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

博客园 - 司徒正美
The GitHub Blog
The GitHub Blog
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Apple Machine Learning Research
Apple Machine Learning Research
L
LangChain Blog
GbyAI
GbyAI
博客园_首页
V
Visual Studio Blog
Martin Fowler
Martin Fowler
WordPress大学
WordPress大学
H
Hackread – Cybersecurity News, Data Breaches, AI and More
博客园 - 叶小钗
腾讯CDC
博客园 - Franky
IT之家
IT之家
Google DeepMind News
Google DeepMind News
Microsoft Azure Blog
Microsoft Azure Blog
D
Docker
大猫的无限游戏
大猫的无限游戏
Recent Announcements
Recent Announcements
小众软件
小众软件
博客园 - 三生石上(FineUI控件)
B
Blog
酷 壳 – CoolShell
酷 壳 – CoolShell

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
qa-lab: support script-backed evidence scenarios (#94276)...
Solvely-Coli · 2026-06-18 · via Recent Commits to openclaw:main
Original file line numberDiff line numberDiff line change

@@ -942,7 +942,12 @@ Every `qa suite` run writes top-level `qa-evidence.json`,

942942

`qa-suite-summary.json`, and `qa-suite-report.md` artifacts for the selected

943943

scenario set. Scenarios that declare `execution.kind: vitest` or

944944

`execution.kind: playwright` run the matching test path and also write

945-

per-scenario logs. When `qa suite` is reached through

945+

per-scenario logs. Scenarios that declare `execution.kind: script` run the

946+

evidence producer at `execution.path` through `node --import tsx` (with

947+

`${outputDir}` and `${scenarioId}` expanded in `execution.args`); the producer

948+

writes its own `qa-evidence.json`, whose entries are imported into the suite

949+

output and whose artifact paths are resolved relative to that producer

950+

`qa-evidence.json`. When `qa suite` is reached through

946951

`qa run --qa-profile`, the same `qa-evidence.json` also includes the profile

947952

scorecard summary for the selected taxonomy categories.

948953

Treat it as a discovery aid, not a gate replacement; the selected scenario still needs the right provider mode, live transport, Multipass, Testbox, or release lane for the behavior under test.

Original file line numberDiff line numberDiff line change

@@ -67,11 +67,13 @@ function scenarioWithCoverage(params: {

6767

primary?: readonly string[];

6868

secondary?: readonly string[];

6969

sourcePath?: string;

70-

executionKind?: "flow" | "vitest" | "playwright";

70+

executionKind?: "flow" | "script" | "vitest" | "playwright";

7171

executionPath?: string;

7272

}): QaSeedScenarioWithSource {

7373

const execution =

74-

params.executionKind === "vitest" || params.executionKind === "playwright"

74+

params.executionKind === "script" ||

75+

params.executionKind === "vitest" ||

76+

params.executionKind === "playwright"

7577

? {

7678

kind: params.executionKind,

7779

path: params.executionPath ?? "src/test.test.ts",

@@ -328,6 +330,37 @@ describe("qa coverage report", () => {

328330

]);

329331

});

330332
333+

it("uses script producer evidence as coverage fulfillment", () => {

334+

const report = buildQaScorecardTaxonomyReport({

335+

taxonomy: testMaturityTaxonomy({

336+

categoryId: TEST_BROWSER_CATEGORY_ID,

337+

coverageIds: [TEST_BROWSER_COVERAGE_ID],

338+

}),

339+

repoRoot: process.cwd(),

340+

scenarios: [

341+

scenarioWithCoverage({

342+

primary: [TEST_BROWSER_COVERAGE_ID],

343+

sourcePath: "qa/scenarios/ui/script-evidence-producer.yaml",

344+

executionKind: "script",

345+

executionPath: "scripts/check-no-conflict-markers.mjs",

346+

}),

347+

],

348+

});

349+
350+

expect(report.validationIssues).toStrictEqual([]);

351+

expect(report.fulfilledCategoryCount).toBe(1);

352+

expect(report.fulfilledFeatureCount).toBe(1);

353+

expect(report.categories[0]?.evidence).toStrictEqual([

354+

{

355+

coverageId: TEST_BROWSER_COVERAGE_ID,

356+

kind: "script",

357+

path: "scripts/check-no-conflict-markers.mjs",

358+

role: "primary",

359+

scenarioRefs: ["qa/scenarios/ui/script-evidence-producer.yaml"],

360+

},

361+

]);

