101674ee69b4dd6ef30bec5dbc1fdc65568c82b62eb139341b8","targetSha256":"7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973","advertisedTools":229,"rootExited":true},{"operation":"pe-resources","evidenceId":"ev_4bf7a05e7af8f7a363f30582bdd4f72500e29783c8cb09cc25e4495c07d7b2bb","targetSha256":"7102754492d544b471ff84afdb3bbec983824049e4c2118bd0e240f8e7cbe973","advertisedTools":229,"rootExited":true}]}
@@ -0,0 +1,6 @@
PASS HTML applies once, ends without tests or continuation prompt, and shows actual model
PASS 390px result and task panel remain usable without horizontal overflow
PASS one approved real failing check is reused across new plans and the no-progress task pauses
PASS diagnostic answer completes separately and preserves original unfinished task at both widths
PASS required empty arguments reject the entire batch and reported usage remains once after reload
{"success":true,"version":"1.22.0","appRoot":"D:\\AWQA22\\s-1fca8c0c","directory":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319","passed":["HTML applies once, ends without tests or continuation prompt, and shows actual model","390px result and task panel remain usable without horizontal overflow","one approved real failing check is reused across new plans and the no-progress task pauses","diagnostic answer completes separately and preserves original unfinished task at both widths","required empty arguments reject the entire batch and reported usage remains once after reload"],"screenshots":[{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\html-desktop.png","sha256":"cf1ee48a2863c5aa028970f05013f0fb64b71bedfb73c1f02031fc8f580eba07"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\html-390.png","sha256":"791c2c57abdddc67fa90be2f7749fd71330d375a8ca968d133b5515332abf77b"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\checks-desktop.png","sha256":"75590359bcf7bf649bff3337bec8f7e844349f5c5fda646b79dd15e6bf834cda"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\diagnostic-desktop.png","sha256":"6fc5be9247a24cf481fd93a1dfde4769393d1da62f28cf6bd100ea8aa526b600"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\diagnostic-390.png","sha256":"cd96ac7b58250445561592adcb9c69c419df4187e1ba7c44265e1a8421bffbfc"},{"path":"D:\\AWQA22\\s-1fca8c0c\\.qa\\task-control-ui-b6295bbb-b968-45e4-a6fb-b709ace5d319\\protocol-desktop.png","sha256":"2169b3229b33d7c9fa73be45cd4f749cf4820f4bd70b3c63c1dc026189cba02a"}],"pageErrors":[],"requestCount":11,"realModelRequests":0}
@@ -0,0 +1,168 @@
[
{
"index": 0,
"files": [
"api.test.mjs",
"browser-api.test.mjs",
"browser-delivery.test.mjs",
"browser-locators.test.mjs",
"browser.test.mjs",
"browsing.test.mjs",
"budget-resume.test.mjs",
"change-set-api.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 1,
"files": [
"change-set-recovery.test.mjs",
"change-sets.test.mjs",
"checks.test.mjs",
"code-tools.test.mjs",
"companion.test.mjs",
"config-transaction-api.test.mjs",
"controlled-engine.test.mjs",
"credential-vault.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 2,
"files": [
"delivery-recovery.test.mjs",
"delivery.test.mjs",
"desktop-bridge.test.mjs",
"desktop-host.test.mjs",
"desktop-install.test.mjs",
"desktop-startup.test.mjs",
"diagnostics.test.mjs",
"engine-api.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 3,
"files": [
"engine-worker-http.test.mjs",
"engine-worker.test.mjs",
"engine.test.mjs",
"environment.test.mjs",
"evaluations.test.mjs",
"execution.test.mjs",
"file-boundaries.test.mjs",
"files.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 4,
"files": [
"initial-example.test.mjs",
"input-attachments.test.mjs",
"mcp-registry.test.mjs",
"mcp-stdio.test.mjs",
"model-capabilities.test.mjs",
"model-center.test.mjs",
"model-fidelity.test.mjs",
"model-protocols.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 5,
"files": [
"model-routing-capabilities.test.mjs",
"model-stream.test.mjs",
"model-wait.test.mjs",
"operations.test.mjs",
"patch.test.mjs",
"preview.test.mjs",
"process-environment.test.mjs",
"process-identity.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 6,
"files": [
"project-cache-api.test.mjs",
"project-cache.test.mjs",
"project-index.test.mjs",
"project-memory-context.test.mjs",
"project-memory.test.mjs",
"purge-strategy.test.mjs",
"python-api.test.mjs",
"python-checks.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 7,
"files": [
"read-budget.test.mjs",
"registered-sources.test.mjs",
"request-plan-api.test.mjs",
"request-plan.test.mjs",
"research.test.mjs",
"runtime.test.mjs",
"skills.test.mjs",
"store.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 8,
"files": [
"task-checkpoints.test.mjs",
"task-control.test.mjs",
"task-plans-api.test.mjs",
"task-plans.test.mjs",
"tool-feedback.test.mjs",
"upgrade-artifacts.test.mjs",
"upgrade-controlled-engines.test.mjs",
"upgrade-model-center.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 9,
"files": [
"workers-http.test.mjs",
"workers-merge.test.mjs",
"workers-recovery.test.mjs",
"workers.test.mjs",
"working-set.test.mjs",
"workspace-api.test.mjs",
"workspace-policy.test.mjs",
"workspace-recovery.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 10,
"files": [
"workspaces.test.mjs"
],
"concurrency": 2,
"timeoutMs": 1800000
},
{
"index": 11,
"files": [
"upgrade.test.mjs"
],
"concurrency": 1,
"timeoutMs": 1800000
}
]
@@ -0,0 +1,268 @@
TAP version 13
# Subtest: the bundled local service enforces host, origin, token and JSON object contracts
ok 1 - the bundled local service enforces host, origin, token and JSON object contracts
---
duration_ms: 2050.9418
type: 'test'
...
# Subtest: an in-flight connection probe prevents configuration changes and another probe until its actual result returns
ok 2 - an in-flight connection probe prevents configuration changes and another probe until its actual result returns
---
duration_ms: 2280.5886
type: 'test'
...
# Subtest: API review applies verified content, detects conflicts, exports sessions and keeps keys in memory
ok 3 - API review applies verified content, detects conflicts, exports sessions and keeps keys in memory
---
duration_ms: 3982.6499
type: 'test'
...
# Subtest: a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume
ok 4 - a real bundle restart preserves proposals, interrupts old approvals and requests fresh consent on resume
---
duration_ms: 8936.5814
type: 'test'
...
# Subtest: runtime diagnostics and model-response validation use actual records and preserve the saved connection
ok 5 - runtime diagnostics and model-response validation use actual records and preserve the saved connection
---
duration_ms: 2050.7757
type: 'test'
...
# Subtest: persistent event replay is read-only and keeps run/artifact identity across reconnects
ok 6 - persistent event replay is read-only and keeps run/artifact identity across reconnects
---
duration_ms: 5151.2028
type: 'test'
...
# Subtest: real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart
ok 7 - real browser HTTP plans, original field pages and PNG bytes preserve ownership and survive host restart
---
duration_ms: 7049.4552
type: 'test'
...
# Subtest: self harness browser tools require approval and feed verified actual page fields back to the original Task
ok 8 - self harness browser tools require approval and feed verified actual page fields back to the original Task
---
duration_ms: 9633.8456
type: 'test'
...
# Subtest: browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement
ok 9 - browser host recovery retains unknown root outcome, blocks replay, and requires an explicit owned acknowledgement
---
duration_ms: 3615.6645
type: 'test'
...
# Subtest: late HTTP stop of a finished browser job cannot interrupt a later job in the same Task
ok 10 - late HTTP stop of a finished browser job cannot interrupt a later job in the same Task
---
duration_ms: 7130.7028
type: 'test'
...
# Subtest: actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records
ok 11 - actual failed page blocks source-passed delivery; a new passing page permits a bound commit and preserves both original records
---
duration_ms: 19752.4656
type: 'test'
...
# Subtest: a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact
ok 12 - a build-only change after Git review invalidates the actual browser evidence and leaves HEAD and the protected index intact
---
duration_ms: 10806.6865
type: 'test'
...
# Subtest: actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels
ok 13 - actual DOM controls include validated unique CSS selectors across repeated parent buttons and escaped labels
---
duration_ms: 6279.2382
type: 'test'
...
# Subtest: browser field coverage distinguishes sections and Run windows while retaining original source identity
ok 14 - browser field coverage distinguishes sections and Run windows while retaining original source identity
---
duration_ms: 0.4914
type: 'test'
...
# Subtest: repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing
ok 15 - repeated original browser pages pause a live Task without re-opening the browser or breaking tool pairing
---
duration_ms: 4012.3317
type: 'test'
...
# Subtest: browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution
ok 16 - browser plan rejects outside builds, invalid interaction scope and unbounded steps before execution
---
duration_ms: 0.9106
type: 'test'
...
# Subtest: real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen
ok 17 - real owned Edge interactions, assertions, raw PNG and stopped process survive exact result reuse and host reopen
---
duration_ms: 3413.9933
type: 'test'
...
# Subtest: failed real page assertion preserves actual value and forbids silent retry of the original plan
ok 18 - failed real page assertion preserves actual value and forbids silent retry of the original plan
---
duration_ms: 7377.9685
type: 'test'
...
# Subtest: build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan
ok 19 - build/source mutation and sealed step tampering reject before browser dispatch; earlier task cannot execute plan
---
duration_ms: 985.1528
type: 'test'
...
# Subtest: outside network never reaches another local service, and original JavaScript/console failures remain failures
ok 20 - outside network never reaches another local service, and original JavaScript/console failures remain failures
---
duration_ms: 2227.2955
type: 'test'
...
# Subtest: stopping a real in-flight browser preserves finished steps, closes its owned root and never replays
ok 21 - stopping a real in-flight browser preserves finished steps, closes its owned root and never replays
---
duration_ms: 2416.4187
type: 'test'
...
# Subtest: 原PNG损坏使原结果校验失败,不能以已有通过状态复用
ok 22 - 原PNG损坏使原结果校验失败,不能以已有通过状态复用
---
duration_ms: 2648.1017
type: 'test'
...
# Subtest: fixed browsing contracts reject local host APIs, credential URLs, protocols, cross-origin and arbitrary execution
ok 23 - fixed browsing contracts reject local host APIs, credential URLs, protocols, cross-origin and arbitrary execution
---
duration_ms: 0.9922
type: 'test'
...
# Subtest: attested desktop queue preserves same-tab observations, original PNG bytes and approval-bound one-shot actions
ok 24 - attested desktop queue preserves same-tab observations, original PNG bytes and approval-bound one-shot actions
---
duration_ms: 889.848
type: 'test'
...
# Subtest: page data cannot grant domains, interaction or other Task scope; nonce and ownership remain fixed
ok 25 - page data cannot grant domains, interaction or other Task scope; nonce and ownership remain fixed
---
duration_ms: 1060.5346
type: 'test'
...
# Subtest: unknown dispatched submission blocks even after a new observation, rejects late success and retains explicit acknowledgement
ok 26 - unknown dispatched submission blocks even after a new observation, rejects late success and retains explicit acknowledgement
---
duration_ms: 2050.5297
type: 'test'
...
# Subtest: downloads require exact approved address, remain original binary artifacts, and cannot reuse consumed observation
ok 27 - downloads require exact approved address, remain original binary artifacts, and cannot reuse consumed observation
---
duration_ms: 1593.1114
type: 'test'
...
# Subtest: revoking shared persistent profile closes all its tabs and clears only that profile after original desktop acknowledgement
ok 28 - revoking shared persistent profile closes all its tabs and clears only that profile after original desktop acknowledgement
---
duration_ms: 2027.5886
type: 'test'
...
# Subtest: service recovery never reopens old tabs or replays dispatched actions and keeps unknown original receipts
ok 29 - service recovery never reopens old tabs or replays dispatched actions and keeps unknown original receipts
---
duration_ms: 1665.1857
type: 'test'
...
# Subtest: agent browser flow waits for original Task/Run approval, dispatches once, and returns paired original results
ok 30 - agent browser flow waits for original Task/Run approval, dispatches once, and returns paired original results
---
duration_ms: 4348.8784
type: 'test'
...
# Subtest: changed approved input and stopped dispatched agent action cannot be accepted or replayed
ok 31 - changed approved input and stopped dispatched agent action cannot be accepted or replayed
---
duration_ms: 1390.6408
type: 'test'
...
# Subtest: browser inventory gives bounded metadata and original references instead of repeating full website histories
ok 32 - browser inventory gives bounded metadata and original references instead of repeating full website histories
---
duration_ms: 1347.4501
type: 'test'
...
# Subtest: receipt storage failure settles the original dispatched action as unknown and never hangs or accepts late success
ok 33 - receipt storage failure settles the original dispatched action as unknown and never hangs or accepts late success
---
duration_ms: 1287.7056
type: 'test'
...
# Subtest: a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request
ok 34 - a budget pause persists concrete text/tool/history/image breakdown and never dispatches an oversized request
---
duration_ms: 2793.1056
type: 'test'
...
# Subtest: explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model
ok 35 - explicit frozen preview resumes the same Task in a new Run, preserves completed tools and does not change global config or selected model
---
duration_ms: 3800.7246
type: 'test'
...
# Subtest: insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget
ok 36 - insufficient budgets, silently clamped capacity and arbitrary config fields reject without a physical request or mutating task budget
---
duration_ms: 2890.9659
type: 'test'
...
# Subtest: changed session, changed registry, expiry and altered frozen preview all require a new explicit preview
ok 37 - changed session, changed registry, expiry and altered frozen preview all require a new explicit preview
---
duration_ms: 3052.9058
type: 'test'
...
# Subtest: preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run
ok 38 - preview preserves unknown invocation status and increasing Task allowance is committed only with confirmed new Run
---
duration_ms: 3623.1941
type: 'test'
...
# Subtest: batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart
ok 39 - batch APIs enforce ownership and review fingerprints, apply once, and persist the completed batch across restart
---
duration_ms: 4857.2478
type: 'test'
...
# Subtest: delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files
ok 40 - delivery reports bind actual batch identity and reject corrupted snapshot evidence without changing project files
---
duration_ms: 2865.2776
type: 'test'
...
# Subtest: a compatible model can seal proposals through the real HTTP loop while application stays behind user review
ok 41 - a compatible model can seal proposals through the real HTTP loop while application stays behind user review
---
duration_ms: 4956.0144
type: 'test'
...
# Subtest: a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools
ok 42 - a step-limited sealed batch applies and continues the same Task into actual checks without replaying saved tools
---
duration_ms: 9309.1219
type: 'test'
...
# Subtest: applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation
ok 43 - applied batches cannot turn cancellation, other budgets, restart or unknown commands into a review continuation
---
duration_ms: 1262.8778
type: 'test'
...
1..43
# tests 43
# suites 0
# pass 43
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 96485.2352
@@ -0,0 +1,571 @@
TAP version 13
# Subtest: actual process exit at file-batch prepared preserves durable identity and never replays writes
ok 1 - actual process exit at file-batch prepared preserves durable identity and never replays writes
---
duration_ms: 1733.2602
type: 'test'
...
# Subtest: actual process exit at file-batch application_started preserves durable identity and never replays writes
ok 2 - actual process exit at file-batch application_started preserves durable identity and never replays writes
---
duration_ms: 1653.7571
type: 'test'
...
# Subtest: actual process exit at file-batch write_intent preserves durable identity and never replays writes
ok 3 - actual process exit at file-batch write_intent preserves durable identity and never replays writes
---
duration_ms: 1496.9175
type: 'test'
...
# Subtest: actual process exit at file-batch staged preserves durable identity and never replays writes
ok 4 - actual process exit at file-batch staged preserves durable identity and never replays writes
---
duration_ms: 1890.527
type: 'test'
...
# Subtest: actual process exit at file-batch replaced preserves durable identity and never replays writes
ok 5 - actual process exit at file-batch replaced preserves durable identity and never replays writes
---
duration_ms: 1954.6893
type: 'test'
...
# Subtest: actual process exit at file-batch file_recorded preserves durable identity and never replays writes
ok 6 - actual process exit at file-batch file_recorded preserves durable identity and never replays writes
---
duration_ms: 2236.0622
type: 'test'
...
# Subtest: actual process exit at file-batch finished preserves durable identity and never replays writes
ok 7 - actual process exit at file-batch finished preserves durable identity and never replays writes
---
duration_ms: 2369.8601
type: 'test'
...
# Subtest: actual process exit at file-batch rollback_started preserves durable identity and never replays writes
ok 8 - actual process exit at file-batch rollback_started preserves durable identity and never replays writes
---
duration_ms: 2538.0476
type: 'test'
...
# Subtest: actual process exit at file-batch restore_intent preserves durable identity and never replays writes
ok 9 - actual process exit at file-batch restore_intent preserves durable identity and never replays writes
---
duration_ms: 2899.2124
type: 'test'
...
# Subtest: actual process exit at file-batch restore_staged preserves durable identity and never replays writes
ok 10 - actual process exit at file-batch restore_staged preserves durable identity and never replays writes
---
duration_ms: 2896.8101
type: 'test'
...
# Subtest: actual process exit at file-batch restored preserves durable identity and never replays writes
ok 11 - actual process exit at file-batch restored preserves durable identity and never replays writes
---
duration_ms: 2509.1368
type: 'test'
...
# Subtest: actual process exit at file-batch restore_recorded preserves durable identity and never replays writes
ok 12 - actual process exit at file-batch restore_recorded preserves durable identity and never replays writes
---
duration_ms: 2339.399
type: 'test'
...
# Subtest: actual process exit at file-batch rollback_finished preserves durable identity and never replays writes
ok 13 - actual process exit at file-batch rollback_finished preserves durable identity and never replays writes
---
duration_ms: 2496.7289
type: 'test'
...
# warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
# warning: in the working copy of 'src/two.mjs', LF will be replaced by CRLF the next time Git touches it
# Subtest: sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files
ok 14 - sealed batches preserve bytes until review, then apply and explicitly restore BOM/CRLF/new files
---
duration_ms: 2350.9665
type: 'test'
...
# Switched to a new branch 'owner-branch'
# Subtest: a conflict in the last file or Git branch prevents writing every file in the batch
ok 15 - a conflict in the last file or Git branch prevents writing every file in the batch
---
duration_ms: 3627.5678
type: 'test'
...
# Subtest: duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch
ok 16 - duplicate canonical paths, ancestor collisions, links, dependencies and Windows aliases never form a batch
---
duration_ms: 1032.2137
type: 'test'
...
# Subtest: fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target
ok 17 - fingerprints, changed proposals and corrupt snapshot artifacts cannot write or restore any target
---
duration_ms: 1997.7297
type: 'test'
...
# Subtest: a failure after replacement restores only batch bytes and never retries an old application
ok 18 - a failure after replacement restores only batch bytes and never retries an old application
---
duration_ms: 1471.7869
type: 'test'
...
# Subtest: rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery
ok 19 - rollback preserves owner edits, blocks other project writers, and explicit acknowledgement releases recovery
---
duration_ms: 1833.457
type: 'test'
...
