Files
Agent-Workbench/docs/m1-live-delivery-validation.json
T

209 lines
17 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
{
"success": true,
"version": "1.1.0",
"testedAt": "2026-10-29T07:20:52.067Z",
"model": "gpt-6.1-sol",
"projectRoot": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431\\交付报告工程",
"projectId": "3423bff0-d418-4a6d-9cc7-66bd85875a51",
"sessionId": "e8846c6e-1ba2-497e-b0db-ca5778181eb0",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb",
"baselineCommit": "badd7f77602c336bed6b00e253d1ef251a3f9922",
"deliveredCommit": "b17492ca0fb9d6ea562290f3857b1c4c06bf6bf2",
"elapsedSeconds": 81,
"runs": 2,
"reviewRounds": 1,
"applied": [
{
"id": "03d3123a-0455-442d-b5f4-085ac5778e39",
"path": "src/normalize.mjs",
"sha256": "57eb47b09913b131982a14c276ba5292aba4c94e0f475c97955221f6a7b7cdcd",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb"
},
{
"id": "798b3829-74a3-415c-aa25-40d8a48fcce3",
"path": "src/summary.mjs",
"sha256": "bf7ada9e5dbca167df2b9a5306c1d9399b4a658fb0777c73812856687ad0c5ef",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb"
},
{
"id": "cf2a2a89-5d77-4675-8dda-5b346ba27989",
"path": "src/render.mjs",
"sha256": "d449524d731a55ef51d0143f38ee8b73db56363c78babc385fa58df7f2a542f0",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb"
},
{
"id": "e5f2372c-7207-4157-9a1f-565467fa7f84",
"path": "src/cli.mjs",
"sha256": "b8223dd1c0a98b3b7a0cd716db0ae053a2ca17fbd8272b005adcedd3ce5f7a69",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb"
}
],
"protectedHashes": {
"README.md": "4279c14b07a2b73a1a2c10ce8e80b6841ad39338b5a121215935c9c668ec2832",
"package.json": "15ac7e2e1840870f36886d634129551dbb8490fd7e5e613292beed95e8c50b6f",
"test/delivery.test.mjs": "90afb188568b27fa5c7c5a721c78e632b90e9e84d3fc75ee9008208d1487bb3f",
"scripts/build.mjs": "9dbc4bea4940fb0e87e7924a4601166c422149d3e9f5ecf1d22efde3b6c8c302",
"fixtures/tasks.json": "0ec1b97c5b84df8e70ff62828e80a0cc548814720ff7b995a2853ab1228d847d",
"fixtures/invalid.json": "f014956200206e75f522e90037ad0ead201b00a368deb58cbbabffa972b4bb50",
".gitignore": "ed19d3c9c8a5e34d0179e0b1a9c2907d2e657738733e4a432a8cf81c76ce56f1",
"OWNER-NOTES.md": "38d076e1255121b92c4e1f8c04ca35155da345ae12df502d921df0bca09fae98",
"UNTRACKED-OWNER.txt": "389faf00156dd9bdc7c9d495be3c1d7a67189fa0e799fabb39400928dfd15fb1"
},
"ownerEditsPreserved": true,
"buildOutput": {
"total": 4,
"counts": {
"todo": 0,
"doing": 1,
"done": 2,
"blocked": 1
},
"completedPercent": 50,
"remainingMinutes": 50
},
"usage": {
"requests": 11,
"inputTokens": 141382,
"outputTokens": 2339,
"totalTokens": 143721,
"unknownRequests": 0,
"estimatedUnknownTokens": 0
},
"checks": [
{
"id": "42e896d0-5ebf-455b-9148-268d32b9513f",
"sessionId": "e8846c6e-1ba2-497e-b0db-ca5778181eb0",
"projectId": "3423bff0-d418-4a6d-9cc7-66bd85875a51",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb",
"runId": "69bf36c5-3997-421a-ae8f-8959556383ec",
"planId": "fc5ec679-798b-4bda-9db4-c3186d6349b8",
"status": "failed",
"source": "agent",
"startedAt": "2026-10-29T07:19:48.909Z",
"finishedAt": "2026-10-29T07:19:50.045Z",
"results": [
{
"id": "80ce215c-bbcd-475e-aec4-404bf522bd70",
"name": "test",
"kind": "test",
"command": "npm run test",
"status": "failed",
"exitCode": 1,
"durationMs": 437,
"tests": {
"total": 14,
"passed": 1,
"failed": 13,
"cancelled": 0,
"skipped": 0
},
"timedOut": false,
"truncated": false,
"logArtifactId": "5c7e0e1e-e748-4288-b35d-d95a7e9d2c0e",
