惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
T
The Blog of Author Tim Ferriss
H
Help Net Security
博客园 - 叶小钗
云风的 BLOG
云风的 BLOG
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
D
DataBreaches.Net
博客园 - 聂微东
A
About on SuperTechFans
大猫的无限游戏
大猫的无限游戏
P
Proofpoint News Feed
Martin Fowler
Martin Fowler
博客园 - 【当耐特】
S
SegmentFault 最新的问题
Blog — PlanetScale
Blog — PlanetScale
酷 壳 – CoolShell
酷 壳 – CoolShell
G
Google Developers Blog
I
InfoQ
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
GbyAI
GbyAI
B
Blog
Engineering at Meta
Engineering at Meta
V
V2EX
Hugging Face - Blog
Hugging Face - Blog

Recent Commits to openclaw:main

test: merge chat side-result checks · openclaw/openclaw@ddd2c2a test: merge cron history checks · openclaw/openclaw@f7eb746 test: merge responsive navigation shell checks · openclaw/openclaw@c2e4b47 docs(changelog): add codex oauth fixes · openclaw/openclaw@628e6cd test: merge navigation routing cases · openclaw/openclaw@5d8cecb Tests: mock channel registry bundled fallback · openclaw/openclaw@2b08233 Secrets: avoid broad web search discovery for single plugin config · openclaw/openclaw@a464f59 test: merge config view browser checks · openclaw/openclaw@20cf511 fix(status): align oauth health with runtime · openclaw/openclaw@eed7116 feat: add macOS screen snapshots for monitor preview (#67954) thanks … · openclaw/openclaw@f377db1 fix: report shared auth scopes in hello-ok (#67810) thanks @BunsDev · openclaw/openclaw@0b6c39b Auto-reply: avoid eager bundled route fallback · openclaw/openclaw@3ea1bf4 Tests: narrow session binding contract setup · openclaw/openclaw@54e4e16 fix(macOS): enable undo/redo in webchat composer text input (#34962) · openclaw/openclaw@00951dc Tests: speed up channel setup promotion · openclaw/openclaw@82b529a Docs: refresh agent instructions · openclaw/openclaw@5775fe2 fix(auth): serialize OAuth refresh across agents to fix #26322 (#67876) · openclaw/openclaw@8e79080 test: allow ollama public surface boundary test · openclaw/openclaw@7d4f1a6 Docs: add test performance guardrails · openclaw/openclaw@89706d3 Tests: restore context-engine usage proof · openclaw/openclaw@e4c4f95 Tests: slim context engine runtime coverage · openclaw/openclaw@74c198f ci: retry failed custom checkouts · openclaw/openclaw@0ee5baf test: trim duplicate provider auth onboarding cases · openclaw/openclaw@1ffc02e matrix: fix sessions_spawn --thread subagent session spawning (#67643) · openclaw/openclaw@1ce2596 test: reduce auth choice fixture churn · openclaw/openclaw@857b9cd test: mock health status config boundaries · openclaw/openclaw@9d5ab4a test: mock onboard config io boundary · openclaw/openclaw@299694d test: mock legacy state plugin boundaries · openclaw/openclaw@2713089 test: mock channel install boundaries · openclaw/openclaw@b945248 test: mock doctor preview channel boundaries · openclaw/openclaw@b1a3ad4
test(qa): embed profile scorecard evidence (#93109) · ope...
RomneyDa · 2026-06-15 · via Recent Commits to openclaw:main

@@ -119,6 +119,15 @@ function expectWriteContains(mock: unknown, fragment: string): void {

119119

).toBe(true);

120120

}

121121122+

function makeQaEvidence(entries: unknown[] = []) {

123+

return {

124+

kind: "openclaw.qa.evidence-summary",

125+

schemaVersion: 2,

126+

generatedAt: "2026-06-14T00:00:00.000Z",

127+

entries,

128+

};

129+

}

130+122131

function flowSuiteRuntimeResult(params: {

123132

evidencePath?: string;

124133

reportPath: string;

@@ -178,7 +187,7 @@ describe("qa cli runtime", () => {

178187

telegramArtifactsDir = await fs.mkdtemp(path.join(os.tmpdir(), "qa-telegram-runtime-"));

179188

telegramSummaryPath = path.join(telegramArtifactsDir, QA_EVIDENCE_FILENAME);

180189

await fs.writeFile(suiteReportPath, "# QA Suite Report\n", "utf8");

181-

await fs.writeFile(suiteEvidencePath, JSON.stringify({ entries: [] }), "utf8");