# Subtest: an unattempted owner-created file identical to a suggestion remains external and is never removed
ok 20 - an unattempted owner-created file identical to a suggestion remains external and is never removed
---
duration_ms: 1431.3355
type: 'test'
...
# Subtest: active batch requests are serialized and cancellation leaves a verifiable ended batch
ok 21 - active batch requests are serialized and cancellation leaves a verifiable ended batch
---
duration_ms: 1076.8225
type: 'test'
...
# Subtest: batch application and rollback preserve unrelated Git index and worktree bytes
ok 22 - batch application and rollback preserve unrelated Git index and worktree bytes
---
duration_ms: 3310.391
type: 'test'
...
# Subtest: recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection
ok 23 - recovery reuses exact staged bytes but retains a conflicting temporary file for owner inspection
---
duration_ms: 2281.3214
type: 'test'
...
# Subtest: one Task can seal pending proposals from earlier Runs while snapshots retain each source Run
ok 24 - one Task can seal pending proposals from earlier Runs while snapshots retain each source Run
---
duration_ms: 1861.9453
type: 'test'
...
# Subtest: engineering inspection preserves a dirty Git baseline and treats project rules as data
ok 25 - engineering inspection preserves a dirty Git baseline and treats project rules as data
---
duration_ms: 2295.9957
type: 'test'
...
# Subtest: real npm tests and build produce counted results, log artifacts and persistent verification
ok 26 - real npm tests and build produce counted results, log artifacts and persistent verification
---
duration_ms: 2384.2945
type: 'test'
...
# Subtest: an actual failing test retains the nonzero exit code and failed count
ok 27 - an actual failing test retains the nonzero exit code and failed count
---
duration_ms: 2194.5273
type: 'test'
...
# Subtest: unchanged automatic checks return original failure evidence, while explicit user reruns and changed source still execute
ok 28 - unchanged automatic checks return original failure evidence, while explicit user reruns and changed source still execute
---
duration_ms: 4249.0484
type: 'test'
...
# Subtest: agent loops cannot hide identical failing checks behind new plan IDs or unrelated reads
ok 29 - agent loops cannot hide identical failing checks behind new plan IDs or unrelated reads
---
duration_ms: 7219.8322
type: 'test'
...
# Subtest: zero tests, skipped tests and unrecognized stdout cannot become verification passes
ok 30 - zero tests, skipped tests and unrecognized stdout cannot become verification passes
---
duration_ms: 7461.0077
type: 'test'
...
# Subtest: a successful build with no selected tests does not verify the task
ok 31 - a successful build with no selected tests does not verify the task
---
duration_ms: 1751.6941
type: 'test'
...
# Subtest: stale check plans and forged script names execute no project commands
ok 32 - stale check plans and forged script names execute no project commands
---
duration_ms: 1193.4713
type: 'test'
...
# Subtest: applying a later proposal invalidates the prior passed engineering snapshot
ok 33 - applying a later proposal invalidates the prior passed engineering snapshot
---
duration_ms: 2348.2033
type: 'test'
...
# Subtest: stopping an actual check terminates its child process and blocks concurrent jobs
ok 34 - stopping an actual check terminates its child process and blocks concurrent jobs
---
duration_ms: 1928.5167
type: 'test'
...
# Subtest: check timeout records a failure with its actual termination result
ok 35 - check timeout records a failure with its actual termination result
---
duration_ms: 1983.1499
type: 'test'
...
# Subtest: source edits during a successful check make the result stale
ok 36 - source edits during a successful check make the result stale
---
duration_ms: 3069.927
type: 'test'
...
# Subtest: bounded large logs retain the test footer and readable artifact instead of inventing counts
ok 37 - bounded large logs retain the test footer and readable artifact instead of inventing counts
---
duration_ms: 1780.8894
type: 'test'
...
# Subtest: model-selected checks require a run-bound decision and denial creates no check job
ok 38 - model-selected checks require a run-bound decision and denial creates no check job
---
duration_ms: 2738.4524
type: 'test'
...
# Subtest: check APIs expose owned plans and jobs and preserve the authoritative results across restart
ok 39 - check APIs expose owned plans and jobs and preserve the authoritative results across restart
---
duration_ms: 6281.0809
type: 'test'
...
# Subtest: reviewed changes continue the original task without reopening a generic completed run
ok 40 - reviewed changes continue the original task without reopening a generic completed run
---
duration_ms: 1673.766
type: 'test'
...
# Subtest: concurrent review-continuation API requests accept one run and retain the goal after restart
ok 41 - concurrent review-continuation API requests accept one run and retain the goal after restart
---
duration_ms: 7198.9173
type: 'test'
...
# Subtest: the model reads owned failure logs without running the check again
ok 42 - the model reads owned failure logs without running the check again
---
duration_ms: 2701.2621
type: 'test'
...
# Subtest: process exit at check queued preserves results and never replays commands
ok 43 - process exit at check queued preserves results and never replays commands
---
duration_ms: 1212.2433
type: 'test'
...
# Subtest: process exit at check result_committed preserves results and never replays commands
ok 44 - process exit at check result_committed preserves results and never replays commands
---
duration_ms: 1468.5508
type: 'test'
...
# Subtest: model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery
ok 45 - model code tools keep Task/Run ownership, index evidence and exact proposals across storage recovery
---
duration_ms: 3463.419
type: 'test'
...
# Subtest: bundled code APIs isolate project results, validate queries and create review-only patches with conflicts
ok 46 - bundled code APIs isolate project results, validate queries and create review-only patches with conflicts
---
duration_ms: 2631.673
type: 'test'
...
# Subtest: code tool arguments reject malformed ownership-independent inputs before side effects
ok 47 - code tool arguments reject malformed ownership-independent inputs before side effects
---
duration_ms: 0.2977
type: 'test'
...
# Subtest: observe-only device authority cannot read, configure or clear project parsing caches
ok 48 - observe-only device authority cannot read, configure or clear project parsing caches
---
duration_ms: 804.8313
type: 'test'
...
# Subtest: pairing is short lived, single-use, generation-bound and validates exact permissions
ok 49 - pairing is short lived, single-use, generation-bound and validates exact permissions
---
duration_ms: 529.5862
type: 'test'
...
# Subtest: device transaction failure neither consumes the ticket nor leaves a credential
ok 50 - device transaction failure neither consumes the ticket nor leaves a credential
---
duration_ms: 701.6271
type: 'test'
...
# Subtest: devices have project and action boundaries; rotation, expiration, revocation and host changes reject old authority
ok 51 - devices have project and action boundaries; rotation, expiration, revocation and host changes reject old authority
---
duration_ms: 730.2581
type: 'test'
...
# Subtest: persistent registry stores hashes and a bounded audit, never raw credentials
ok 52 - persistent registry stores hashes and a bounded audit, never raw credentials
---
duration_ms: 659.9232
type: 'test'
...
# Subtest: real TLS verifies IP SAN, CA chain, encrypted restart and public fingerprint
ok 53 - real TLS verifies IP SAN, CA chain, encrypted restart and public fingerprint
---
duration_ms: 929.8717
type: 'test'
...
# Subtest: TLS sealing failure leaves listener closed and no plaintext or successful TLS registration
ok 54 - TLS sealing failure leaves listener closed and no plaintext or successful TLS registration
---
duration_ms: 522.5079
type: 'test'
...
# Subtest: HTTP pairing is concurrent single-use; secure cookie and strict origin/host checks
ok 55 - HTTP pairing is concurrent single-use; secure cookie and strict origin/host checks
---
duration_ms: 850.8115
type: 'test'
...
# Subtest: gateway never exposes management routes, arbitrary assets or unpaired project data
ok 56 - gateway never exposes management routes, arbitrary assets or unpaired project data
---
duration_ms: 690.6531
type: 'test'
...
# Subtest: authorized project events paginate from original seq without leaking other project events or payloads
ok 57 - authorized project events paginate from original seq without leaking other project events or payloads
---
duration_ms: 1332.8627
type: 'test'
...
# Subtest: remote task projection excludes raw model history, host configuration, tool input and credentials
ok 58 - remote task projection excludes raw model history, host configuration, tool input and credentials
---
duration_ms: 715.5196
type: 'test'
...
# Subtest: permission checks apply to direct remote mutation, not only UI controls
ok 59 - permission checks apply to direct remote mutation, not only UI controls
---
duration_ms: 956.855
type: 'test'
...
# Subtest: approval fingerprint and exact task/revision are bound; duplicate requests never execute twice
ok 60 - approval fingerprint and exact task/revision are bound; duplicate requests never execute twice
---
duration_ms: 815.1868
type: 'test'
...
# Subtest: unknown original operation is recorded and never replayed after response failure
ok 61 - unknown original operation is recorded and never replayed after response failure
---
duration_ms: 1045.7579
type: 'test'
...
# Subtest: revocation and gateway closure reject old access without invoking runtime stop
ok 62 - revocation and gateway closure reject old access without invoking runtime stop
---
duration_ms: 667.8086
type: 'test'
...
# Subtest: rate limits reject pairing brute force and do not persist candidate secrets
ok 63 - rate limits reject pairing brute force and do not persist candidate secrets
---
duration_ms: 766.0217
type: 'test'
...
# Subtest: real Windows CurrentUser DPAPI persists only a sealed CA and reopens it
ok 64 - real Windows CurrentUser DPAPI persists only a sealed CA and reopens it
---
duration_ms: 2145.4737
type: 'test'
...
# Subtest: mobile approval executes the original Runtime command exactly once and rejects the later desktop decision
ok 65 - mobile approval executes the original Runtime command exactly once and rejects the later desktop decision
---
duration_ms: 2013.3346
type: 'test'
...
# Subtest: desktop rejection wins a concurrent mobile request and original command remains unexecuted
ok 66 - desktop rejection wins a concurrent mobile request and original command remains unexecuted
---
duration_ms: 1908.9839
type: 'test'
...
# Subtest: phone stop waits for the original process exit and prevents later heartbeats and command replay
ok 67 - phone stop waits for the original process exit and prevents later heartbeats and command replay
---
duration_ms: 2182.1828
type: 'test'
...
# Subtest: Run replacement during parent-stop wait is rejected rather than stopping the new Run
ok 68 - Run replacement during parent-stop wait is rejected rather than stopping the new Run
---
duration_ms: 499.2893
type: 'test'
...
# Subtest: diff pages preserve source SHA; report reads verify blobs and exclude unrelated artifact kinds
ok 69 - diff pages preserve source SHA; report reads verify blobs and exclude unrelated artifact kinds
---
duration_ms: 1124.3177
type: 'test'
...
# Subtest: hot upgrade refuses an active gateway and restores closed gateway ownership on failure
ok 70 - hot upgrade refuses an active gateway and restores closed gateway ownership on failure
---
duration_ms: 535.7065
type: 'test'
...
# Subtest: damaged device permissions or expiry fail closed and never overwrite the original registry
ok 71 - damaged device permissions or expiry fail closed and never overwrite the original registry
---
duration_ms: 601.071
type: 'test'
...
# Subtest: device revocation destroys its actual authenticated TLS connection
ok 72 - device revocation destroys its actual authenticated TLS connection
---
duration_ms: 572.3311
type: 'test'
...
# Subtest: companion observes only current Task screenshots, verifies original PNG bytes and loses access immediately on revoke
ok 73 - companion observes only current Task screenshots, verifies original PNG bytes and loses access immediately on revoke
---
duration_ms: 1114.002
type: 'test'
...
# Subtest: mobile browser observation is current Task/project scoped, preserves original PNG and exposes no browser control or profile data
ok 74 - mobile browser observation is current Task/project scoped, preserves original PNG and exposes no browser control or profile data
---
duration_ms: 1094.7402
type: 'test'
...
# Subtest: actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry
ok 75 - actual config HTTP failure preserves the committed selection, config and volatile credential before a successful retry
---
duration_ms: 1081.017
type: 'test'
...
# Subtest: controlled installation pins the native kernel and bridge independently of the existing connection-probe identity
ok 76 - controlled installation pins the native kernel and bridge independently of the existing connection-probe identity
---
duration_ms: 791.0236
type: 'test'
...
# Subtest: controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract
ok 77 - controlled profiles disable every native project/terminal provider and native model/retry route using the actual include patch contract
---
duration_ms: 0.5735
type: 'test'
...
# Subtest: owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations
ok 78 - owned tool catalogues seal full schemas canonically and reject duplicate or malformed declarations
---
duration_ms: 5.0232
type: 'test'
...
# Subtest: bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch
ok 79 - bridge authentication, current Run, process, SDK session and browser-origin checks reject before dispatch
---
duration_ms: 668.798
type: 'test'
...
# Subtest: bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect
ok 80 - bridge duplicates, unknown tools, malformed arguments and source changes are refused before a second side effect
---
duration_ms: 691.8977
type: 'test'
...
# Subtest: bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity
ok 81 - bridge model requests bind the exact catalogue, route and output bound and preserve raw request/result identity
---
duration_ms: 834.5031
type: 'test'
...
# Subtest: stopped and oversized bridge requests never reach a local model or tool callback
ok 82 - stopped and oversized bridge requests never reach a local model or tool callback
---
duration_ms: 630.4877
type: 'test'
...
# Subtest: a Windows virtual data-directory name binds new storage and credentials to its actual physical root
ok 83 - a Windows virtual data-directory name binds new storage and credentials to its actual physical root
---
duration_ms: 1542.0239
type: 'test'
...
# Subtest: physical data-root adoption still rejects explicit junctions at the directory or any ancestor
ok 84 - physical data-root adoption still rejects explicit junctions at the directory or any ancestor
---
duration_ms: 453.0992
type: 'test'
...
# Subtest: actual Windows CurrentUser DPAPI roundtrips owned UTF-8 and rejects damaged bytes and wrong entropy
ok 85 - actual Windows CurrentUser DPAPI roundtrips owned UTF-8 and rejects damaged bytes and wrong entropy
---
duration_ms: 1473.4617
type: 'test'
...
# Subtest: only explicitly supplied keys persist; new provider restores original revisions and public views contain no key
ok 86 - only explicitly supplied keys persist; new provider restores original revisions and public views contain no key
---
duration_ms: 2265.8166
type: 'test'
...
# Subtest: registry and cipher commit failure restores original routing, keys, block and every database row
ok 87 - registry and cipher commit failure restores original routing, keys, block and every database row
---
duration_ms: 1751.5893
type: 'test'
...
# Subtest: a two-key import with a protection failure rolls back all registry and cipher entries and retains its preview
ok 88 - a two-key import with a protection failure rolls back all registry and cipher entries and retains its preview
---
duration_ms: 1837.1147
type: 'test'
...
# Subtest: connection revision changes retain the original saved block and report a source mismatch on restart
ok 89 - connection revision changes retain the original saved block and report a source mismatch on restart
---
duration_ms: 2124.9073
type: 'test'
...
# Subtest: disable skips real restart loading, explicit enable restores, delete preserves memory and forget removes both
ok 90 - disable skips real restart loading, explicit enable restores, delete preserves memory and forget removes both
---
duration_ms: 2266.9767
type: 'test'
...
# Subtest: corrupt saved block and another SID do not load; failures are visible without returning ciphertext or plaintext
ok 91 - corrupt saved block and another SID do not load; failures are visible without returning ciphertext or plaintext
---
duration_ms: 2412.4534
type: 'test'
...
# Subtest: legacy persistence requires a new explicit key and binds config and credential revisions; stale requests cannot save
ok 92 - legacy persistence requires a new explicit key and binds config and credential revisions; stale requests cannot save
---
duration_ms: 2333.1745
type: 'test'
...
# Subtest: owned plaintext keys never reach SQLite pages, WAL, config or public execution exports
ok 93 - owned plaintext keys never reach SQLite pages, WAL, config or public execution exports
---
duration_ms: 1218.9234
type: 'test'
...
1..93
# tests 93
# suites 0
# pass 93
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 86936.6044
@@ -0,0 +1,421 @@
TAP version 13
# Subtest: actual process exit at Git queued never replays a commit and can reconcile the durable result
ok 1 - actual process exit at Git queued never replays a commit and can reconcile the durable result
---
duration_ms: 15189.3374
type: 'test'
...
# Subtest: actual process exit at Git preparing never replays a commit and can reconcile the durable result
ok 2 - actual process exit at Git preparing never replays a commit and can reconcile the durable result
---
duration_ms: 15510.2768
type: 'test'
...
# Subtest: actual process exit at Git index_locked never replays a commit and can reconcile the durable result
ok 3 - actual process exit at Git index_locked never replays a commit and can reconcile the durable result
---
duration_ms: 15379.2466
type: 'test'
...
# Subtest: actual process exit at Git prepared never replays a commit and can reconcile the durable result
ok 4 - actual process exit at Git prepared never replays a commit and can reconcile the durable result
---
duration_ms: 15525.7829
type: 'test'
...
# Subtest: actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result
ok 5 - actual process exit at Git ref_prepared never replays a commit and can reconcile the durable result
---
duration_ms: 16168.784
type: 'test'
...
# Subtest: actual process exit at Git publishing never replays a commit and can reconcile the durable result
ok 6 - actual process exit at Git publishing never replays a commit and can reconcile the durable result
---
duration_ms: 16315.7358
type: 'test'
...
# Subtest: actual process exit at Git committed never replays a commit and can reconcile the durable result
ok 7 - actual process exit at Git committed never replays a commit and can reconcile the durable result
---
duration_ms: 11980.8148
type: 'test'
...
# Subtest: actual process exit at Git index_published never replays a commit and can reconcile the durable result
ok 8 - actual process exit at Git index_published never replays a commit and can reconcile the durable result
---
duration_ms: 12723.502
type: 'test'
...
# Subtest: actual process exit at Git finished never replays a commit and can reconcile the durable result
ok 9 - actual process exit at Git finished never replays a commit and can reconcile the durable result
---
duration_ms: 12129.295
type: 'test'
...
# Subtest: an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock
ok 10 - an unknown Git result cannot overwrite an externally changed index or delete an unrelated lock
---
duration_ms: 10695.9812
type: 'test'
...
# Subtest: known publication with a later source edit retains the commit and marks the delivery for inspection
ok 11 - known publication with a later source edit retains the commit and marks the delivery for inspection
---
duration_ms: 11424.7342
type: 'test'
...
# Subtest: CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership
ok 12 - CRLF normalization, multiple applied revisions and unrelated special index flags preserve exact bytes and ownership
---
duration_ms: 13859.8376
type: 'test'
...
# Subtest: adding new durable record kinds to an existing hot Store preserves all existing Maps and records
ok 13 - adding new durable record kinds to an existing hot Store preserves all existing Maps and records
---
duration_ms: 9352.6373
type: 'test'
...
# Subtest: an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected
ok 14 - an unrelated owner deletion is fingerprinted and preserved while linked task paths are rejected
---
duration_ms: 14144.9193
type: 'test'
...
# Subtest: actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files
ok 15 - actual failed tests become a reviewed local commit and evidence report while preserving unrelated index and files
---
duration_ms: 16760.2976
type: 'test'
...
# Subtest: selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit
ok 16 - selected preexisting unstaged, staged and untracked owner edits cannot enter a task commit
---
duration_ms: 17902.4315
type: 'test'
...