"logExcerpt": "rnal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: { id: 'one', title: '任务', status: 'todo', minutes: 5, unrelated: true },\n expected: { id: 'one', title: '任务', status: 'todo', minutes: 5 },\n operator: 'deepStrictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:19:1\n✖ summary reports complete state counts and excludes completed work from remaining time (0.3599ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:\n + actual - expected\n \n {\n + completedPercent: 100,\n - completedPercent: 50,\n counts: {\n - blocked: 1,\n - doing: 1,\n done: 2,\n - todo: 0\n },\n + remainingMinutes: 100,\n - remainingMinutes: 50,\n total: 4\n }\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:19:108)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: { total: 4, counts: { done: 2 }, completedPercent: 100, remainingMinutes: 100 },\n expected: { total: 4, counts: { todo: 0, doing: 1, done: 2, blocked: 1 }, completedPercent: 50, remainingMinutes: 50 },\n operator: 'deepStrictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:20:1\n✖ summary rounds progress instead of truncating percentages (0.1154ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:\n \n 100 !== 67\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:20:80)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: 100,\n expected: 67,\n operator: 'strictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:21:1\n✖ summary handles an empty plan with every state present (0.1647ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly deep-equal:\n + actual - expected\n \n {\n completedPercent: 0,\n counts: {\n - blocked: 0,\n - doing: 0,\n done: 0,\n - todo: 0\n },\n remainingMinutes: 0,\n total: 0\n }\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:21:77)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: { total: 0, counts: { done: 0 }, completedPercent: 0, remainingMinutes: 0 },\n expected: { total: 0, counts: { todo: 0, doing: 0, done: 0, blocked: 0 }, completedPercent: 0, remainingMinutes: 0 },\n operator: 'deepStrictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:22:1\n✖ text rendering keeps the required three readable Chinese lines (0.2086ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:\n + actual - expected\n \n + 'Done: 2/4'\n - '交付进度:2/4(50%)\\n待办 0 · 进行中 1 · 已完成 2 · 阻塞 1\\n剩余预计:50 分钟'\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:22:85)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: 'Done: 2/4',\n expected: '交付进度:2/4(50%)\\n待办 0 · 进行中 1 · 已完成 2 · 阻塞 1\\n剩余预计:50 分钟',\n operator: 'strictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:23:1\n✖ CLI JSON output matches the summary contract and has a trailing newline (47.715ms)\n SyntaxError [Error]: Unexpected token 'D', \"Done: 2/4\n \" is not valid JSON\n at JSON.parse (<anonymous>)\n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:23:232)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7)\n\ntest at test\\delivery.test.mjs:25:1\n✖ CLI missing arguments and unknown options return exit 2 without output (41.8575ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:\n \n 0 !== 2\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:25:237)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: 0,\n expected: 2,\n operator: 'strictEqual',\n diff: 'simple'\n }\n\ntest at test\\delivery.test.mjs:26:1\n✖ CLI invalid JSON and missing files preserve the failure exit code (41.2206ms)\n AssertionError [ERR_ASSERTION]: Expected values to be strictly equal:\n \n 0 !== 2\n \n at TestContext.<anonymous> (file:///D:/Ai-project/REA%E9%80%86%E5%90%91/Agent-Workbench/.qa/live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431/%E4%BA%A4%E4%BB%98%E6%8A%A5%E5%91%8A%E5%B7%A5%E7%A8%8B/test/delivery.test.mjs:26:194)\n at Test.runInAsyncScope (node:async_hooks:227:14)\n at Test.run (node:internal/test_runner/test:1402:25)\n at Test.processPendingSubtests (node:internal/test_runner/test:974:18)\n at Test.postRun (node:internal/test_runner/test:1542:19)\n at Test.run (node:internal/test_runner/test:1467:12)\n at async Test.processPendingSubtests (node:internal/test_runner/test:974:7) {\n generatedMessage: true,\n code: 'ERR_ASSERTION',\n actual: 0,\n expected: 2,\n operator: 'strictEqual',\n diff: 'simple'\n }\n"
},
{
"id": "7fb6ab17-b2c7-4514-80b9-7979b4ddf201",
"name": "build",
"kind": "build",
"command": "npm run build",
"status": "passed",
"exitCode": 0,
"durationMs": 322,
"tests": null,
"timedOut": false,
"truncated": false,
"logArtifactId": "d5e217e5-9ced-4f6b-b6e9-3e75587a7ba6",
"logExcerpt": "\n> delivery-report-lab@0.1.0 build\n> node scripts/build.mjs\n\n四个模块语法检查及可运行构建完成。\n"