190+

await fs.writeFile(suiteEvidencePath, JSON.stringify(makeQaEvidence()), "utf8");

182191

await fs.writeFile(

183192

suiteSummaryPath,

184193

JSON.stringify({

@@ -301,7 +310,7 @@ describe("qa cli runtime", () => {

301310302311

it("runs selected Playwright scenarios through the suite command", async () => {

303312

const evidencePath = path.join(suiteArtifactsDir, "qa-evidence.json");

304-

await fs.writeFile(evidencePath, JSON.stringify({ entries: [] }), "utf8");

313+

await fs.writeFile(evidencePath, JSON.stringify(makeQaEvidence()), "utf8");

305314

runQaSuite.mockResolvedValueOnce(

306315

unifiedSuiteRuntimeResult({

307316

outputDir: suiteArtifactsDir,

@@ -349,6 +358,63 @@ describe("qa cli runtime", () => {

349358

try {

350359

runQaSuite.mockImplementationOnce(async () => {

351360

expect(process.env.OPENCLAW_QA_PROFILE).toBe("smoke-ci");

361+

await fs.writeFile(

362+

suiteEvidencePath,

363+

JSON.stringify(

364+

makeQaEvidence([

365+

{

366+

test: {

367+

kind: "qa-scenario",

368+

id: "dm-chat-baseline",

369+

title: "DM baseline conversation",

370+

source: {

371+

path: "qa/scenarios/channels/dm-chat-baseline.yaml",

372+

},

373+

},

374+

mapping: {

375+

profile: "smoke-ci",

376+

coverage: [

377+

{

378+

id: "channels.dm",

379+

role: "primary",

380+

surfaceIds: ["dm"],

381+

categoryIds: ["agent-runtime-and-provider-execution.agent-turn-execution"],

382+

},

383+

],

384+

},

385+

execution: {

386+

runner: "host",

387+

environment: {

388+

ref: null,

389+

os: process.platform,

390+

nodeVersion: process.version,

391+

},

392+

provider: {

393+

id: "openai",

394+

live: false,

395+

model: {

396+

name: "gpt-5.5",

397+

ref: "mock-openai/gpt-5.5",

398+

},

399+

fixture: "mock-openai",

400+

},

401+

channel: {

402+

id: "qa-channel",

403+

live: false,

404+

},

405+

packageSource: {

406+

kind: "source-checkout",

407+

},

408+

artifacts: [],

409+

},

410+

result: {

411+

status: "pass",

412+

},

413+

},

414+

]),

415+

),

416+

"utf8",

417+

);

352418

return flowSuiteRuntimeResult({

353419

reportPath: suiteReportPath,

354420

summaryPath: suiteSummaryPath,

@@ -379,7 +445,34 @@ describe("qa cli runtime", () => {

379445

expect(suiteArgs.scenarioIds).toEqual(expect.arrayContaining(["dm-chat-baseline"]));

380446

expect(suiteArgs.scenarioIds).not.toContain("thinking-slash-model-remap");

381447

expect(process.env.OPENCLAW_QA_PROFILE).toBe("release");

448+

const evidence = JSON.parse(await fs.readFile(suiteEvidencePath, "utf8")) as {

449+

scorecard?: {

450+

profile?: unknown;

451+

run?: { evidenceEntryCount?: unknown };

452+

features?: { fulfilled?: unknown };

453+

categoryReports?: Array<{

454+

id?: unknown;

455+

features?: { fulfilled?: unknown };

456+

missingCoverageIds?: unknown;

457+

}>;

458+

};

459+

};

460+

expect(evidence.scorecard).toMatchObject({

461+

profile: "smoke-ci",

462+

run: {

463+

evidenceEntryCount: 1,

464+

},

465+

});

466+

expect(evidence.scorecard?.features?.fulfilled).toBe(1);

467+

expect(evidence.scorecard?.categoryReports?.[0]).toMatchObject({

468+

id: "agent-runtime-and-provider-execution.agent-turn-execution",

469+

features: {

470+

fulfilled: 1,

471+

},

472+

});

473+

expect(JSON.stringify(evidence.scorecard)).not.toContain("dm-chat-baseline");

382474

expectWriteContains(stdoutWrite, "QA run profile: smoke-ci; categories: 1; scenarios:");

475+

expectWriteContains(stdoutWrite, `QA profile scorecard: ${suiteEvidencePath}`);

383476

} finally {

384477

if (previousProfile === undefined) {

385478

delete process.env.OPENCLAW_QA_PROFILE;