# Switched to a new branch 'owner-branch'
# Subtest: source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD
ok 17 - source, unrelated stage and branch changes after review invalidate a commit plan without changing HEAD
---
duration_ms: 24541.1042
type: 'test'
...
# Switched to a new branch 'delivery-branch'
# Subtest: a later Git metadata change keeps matching source evidence valid but a real source edit requires checks
ok 18 - a later Git metadata change keeps matching source evidence valid but a real source edit requires checks
---
duration_ms: 12045.4771
type: 'test'
...
# Subtest: a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence
ok 19 - a corrupt passed-check log and a pending proposal block Git delivery instead of inventing evidence
---
duration_ms: 5769.988
type: 'test'
...
# HEAD is now at 38a2cd0 Sealed delivery fixture baseline
# Subtest: Git filters, merge state, detached HEAD and old task ownership are explicitly rejected
ok 20 - Git filters, merge state, detached HEAD and old task ownership are explicitly rejected
---
duration_ms: 24435.2067
type: 'test'
...
# Subtest: local snapshot commits disable repository hooks and signing and isolate the Git child environment
ok 21 - local snapshot commits disable repository hooks and signing and isolate the Git child environment
---
duration_ms: 10128.4506
type: 'test'
...
# Subtest: stopping before publication cancels safely; stopping after publication preserves the actual completed commit
ok 22 - stopping before publication cancels safely; stopping after publication preserves the actual completed commit
---
duration_ms: 19187.909
type: 'test'
...
# Subtest: delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart
ok 23 - delivery API confirms exactly one owned plan, serves verified reports and preserves results across restart
---
duration_ms: 14931.87
type: 'test'
...
# Subtest: the model can prepare an owned Git review and evidence report while publishing remains a separate user action
ok 24 - the model can prepare an owned Git review and evidence report while publishing remains a separate user action
---
duration_ms: 12402.3884
type: 'test'
...
# Subtest: HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved
ok 25 - HTTP Git review pairs deferred calls, survives reload and never requests more work until the saved preview is resolved
---
duration_ms: 11203.6096
type: 'test'
...
# Subtest: a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task
ok 26 - a reviewed Git preview can be revised or withdrawn without publishing or losing the current Task
---
duration_ms: 9278.396
type: 'test'
...
# Subtest: actual Electron debug argument ordering retains exactly the compiled entry and rejects extra or repeated actions
ok 27 - actual Electron debug argument ordering retains exactly the compiled entry and rejects extra or repeated actions
---
duration_ms: 1.0707
type: 'test'
...
# Subtest: native bridge refuses other origins, subframes, other windows and unsupported inputs before connecting
ok 28 - native bridge refuses other origins, subframes, other windows and unsupported inputs before connecting
---
duration_ms: 503.2812
type: 'test'
...
# Subtest: file reveal binds the current project, task, path, UTF-8 bytes and original SHA without executing the file
ok 29 - file reveal binds the current project, task, path, UTF-8 bytes and original SHA without executing the file
---
duration_ms: 548.3612
type: 'test'
...
# Subtest: file changed during asynchronous task recheck is not revealed as the old bytes
ok 30 - file changed during asynchronous task recheck is not revealed as the old bytes
---
duration_ms: 474.5377
type: 'test'
...
# Subtest: desktop browser profile and aliases stay outside project inventory and file access
ok 31 - desktop browser profile and aliases stay outside project inventory and file access
---
duration_ms: 489.6522
type: 'test'
...
# Subtest: native picker cancel and origin change after dialog publish no project registration
ok 32 - native picker cancel and origin change after dialog publish no project registration
---
duration_ms: 484.8091
type: 'test'
...
# Subtest: pending native action is not dispatched twice, and current task review returns its original seq
ok 33 - pending native action is not dispatched twice, and current task review returns its original seq
---
duration_ms: 488.4523
type: 'test'
...
# Subtest: native stop cancellation and changed original host never stop a replacement process
ok 34 - native stop cancellation and changed original host never stop a replacement process
---
duration_ms: 510.7507
type: 'test'
...
# Subtest: window register rejects host PID, stale installation, extra fields and missing creation identity
ok 35 - window register rejects host PID, stale installation, extra fields and missing creation identity
---
duration_ms: 0.3464
type: 'test'
...
# Subtest: a rebuilt source archive binds actual generated client assets and retains its original running identity after disk changes
ok 36 - a rebuilt source archive binds actual generated client assets and retains its original running identity after disk changes
---
duration_ms: 2366.6984
type: 'test'
...
# Subtest: host challenge proof rejects a stale challenge, changed identity and changed signature
ok 37 - host challenge proof rejects a stale challenge, changed identity and changed signature
---
duration_ms: 0.7911
type: 'test'
...
# Subtest: stop confirmation binds the original instance, creation and loaded runtime
ok 38 - stop confirmation binds the original instance, creation and loaded runtime
---
duration_ms: 0.1582
type: 'test'
...
# Subtest: state paths reject escaping, linked ancestors, ambiguous hardlinks and damaged JSON
ok 39 - state paths reject escaping, linked ancestors, ambiguous hardlinks and damaged JSON
---
duration_ms: 670.2656
type: 'test'
...
# Subtest: failed registration publishes no initialized memory and can complete after its actual inputs are supplied
ok 40 - failed registration publishes no initialized memory and can complete after its actual inputs are supplied
---
duration_ms: 3174.3609
type: 'test'
...
# Subtest: host shutdown cancels an un-signalled HTTP model request and refuses later requests until recovered
ok 41 - host shutdown cancels an un-signalled HTTP model request and refuses later requests until recovered
---
duration_ms: 1.2357
type: 'test'
...
# Subtest: host shutdown cancels model-pool acquisition and releases queue ownership without inventing attempts
ok 42 - host shutdown cancels model-pool acquisition and releases queue ownership without inventing attempts
---
duration_ms: 588.3477
type: 'test'
...
# Subtest: full candidate validation returns the exact loaded-input host identity and rejects undeclared or altered files
ok 43 - full candidate validation returns the exact loaded-input host identity and rejects undeclared or altered files
---
duration_ms: 1745.8619
type: 'test'
...
# Subtest: installation requires separate absolute program/data directories and a candidate in its own versions namespace
ok 44 - installation requires separate absolute program/data directories and a candidate in its own versions namespace
---
duration_ms: 1490.6803
type: 'test'
...
# Subtest: staging retains the original data and pointer without querying or restarting a host
ok 45 - staging retains the original data and pointer without querying or restarting a host
---
duration_ms: 2366.7272
type: 'test'
...
# Subtest: a post-pointer failure restores every original pointer byte and persistent row; a first-install failure removes only its published pointer
ok 46 - a post-pointer failure restores every original pointer byte and persistent row; a first-install failure removes only its published pointer
---
duration_ms: 5826.5645
type: 'test'
...
# Subtest: changed active manifest and concurrent pointer changes are rejected without overwriting the unknown record
ok 47 - changed active manifest and concurrent pointer changes are rejected without overwriting the unknown record
---
duration_ms: 2885.1995
type: 'test'
...
# Subtest: an unregistered non-HTTP listener blocks preflight even when service-info is absent
ok 48 - an unregistered non-HTTP listener blocks preflight even when service-info is absent
---
duration_ms: 1572.8937
type: 'test'
...
# Subtest: uninstall archives its original pointer and preserves every data row/artifact instead of recursively deleting data
ok 49 - uninstall archives its original pointer and preserves every data row/artifact instead of recursively deleting data
---
duration_ms: 3712.6358
type: 'test'
...
# Subtest: preflight rejects an unrelated program root or changed native bootstrap while preserving its original bytes
ok 50 - preflight rejects an unrelated program root or changed native bootstrap while preserving its original bytes
---
duration_ms: 1737.9328
type: 'test'
...
# Subtest: a changed owned bootstrap follows its candidate and a post-pointer fault restores both original bytes
ok 51 - a changed owned bootstrap follows its candidate and a post-pointer fault restores both original bytes
---
duration_ms: 6520.4347
type: 'test'
...
# Subtest: an external bootstrap change after preflight is preserved and never overwritten as an update or rollback
ok 52 - an external bootstrap change after preflight is preserved and never overwritten as an update or rollback
---
duration_ms: 4475.2565
type: 'test'
...
# Subtest: owned startup retries only read-only observation after a slow health response and attests the same original child
ok 53 - owned startup retries only read-only observation after a slow health response and attests the same original child
---
duration_ms: 4051.9566
type: 'test'
...
# Subtest: unverified startup expires with its original live child and never treats timeout or an unrelated health PID as proof
ok 54 - unverified startup expires with its original live child and never treats timeout or an unrelated health PID as proof
---
duration_ms: 5717.3495
type: 'test'
...
# Subtest: a question about the previous workbench error receives local error context and current change states
ok 55 - a question about the previous workbench error receives local error context and current change states
---
duration_ms: 1461.4897
type: 'test'
...
# Subtest: a transient model failure after an approved command retries only the model request
ok 56 - a transient model failure after an approved command retries only the model request
---
duration_ms: 2292.4474
type: 'test'
...
# Subtest: exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay
ok 57 - exhausted model retries preserve tool results, and explicit resume adds no new user turn or replay
---
duration_ms: 2297.9032
type: 'test'
...
# Subtest: stopping during model backoff cancels further requests and clears the running request state
ok 58 - stopping during model backoff cancels further requests and clears the running request state
---
duration_ms: 916.2731
type: 'test'
...
# Subtest: HTTP authentication errors are classified, redacted and never automatically retried
ok 59 - HTTP authentication errors are classified, redacted and never automatically retried
---
duration_ms: 19.8245
type: 'test'
...
# Subtest: temporary HTTP service errors retry and recover with recorded attempt counts
ok 60 - temporary HTTP service errors retry and recover with recorded attempt counts
---
duration_ms: 9.8777
type: 'test'
...
# Subtest: invalid and oversized protocol responses fail once with a useful response-format diagnosis
ok 61 - invalid and oversized protocol responses fail once with a useful response-format diagnosis
---
duration_ms: 4.075
type: 'test'
...
# Subtest: HTTP rate limits expose their source and obey the service retry interval before recovery
ok 62 - HTTP rate limits expose their source and obey the service retry interval before recovery
---
duration_ms: 1011.0537
type: 'test'
...
# Subtest: Windows commands preserve Chinese through a PowerShell pipeline into Node
ok 63 - Windows commands preserve Chinese through a PowerShell pipeline into Node
---
duration_ms: 680.6038
type: 'test'
...
# Subtest: Windows shell syntax errors stay readable and native command exit codes are retained
ok 64 - Windows shell syntax errors stay readable and native command exit codes are retained
---
duration_ms: 979.6148
type: 'test'
...
# Subtest: review and completed states do not turn a generic continue click into a new model request
ok 65 - review and completed states do not turn a generic continue click into a new model request
---
duration_ms: 634.32
type: 'test'
...
# Subtest: old session data receives a truthful historical connection diagnosis without rewriting history
ok 66 - old session data receives a truthful historical connection diagnosis without rewriting history
---
duration_ms: 685.0229
type: 'test'
...
# Subtest: engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart
ok 67 - engine HTTP checks bind the detected installation and current task, page original bytes and preserve them across host restart
---
duration_ms: 4684.2325
type: 'test'
...
# Subtest: HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session
ok 68 - HTTP stop seals a pending SDK call, rejects automatic replay and keeps failures attached to the original session
---
duration_ms: 3637.8156
type: 'test'
...
1..68
# tests 68
# suites 0
# pass 68
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 221725.5377
@@ -0,0 +1,502 @@
TAP version 13
# Subtest: controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse
ok 1 - controlled engine HTTP freezes one child, pages original owned input/report, rejects foreign reads and prevents changed-source reuse
---
duration_ms: 18125.3841
type: 'test'
...
# Subtest: native text and call IDs preserve original result pairing while unsupported content fails closed
ok 2 - native text and call IDs preserve original result pairing while unsupported content fails closed
---
duration_ms: 0.767
type: 'test'
...
# Subtest: one engine child freezes real installation identity before creating tasks and rejects a changed source
ok 3 - one engine child freezes real installation identity before creating tasks and rejects a changed source
---
duration_ms: 13620.8925
type: 'test'
...
# Subtest: owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs
ok 4 - owned native tools return saved results, use real approvals/checks and account each actual request once across new engine Runs
---
duration_ms: 28081.4713
type: 'test'
...
# Subtest: forged native scope cannot change a parent file and a final completion claim cannot replace worker proof
ok 5 - forged native scope cannot change a parent file and a final completion claim cannot replace worker proof
---
duration_ms: 18692.576
type: 'test'
...
# Subtest: duplicate native IDs are rejected without replaying a saved tool
ok 6 - duplicate native IDs are rejected without replaying a saved tool
---
duration_ms: 16645.3066
type: 'test'
...
# Subtest: native input exceeding the context budget is retained and sends no model request
ok 7 - native input exceeding the context budget is retained and sends no model request
---
duration_ms: 15637.3237
type: 'test'
...
# Subtest: stop retains a late reported model usage once and executes no tool from that output
ok 8 - stop retains a late reported model usage once and executes no tool from that output
---
duration_ms: 15341.3648
type: 'test'
...
# Subtest: a source change after the original model intent stops before native tools execute
ok 9 - a source change after the original model intent stops before native tools execute
---
duration_ms: 14806.644
type: 'test'
...
# Subtest: an engine source change while approval is pending invalidates the old permission before any check starts
ok 10 - an engine source change while approval is pending invalidates the old permission before any check starts
---
duration_ms: 17677.9091
type: 'test'
...
# Subtest: missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text
ok 11 - missing or noncompleted turn end cannot be adopted even with an owned receipt and assistant text
---
duration_ms: 0.6065
type: 'test'
...
# Subtest: closed root with an original live descendant remains unknown and retains its process tree
ok 12 - closed root with an original live descendant remains unknown and retains its process tree
---
duration_ms: 0.2728
type: 'test'
...
# Subtest: host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes
ok 13 - host recovery reserves original pending attempts exactly once and explicit review preserves unknown outcomes
---
duration_ms: 18776.9376
type: 'test'
...
# Subtest: corrupted model reservation cannot reduce recovered budget or permit a new engine request
ok 14 - corrupted model reservation cannot reduce recovered budget or permit a new engine request
---
duration_ms: 16334.4486
type: 'test'
...
# Subtest: engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch
ok 15 - engine detection seals the actual CLI, SDK, profile and Node and rejects mixed versions without launch
---
duration_ms: 693.4737
type: 'test'
...
# Subtest: owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence
ok 16 - owned engine probe waits for real ready identity, verifies six native responses and saves immutable task evidence
---
duration_ms: 1308.38
type: 'test'
...
# Subtest: an invalid startup nonce is rejected before initialize and preserves the process close and partial report
ok 17 - an invalid startup nonce is rejected before initialize and preserves the process close and partial report
---
duration_ms: 1237.4273
type: 'test'
...
# Subtest: SDK identity and session directory mismatches retain raw responses and never become verified
ok 18 - SDK identity and session directory mismatches retain raw responses and never become verified
---
duration_ms: 3731.1735
type: 'test'
...
# Subtest: cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation
ok 19 - cancel during a pending initialize closes only the owned process without sending an unsupported MCP cancellation
---
duration_ms: 1444.0536
type: 'test'
...
# Subtest: cancel before readiness sends no protocol request and a user retry creates a different process and record
ok 20 - cancel before readiness sends no protocol request and a user retry creates a different process and record
---
duration_ms: 1964.6608
type: 'test'
...
# Subtest: source or scratch changes and unexpected model traffic fail after preserving the actual observed result
ok 21 - source or scratch changes and unexpected model traffic fail after preserving the actual observed result
---
duration_ms: 4106.4654
type: 'test'
...
# Subtest: unowned idle notifications stay quarantined and server requests receive a rejection without granting operations
ok 22 - unowned idle notifications stay quarantined and server requests receive a rejection without granting operations
---
duration_ms: 2189.9595
type: 'test'
...
# Subtest: engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths
ok 23 - engine probe environment excludes parent secrets and NODE_OPTIONS while preserving operating system paths
---
duration_ms: 1099.8417
type: 'test'
...
# Subtest: foreign sessions and altered reports or task bindings cannot reuse verified engine evidence
ok 24 - foreign sessions and altered reports or task bindings cannot reuse verified engine evidence
---
duration_ms: 1017.5919
type: 'test'
...
# Subtest: restart never replays an active engine check or stops a historical PID, and keeps prior task state
ok 25 - restart never replays an active engine check or stops a historical PID, and keeps prior task state
---
duration_ms: 1333.3994
type: 'test'
...
# Subtest: model argument validation and runtime activity do not grant external engine prompt or project execution
ok 26 - model argument validation and runtime activity do not grant external engine prompt or project execution
---
duration_ms: 513.7503
type: 'test'
...
# Subtest: a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged
ok 27 - a follow-up question receives the actual failed engine check from its original Task and keeps its report unchanged
---
duration_ms: 1886.823
type: 'test'
...
# Subtest: unfixed dependency URLs and invalid integrity are reported without exposing URL credentials or allowing a plan
ok 28 - unfixed dependency URLs and invalid integrity are reported without exposing URL credentials or allowing a plan
---
duration_ms: 675.566
type: 'test'
...
# Subtest: hot upgrade refuses an active dependency operation or evaluation before changing runtime objects
ok 29 - hot upgrade refuses an active dependency operation or evaluation before changing runtime objects
---
duration_ms: 0.6279
type: 'test'
...
# Subtest: read-only environment diagnosis identifies actual runtime, missing dependencies and sealed inputs without installing or running scripts
ok 30 - read-only environment diagnosis identifies actual runtime, missing dependencies and sealed inputs without installing or running scripts
---
duration_ms: 9183.1012
type: 'test'
...
# Subtest: diagnosis rejects unsupported managers, lock integrity and credential configuration without reading config content
ok 31 - diagnosis rejects unsupported managers, lock integrity and credential configuration without reading config content
---
duration_ms: 8214.3234
type: 'test'
...
# Subtest: approved real npm ci runs only in owned worktree, skips scripts, retains logs and binds later actual tests
ok 32 - approved real npm ci runs only in owned worktree, skips scripts, retains logs and binds later actual tests
---
duration_ms: 15494.6745
type: 'test'
...
# Subtest: explicitly allowing lifecycle scripts executes sealed root script and preserves the separate preparation result
ok 33 - explicitly allowing lifecycle scripts executes sealed root script and preserves the separate preparation result
---
duration_ms: 12797.0205
type: 'test'
...
# Subtest: stale lockfile, tampered plan/config, cross-session identities and mismatched download sources never dispatch npm
ok 34 - stale lockfile, tampered plan/config, cross-session identities and mismatched download sources never dispatch npm
---
duration_ms: 9173.3543
type: 'test'
...
# Subtest: registry failure keeps original npm exit/log and performs no automatic fallback or replay
ok 35 - registry failure keeps original npm exit/log and performs no automatic fallback or replay
---
duration_ms: 11250.1949
type: 'test'
...
# Subtest: stopping a hanging dependency download records only its owned process and preserves stopped logs
ok 36 - stopping a hanging dependency download records only its owned process and preserves stopped logs
---
duration_ms: 12298.013
type: 'test'
...