362+

});

363+
331364

it("reports profile membership refs missing from taxonomy categories", () => {

332365

const report = buildQaScorecardTaxonomyReport({

333366

taxonomy: testMaturityTaxonomy({

Original file line numberDiff line numberDiff line change

@@ -465,7 +465,12 @@ function scenarioMatchCommandGroups(matches: readonly QaScenarioSearchMatch[]) {

465465

group.push(match);

466466

groups.set(match.executionKind, group);

467467

}

468-

const executionOrder: QaScenarioSearchMatch["executionKind"][] = ["flow", "vitest", "playwright"];

468+

const executionOrder: QaScenarioSearchMatch["executionKind"][] = [

469+

"flow",

470+

"script",

471+

"vitest",

472+

"playwright",

473+

];

469474

return executionOrder.flatMap((executionKind) => {

470475

const group = groups.get(executionKind);

471476

return group && group.length > 0 ? [{ executionKind, matches: group }] : [];

Original file line numberDiff line numberDiff line change

@@ -349,7 +349,7 @@ function uniqueSortedStrings(values: readonly (string | undefined)[]) {

349349

);

350350

}

351351
352-

function resolveQaEvidenceProfile(params: {

352+

export function resolveQaEvidenceProfile(params: {

353353

env?: NodeJS.ProcessEnv;

354354

explicit?: QaEvidenceProfile;

355355

}) {

@@ -705,6 +705,20 @@ export function buildPlaywrightEvidenceSummary(

705705

});

706706

}

707707
708+

export function buildScriptEvidenceSummary(

709+

params: QaEvidenceBuildBase & {

710+

targets: readonly QaEvidenceTestTargetInput[];

711+

results: readonly QaEvidenceTestResultInput[];

712+

},

713+

): QaEvidenceSummaryJson {

714+

return buildTestRunnerEvidenceSummary({

715+

...params,

716+

defaultRunner: "script",

717+

testKind: "script-test",

718+

runner: params.runner ?? "script",

719+

});

720+

}

721+
708722

export function buildLiveTransportEvidenceSummary(

709723

params: QaEvidenceBuildBase & {

710724

checks: readonly QaEvidenceLiveTransportCheckInput[];

Original file line numberDiff line numberDiff line change

@@ -73,6 +73,10 @@ const qaTestFileScenarioExecutionBaseSchema = z.object({

7373

const qaTestFileScenarioExecutionSchema = z.discriminatedUnion("kind", [

7474

qaTestFileScenarioExecutionBaseSchema.extend({ kind: z.literal("vitest") }),

7575

qaTestFileScenarioExecutionBaseSchema.extend({ kind: z.literal("playwright") }),

76+

qaTestFileScenarioExecutionBaseSchema.extend({

77+

kind: z.literal("script"),

78+

args: z.array(z.string()).optional(),

79+

}),

7680

]);

7781
7882

const qaScenarioExecutionSchema = z.union([

Original file line numberDiff line numberDiff line change

@@ -90,7 +90,7 @@ const qaMaturityTaxonomySchema = z

9090

}

9191

});

9292
93-

export type QaNativeCoverageEvidenceKind = "vitest" | "playwright";

93+

export type QaNativeCoverageEvidenceKind = "script" | "vitest" | "playwright";

9494

export type QaScorecardEvidenceKind = QaNativeCoverageEvidenceKind | "qa-scenario";

9595

export type QaScorecardEvidenceMode = z.infer<typeof qaScorecardEvidenceModeSchema>;

9696

type QaCoverageEvidenceRole = z.infer<typeof qaCoverageEvidenceRoleSchema>;

Original file line numberDiff line numberDiff line change

@@ -74,7 +74,7 @@ describe("qa suite runtime launcher", () => {

7474

runQaTestFileScenarios.mockImplementation(

7575

async (params: {

7676

outputDir: string;

77-

scenarios: Array<{ id: string; execution: { kind: "vitest" | "playwright" } }>;

77+

scenarios: Array<{ id: string; execution: { kind: "script" | "vitest" | "playwright" } }>;

7878

}) => {

7979

const [scenario] = params.scenarios;

8080

if (!scenario) {