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

人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
云风的 BLOG
云风的 BLOG
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
量子位
GbyAI
GbyAI
腾讯CDC
T
Tailwind CSS Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Docker
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
Jina AI
Jina AI
IT之家
IT之家
Y
Y Combinator 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
fix: count maturity coverage ids (#96543) · openclaw/open...
RomneyDa · 2026-06-25 · via Recent Commits to openclaw:main

@@ -182,9 +182,9 @@ describe("qa coverage report", () => {

182182

expect(inventory.scorecardTaxonomy.requiredCategoryCount).toBeLessThanOrEqual(

183183

inventory.scorecardTaxonomy.categoryCount,

184184

);

185-

expect(inventory.scorecardTaxonomy.requiredFeatureCount).toBeGreaterThan(0);

186-

expect(inventory.scorecardTaxonomy.fulfilledFeatureCount).toBeGreaterThan(0);

187-

expect(inventory.scorecardTaxonomy.taxonomyFulfillmentPercent).toBeGreaterThan(0);

185+

expect(inventory.scorecardTaxonomy.requiredCoverageIdCount).toBeGreaterThan(0);

186+

expect(inventory.scorecardTaxonomy.fulfilledCoverageIdCount).toBeGreaterThan(0);

187+

expect(inventory.scorecardTaxonomy.coverageIdFulfillmentPercent).toBeGreaterThan(0);

188188

expect(inventory.scorecardTaxonomy.evidenceRefCount).toBeGreaterThan(0);

189189

expect(inventory.scorecardTaxonomy.scenarioCoverageIdCount).toBeGreaterThan(0);

190190

expect(inventory.scorecardTaxonomy.unknownCoverageIdCount).toBe(0);

@@ -259,7 +259,7 @@ describe("qa coverage report", () => {

259259

expect(report).toContain("## Scorecard Taxonomy");

260260

expect(report).toContain("- Taxonomy: taxonomy.yaml");

261261

expect(report).toContain("- Fulfilled taxonomy categories:");

262-

expect(report).toContain("- Fulfilled taxonomy features:");

262+

expect(report).toContain("- Fulfilled taxonomy coverage IDs:");

263263

expect(report).toContain("- Evidence refs:");

264264

expect(report).toContain("- Scenario coverage IDs:");

265265

expect(report).toContain(

@@ -347,7 +347,7 @@ describe("qa coverage report", () => {

347347

],

348348

});

349349350-

expect(report.fulfilledFeatureCount).toBe(0);

350+

expect(report.fulfilledCoverageIdCount).toBe(0);

351351

expect(report.categories[0]?.coverageStatus).toBe("missing");

352352

expect(report.validationIssues.map((issue) => issue.code)).toEqual([

353353

"coverage-id-not-found",

@@ -375,7 +375,7 @@ describe("qa coverage report", () => {

375375376376

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

377377

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

378-

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

378+

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

379379

expect(report.categories[0]?.coverageStatus).toBe("covered");

380380

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

381381

"qa/scenarios/ui/control-ui-chat-flow-playwright.yaml",

@@ -391,7 +391,7 @@ describe("qa coverage report", () => {

391391

]);

392392

});

393393394-

it("requires every coverage ID on a taxonomy feature to have primary evidence", () => {

394+

it("counts partial coverage IDs proportionately for taxonomy fulfillment", () => {

395395

const report = buildQaScorecardTaxonomyReport({

396396

taxonomy: testMaturityTaxonomy({

397397

featureCoverageIds: [[TEST_EXECUTABLE_COVERAGE_ID, TEST_WEBCHAT_COVERAGE_ID]],

@@ -407,7 +407,9 @@ describe("qa coverage report", () => {

407407

});

408408409409

expect(report.fulfilledCategoryCount).toBe(0);

410-

expect(report.fulfilledFeatureCount).toBe(0);

410+

expect(report.requiredCoverageIdCount).toBe(2);

411+

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

412+

expect(report.coverageIdFulfillmentPercent).toBe(50);

411413

expect(report.categories[0]?.coverageStatus).toBe("partial");

412414

expect(report.categories[0]?.fulfilledCoverageIds).toStrictEqual([TEST_EXECUTABLE_COVERAGE_ID]);

413415

expect(report.validationIssues).toContainEqual(

@@ -418,6 +420,75 @@ describe("qa coverage report", () => {

418420

);

419421

});

420422423+

it("counts each required taxonomy coverage ID once across categories", () => {

424+

const taxonomy: QaMaturityTaxonomy = {

425+

...testMaturityTaxonomy(),

426+

profiles: [

427+

{

428+

id: "release",

429+

description: "Test release profile.",

430+

includeAllCategories: false,

431+

channelDriver: "qa-channel",

432+

categoryIds: [

433+

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

434+

"agent-runtime-and-provider-execution.tool-execution-controls",

435+

],

436+

},

437+

],

438+

surfaces: [

439+

{

440+

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

441+

name: "Agent Runtime",

442+

family: "test",

443+

level: "experimental",

444+

categories: [

445+

{

446+

id: "agent-turn-execution",

447+

name: "Agent Turn Execution",

448+

category_note: "agent-turn-execution.md",

449+

docs: [],

450+

search_anchors: [],

451+

features: [

452+

{

453+

name: "shared plus unique",

454+

coverageIds: [TEST_EXECUTABLE_COVERAGE_ID, TEST_WEBCHAT_COVERAGE_ID],

455+

},

456+

],

457+

},

458+

{

459+

id: "tool-execution-controls",

460+

name: "Tool Execution Controls",

461+

category_note: "tool-execution-controls.md",

462+

docs: [],

463+

search_anchors: [],

464+

features: [

465+

{

466+

name: "shared",

467+

coverageIds: [TEST_EXECUTABLE_COVERAGE_ID],

468+

},

469+

],

470+

},

471+

],

472+

},

473+

],

474+

};

475+

const report = buildQaScorecardTaxonomyReport({

476+

taxonomy,

477+

repoRoot: process.cwd(),

478+

scenarios: [

479+

scenarioWithCoverage({

480+

primary: [TEST_EXECUTABLE_COVERAGE_ID],

481+

secondary: [TEST_WEBCHAT_COVERAGE_ID],

482+

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

483+

}),

484+

],

485+

});

486+487+

expect(report.requiredCoverageIdCount).toBe(2);

488+

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

489+

expect(report.coverageIdFulfillmentPercent).toBe(50);

490+

});

491+421492

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

422493

const report = buildQaScorecardTaxonomyReport({

423494

taxonomy: testMaturityTaxonomy({

@@ -437,7 +508,7 @@ describe("qa coverage report", () => {

437508438509

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

439510

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

440-

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

511+

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

441512

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

442513

{

443514

coverageId: TEST_BROWSER_COVERAGE_ID,

@@ -555,7 +626,7 @@ describe("qa coverage report", () => {

555626

],

556627

});

557628558-

expect(report.fulfilledFeatureCount).toBe(0);

629+

expect(report.fulfilledCoverageIdCount).toBe(0);

559630

expect(report.categories[0]?.coverageStatus).toBe("partial");

560631

expect(report.validationIssues.map((issue) => issue.code)).toEqual([

561632

"coverage-id-not-found",