# Subtest: restart retains unknown preparation, blocks writes and checks, and requires explicit read-only reconciliation
ok 37 - restart retains unknown preparation, blocks writes and checks, and requires explicit read-only reconciliation
---
duration_ms: 8581.7194
type: 'test'
...
# Subtest: HTTP environment flow survives refresh, requires explicit approval and preserves task and artifact ownership
ok 38 - HTTP environment flow survives refresh, requires explicit approval and preserves task and artifact ownership
---
duration_ms: 14908.9735
type: 'test'
...
# Subtest: Python environment diagnosis reads declarations and runtime identity without executing project code or installing packages
ok 39 - Python environment diagnosis reads declarations and runtime identity without executing project code or installing packages
---
duration_ms: 704.5015
type: 'test'
...
# Subtest: empty build cache directories keep dependency identity while added executable files invalidate it
ok 40 - empty build cache directories keep dependency identity while added executable files invalidate it
---
duration_ms: 800.6287
type: 'test'
...
# Subtest: dependency snapshots reject external links and incomplete budgets instead of claiming environment equivalence
ok 41 - dependency snapshots reject external links and incomplete budgets instead of claiming environment equivalence
---
duration_ms: 540.3623
type: 'test'
...
# Subtest: model-requested environment preparation uses the original approval boundary and never treats preparation as passed engineering checks
ok 42 - model-requested environment preparation uses the original approval boundary and never treats preparation as passed engineering checks
---
duration_ms: 14306.8349
type: 'test'
...
# Subtest: timeout and offline cache miss retain actual failures and new attempts require newly sealed plans
ok 43 - timeout and offline cache miss retain actual failures and new attempts require newly sealed plans
---
duration_ms: 16432.2702
type: 'test'
...
# Subtest: both evaluation worktrees can approve fixed dependency preparation and different actual dependencies reject candidate execution
ok 44 - both evaluation worktrees can approve fixed dependency preparation and different actual dependencies reject candidate execution
---
duration_ms: 34243.0862
type: 'test'
...
# Subtest: evaluation denominator distinguishes attempted unsealed candidates from unexecuted samples
ok 45 - evaluation denominator distinguishes attempted unsealed candidates from unexecuted samples
---
duration_ms: 0.3052
type: 'test'
...
# Subtest: evaluation summary retains sealed outcomes and stopped or failed original attempts
ok 46 - evaluation summary retains sealed outcomes and stopped or failed original attempts
---
duration_ms: 0.4207
type: 'test'
...
# Subtest: evaluation contract fixes bounded samples, source paths, checks and aggregate budget
ok 47 - evaluation contract fixes bounded samples, source paths, checks and aggregate budget
---
duration_ms: 458.2375
type: 'test'
...
# Subtest: same-source workspaces seal real commands before execution and preserve original staged and unstaged bytes
ok 48 - same-source workspaces seal real commands before execution and preserve original staged and unstaged bytes
---
duration_ms: 18803.7766
type: 'test'
...
# Subtest: actual original failures and candidate success are both preserved, then adoption requires parent review, checks and Git
ok 49 - actual original failures and candidate success are both preserved, then adoption requires parent review, checks and Git
---
duration_ms: 63704.4294
type: 'test'
...
# Subtest: candidate cannot shrink tests and changing original test bytes rejects execution before any model request
ok 50 - candidate cannot shrink tests and changing original test bytes rejects execution before any model request
---
duration_ms: 23829.0285
type: 'test'
...
# Subtest: missing upstream usage remains unknown and does not become a free run or invented cost
ok 51 - missing upstream usage remains unknown and does not become a free run or invented cost
---
duration_ms: 39366.3014
type: 'test'
...
# Subtest: missing raw check logs preserve unknown result and original sample denominator
ok 52 - missing raw check logs preserve unknown result and original sample denominator
---
duration_ms: 38521.8805
type: 'test'
...
# Subtest: source and model changes never silently replace an existing batch input
ok 53 - source and model changes never silently replace an existing batch input
---
duration_ms: 2907.18
type: 'test'
...
# Subtest: model revision change before preparing a fixed sample cannot silently use the replacement connection
ok 54 - model revision change before preparing a fixed sample cannot silently use the replacement connection
---
duration_ms: 2511.2493
type: 'test'
...
# Subtest: HTTP evaluations require host token, original fingerprint and session ownership; worker API cannot bypass evaluation flow
ok 55 - HTTP evaluations require host token, original fingerprint and session ownership; worker API cannot bypass evaluation flow
---
duration_ms: 17570.4015
type: 'test'
...
# Subtest: sample queue cannot skip or reset attempted samples, and reports freeze further writes
ok 56 - sample queue cannot skip or reset attempted samples, and reports freeze further writes
---
duration_ms: 33124.2297
type: 'test'
...
# Subtest: stop cancels only current candidate and preserves partial results instead of replaying a request
ok 57 - stop cancels only current candidate and preserves partial results instead of replaying a request
---
duration_ms: 25606.0386
type: 'test'
...
# Subtest: restart recovers interrupted evaluations as unknown and keeps completed checks and plan identity
ok 58 - restart recovers interrupted evaluations as unknown and keeps completed checks and plan identity
---
duration_ms: 24238.5482
type: 'test'
...
# Subtest: JSON migration survives process exit before commit and retains exact legacy backups
ok 59 - JSON migration survives process exit before commit and retains exact legacy backups
---
duration_ms: 1659.3039
type: 'test'
...
# Subtest: process exit after_state rolls back state, event and outbox together
ok 60 - process exit after_state rolls back state, event and outbox together
---
duration_ms: 1458.5712
type: 'test'
...
# Subtest: process exit after_event rolls back state, event and outbox together
ok 61 - process exit after_event rolls back state, event and outbox together
---
duration_ms: 1564.7001
type: 'test'
...
# Subtest: crash recovery at accepted retains execution identity and never replays side effects
ok 62 - crash recovery at accepted retains execution identity and never replays side effects
---
duration_ms: 1490.9235
type: 'test'
...
# Subtest: crash recovery at queued retains execution identity and never replays side effects
ok 63 - crash recovery at queued retains execution identity and never replays side effects
---
duration_ms: 1791.188
type: 'test'
...
# Subtest: crash recovery at approval_wait retains execution identity and never replays side effects
ok 64 - crash recovery at approval_wait retains execution identity and never replays side effects
---
duration_ms: 1965.7457
type: 'test'
...
# Subtest: crash recovery at approved retains execution identity and never replays side effects
ok 65 - crash recovery at approved retains execution identity and never replays side effects
---
duration_ms: 2041.8959
type: 'test'
...
# Subtest: crash recovery at effect_unrecorded retains execution identity and never replays side effects
ok 66 - crash recovery at effect_unrecorded retains execution identity and never replays side effects
---
duration_ms: 2364.9526
type: 'test'
...
# Subtest: crash recovery at result_committed retains execution identity and never replays side effects
ok 67 - crash recovery at result_committed retains execution identity and never replays side effects
---
duration_ms: 2399.5817
type: 'test'
...
# Subtest: crash recovery at before_next_model retains execution identity and never replays side effects
ok 68 - crash recovery at before_next_model retains execution identity and never replays side effects
---
duration_ms: 2865.6563
type: 'test'
...
# Subtest: state and event failures publish no success and preserve the last committed memory snapshot
ok 69 - state and event failures publish no success and preserve the last committed memory snapshot
---
duration_ms: 532.5961
type: 'test'
...
# Subtest: tool result artifacts and event cursors retain project ownership across restart
ok 70 - tool result artifacts and event cursors retain project ownership across restart
---
duration_ms: 1274.305
type: 'test'
...
# Subtest: token budgets pause before tools execute and continuation keeps original task and accumulated usage
ok 71 - token budgets pause before tools execute and continuation keeps original task and accumulated usage
---
duration_ms: 1251.9242
type: 'test'
...
# Subtest: a time budget interrupts an unresponsive model and persists a resumable run
ok 72 - a time budget interrupts an unresponsive model and persists a resumable run
---
duration_ms: 769.7821
type: 'test'
...
# Subtest: a corrupted large result artifact cannot become a recovered success
ok 73 - a corrupted large result artifact cannot become a recovered success
---
duration_ms: 767.7178
type: 'test'
...
# Subtest: hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules
ok 74 - hard-link aliases cannot expose protected bytes through reads, proposals, inventory or automatic project rules
---
duration_ms: 569.9285
type: 'test'
...
# Subtest: ambiguous project hard links are explicit and ordinary independent file copies remain readable
ok 75 - ambiguous project hard links are explicit and ordinary independent file copies remain readable
---
duration_ms: 450.5172
type: 'test'
...
# Subtest: proposals preserve project bytes until review; apply backs up the exact original bytes
ok 76 - proposals preserve project bytes until review; apply backs up the exact original bytes
---
duration_ms: 581.0847
type: 'test'
...
# Subtest: new nested files are created only on apply and unchanged content creates no proposal
ok 77 - new nested files are created only on apply and unchanged content creates no proposal
---
duration_ms: 540.8273
type: 'test'
...
# Subtest: stale reads and changed baselines are rejected without overwriting external edits
ok 78 - stale reads and changed baselines are rejected without overwriting external edits
---
duration_ms: 561.6037
type: 'test'
...
# Subtest: file paths reject traversal, absolute paths, credentials and outside junctions
ok 79 - file paths reject traversal, absolute paths, credentials and outside junctions
---
duration_ms: 559.4603
type: 'test'
...
# Subtest: read and search expose bounded text scopes and reject non UTF-8 / oversized files
ok 80 - read and search expose bounded text scopes and reject non UTF-8 / oversized files
---
duration_ms: 499.1218
type: 'test'
...
# Subtest: project-local junctions cannot expose or create protected Git and credential files
ok 81 - project-local junctions cannot expose or create protected Git and credential files
---
duration_ms: 482.2369
type: 'test'
...
# Subtest: Windows trailing-dot and trailing-space path aliases cannot bypass protected paths
ok 82 - Windows trailing-dot and trailing-space path aliases cannot bypass protected paths
---
duration_ms: 516.8049
type: 'test'
...
1..82
# tests 82
# suites 0
# pass 82
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 500879.455
@@ -0,0 +1,486 @@
TAP version 13
# Subtest: a starter is copied into user data once; restarting from another program version preserves existing projects and editable bytes
ok 1 - a starter is copied into user data once; restarting from another program version preserves existing projects and editable bytes
---
duration_ms: 1273.5186
type: 'test'
...
# Subtest: startup does not insert a demo or rewrite/reorder an existing user project registry
ok 2 - startup does not insert a demo or rewrite/reorder an existing user project registry
---
duration_ms: 767.0214
type: 'test'
...
# Subtest: PNG bytes are fully decoded, metadata-free and bounded; JPEG EXIF orientation is applied to the sent PNG
ok 3 - PNG bytes are fully decoded, metadata-free and bounded; JPEG EXIF orientation is applied to the sent PNG
---
duration_ms: 103.6841
type: 'test'
...
# Subtest: forged type, short headers, CRC damage, incomplete chunks, trailing payloads, animation and dimension bombs reject
ok 4 - forged type, short headers, CRC damage, incomplete chunks, trailing payloads, animation and dimension bombs reject
---
duration_ms: 23.3615
type: 'test'
...
# Subtest: draft image ownership, withdrawal, reload and atomic Task binding retain original SHA and original bytes
ok 5 - draft image ownership, withdrawal, reload and atomic Task binding retain original SHA and original bytes
---
duration_ms: 1431.269
type: 'test'
...
# Subtest: a failed session transaction restores draft status and cannot leave a Run consuming the attachment
ok 6 - a failed session transaction restores draft status and cannot leave a Run consuming the attachment
---
duration_ms: 804.8052
type: 'test'
...
# Subtest: draft limits, duplicate selection, source changes and cross-Task association reject before dispatch
ok 7 - draft limits, duplicate selection, source changes and cross-Task association reject before dispatch
---
duration_ms: 1378.4354
type: 'test'
...
# Subtest: demo and legacy paths refuse image dispatch without creating a Task or consuming the draft
ok 8 - demo and legacy paths refuse image dispatch without creating a Task or consuming the draft
---
duration_ms: 741.5989
type: 'test'
...
# Subtest: chat-completions sends one owned image per actual request, pairs original tools and verifies exact sealed bytes
ok 9 - chat-completions sends one owned image per actual request, pairs original tools and verifies exact sealed bytes
---
duration_ms: 2628.833
type: 'test'
...
# Subtest: responses sends one owned image per actual request, pairs original tools and verifies exact sealed bytes
ok 10 - responses sends one owned image per actual request, pairs original tools and verifies exact sealed bytes
---
duration_ms: 2485.0148
type: 'test'
...
# Subtest: mixed pool excludes unknown vision before lease and sends zero HTTP to the incompatible member
ok 11 - mixed pool excludes unknown vision before lease and sends zero HTTP to the incompatible member
---
duration_ms: 1882.2184
type: 'test'
...
# Subtest: vision probe requires correct randomized pixel order and evidence expires when the connection revision changes
ok 12 - vision probe requires correct randomized pixel order and evidence expires when the connection revision changes
---
duration_ms: 980.9782
type: 'test'
...
# Subtest: HTTP upload/read/withdraw uses session authorization, returns byte SHA and refuses unknown ownership
ok 13 - HTTP upload/read/withdraw uses session authorization, returns byte SHA and refuses unknown ownership
---
duration_ms: 846.0025
type: 'test'
...
# Subtest: image accounting excludes Base64 as text but seals every original request byte and reserves image input separately
ok 14 - image accounting excludes Base64 as text but seals every original request byte and reserves image input separately
---
duration_ms: 3.7722
type: 'test'
...
# Subtest: MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup
ok 15 - MCP registration stays disabled until an explicit real stdio probe and schema-based tool selection, with actual process cleanup
---
duration_ms: 2321.6488
type: 'test'
...
# Subtest: MCP probe holds the project operation lock until its owned process and report are settled
ok 16 - MCP probe holds the project operation lock until its owned process and report are settled
---
duration_ms: 1905.1944
type: 'test'
...
# Subtest: MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch
ok 17 - MCP validates the declared JSON schema subset and rejects unsupported schemas before external dispatch
---
duration_ms: 1.2722
type: 'test'
...
# Subtest: actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets
ok 18 - actual model MCP call approves long schema-valid arguments, validates the sent catalog and stores one original result without leaking environment secrets
---
duration_ms: 4815.7068
type: 'test'
...
# Subtest: denying an MCP call never starts another process or executes the external tool
ok 19 - denying an MCP call never starts another process or executes the external tool
---
duration_ms: 3603.7877
type: 'test'
...
# Subtest: actual handshake drift rejects tools/call even if program entry hash is unchanged
ok 20 - actual handshake drift rejects tools/call even if program entry hash is unchanged
---
duration_ms: 4893.4631
type: 'test'
...
# Subtest: cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen
ok 21 - cancelled dispatched external side effect stays unknown, closes its owned process and cannot replay on reopen
---
duration_ms: 3588.7111
type: 'test'
...
# Subtest: changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch
ok 22 - changed executable input, foreign project IDs and corrupted original contracts block enable and dispatch
---
duration_ms: 1867.5157
type: 'test'
...
# Subtest: registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests
ok 23 - registered MCP HTTP API uses fixed execution contracts and project-owned probe records with no model requests
---
duration_ms: 3599.2259
type: 'test'
...
# Subtest: unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay
ok 24 - unknown MCP pauses later tool calls and all project writers; fingerprinted acknowledgement clears only the review gates and explicit resume does not replay
---
duration_ms: 6537.7718
type: 'test'
...
# Subtest: MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged
ok 25 - MCP acknowledgement persistence failure restores both job and tool review gates; corrupt evidence cannot be acknowledged
---
duration_ms: 4788.3117
type: 'test'
...
# Subtest: actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call
ok 26 - actual host exit after an external effect restores unknown jobs without a fabricated report, allows source-bound review and never replays the call
---
duration_ms: 3951.4659
type: 'test'
...
# Subtest: changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source
ok 27 - changed enabled MCP programs can be explicitly disabled without launching or trusting their changed source
---
duration_ms: 1796.8962
type: 'test'
...
# Subtest: stdio preserves split UTF-8 frames and final replies drained after process exit
ok 28 - stdio preserves split UTF-8 frames and final replies drained after process exit
---
duration_ms: 1910.1405
type: 'test'
...
# Subtest: server-initiated model requests are refused instead of inheriting provider privileges
ok 29 - server-initiated model requests are refused instead of inheriting provider privileges
---
duration_ms: 699.9431
type: 'test'
...
# Subtest: invalid or over-budget protocol invalid closes only its owned process and is not retried
ok 30 - invalid or over-budget protocol invalid closes only its owned process and is not retried
---
duration_ms: 884.1778
type: 'test'
...
# Subtest: invalid or over-budget protocol oversized closes only its owned process and is not retried
ok 31 - invalid or over-budget protocol oversized closes only its owned process and is not retried
---
duration_ms: 890.6013
type: 'test'
...
# Subtest: cancel and timeout do not resend a dispatched request and pre-cancel has no request trace
ok 32 - cancel and timeout do not resend a dispatched request and pre-cancel has no request trace
---
duration_ms: 850.3203
type: 'test'
...
# Subtest: startup failure remains undispatched and has no process PID to terminate
ok 33 - startup failure remains undispatched and has no process PID to terminate
---
duration_ms: 673.7667
type: 'test'
...
# Subtest: REA launch filters a fixture credential canary and rejects changed entry identity before a new connection
ok 34 - REA launch filters a fixture credential canary and rejects changed entry identity before a new connection
---
duration_ms: 949.4466
type: 'test'
...
# Subtest: schema1 connections remain readable without inventing observed capabilities or migrating original state
ok 35 - schema1 connections remain readable without inventing observed capabilities or migrating original state
---
duration_ms: 668.5538
type: 'test'
...
# Subtest: protocol, unsupported capabilities and stream choice persist; client claims cannot forge verified evidence
ok 36 - protocol, unsupported capabilities and stream choice persist; client claims cannot forge verified evidence
---
duration_ms: 908.6869
type: 'test'
...
# Subtest: ability evidence belongs to exact connection and credential revision; unknown and unsupported reject required routing
ok 37 - ability evidence belongs to exact connection and credential revision; unknown and unsupported reject required routing
---
duration_ms: 0.2862
type: 'test'
...
# Subtest: invalid declarations and inconsistent stream settings reject before registry, revision and credentials mutate
ok 38 - invalid declarations and inconsistent stream settings reject before registry, revision and credentials mutate
---
duration_ms: 621.094
type: 'test'
...
# Subtest: model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart
ok 39 - model registry keeps original credentials/endpoint intact, rejects stale edits, and forgets only volatile keys on restart
---
duration_ms: 1104.4604
type: 'test'
...
# Subtest: config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts
ok 40 - config import previews exact revisions, keeps secrets volatile, syncs only when enabled and preserves manual edits on conflicts
---
duration_ms: 748.6881
type: 'test'
...
# Subtest: real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity
ok 41 - real HTTP pool fails over 429 to another model and never repeats completed tools; attempts seal actual request bytes and Run identity
---
duration_ms: 3036.9428
type: 'test'
...