}
],
"fingerprint": "8e53f7480212b8482fdc6a1febe111ea4a165d8524cc4b9622b790e4e83c6132",
"baseline": {
"head": "badd7f77602c336bed6b00e253d1ef251a3f9922",
"branch": "main",
"dirty": true
},
"originalSessionStatus": "running",
"currentCheck": null,
"stale": false,
"summary": "有检查失败,请查看退出码和日志后修复。"
},
{
"id": "54f3e5fc-dbab-4242-a8e3-20303c734251",
"sessionId": "e8846c6e-1ba2-497e-b0db-ca5778181eb0",
"projectId": "3423bff0-d418-4a6d-9cc7-66bd85875a51",
"taskId": "5237de95-826f-45f2-9784-0402e59f52bb",
"runId": "73666cd2-a5dd-444a-bd20-509b24fb141e",
"planId": "adc1247f-6204-486d-9bd5-4fe6fecf4f45",
"status": "passed",
"source": "agent",
"startedAt": "2026-10-29T07:20:40.107Z",
"finishedAt": "2026-10-29T07:20:41.302Z",
"results": [
{
"id": "0361f013-5df4-4f06-9bee-3622949a0cba",
"name": "test",
"kind": "test",
"command": "npm run test",
"status": "passed",
"exitCode": 0,
"durationMs": 508,
"tests": {
"total": 14,
"passed": 14,
"failed": 0,
"cancelled": 0,
"skipped": 0
},
"timedOut": false,
"truncated": false,
"logArtifactId": "bb8a4592-3e94-4252-98e7-de7e7a72be20",
"logExcerpt": "\n> delivery-report-lab@0.1.0 test\n> node --test test/*.test.mjs\n\n✔ normalize trims identifiers and titles into independent records (1.0355ms)\n✔ normalize rejects blank and duplicate normalized identifiers (0.2485ms)\n✔ normalize validates record shape and bounded collection size (11.7295ms)\n✔ normalize supports all four states and rejects unknown states (0.2693ms)\n✔ normalize rejects noninteger and out-of-range estimates (0.1754ms)\n✔ normalize emits only the declared four-field contract (0.0834ms)\n✔ summary reports complete state counts and excludes completed work from remaining time (0.1883ms)\n✔ summary rounds progress instead of truncating percentages (0.0895ms)\n✔ summary handles an empty plan with every state present (0.0786ms)\n✔ text rendering keeps the required three readable Chinese lines (0.1182ms)\n✔ CLI JSON output matches the summary contract and has a trailing newline (43.1196ms)\n✔ CLI text output is readable and matches the shared rendering (41.0303ms)\n✔ CLI missing arguments and unknown options return exit 2 without output (122.5147ms)\n✔ CLI invalid JSON and missing files preserve the failure exit code (85.597ms)\nℹ tests 14\nℹ suites 0\nℹ pass 14\nℹ fail 0\nℹ cancelled 0\nℹ skipped 0\nℹ todo 0\nℹ duration_ms 359.2566\n"
},
{
"id": "f73fa444-c7ea-4ce1-8d40-51e3629c4024",
"name": "build",
"kind": "build",
"command": "npm run build",
"status": "passed",
"exitCode": 0,
"durationMs": 306,
"tests": null,
"timedOut": false,
"truncated": false,
"logArtifactId": "26bde9cd-55ad-48e2-9193-e6c5f29ec798",
"logExcerpt": "\n> delivery-report-lab@0.1.0 build\n> node scripts/build.mjs\n\n四个模块语法检查及可运行构建完成。\n"
}
],
"fingerprint": "131d12c5615006344b30a735f26c50d62369839ace954b17d7216cbaf0a237dc",
"baseline": {
"head": "badd7f77602c336bed6b00e253d1ef251a3f9922",
"branch": "main",
"dirty": true
},
"originalSessionStatus": "running",
"currentCheck": null,
"stale": false,
"summary": "所选检查全部通过,测试数量与源码快照已记录。"
}
],
"decisions": [
{
"approvalId": "ca959fc7-8b32-4be8-927b-108a1a71f76c",
"planId": "fc5ec679-798b-4bda-9db4-c3186d6349b8",
"command": "npm run test\nnpm run build",
"allow": true
},
{
"approvalId": "eed3ac40-70b3-437a-81a4-24375439453e",
"planId": "adc1247f-6204-486d-9bd5-4fe6fecf4f45",
"command": "npm run test\nnpm run build",
"allow": true
}
],
"diffPath": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431\\reviewed-changes.diff",
"sessionPath": "D:\\Ai-project\\REA逆向\\Agent-Workbench\\.qa\\live-delivery-c4fa89f0-46fe-4923-8a1f-4e3d028f3431\\session.json",
"credentialsHandling": "Calls use the running host model configuration; no model key was read, copied or saved.",
"intervention": "Verifier approved only sealed npm scripts, checked four source proposals and applied them; implementation came from the configured model. The verifier saved a source-only local Git commit.",
"scope": "One synthetic Node engineering sample; does not establish M2 or M6 delivery success rates."
}