# Subtest: pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests
ok 42 - pool rotation and weights select members on new Runs; disabled and missing credentials are excluded without requests
---
duration_ms: 3856.1391
type: 'test'
...
# Subtest: 401 blocks the credential revision; updating the key restores availability without leaking error echoes
ok 43 - 401 blocks the credential revision; updating the key restores availability without leaking error echoes
---
duration_ms: 1852.8664
type: 'test'
...
# Subtest: queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request
ok 44 - queued request cancellation and in-flight disable release only owned leases and do not dispatch another HTTP request
---
duration_ms: 1018.3436
type: 'test'
...
# Subtest: compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model
ok 45 - compiled model-center HTTP API persists public profiles, blocks forged origins, and local operations never invoke a model
---
duration_ms: 2163.1805
type: 'test'
...
# Subtest: model registry disk failures restore routing, pool profiles and credential references without partial updates
ok 46 - model registry disk failures restore routing, pool profiles and credential references without partial updates
---
duration_ms: 518.0135
type: 'test'
...
# Subtest: model selection and saved configuration commit together and failures preserve the original mode and endpoint
ok 47 - model selection and saved configuration commit together and failures preserve the original mode and endpoint
---
duration_ms: 641.4248
type: 'test'
...
# Subtest: configuration imports roll back the entire batch and retain one usable preview after validation or commit failure
ok 48 - configuration imports roll back the entire batch and retain one usable preview after validation or commit failure
---
duration_ms: 911.3854
type: 'test'
...
# Subtest: HTTP quota retains native code/type/param/request id, bounded original and allowlisted headers, never repeats that connection
ok 49 - HTTP quota retains native code/type/param/request id, bounded original and allowlisted headers, never repeats that connection
---
duration_ms: 1760.9142
type: 'test'
...
# Subtest: Retry-After above 90 seconds remains exact and a short local budget cannot trigger an early retry
ok 50 - Retry-After above 90 seconds remains exact and a short local budget cannot trigger an early retry
---
duration_ms: 1.1913
type: 'test'
...
# Subtest: Retry-After date, expired date, huge value and invalid header retain explicit semantics
ok 51 - Retry-After date, expired date, huge value and invalid header retain explicit semantics
---
duration_ms: 0.869
type: 'test'
...
# Subtest: unclassified 429 remains unspecified and every bounded actual retry retains its own original error
ok 52 - unclassified 429 remains unspecified and every bounded actual retry retains its own original error
---
duration_ms: 1471.8556
type: 'test'
...
# Subtest: oversized HTTP error saves exactly the bounded prefix and labels its incomplete range
ok 53 - oversized HTTP error saves exactly the bounded prefix and labels its incomplete range
---
duration_ms: 1757.9041
type: 'test'
...
# Subtest: Chat SSE error preserves upstream fields, original failed event, partial tool and reported usage without executing or retrying
ok 54 - Chat SSE error preserves upstream fields, original failed event, partial tool and reported usage without executing or retrying
---
duration_ms: 1579.9654
type: 'test'
...
# Subtest: Responses failed SSE retains original event/response identity and usage
ok 55 - Responses failed SSE retains original event/response identity and usage
---
duration_ms: 2405.227
type: 'test'
...
# Subtest: Responses incomplete SSE retains original event/response identity and usage
ok 56 - Responses incomplete SSE retains original event/response identity and usage
---
duration_ms: 1959.4875
type: 'test'
...
# Subtest: unsupported successful Responses output retains original JSON and usage with a local protocol origin
ok 57 - unsupported successful Responses output retains original JSON and usage with a local protocol origin
---
duration_ms: 2050.1491
type: 'test'
...
# Subtest: HTTP 200 native error is still an upstream failure rather than a fabricated successful answer
ok 58 - HTTP 200 native error is still an upstream failure rather than a fabricated successful answer
---
duration_ms: 0.995
type: 'test'
...
# Subtest: JSON-escaped credential echoes are redacted in the original preview and capture as well as parsed fields
ok 59 - JSON-escaped credential echoes are redacted in the original preview and capture as well as parsed fields
---
duration_ms: 0.6184
type: 'test'
...
# Subtest: quota failover uses another independent pool member and never replays a failed stream
ok 60 - quota failover uses another independent pool member and never replays a failed stream
---
duration_ms: 2503.4894
type: 'test'
...
# Subtest: native parameters are isolated by pool member, preserve Responses state and bind the original output reservation
ok 61 - native parameters are isolated by pool member, preserve Responses state and bind the original output reservation
---
duration_ms: 0.4934
type: 'test'
...
# Subtest: unsupported native fields and invalid values reject before dispatch instead of silently dropping or overriding constraints
ok 62 - unsupported native fields and invalid values reject before dispatch instead of silently dropping or overriding constraints
---
duration_ms: 0.4994
type: 'test'
...
# Subtest: native settings for legacy and registered profiles persist without changing credentials or old records and reject stale edits
ok 63 - native settings for legacy and registered profiles persist without changing credentials or old records and reject stale edits
---
duration_ms: 1188.821
type: 'test'
...
# Subtest: compiled native settings API saves/restores exact parameters and rejects reserved fields without mutating the profile
ok 64 - compiled native settings API saves/restores exact parameters and rejects reserved fields without mutating the profile
---
duration_ms: 2462.8684
type: 'test'
...
# Subtest: legacy connection test sends its saved native fields and selected output limit field without changing the configuration
ok 65 - legacy connection test sends its saved native fields and selected output limit field without changing the configuration
---
duration_ms: 2255.4759
type: 'test'
...
# Subtest: saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance
ok 66 - saved engine budgets verify all Chat/Responses route variants and reject a mismatched output allowance
---
duration_ms: 906.4599
type: 'test'
...
# Subtest: owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched
ok 67 - owned CC Switch SQLite imports the selected TOML Responses wire_api and leaves unknown clients untouched
---
duration_ms: 1278.9938
type: 'test'
...
# Subtest: Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes
ok 68 - Responses executes one original tool through Runtime, carries encrypted Items, reports raw usage and seals exact wire bytes
---
duration_ms: 2957.5312
type: 'test'
...
# Subtest: mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools
ok 69 - mixed-protocol pool keeps both actual variants and changes route on 429 without re-executing completed tools
---
duration_ms: 3841.9424
type: 'test'
...
# Subtest: Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
# Subtest: Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial"
ok 1 - Reject {"body":{"id":"resp_owned","status":"incomplete","output":[{"type":"function_call","id":"fc_partial"
---
duration_ms: 1960.1612
type: 'test'
...
# Subtest: Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal
ok 2 - Reject {"body":{"id":"resp_owned","status":"failed","output":[{"type":"function_call","id":"fc_failed","cal
---
duration_ms: 1638.7724
type: 'test'
...
# Subtest: Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal
ok 3 - Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"function_call","id":"fc_bad","cal
---
duration_ms: 1729.1641
type: 'test'
...
# Subtest: Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte
ok 4 - Reject {"body":{"id":"resp_owned","status":"completed","output":[{"type":"computer_call","id":"not-supporte
---
duration_ms: 1493.7161
type: 'test'
...
1..4
ok 70 - Responses incomplete, failed, missing call identity and unsupported hosted outputs never dispatch a tool
---
duration_ms: 6822.7622
type: 'test'
...
# Subtest: invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
# Subtest: chat-completions
ok 1 - chat-completions
---
duration_ms: 1259.0441
type: 'test'
...
# Subtest: responses
ok 2 - responses
---
duration_ms: 1415.5028
type: 'test'
...
1..2
ok 71 - invalid JSON in a nonstream Chat or Responses tool group prevents every tool and pool replay
---
duration_ms: 2675.0605
type: 'test'
...
# Subtest: wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint
ok 72 - wire adapter preserves tool IDs but never passes Responses-private Items to Chat or another endpoint
---
duration_ms: 0.2039
type: 'test'
...
# Subtest: connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions
ok 73 - connection JSON import accepts explicit Responses protocol and continues to reject unknown protocols without reading client sessions
---
duration_ms: 498.912
type: 'test'
...
1..73
# tests 79
# suites 0
# pass 79
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 65627.7853
@@ -0,0 +1,317 @@
TAP version 13
# Subtest: capability routing skips text-only members before acquiring a lease and records exact refusal in the original Run
ok 1 - capability routing skips text-only members before acquiring a lease and records exact refusal in the original Run
---
duration_ms: 1542.2905
type: 'test'
...
# Subtest: all incompatible members reject with no network request, no lease, preserved Task and explicit non-dispatched ledger
ok 2 - all incompatible members reject with no network request, no lease, preserved Task and explicit non-dispatched ledger
---
duration_ms: 1308.0381
type: 'test'
...
# Subtest: explicit synthetic tool probe verifies only actual matching call, never executes it and loses verification on revision changes
ok 3 - explicit synthetic tool probe verifies only actual matching call, never executes it and loses verification on revision changes
---
duration_ms: 901.6395
type: 'test'
...
# Subtest: plain text probe cannot verify tools; wrong tool nonce and client supplied evidence cannot claim verified support
ok 4 - plain text probe cannot verify tools; wrong tool nonce and client supplied evidence cannot claim verified support
---
duration_ms: 1038.1149
type: 'test'
...
# Subtest: a disabled connection invalidates an in-flight probe even when toggle mutates its original registry object
ok 5 - a disabled connection invalidates an in-flight probe even when toggle mutates its original registry object
---
duration_ms: 793.7248
type: 'test'
...
# Subtest: HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8
ok 6 - HTTP download preserves original malformed SSE bytes and artifact SHA instead of decoding invalid UTF8
---
duration_ms: 2309.0507
type: 'test'
...
# Subtest: terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once
ok 7 - terminated SSE adapts empty optional tool arguments, retains the exact wire bytes and executes the validated batch once
---
duration_ms: 3811.8595
type: 'test'
...
# Subtest: reported SSE usage survives rejected required arguments "" without dispatching any tool
ok 8 - reported SSE usage survives rejected required arguments "" without dispatching any tool
---
duration_ms: 2087.8466
type: 'test'
...
# Subtest: reported SSE usage survives rejected required arguments "{\\"path\\":" without dispatching any tool
ok 9 - reported SSE usage survives rejected required arguments "{\\"path\\":" without dispatching any tool
---
duration_ms: 2173.9572
type: 'test'
...
# Subtest: reported SSE usage survives rejected required arguments "null" without dispatching any tool
ok 10 - reported SSE usage survives rejected required arguments "null" without dispatching any tool
---
duration_ms: 2081.5226
type: 'test'
...
# Subtest: a stream without DONE retains reported usage but cannot adapt or execute even an optional tool
ok 11 - a stream without DONE retains reported usage but cannot adapt or execute even an optional tool
---
duration_ms: 2042.5277
type: 'test'
...
# Subtest: a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens
ok 12 - a timeout after reasoning-only fragments creates one unknown receipt and never invents reported tokens
---
duration_ms: 2483.2786
type: 'test'
...
# Subtest: real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage
ok 13 - real Chat SSE carries UTF8 and split tool JSON; Runtime executes only after DONE, stores partial progress and original usage
---
duration_ms: 2784.9399
type: 'test'
...
# Subtest: Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair
ok 14 - Responses typed SSE validates original item identity, terminal data, raw usage and tool result pair
---
duration_ms: 2074.954
type: 'test'
...
# Subtest: incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools
ok 15 - incomplete network stream retains unknown attempt and never automatically switches pool or dispatches fragment tools
---
duration_ms: 1336.0963
type: 'test'
...
# Subtest: stopping an active HTTP stream closes only original request and keeps partial text without executing tools
ok 16 - stopping an active HTTP stream closes only original request and keeps partial text without executing tools
---
duration_ms: 1982.053
type: 'test'
...
# Subtest: explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt
ok 17 - explicit streaming probe uses actual SSE despite unknown declaration and binds its own original attempt
---
duration_ms: 925.4285
type: 'test'
...
# Subtest: coalesced initial SSE events publish the latest partial state even when the upstream stays idle
ok 18 - coalesced initial SSE events publish the latest partial state even when the upstream stays idle
---
duration_ms: 1275.2659
type: 'test'
...
# Subtest: stream timeout closes the original HTTP response, preserves redacted capture and never retries
ok 19 - stream timeout closes the original HTTP response, preserves redacted capture and never retries
---
duration_ms: 846.766
type: 'test'
...
# Subtest: stream idle timeout preserves incomplete tool arguments, records unknown use and never fails over
ok 20 - stream idle timeout preserves incomplete tool arguments, records unknown use and never fails over
---
duration_ms: 1003.9154
type: 'test'
...
# Subtest: SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch
ok 21 - SSE accepts CR-only final event boundaries and retains exact invalid UTF8 bytes without dispatch
---
duration_ms: 0.7113
type: 'test'
...
# Subtest: stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data
# Subtest: reject 0
ok 1 - reject 0
---
duration_ms: 0.1654
type: 'test'
...
# Subtest: reject 1
ok 2 - reject 1
---
duration_ms: 0.1308
type: 'test'
...
# Subtest: reject 2
ok 3 - reject 2
---
duration_ms: 0.1581
type: 'test'
...
# Subtest: reject 3
ok 4 - reject 3
---
duration_ms: 4.9479
type: 'test'
...
# Subtest: reject 4
ok 5 - reject 4
---
duration_ms: 0.1175
type: 'test'
...
# Subtest: reject 5
ok 6 - reject 5
---
duration_ms: 0.1644
type: 'test'
...
1..6
ok 22 - stream parser rejects truncation, finish length, malformed JSON, duplicate sequence, changed final item and oversized data
---
duration_ms: 6.1272
type: 'test'
...
# Subtest: older configurations receive bounded wait defaults without changing the original object
ok 23 - older configurations receive bounded wait defaults without changing the original object
---
duration_ms: 1.0192
type: 'test'
...
# Subtest: active stream survives sixty seconds; byte activity resets idle but cannot extend total deadline
ok 24 - active stream survives sixty seconds; byte activity resets idle but cannot extend total deadline
---
duration_ms: 0.791
type: 'test'
...
# Subtest: silent stream has its own accurate deadline; caller cancellation and cleanup preserve their cause
ok 25 - silent stream has its own accurate deadline; caller cancellation and cleanup preserve their cause
---
duration_ms: 1.2996
type: 'test'
...
# Subtest: waiting for headers is bounded independently of stream-idle time
ok 26 - waiting for headers is bounded independently of stream-idle time
---
duration_ms: 0.2211
type: 'test'
...
# Subtest: wait settings persist, pin new runs and leave model pool, credentials and old run snapshots intact
ok 27 - wait settings persist, pin new runs and leave model pool, credentials and old run snapshots intact
---
duration_ms: 1330.4231
type: 'test'
...
# Subtest: paged inspection finds a corrupted old artifact outside the recent fifty and retains original evidence without model/tool execution
ok 28 - paged inspection finds a corrupted old artifact outside the recent fifty and retains original evidence without model/tool execution
---
duration_ms: 4889.1646
type: 'test'
...
# Subtest: inspection rejects ambiguous/out-of-range pagination and reports unknown tool/task identity without resolving it
ok 29 - inspection rejects ambiguous/out-of-range pagination and reports unknown tool/task identity without resolving it
---
duration_ms: 1005.2663
type: 'test'
...
# Subtest: exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply
ok 30 - exact patches preserve BOM/CRLF, unicode and all unselected bytes and back up the original on apply
---
duration_ms: 765.0854
type: 'test'
...
# Subtest: several patches are matched against one original snapshot in any input order and keep LF
ok 31 - several patches are matched against one original snapshot in any input order and keep LF
---
duration_ms: 843.8708
type: 'test'
...
# Subtest: mixed line endings require exact anchors and preserve untouched formatting
ok 32 - mixed line endings require exact anchors and preserve untouched formatting
---
duration_ms: 950.3064
type: 'test'
...
# Subtest: ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write
ok 33 - ambiguous, overlapping, missing and malformed patch anchors never create a proposal or write
---
duration_ms: 662.2229
type: 'test'
...
# Subtest: stale original hashes and changes before apply preserve owner edits and mark conflicts
ok 34 - stale original hashes and changes before apply preserve owner edits and mark conflicts
---
duration_ms: 818.5404
type: 'test'
...
# Subtest: no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes
ok 35 - no-op BOM patches/full content produce no change and replacements cannot split Unicode bytes
---
duration_ms: 609.6052
type: 'test'
...
# Subtest: real owned Vite starts only after approval, records OS ownership and live changes, and stops its tree
ok 36 - real owned Vite starts only after approval, records OS ownership and live changes, and stops its tree
---
duration_ms: 14844.8513
type: 'test'
...
# Subtest: occupied ports and approval-time conflicts never take over an unrelated listener
ok 37 - occupied ports and approval-time conflicts never take over an unrelated listener
---
duration_ms: 9747.8297
type: 'test'
...
# Subtest: background preview final-log failure retains unknown evidence without an unhandled startup promise
ok 38 - background preview final-log failure retains unknown evidence without an unhandled startup promise
---
duration_ms: 11956.843
type: 'test'
...
# Subtest: stale source, tampered plans, wrong ownership and arbitrary scripts cannot dispatch a preview
ok 39 - stale source, tampered plans, wrong ownership and arbitrary scripts cannot dispatch a preview
---
duration_ms: 9788.2768
type: 'test'
...
# Subtest: restart retains original unknown preview, blocks mutation, reconciles absent identity without replay
ok 40 - restart retains original unknown preview, blocks mutation, reconciles absent identity without replay
---
duration_ms: 9214.1094
type: 'test'
...
# Subtest: an actual shell command keeps Node and UTF-8 output while omitting host-only credentials
ok 41 - an actual shell command keeps Node and UTF-8 output while omitting host-only credentials
---
duration_ms: 746.7381
type: 'test'
...
# Subtest: real npm tests and build do not inherit arbitrary host credentials or Node injection settings
ok 42 - real npm tests and build do not inherit arbitrary host credentials or Node injection settings
---
duration_ms: 1992.8528
type: 'test'
...
# Subtest: real Python tests and compilation keep their sealed inputs without host credentials
ok 43 - real Python tests and compilation keep their sealed inputs without host credentials
---
duration_ms: 1648.684
type: 'test'
...
# Subtest: a process exiting between the Windows snapshot and owner query is absent only after a fresh query
ok 44 - a process exiting between the Windows snapshot and owner query is absent only after a fresh query
---
duration_ms: 2236.4529
type: 'test'
...
# Subtest: owner observation errors remain errors while a process is present, replaced, or cannot be rechecked
ok 45 - owner observation errors remain errors while a process is present, replaced, or cannot be rechecked
---
duration_ms: 1856.0278
type: 'test'
...
1..45
# tests 51
# suites 0
# pass 51
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 73554.0798
@@ -0,0 +1,428 @@
TAP version 13
# Subtest: cache controls require desktop authority, exact inputs and owned project identity while preserving task evidence
ok 1 - cache controls require desktop authority, exact inputs and owned project identity while preserving task evidence
---
duration_ms: 2216.2195
type: 'test'
...
# Subtest: cache enablement and derived reuse survive a real host restart without becoming task recovery state
ok 2 - cache enablement and derived reuse survive a real host restart without becoming task recovery state
---
duration_ms: 4006.8067
type: 'test'
...
# Subtest: persistent parsing is project/SHA/config bound and produces identical semantic indexes after restart
ok 3 - persistent parsing is project/SHA/config bound and produces identical semantic indexes after restart
---
duration_ms: 764.4752
type: 'test'
...
# warning: in the working copy of 'README.md', LF will be replaced by CRLF the next time Git touches it
# warning: in the working copy of 'main.ts', LF will be replaced by CRLF the next time Git touches it
# warning: in the working copy of 'value.ts', LF will be replaced by CRLF the next time Git touches it
# Subtest: same-size restored-mtime changes, additions, renames and deletions cannot reuse stale entries or import targets
ok 4 - same-size restored-mtime changes, additions, renames and deletions cannot reuse stale entries or import targets
---
duration_ms: 659.2354
type: 'test'
...
# Switched to a new branch 'other'
# Subtest: branch and commit changes invalidate even byte-identical sources
ok 5 - branch and commit changes invalidate even byte-identical sources
---
duration_ms: 1990.3138
type: 'test'
...
# Subtest: corrupt, malformed and schema-invalid records fall back to fresh parsing
ok 6 - corrupt, malformed and schema-invalid records fall back to fresh parsing
---
duration_ms: 623.0969
type: 'test'
...
# Subtest: disable and clear persist without touching sources, sessions, configuration or original artifacts
ok 7 - disable and clear persist without touching sources, sessions, configuration or original artifacts
---
duration_ms: 651.5014
type: 'test'
...
# Subtest: cache capacity bounds disk and memory by bytes and LRU project count
ok 8 - cache capacity bounds disk and memory by bytes and LRU project count
---
duration_ms: 541.864
type: 'test'
...
# Subtest: incomplete scans do not load or save cached entries; unavailable files leave the current result scope
ok 9 - incomplete scans do not load or save cached entries; unavailable files leave the current result scope
---
duration_ms: 525.7419
type: 'test'
...
# Subtest: project and cache junctions cannot expose or delete an outside directory
ok 10 - project and cache junctions cannot expose or delete an outside directory
---
duration_ms: 758.597
type: 'test'
...
# Subtest: concurrent file changes refuse a snapshot and clear during pending work cannot repopulate it
ok 11 - concurrent file changes refuse a snapshot and clear during pending work cannot repopulate it
---
duration_ms: 911.2404
type: 'test'
...
# Subtest: file access mode changes invalidate parsed material even when bytes are unchanged
ok 12 - file access mode changes invalidate parsed material even when bytes are unchanged
---
duration_ms: 890.0473
type: 'test'
...
# Subtest: tracked directory replaced by a junction invalidates access scope and never uses its old cache
ok 13 - tracked directory replaced by a junction invalidates access scope and never uses its old cache
---
duration_ms: 2602.7499
type: 'test'
...
# Subtest: JS/TS/React AST indexes actual declarations, exports, imports and verified source lines
ok 14 - JS/TS/React AST indexes actual declarations, exports, imports and verified source lines
---
duration_ms: 746.5217
type: 'test'
...
# Subtest: default expressions, named default exports and declared functions retain their AST evidence
ok 15 - default expressions, named default exports and declared functions retain their AST evidence
---
duration_ms: 864.7296
type: 'test'
...
# Subtest: incremental refresh invalidates changed/deleted symbols and recalculates reused import targets
ok 16 - incremental refresh invalidates changed/deleted symbols and recalculates reused import targets
---
duration_ms: 1011.2166
type: 'test'
...
# Subtest: Python candidates exclude comments and multiline strings and declare limited evidence
ok 17 - Python candidates exclude comments and multiline strings and declare limited evidence
---
duration_ms: 732.4105
type: 'test'
...
# Subtest: indexes isolate project identity and root and evict bounded caches without sharing results
ok 18 - indexes isolate project identity and root and evict bounded caches without sharing results
---
duration_ms: 1193.5608
type: 'test'
...
# Subtest: Git ignore, credential paths and links stay outside the index and no project files are executed
ok 19 - Git ignore, credential paths and links stay outside the index and no project files are executed
---
duration_ms: 1467.1212
type: 'test'
...
# Subtest: malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable
ok 20 - malformed, binary, non-UTF8 and bounded files expose partial coverage while good files remain searchable
---
duration_ms: 706.4957
type: 'test'
...
# Subtest: index query rejects invalid limits/types and does not imply reference or alias resolution
ok 21 - index query rejects invalid limits/types and does not imply reference or alias resolution
---
duration_ms: 763.7917
type: 'test'
...
# Subtest: read-only engineering inspection disables configured Git clean filters and preserves index bytes
ok 22 - read-only engineering inspection disables configured Git clean filters and preserves index bytes
---
duration_ms: 2389.8343
type: 'test'
...
# Subtest: Python multiline declarations retain candidate scope without interpreting expressions as declarations
ok 23 - Python multiline declarations retain candidate scope without interpreting expressions as declarations
---
duration_ms: 671.0478
type: 'test'
...
# Subtest: TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit
ok 24 - TypeScript module candidates support import-equals and MTS/CTS while opaque imports stay explicit
---
duration_ms: 718.9657
type: 'test'
...
# Subtest: actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart
ok 25 - actual HTTP requests reuse only this project source-checked memory as redacted data and preserve sent evidence after archive/restart
---
duration_ms: 1882.9834
type: 'test'
...
# Subtest: actual HTTP request excludes archived, timed-out and foreign-project memories
ok 26 - actual HTTP request excludes archived, timed-out and foreign-project memories
---
duration_ms: 2514.6159
type: 'test'
...
# Subtest: actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool
ok 27 - actual next HTTP request removes expired memory after a tool observes a source change without replaying that tool
---
duration_ms: 2662.4005
type: 'test'
...
# Subtest: incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots
ok 28 - incomplete inventory and excluded-file SHA changes cannot enter actual HTTP memory context or inspect_session snapshots
---
duration_ms: 2449.5417
type: 'test'
...
# Subtest: corrupt original artifact expires its memory and cannot reach an HTTP model request
ok 29 - corrupt original artifact expires its memory and cannot reach an HTTP model request
---
duration_ms: 1880.0086
type: 'test'
...
# Subtest: memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values
ok 30 - memory JSON is bounded in escaped UTF-8 bytes and entry count, skips oversized entries and retains complete multilingual values
---
duration_ms: 2562.6423
type: 'test'
...
# Subtest: optional memory yields to the complete goal and original code evidence under the whole-request budget
ok 31 - optional memory yields to the complete goal and original code evidence under the whole-request budget
---
duration_ms: 883.6204
type: 'test'
...
# Subtest: changed sealed memory artifacts or binding fields fail verification while the original request remains immutable
ok 32 - changed sealed memory artifacts or binding fields fail verification while the original request remains immutable
---
duration_ms: 1882.8626
type: 'test'
...
# Subtest: a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service
ok 33 - a malformed project declaration omits optional memory while the repair Task still reaches the owned HTTP service
---
duration_ms: 1760.301
type: 'test'
...
# Subtest: an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure
ok 34 - an expiration persistence failure prevents dispatch and is not hidden as an optional scan failure
---
duration_ms: 960.8277
type: 'test'
...
# Subtest: project memories persist across restart, keep source provenance, and are visible across tasks
ok 35 - project memories persist across restart, keep source provenance, and are visible across tasks
---
duration_ms: 1098.0291
type: 'test'
...
# Subtest: source changes expire current project memories and keep the original evidence
ok 36 - source changes expire current project memories and keep the original evidence
---
duration_ms: 951.8562
type: 'test'
...
# Subtest: incomplete source scans mark current memories unverified without expiring or reusing them
ok 37 - incomplete source scans mark current memories unverified without expiring or reusing them
---
duration_ms: 976.5763
type: 'test'
...
# Subtest: explicit file provenance is rechecked even when the inventory excludes that path
ok 38 - explicit file provenance is rechecked even when the inventory excludes that path
---
duration_ms: 965.1708
type: 'test'
...
# Subtest: execution snapshots do not expose project memories before their source scope is validated
ok 39 - execution snapshots do not expose project memories before their source scope is validated
---
duration_ms: 783.7698
type: 'test'
...
# Subtest: project memory records stay isolated and archive requires the owning session
ok 40 - project memory records stay isolated and archive requires the owning session
---
duration_ms: 1024.0775
type: 'test'
...
# Subtest: project memory HTTP API exposes read-only source status and explicit writes
ok 41 - project memory HTTP API exposes read-only source status and explicit writes
---
duration_ms: 2413.3824
type: 'test'
...
# Subtest: two Purge source versions lock nine original inputs without executing JavaScript or postinstall and remain disabled by default
ok 42 - two Purge source versions lock nine original inputs without executing JavaScript or postinstall and remain disabled by default
---
duration_ms: 776.2628
type: 'test'
...
# Subtest: incomplete, unsupported, relative and oversized sources cannot enable the experiment
ok 43 - incomplete, unsupported, relative and oversized sources cannot enable the experiment
---
duration_ms: 683.0708
type: 'test'
...
# Subtest: invalid source fingerprints and invented privilege or retry fields fail before any parent Task is created
ok 44 - invalid source fingerprints and invented privilege or retry fields fail before any parent Task is created
---
duration_ms: 2381.5158
type: 'test'
...
# Subtest: source edits between detection and plan are rejected without creating a parent Task
ok 45 - source edits between detection and plan are rejected without creating a parent Task
---
duration_ms: 1902.67
type: 'test'
...
# Subtest: source edits after sealing cannot launch a child and do not reset its cumulative budget
ok 46 - source edits after sealing cannot launch a child and do not reset its cumulative budget
---
duration_ms: 12082.3659
type: 'test'
...
# Subtest: literal experiment text is sealed into the parent, worker and each new Run while actual host approvals and saved results remain required
ok 47 - literal experiment text is sealed into the parent, worker and each new Run while actual host approvals and saved results remain required
---
duration_ms: 33809.4047
type: 'test'
...
# Subtest: source changes after a model response stop before any native tool is accepted, retaining the actual usage once
ok 48 - source changes after a model response stop before any native tool is accepted, retaining the actual usage once
---
duration_ms: 13517.039
type: 'test'
...
# Subtest: source changes while approval is pending invalidate the old permission before an engineering check starts
ok 49 - source changes while approval is pending invalidate the old permission before an engineering check starts
---
duration_ms: 17598.3398
type: 'test'
...
# Subtest: altered text, interpolation, section order and policy flags cannot reuse a sealed experiment
ok 50 - altered text, interpolation, section order and policy flags cannot reuse a sealed experiment
---
duration_ms: 1910.7223
type: 'test'
...
# Subtest: the observed SDK system-message layout and the explicit system field both require exactly one effective section, never a user or tool copy
ok 51 - the observed SDK system-message layout and the explicit system field both require exactly one effective section, never a user or tool copy
---
duration_ms: 1790.9481
type: 'test'
...
# Subtest: a missing or duplicated experimental section in the actual input is rejected before any model dispatch
ok 52 - a missing or duplicated experimental section in the actual input is rejected before any model dispatch
---
duration_ms: 23624.3076
type: 'test'
...
# Subtest: experimental prompt overhead still participates in the original complete-input budget guard
ok 53 - experimental prompt overhead still participates in the original complete-input budget guard
---
duration_ms: 11408.3302
type: 'test'
...
# Subtest: source detection HTTP remains local-authenticated and read-only with no configured model requests
ok 54 - source detection HTTP remains local-authenticated and read-only with no configured model requests
---
duration_ms: 1519.2641
type: 'test'
...
# Subtest: Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart
ok 55 - Python HTTP plans keep npm defaults, require owned approval and preserve actual results across restart
---
duration_ms: 10100.9924
type: 'test'
...
# Subtest: an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls
ok 56 - an isolated three-module Python Task repairs, checks and delivers a source-bound Git report without extra model calls
---
duration_ms: 41228.3793
type: 'test'
...
# Subtest: Python static inspection does not import project code or probe a project interpreter before approval
ok 57 - Python static inspection does not import project code or probe a project interpreter before approval
---
duration_ms: 1038.9528
type: 'test'
...
# Subtest: a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence
ok 58 - a real three-module Python failure, reviewed repairs, tests and compilation retain exact structured evidence
---
duration_ms: 4466.1736
type: 'test'
...
# Subtest: unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names
ok 59 - unittest counts repeated execution ordinals and subtest skips rather than deduplicating display names
---
duration_ms: 2677.3498
type: 'test'
...
# Subtest: unittest empty, skipped, expected failure and class initialization errors never verify a task
ok 60 - unittest empty, skipped, expected failure and class initialization errors never verify a task
---
duration_ms: 7020.0159
type: 'test'
...
# Subtest: stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector
ok 61 - stdout claims cannot replace actual unittest results and an early exit cannot forge a successful collector
---
duration_ms: 2950.2153
type: 'test'
...
# Subtest: compilation reads actual Python source bytes without executing top-level project code
ok 62 - compilation reads actual Python source bytes without executing top-level project code
---
duration_ms: 3115.6642
type: 'test'
...
# Subtest: Node and Python mixed projects retain the existing npm default and require an explicit Python selection
ok 63 - Node and Python mixed projects retain the existing npm default and require an explicit Python selection
---
duration_ms: 2400.6503
type: 'test'
...
# Subtest: changed project interpreters and forged Python plan bindings execute no check
ok 64 - changed project interpreters and forged Python plan bindings execute no check
---
duration_ms: 1306.9328
type: 'test'
...
# Subtest: malformed TOML and invalid Python test paths are reported without expanding npm check scope
ok 65 - malformed TOML and invalid Python test paths are reported without expanding npm check scope
---
duration_ms: 978.9113
type: 'test'
...
# Subtest: stopping a real Python check terminates its child and keeps the completed result as cancelled
ok 66 - stopping a real Python check terminates its child and keeps the completed result as cancelled
---
duration_ms: 1885.0225
type: 'test'
...
# Subtest: real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes
ok 67 - real pytest pass, failure, skip, collection errors and teardown errors use collected case outcomes
---
duration_ms: 14162.6352
type: 'test'
...
# Subtest: a real project virtual environment is detected statically and its actual version is recorded only during the approved check
ok 68 - a real project virtual environment is detected statically and its actual version is recorded only during the approved check
---
duration_ms: 7908.722
type: 'test'
...
# Subtest: a missing interpreter and repeated pytest item objects cannot create a false verification pass
ok 69 - a missing interpreter and repeated pytest item objects cannot create a false verification pass
---
duration_ms: 2630.9486
type: 'test'
...
1..69
# tests 69
# suites 0
# pass 69
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 149220.2699
@@ -0,0 +1,406 @@
TAP version 13
# Subtest: continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause
ok 1 - continuation reads advance through historical pages without a false pause while repeated current-Run pages still pause
---
duration_ms: 1.8573
type: 'test'
...
# Subtest: a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget
ok 2 - a new tool page replaces old latest-feedback space and still obeys its escaped protocol budget
---
duration_ms: 0.6217
type: 'test'
...
# Subtest: budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters
ok 3 - budgeted artifact pages count escaped protocol bytes and reconstruct original multilingual JSON without losing characters
---
duration_ms: 9.087
type: 'test'
...
# Subtest: known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress
ok 4 - known artifact coverage detects semantic repeats despite changing limits, and advancing pages or direct evidence restore progress
---
duration_ms: 0.3436
type: 'test'
...
# Subtest: actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools
ok 5 - actual large artifact reads are present in the next bounded HTTP request and next_offset progresses without redoing tools
---
duration_ms: 4366.0662
type: 'test'
...
# Subtest: a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly
ok 6 - a real repeated artifact loop pauses the same Task after recorded results, survives reload and only resumes explicitly
---
duration_ms: 4460.2273
type: 'test'
...
# Subtest: actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay
ok 7 - actual HTTP continuation after reload sends distinct historically covered pages without false no_progress or replay
---
duration_ms: 5438.6388
type: 'test'
...
# Subtest: an installed app outside the source drive resolves registered SDK and Purge through actual input verification
ok 8 - an installed app outside the source drive resolves registered SDK and Purge through actual input verification
---
duration_ms: 785.7047
type: 'test'
...
# Subtest: standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source
ok 9 - standalone registration resolves the upstream metadata directory and missing upstream falls back to the other registered source
---
duration_ms: 672.7307
type: 'test'
...
# Subtest: registered hints keep explicit roots, environment and existing app-relative candidates in their original priority
ok 10 - registered hints keep explicit roots, environment and existing app-relative candidates in their original priority
---
duration_ms: 848.0335
type: 'test'
...
# Subtest: unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates
ok 11 - unknown IDs, duplicate registered IDs, wrong versions and relative or inconsistent metadata are not lookup candidates
---
duration_ms: 509.8534
type: 'test'
...
# Subtest: oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source
ok 12 - oversized, malformed, invalid UTF-8 and non-file registry inputs cannot silently enable a source
---
duration_ms: 654.1487
type: 'test'
...
# Subtest: a linked registry directory is rejected without reading or deleting its external source
ok 13 - a linked registry directory is rejected without reading or deleting its external source
---
duration_ms: 614.6702
type: 'test'
...
# Subtest: matching research declarations do not replace actual installed version and critical-source checks
ok 14 - matching research declarations do not replace actual installed version and critical-source checks
---
duration_ms: 596.2924
type: 'test'
...
# Subtest: context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs
ok 15 - context APIs retain exact request identity, paginate archived groups and reject foreign sessions/runs
---
duration_ms: 3207.5658
type: 'test'
...
# Subtest: delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification
ok 16 - delivery reports verify request body, sealed plan and original archived bytes, and show corruption as needing verification
---
duration_ms: 2387.9285
type: 'test'
...
# Subtest: direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget
ok 17 - direct code evidence remains selected while recent historical-index browsing is archived within the complete request budget
---
duration_ms: 1828.5917
type: 'test'
...
# Subtest: one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments
ok 18 - one long user turn becomes bounded complete groups with exact UTF-8 history and recent JSON arguments
---
duration_ms: 4002.6871
type: 'test'
...
# Subtest: tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests
ok 19 - tool definitions, exact system bytes, output reserve and remaining Run/Task budget are accounted before requests
---
duration_ms: 841.8072
type: 'test'
...
# Subtest: oversized required user instructions pause intact and can be explicitly resumed after increasing the window
ok 20 - oversized required user instructions pause intact and can be explicitly resumed after increasing the window
---
duration_ms: 1698.0596
type: 'test'
...
# Subtest: all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix
ok 21 - all task instructions, constraints and acceptance remain in the runtime system instead of an eight-item or byte prefix
---
duration_ms: 1529.6487
type: 'test'
...
# Subtest: a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived
ok 22 - a newest manageable multi-tool group stays exact even beyond the working target; oversized earlier groups are archived
---
duration_ms: 1184.0462
type: 'test'
...
# Subtest: invalid orphan result is rejected before archive or network preparation
ok 23 - invalid orphan result is rejected before archive or network preparation
---
duration_ms: 655.6305
type: 'test'
...
# Subtest: invalid missing result is rejected before archive or network preparation
ok 24 - invalid missing result is rejected before archive or network preparation
---
duration_ms: 769.2707
type: 'test'
...
# Subtest: invalid wrong result is rejected before archive or network preparation
ok 25 - invalid wrong result is rejected before archive or network preparation
---
duration_ms: 711.4964
type: 'test'
...
# Subtest: invalid duplicate call is rejected before archive or network preparation
ok 26 - invalid duplicate call is rejected before archive or network preparation
---
duration_ms: 684.6573
type: 'test'
...
# Subtest: a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON
ok 27 - a group larger than the artifact limit uses verified Unicode-safe chunks without replacing tool JSON
---
duration_ms: 1946.1996
type: 'test'
...
# Subtest: changed or missing archived evidence stops reuse and is never silently recreated
ok 28 - changed or missing archived evidence stops reuse and is never silently recreated
---
duration_ms: 974.4496
type: 'test'
...
# Subtest: transaction failure prevents publishing a plan and any corresponding model request
ok 29 - transaction failure prevents publishing a plan and any corresponding model request
---
duration_ms: 892.6074
type: 'test'
...
# Subtest: the Provider rejects body mutation after a sealed plan before calling HTTP
ok 30 - the Provider rejects body mutation after a sealed plan before calling HTTP
---
duration_ms: 574.1242
type: 'test'
...
# Subtest: HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command
ok 31 - HTTP failure and explicit same-Task resume reuse exact completed results and request hashes without repeating a command
---
duration_ms: 7888.1504
type: 'test'
...
# Subtest: a real process exit after plan persistence marks interruption and never issues an automatic model request
ok 32 - a real process exit after plan persistence marks interruption and never issues an automatic model request
---
duration_ms: 1487.8619
type: 'test'
...
# Subtest: deep Windows data directories keep REA output within the external path allowance and retain owned evidence
ok 33 - deep Windows data directories keep REA output within the external path allowance and retain owned evidence
---
duration_ms: 2490.2576
type: 'test'
...
# Subtest: user research registration creates an owned Task without model requests and seals the exact artifact identity
ok 34 - user research registration creates an owned Task without model requests and seals the exact artifact identity
---
duration_ms: 848.4883
type: 'test'
...
# Subtest: complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload
ok 35 - complete research binds original Evidence and Bundle, pages exact fields and reuses verified results after reload
---
duration_ms: 2083.8359
type: 'test'
...
# Subtest: artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses
ok 36 - artifact changes before analysis refuse dispatch and changes during analysis preserve unverified original responses
---
duration_ms: 2913.8023
type: 'test'
...
# Subtest: owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history
ok 37 - owned cancellation closes the connection, concurrent and automatic retries are refused, explicit new analysis preserves history
---
duration_ms: 2239.3451
type: 'test'
...
# Subtest: a dispatched transport timeout stays unknown and reload never launches or kills a saved PID
ok 38 - a dispatched transport timeout stays unknown and reload never launches or kills a saved PID
---
duration_ms: 1441.8462
type: 'test'
...
# Subtest: corrupt Evidence parts and changed binding records are refused instead of silently re-analysed
ok 39 - corrupt Evidence parts and changed binding records are refused instead of silently re-analysed
---
duration_ms: 1627.0665
type: 'test'
...
# Subtest: research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts
ok 40 - research documents over the single-artifact limit preserve exact Unicode bytes with owned verifiable parts
---
duration_ms: 1013.7357
type: 'test'
...
# Subtest: research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay
ok 41 - research tools are only sent for registered Task artifacts and actual HTTP uses the sealed tool contract without replay
---
duration_ms: 5622.8218
type: 'test'
...
# Subtest: file identity rejects directory and invalid formats without running a target
ok 42 - file identity rejects directory and invalid formats without running a target
---
duration_ms: 554.6553
type: 'test'
...
# Subtest: a stop from the event loop interrupts immediate model replies before later tools
ok 43 - a stop from the event loop interrupts immediate model replies before later tools
---
duration_ms: 1317.3791
type: 'test'
...
# Subtest: a stop after the first tool preserves a complete interrupted multi-call protocol group
ok 44 - a stop after the first tool preserves a complete interrupted multi-call protocol group
---
duration_ms: 2148.6376
type: 'test'
...
# Subtest: the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands
ok 45 - the compatible HTTP loop preserves call IDs, validates errors and waits before executing commands
---
duration_ms: 5517.9397
type: 'test'
...
# Subtest: denial prevents command execution and produces a paired denied result
ok 46 - denial prevents command execution and produces a paired denied result
---
duration_ms: 2031.434
type: 'test'
...
# Subtest: stopping during approval interrupts pending calls without executing or replaying them
ok 47 - stopping during approval interrupts pending calls without executing or replaying them
---
duration_ms: 1559.1363
type: 'test'
...
# Subtest: stopping a running fixture command terminates its own process tree and retains uncertain state
ok 48 - stopping a running fixture command terminates its own process tree and retains uncertain state
---
duration_ms: 2154.6313
type: 'test'
...
# Subtest: command output decodes split UTF-8 and excludes the workbench key from child environment
ok 49 - command output decodes split UTF-8 and excludes the workbench key from child environment
---
duration_ms: 1149.421
type: 'test'
...
# Subtest: model-list testing uses a tentative key without changing the saved connection and redacts service errors
ok 50 - model-list testing uses a tentative key without changing the saved connection and redacts service errors
---
duration_ms: 6.1892
type: 'test'
...
# Subtest: truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities
ok 51 - truncated or repeated model calls fail before execution; tool input validation rejects unknown capabilities
---
duration_ms: 2991.6273
type: 'test'
...
# Subtest: request projection keeps exact tool pairs and complete recent user instructions while preserving disk history
ok 52 - request projection keeps exact tool pairs and complete recent user instructions while preserving disk history
---
duration_ms: 1490.2048
type: 'test'
...
# Subtest: local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project
ok 53 - local skill revisions require explicit enable, retain original text, survive restart and stay within the selected project
---
duration_ms: 1088.1479
type: 'test'
...
# Subtest: registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code
ok 54 - registration rejects non-SKILL paths, oversized/non-UTF8 files, duplicate sources and wrong field shapes without running project code
---
duration_ms: 826.1427
type: 'test'
...
# Subtest: actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing
ok 55 - actual HTTP models receive only enabled current-project metadata, then a redacted owned skill page with complete tool pairing
---
duration_ms: 2655.9279
type: 'test'
...
# Subtest: source edits after a catalog request prevent the read and appear as changed on the next request without replay
ok 56 - source edits after a catalog request prevent the read and appear as changed on the next request without replay
---
duration_ms: 2633.5988
type: 'test'
...
# Subtest: disabled and foreign skills cannot be read by guessing their IDs from another project
ok 57 - disabled and foreign skills cannot be read by guessing their IDs from another project
---
duration_ms: 2525.034
type: 'test'
...
# Subtest: skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code
ok 58 - skill catalog takes remaining escaped JSON budget and cannot evict the user goal or current code
---
duration_ms: 1158.4951
type: 'test'
...
# Subtest: multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact
ok 59 - multilingual skill body pages fit actual tool JSON bytes and every page uses the same immutable artifact
---
duration_ms: 3686.1499
type: 'test'
...
# Subtest: registry failures roll back enable and refresh state; corrupted snapshots block requests before network
ok 60 - registry failures roll back enable and refresh state; corrupted snapshots block requests before network
---
duration_ms: 1289.8397
type: 'test'
...
# Subtest: saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs
ok 61 - saved skill catalogs retain SHA-bound historical evidence and reject corrupt catalog blobs
---
duration_ms: 1905.6989
type: 'test'
...
# Subtest: HTTP skill administration enforces project scope, revision checks and idle mutation without model calls
ok 62 - HTTP skill administration enforces project scope, revision checks and idle mutation without model calls
---
duration_ms: 3105.8692
type: 'test'
...
# Subtest: JSON state keeps an atomic backup and preserves corrupt primary files
ok 63 - JSON state keeps an atomic backup and preserves corrupt primary files
---
duration_ms: 776.3845
type: 'test'
...
# Subtest: tool-pair recovery fills missing results and drops orphan or duplicate results
ok 64 - tool-pair recovery fills missing results and drops orphan or duplicate results
---
duration_ms: 0.4041
type: 'test'
...
# Subtest: restart pauses unfinished work, retains proposals and never replays a command
ok 65 - restart pauses unfinished work, retains proposals and never replays a command
---
duration_ms: 680.1772
type: 'test'
...
# Subtest: public snapshots carry increasing revisions without the private provider transcript or config key
ok 66 - public snapshots carry increasing revisions without the private provider transcript or config key
---
duration_ms: 1103.7487
type: 'test'
...
1..66
# tests 66
# suites 0
# pass 66
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 59273.1139
@@ -0,0 +1,346 @@
TAP version 13
# Subtest: a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay
ok 1 - a checkpoint seals all task requirements and original results without a model request and explicit continuation keeps the same Task without replay
---
duration_ms: 4145.565
type: 'test'
...
# Subtest: checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact
ok 2 - checkpoint sources, requirements, plan and original tool changes block continuation and leave original checkpoint bytes intact
---
duration_ms: 3036.9164
type: 'test'
...
# Subtest: unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work
ok 3 - unknown tool effects and pending proposals stay blocked in recovery packages rather than being changed into completed work
---
duration_ms: 3432.684
type: 'test'
...
# Subtest: checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt
ok 4 - checkpoint and referenced result corruption are rejected before dispatch and historical blobs are never rebuilt
---
duration_ms: 2833.3038
type: 'test'
...
# Subtest: checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes
ok 5 - checkpoint ownership, exact confirmation and concurrent operations reject foreign or stale resumes
---
duration_ms: 3204.5233
type: 'test'
...
# Subtest: Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state
ok 6 - Git identity changes and altered plan proofs cannot be accepted as the sealed recovery state
---
duration_ms: 3437.5028
type: 'test'
...
# Subtest: checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay
ok 7 - checkpoint records survive SQLite reopen and do not trigger automatic model or tool replay
---
duration_ms: 2940.2587
type: 'test'
...
# Subtest: incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements
ok 8 - incomplete scans and in-progress project activity refuse checkpoint creation while private credentials are redacted from saved requirements
---
duration_ms: 2832.376
type: 'test'
...
# Subtest: oversized recovery evidence is refused before reading or publishing the checkpoint
ok 9 - oversized recovery evidence is refused before reading or publishing the checkpoint
---
duration_ms: 2496.6482
type: 'test'
...
# Subtest: compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation
ok 10 - compiled checkpoint HTTP APIs bind current Task/Run, isolate sessions and only resume on an explicit matching confirmation
---
duration_ms: 6067.8724
type: 'test'
...
# Subtest: actual process exit before checkpoint commit retains only durable records without replay
ok 11 - actual process exit before checkpoint commit retains only durable records without replay
---
duration_ms: 2218.9843
type: 'test'
...
# Subtest: actual process exit after checkpoint commit retains only durable records without replay
ok 12 - actual process exit after checkpoint commit retains only durable records without replay
---
duration_ms: 3436.133
type: 'test'
...
# Subtest: operational questions are diagnostic while explicit repair requests remain execution instructions
ok 13 - operational questions are diagnostic while explicit repair requests remain execution instructions
---
duration_ms: 1.0365
type: 'test'
...
# Subtest: file delivery requires a positive instruction, not saved evidence or a prohibited write
ok 14 - file delivery requires a positive instruction, not saved evidence or a prohibited write
---
duration_ms: 1.2284
type: 'test'
...
# Subtest: an unsubstantiated text claim cannot complete a requested file delivery
ok 15 - an unsubstantiated text claim cannot complete a requested file delivery
---
duration_ms: 1442.2692
type: 'test'
...
# Subtest: HTML without tests ends at reviewed file delivery and never offers automatic rechecking
ok 16 - HTML without tests ends at reviewed file delivery and never offers automatic rechecking
---
duration_ms: 2490.2067
type: 'test'
...
# Subtest: diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools
ok 17 - diagnostic answers retain the unfinished task, limits and check result, and enforce read-only tools
---
duration_ms: 3198.1153
type: 'test'
...
# Subtest: review continuation is a system action and adds no testing demand or fake user instruction
ok 18 - review continuation is a system action and adds no testing demand or fake user instruction
---
duration_ms: 2797.406
type: 'test'
...
# Subtest: a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools
ok 19 - a provider cannot execute tests against an explicit no-test task even if it ignores advertised tools
---
duration_ms: 2037.9703
type: 'test'
...
# Subtest: a budget pause becomes visible only after its input snapshot can be sealed with the original Run
ok 20 - a budget pause becomes visible only after its input snapshot can be sealed with the original Run
---
duration_ms: 1377.9282
type: 'test'
...
# Subtest: alternating duplicate file reads and listing files still pauses without treating new pages as duplicates
ok 21 - alternating duplicate file reads and listing files still pauses without treating new pages as duplicates
---
duration_ms: 15984.6686
type: 'test'
...
# Subtest: task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart
ok 22 - task-plan HTTP mutations bind current Task/Run and retain original evidence through real host restart
---
duration_ms: 4508.037
type: 'test'
...
# Subtest: concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan
ok 23 - concurrent stale HTTP plan revisions cannot replace conditions or attach proofs to a different plan
---
duration_ms: 2979.6842
type: 'test'
...
# Subtest: a real escaped long-file tool message keeps its proof identity within a tight request budget
ok 24 - a real escaped long-file tool message keeps its proof identity within a tight request budget
---
duration_ms: 1285.7027
type: 'test'
...
# Subtest: task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies
ok 25 - task plans reject fabricated completion, invalid scopes and cyclic or missing dependencies
---
duration_ms: 0.4634
type: 'test'
...
# Subtest: sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools
ok 26 - sealed plans retain goal, contract hash and original steps through SQLite reopen without executing tools
---
duration_ms: 1099.1704
type: 'test'
...
# Subtest: proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes
ok 27 - proofs require original owned reads, honor dependencies and reject altered invocation arguments and bytes
---
duration_ms: 1452.9161
type: 'test'
...
# Subtest: new user requirements invalidate current proofs and reseal the same original operations in a new revision
ok 28 - new user requirements invalidate current proofs and reseal the same original operations in a new revision
---
duration_ms: 1659.5855
type: 'test'
...
# Subtest: applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits
ok 29 - applied change-set evidence binds reviewed current files and invalidates dependent steps after outside edits
---
duration_ms: 1907.5968
type: 'test'
...
# Subtest: actual npm checks are verified by original counted logs and current source, with failure history retained
ok 30 - actual npm checks are verified by original counted logs and current source, with failure history retained
---
duration_ms: 8261.4609
type: 'test'
...
# Subtest: real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds
ok 31 - real desktop and mobile browser proofs bind required actions and PNGs, rejecting source changes, a later failed plan and changed builds
---
duration_ms: 11690.6117
type: 'test'
...
# Subtest: Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit
ok 32 - Git delivery blocks incomplete plans and changed preview bindings, preserving HEAD and owner index before a fresh verified commit
---
duration_ms: 13690.0702
type: 'test'
...
# Subtest: the runtime supplies owned read IDs and completes a plan only after original step evidence verification
ok 33 - the runtime supplies owned read IDs and completes a plan only after original step evidence verification
---
duration_ms: 1820.3327
type: 'test'
...
# Subtest: premature model completion pauses the original Task and resume preserves the existing plan without replay
ok 34 - premature model completion pauses the original Task and resume preserves the existing plan without replay
---
duration_ms: 2388.6158
type: 'test'
...
# Subtest: plan operations participate in project activity and orderly shutdown
ok 35 - plan operations participate in project activity and orderly shutdown
---
duration_ms: 501.7874
type: 'test'
...
# Subtest: actual process exit before plan save restores only committed plan evidence without replay
ok 36 - actual process exit before plan save restores only committed plan evidence without replay
---
duration_ms: 965.6203
type: 'test'
...
# Subtest: actual process exit after plan save restores only committed plan evidence without replay
ok 37 - actual process exit after plan save restores only committed plan evidence without replay
---
duration_ms: 1004.991
type: 'test'
...
# Subtest: actual process exit before proof save restores only committed plan evidence without replay
ok 38 - actual process exit before proof save restores only committed plan evidence without replay
---
duration_ms: 1046.5848
type: 'test'
...
# Subtest: actual process exit after proof save restores only committed plan evidence without replay
ok 39 - actual process exit after proof save restores only committed plan evidence without replay
---
duration_ms: 1083.8356
type: 'test'
...
# Subtest: the latest oversized session result reaches the next request together with already read source modules
ok 40 - the latest oversized session result reaches the next request together with already read source modules
---
duration_ms: 2890.0961
type: 'test'
...
# Subtest: every call in a large latest group keeps its actual outcome, including denied and unknown results
ok 41 - every call in a large latest group keeps its actual outcome, including denied and unknown results
---
duration_ms: 1444.4492
type: 'test'
...
# Subtest: a small complete latest tool group is sent once and needs no duplicate feedback view
ok 42 - a small complete latest tool group is sent once and needs no duplicate feedback view
---
duration_ms: 1114.7273
type: 'test'
...
# Subtest: real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing
ok 43 - real HTTP repeated state inspection pauses after three identical engineering outcomes and preserves tool pairing
---
duration_ms: 3053.1629
type: 'test'
...
# Subtest: a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes
ok 44 - a live SQLite host with the actual 1.9 artifact object upgrades, keeps its original blobs and verifies real browser PNG bytes
---
duration_ms: 4146.3265
type: 'test'
...
# Subtest: failed upgrade restores the original artifact object, provider and request handler
ok 45 - failed upgrade restores the original artifact object, provider and request handler
---
duration_ms: 1725.7056
type: 'test'
...
# Subtest: claiming the same runtime owner twice preserves its original metadata and every database row
ok 46 - claiming the same runtime owner twice preserves its original metadata and every database row
---
duration_ms: 608.9787
type: 'test'
...
# Subtest: sessions without controlled-engine history retain their prior export shape and never expose another session record
ok 47 - sessions without controlled-engine history retain their prior export shape and never expose another session record
---
duration_ms: 607.1379
type: 'test'
...
# Subtest: live workers, controlled drivers, or MCP operations refuse an upgrade before changing handlers, managers or database rows
ok 48 - live workers, controlled drivers, or MCP operations refuse an upgrade before changing handlers, managers or database rows
---
duration_ms: 632.5226
type: 'test'
...
# Subtest: an idle upgrade loads the newly introduced engine record map, resets obsolete managers and preserves original rows, sessions and provider objects
ok 49 - an idle upgrade loads the newly introduced engine record map, resets obsolete managers and preserves original rows, sessions and provider objects
---
duration_ms: 598.9455
type: 'test'
...
# Subtest: an installation failure restores old managers, original record maps, handlers and all existing database rows
ok 50 - an installation failure restores old managers, original record maps, handlers and all existing database rows
---
duration_ms: 1333.2536
type: 'test'
...
# Subtest: the owned controlled driver remains an active session and project even after outer task activity has ended
ok 51 - the owned controlled driver remains an active session and project even after outer task activity has ended
---
duration_ms: 592.7023
type: 'test'
...
# Subtest: release and upgrade help or invalid arguments have no file or network setup side effects in an independent directory
ok 52 - release and upgrade help or invalid arguments have no file or network setup side effects in an independent directory
---
duration_ms: 916.9006
type: 'test'
...
# Subtest: hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing
ok 53 - hot upgrade adopts a retained virtual data root without reopening SQLite or changing rows, Provider or routing
---
duration_ms: 1158.1099
type: 'test'
...
# Subtest: failed adoption restores the original virtual data-root name and original open database
ok 54 - failed adoption restores the original virtual data-root name and original open database
---
duration_ms: 519.6915
type: 'test'
...
# Subtest: hot upgrade refreshes retained model and importer methods while preserving credential and routing objects
ok 55 - hot upgrade refreshes retained model and importer methods while preserving credential and routing objects
---
duration_ms: 480.1114
type: 'test'
...
# Subtest: hot upgrade refuses active probes and restores retained model methods if installation fails
ok 56 - hot upgrade refuses active probes and restores retained model methods if installation fails
---
duration_ms: 497.0851
type: 'test'
...
1..56
# tests 56
# suites 0
# pass 56
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 87041.6307
@@ -0,0 +1,437 @@
TAP version 13
# Subtest: HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source
ok 1 - HTTP worker identities require a current sealed plan, reject overrides and close unused plans without touching source
---
duration_ms: 24839.384
type: 'test'
...
# Subtest: HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention
ok 2 - HTTP unknown recovery only accepts the original evidence SHA and preserves changed source for explicit retention
---
duration_ms: 30749.8954
type: 'test'
...
# Subtest: verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source
ok 3 - verified isolated outputs form a new parent batch, rerun real checks and commit only reviewed source
---
duration_ms: 84568.7571
type: 'test'
...
# Subtest: overlapping worker paths are explicit conflicts even if each independent task checks successfully
ok 4 - overlapping worker paths are explicit conflicts even if each independent task checks successfully
---
duration_ms: 51465.342
type: 'test'
...
# Subtest: source edits after isolated work preserve the owner file and invalidate collection without proposing a merge
ok 5 - source edits after isolated work preserve the owner file and invalidate collection without proposing a merge
---
duration_ms: 46435.7836
type: 'test'
...
# Subtest: changed child bytes after parent preview block the entire batch before any parent write
ok 6 - changed child bytes after parent preview block the entire batch before any parent write
---
duration_ms: 69621.2686
type: 'test'
...
# Subtest: corrupt original check logs cannot become collected outputs or a parent review
ok 7 - corrupt original check logs cannot become collected outputs or a parent review
---
duration_ms: 46947.8993
type: 'test'
...
# Subtest: stopping a parent accounts late responses and executes none of their proposed tools
ok 8 - stopping a parent accounts late responses and executes none of their proposed tools
---
duration_ms: 22730.3694
type: 'test'
...
# Subtest: unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume
ok 9 - unreported interrupted requests reserve estimated usage and the total deadline cannot reset on resume
---
duration_ms: 25316.2298
type: 'test'
...
# Subtest: a deadline before worker request dispatch records no invented usage and cannot reset on resume
ok 10 - a deadline before worker request dispatch records no invented usage and cannot reset on resume
---
duration_ms: 23406.6188
type: 'test'
...
# Subtest: a response exceeding the cumulative token allocation stops before registering or executing its tools
ok 11 - a response exceeding the cumulative token allocation stops before registering or executing its tools
---
duration_ms: 25136.2002
type: 'test'
...
# Subtest: cumulative tool allocation rejects the entire returned batch before any tool side effect
ok 12 - cumulative tool allocation rejects the entire returned batch before any tool side effect
---
duration_ms: 23500.1672
type: 'test'
...
# Subtest: single response 16 tool ceiling rejects the entire returned batch before any tool side effect
ok 13 - single response 16 tool ceiling rejects the entire returned batch before any tool side effect
---
duration_ms: 24475.1075
type: 'test'
...
# Subtest: consumed request steps remain consumed across explicit worker resumes
ok 14 - consumed request steps remain consumed across explicit worker resumes
---
duration_ms: 28253.1366
type: 'test'
...
# Subtest: a saved completed response with missing usage is conservatively accounted exactly once during recovery
ok 15 - a saved completed response with missing usage is conservatively accounted exactly once during recovery
---
duration_ms: 23113.8372
type: 'test'
...
# Subtest: an unexecuted second workspace plan resumes its original identity without recreating the first checkout
ok 16 - an unexecuted second workspace plan resumes its original identity without recreating the first checkout
---
duration_ms: 26711.8935
type: 'test'
...
# Subtest: a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change
ok 17 - a verified interrupted parent proposal resumes sealing without duplicating or replacing its original change
---
duration_ms: 77742.9465
type: 'test'
...
# Subtest: recovery attaches a sealed parent batch saved before its group reference without creating another batch
ok 18 - recovery attaches a sealed parent batch saved before its group reference without creating another batch
---
duration_ms: 69664.113
type: 'test'
...
# Subtest: explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal
ok 19 - explicitly retaining an unexecuted parent merge cancels its batch and frees the next parent goal
---
duration_ms: 57954.4208
type: 'test'
...
# Subtest: unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback
ok 20 - unknown collaboration blocks ordinary proposals but permits only original batch recovery and rollback
---
duration_ms: 73993.6656
type: 'test'
...
# Subtest: after a restart the batch application lazily reinstates the worker result guard before any parent write
ok 21 - after a restart the batch application lazily reinstates the worker result guard before any parent write
---
duration_ms: 61594.0346
type: 'test'
...
# Subtest: unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact
ok 22 - unknown original tool inputs must match before acknowledgement, and reviewed checkpoint IDs preserve the unknown fact
---
duration_ms: 26837.0233
type: 'test'
...
# Subtest: a parent stop observes and waits for a manually approved child check and its real descendant process
ok 23 - a parent stop observes and waits for a manually approved child check and its real descendant process
---
duration_ms: 23658.17
type: 'test'
...
# Subtest: a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool
ok 24 - a real host crash preserves unknown checks, refuses a still living owned PID and never replays a model or tool
---
duration_ms: 39890.65
type: 'test'
...
# Subtest: a persisted child initialization resumes the original control run after a failure before its worker record
ok 25 - a persisted child initialization resumes the original control run after a failure before its worker record
---
duration_ms: 18603.3667
type: 'test'
...
# Subtest: failed request intent persistence never dispatches a worker request or changes source
ok 26 - failed request intent persistence never dispatches a worker request or changes source
---
duration_ms: 17775.6332
type: 'test'
...
# Subtest: failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools
ok 27 - failed usage persistence rolls back the uncommitted usage and conservatively reserves one unknown request without tools
---
duration_ms: 17084.2277
type: 'test'
...
# Subtest: a child file change after observation prevents acknowledgement even when the tool inputs did not change
ok 28 - a child file change after observation prevents acknowledgement even when the tool inputs did not change
---
duration_ms: 18006.9111
type: 'test'
...
# Subtest: worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow
ok 29 - worker scopes and allocated budgets reject aliases, extra permissions and aggregate overflow
---
duration_ms: 442.4664
type: 'test'
...
# Subtest: two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes
ok 30 - two sequential Git workspaces freeze a new parent goal, separate owned tasks and preserve all source bytes
---
duration_ms: 20216.3887
type: 'test'
...
# Subtest: real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims
ok 31 - real isolated changes, approvals and npm checks produce original owned outputs, not model completion claims
---
duration_ms: 52486.544
type: 'test'
...
# Subtest: forged worker tools cannot execute terminal or Git even when absent from the advertised tool list
ok 32 - forged worker tools cannot execute terminal or Git even when absent from the advertised tool list
---
duration_ms: 20228.8477
type: 'test'
...
# Subtest: a completion-only model pauses each worker without fabricated changes or checks
ok 33 - a completion-only model pauses each worker without fabricated changes or checks
---
duration_ms: 28610.8281
type: 'test'
...
# Subtest: restart retains frozen scope and marks interrupted parent and workers unknown without sending requests
ok 34 - restart retains frozen scope and marks interrupted parent and workers unknown without sending requests
---
duration_ms: 22130.3588
type: 'test'
...
# Subtest: small code and actual failed command stay visible when their original multi-tool group cannot fit
ok 35 - small code and actual failed command stay visible when their original multi-tool group cannot fit
---
duration_ms: 1124.5224
type: 'test'
...
# Subtest: mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes
ok 36 - mixed group retains six distinct small file observations with exact multilingual text and bounded request bytes
---
duration_ms: 1632.2738
type: 'test'
...
# Subtest: working observations are bound to the current Task and stop treating a pre-application file revision as current evidence
ok 37 - working observations are bound to the current Task and stop treating a pre-application file revision as current evidence
---
duration_ms: 1857.3305
type: 'test'
...
# Subtest: a sealed observation rejects changed or missing original result artifacts instead of recreating evidence
ok 38 - a sealed observation rejects changed or missing original result artifacts instead of recreating evidence
---
duration_ms: 1224.1873
type: 'test'
...
# Subtest: a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid
ok 39 - a real passed-check observation is excluded after a source edit invalidates the check, while its historical sent evidence remains valid
---
duration_ms: 6677.129
type: 'test'
...
# Subtest: budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries
ok 40 - budgeted file pages reconstruct UTF-8 text including long single lines and surrogate boundaries
---
duration_ms: 4.3362
type: 'test'
...
# Subtest: actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening
ok 41 - actual HTTP multi-tool reads survive an oversized runtime snapshot and the sealed evidence survives reopening
---
duration_ms: 8632.3436
type: 'test'
...
# Subtest: actual HTTP file pagination advances over a long file with each returned page visible in the next request
ok 42 - actual HTTP file pagination advances over a long file with each returned page visible in the next request
---
duration_ms: 2569.4598
type: 'test'
...
# Subtest: later mixed history pages cannot displace the actual module sources and complete requirements
ok 43 - later mixed history pages cannot displace the actual module sources and complete requirements
---
duration_ms: 4679.1204
type: 'test'
...
# Subtest: a later narrow page of the same file revision cannot evict the wider actual observation
ok 44 - a later narrow page of the same file revision cannot evict the wider actual observation
---
duration_ms: 2610.8342
type: 'test'
...
# Subtest: historical read-artifact navigation points to the original artifact and next page, never its result wrapper
ok 45 - historical read-artifact navigation points to the original artifact and next page, never its result wrapper
---
duration_ms: 814.576
type: 'test'
...
# Subtest: a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view
ok 46 - a 1.6.1 full-provenance sent view remains verifiable after introducing the compact view
---
duration_ms: 970.6661
type: 'test'
...
# Subtest: actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes
ok 47 - actual HTTP requests keep four observed modules after a later large history read and preserve all source bytes
---
duration_ms: 8852.0209
type: 'test'
...
# Subtest: workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files
ok 48 - workspace HTTP ownership, reviewed creation and reopen survive restart without changing source files
---
duration_ms: 15077.2415
type: 'test'
...
# Subtest: isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report
ok 49 - isolated model Task applies a batch, executes real checks and commits at the Git review boundary with a source-bound report
---
duration_ms: 40964.3271
type: 'test'
...
# warning: in the working copy of 'src/空 格.mjs', LF will be replaced by CRLF the next time Git touches it
# Subtest: worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion
ok 50 - worktree checkout disables hooks, fsmonitor and all filter command variants while honoring built-in EOL conversion
---
duration_ms: 11946.0987
type: 'test'
...
# Subtest: an ignored external file at checkout is observed and never accepted as pristine creation
ok 51 - an ignored external file at checkout is observed and never accepted as pristine creation
---
duration_ms: 7930.0732
type: 'test'
...
# Subtest: outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution
ok 52 - outside content hidden by assume-unchanged cannot pass workspace verification and blocks further source execution
---
duration_ms: 7241.962
type: 'test'
...
# Subtest: workspace preparation refuses known shared-repository activity and preserves archived child sessions
ok 53 - workspace preparation refuses known shared-repository activity and preserves archived child sessions
---
duration_ms: 9417.8921
type: 'test'
...
# Subtest: compact checkout identities create in deep Unicode source directories while retaining the human branch name
ok 54 - compact checkout identities create in deep Unicode source directories while retaining the human branch name
---
duration_ms: 9697.1568
type: 'test'
...
# Subtest: Windows Git metadata path limits reject creation before publishing a branch or changing source bytes
ok 55 - Windows Git metadata path limits reject creation before publishing a branch or changing source bytes
---
duration_ms: 3191.0618
type: 'test'
...
# Subtest: a pending source snapshot participates in shutdown and completes before storage can close
ok 56 - a pending source snapshot participates in shutdown and completes before storage can close
---
duration_ms: 2370.726
type: 'test'
...
# Subtest: source configuration values stay private and a configuration change invalidates a saved review
ok 57 - source configuration values stay private and a configuration change invalidates a saved review
---
duration_ms: 3134.6382
type: 'test'
...
# Subtest: workspace review rejects excluded dependency before any checkout
ok 58 - workspace review rejects excluded dependency before any checkout
---
duration_ms: 3525.1835
type: 'test'
...
# Subtest: workspace review rejects large committed blob before any checkout
ok 59 - workspace review rejects large committed blob before any checkout
---
duration_ms: 3696.8478
type: 'test'
...
# Subtest: workspace review rejects case collision before any checkout
ok 60 - workspace review rejects case collision before any checkout
---
duration_ms: 3238.7636
type: 'test'
...
# Subtest: workspace review rejects committed symbolic link before any checkout
ok 61 - workspace review rejects committed symbolic link before any checkout
---
duration_ms: 2860.2245
type: 'test'
...
# Subtest: workspace review rejects external config include before any checkout
ok 62 - workspace review rejects external config include before any checkout
---
duration_ms: 2114.8837
type: 'test'
...
# Subtest: actual process exit at workspace intent preserves source and reconciles without creation replay
ok 63 - actual process exit at workspace intent preserves source and reconciles without creation replay
---
duration_ms: 7745.0217
type: 'test'
...
# Subtest: actual process exit at workspace git_started preserves source and reconciles without creation replay
ok 64 - actual process exit at workspace git_started preserves source and reconciles without creation replay
---
duration_ms: 11596.3794
type: 'test'
...
# Subtest: actual process exit at workspace git_finished preserves source and reconciles without creation replay
ok 65 - actual process exit at workspace git_finished preserves source and reconciles without creation replay
---
duration_ms: 10433.1317
type: 'test'
...
# Subtest: actual process exit at workspace verifying preserves source and reconciles without creation replay
ok 66 - actual process exit at workspace verifying preserves source and reconciles without creation replay
---
duration_ms: 9063.006
type: 'test'
...
# Subtest: actual process exit at workspace registering preserves source and reconciles without creation replay
ok 67 - actual process exit at workspace registering preserves source and reconciles without creation replay
---
duration_ms: 11771.9087
type: 'test'
...
# Subtest: actual process exit at workspace project_registered preserves source and reconciles without creation replay
ok 68 - actual process exit at workspace project_registered preserves source and reconciles without creation replay
---
duration_ms: 11387.8748
type: 'test'
...
# Subtest: actual process exit at workspace session_registered preserves source and reconciles without creation replay
ok 69 - actual process exit at workspace session_registered preserves source and reconciles without creation replay
---
duration_ms: 14811.8058
type: 'test'
...
# Subtest: actual process exit at workspace ready preserves source and reconciles without creation replay
ok 70 - actual process exit at workspace ready preserves source and reconciles without creation replay
---
duration_ms: 10414.7013
type: 'test'
...
# Subtest: outside changes at project registration remain unknown and preserve the already registered child identity
ok 71 - outside changes at project registration remain unknown and preserve the already registered child identity
---
duration_ms: 10237.4505
type: 'test'
...
1..71
# tests 71
# suites 0
# pass 71
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 781413.2699
@@ -0,0 +1,28 @@
TAP version 13
# Subtest: managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity
ok 1 - managed worktree preserves source index and dirty files, opens a distinct project and binds Run identity
---
duration_ms: 7722.8908
type: 'test'
...
# Subtest: stale review, branch/path collisions and forged ownership do not run worktree creation
ok 2 - stale review, branch/path collisions and forged ownership do not run worktree creation
---
duration_ms: 3791.9824
type: 'test'
...
# Subtest: workspace project verification is read-only and rejects physical Git identity changes
ok 3 - workspace project verification is read-only and rejects physical Git identity changes
---
duration_ms: 6447.528
type: 'test'
...
1..3
# tests 3
# suites 0
# pass 3
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 18059.5622
@@ -0,0 +1,22 @@
TAP version 13
# Subtest: a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider
ok 1 - a directly started compiled host upgrades twice with the same PID, sessions, applied bytes and volatile provider
---
duration_ms: 4368.9381
type: 'test'
...
# Subtest: the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection
ok 2 - the running 0.1.0 process upgrades in place and retains its project, session, files and volatile model connection
---
duration_ms: 7631.5041
type: 'test'
...
1..2
# tests 2
# suites 0
# pass 2
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 12091.7595
@@ -0,0 +1,6 @@
PASS desktop upload, explicit route, refreshed draft, original download SHA, one paired tool and narrow task history
PASS forged image rejects without losing task text or sending a model request
PASS explicit budget preview and confirmation retain Task, attachment and completed tool while global capacity stays unchanged
PASS paired TLS companion verifies same screenshot, refresh restores it and revoke clears project/image content
PASS stopping screenshot SSE closes original HTTP and dispatches zero partial tools
EVIDENCE D:\AWQA22\s-1fca8c0c\.qa\vision-ui-26ae8298-0577-4ebd-9564-0c3ce988dddb
+8 -1
View File
@@ -51,7 +51,14 @@ export async function desktopProjectQa({ store, provider, runtime, sample, kind
const confirm = dialog.getByRole('button', { name: '确认应用全部 ' + ids.length + ' 项', exact: true }); await confirm.waitFor();
const matching = [...store.core.change_set.values()].filter(value => value.sessionId === session.id && value.status !== 'completed' && JSON.stringify(value.files.map(file => file.changeId).sort()) === JSON.stringify(ids.slice().sort()));
assert.equal(matching.length, 1); const set = matching[0];
await confirm.click(); await expect(dialog).toContainText('全部应用完成'); await page.keyboard.press('Escape');
const response = page.waitForResponse(value => new URL(value.url()).pathname === '/api/sessions/' + session.id + '/change-sets/' + set.id + '/apply'
&& value.request().method() === 'POST', { timeout: 120000 });
await confirm.click(); const applied = await response;
assert.equal(applied.status(), 200, 'Original desktop apply request was rejected');
const operation = runtime.changeSetManager().active.get(set.id);
if (operation) await operation.promise;
assert.equal(set.status, 'completed', JSON.stringify({ status: set.status, summary: set.summary, requiresVerification: set.requiresVerification }));
await expect(dialog).toContainText('全部应用完成', { timeout: 20000 }); await page.keyboard.press('Escape');
assert.equal(set.status, 'completed'); events.push({ action: 'actual-desktop-file-review', taskId: session.taskId, changeSetId: set.id, fingerprint: set.fingerprint, paths: set.files.map(value => value.path) }); return set;
}
async function approve(session, approval) {