Files
wehub-resource-sync 7a0da7932b
OSV-Scanner (Scheduled) / scan-scheduled (push) Failing after 0s
Create Release / test-gate (push) Has been cancelled
Create Release / release-gate (push) Has been cancelled
Create Release / ci-gate (push) Has been cancelled
Create Release / version-check (push) Has been cancelled
Create Release / e2e-test-gate (push) Has been cancelled
Create Release / responsive-test-gate (push) Has been cancelled
Create Release / compat-test-gate (push) Has been cancelled
Create Release / compose-integration-gate (push) Has been cancelled
Create Release / vulture-gate (push) Has been cancelled
Create Release / build (push) Has been cancelled
Create Release / provenance (push) Has been cancelled
Create Release / prerelease-docker (push) Has been cancelled
Create Release / publish-docker (push) Has been cancelled
Create Release / create-release (push) Has been cancelled
Create Release / cleanup-changelog (push) Has been cancelled
Create Release / trigger-pypi (push) Has been cancelled
Create Release / monitor-pypi (push) Has been cancelled
Create Release / Clean up orphan prerelease tags and signatures (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-form] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-metrics] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [research-workflow] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [settings-core] (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [history-news] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [library] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [link-analytics] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [chat-core] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [chat-lifecycle] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [error-benchmark] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [settings-pages] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) (push) Has been cancelled
Docker Tests (Consolidated) / Accessibility Tests (push) Has been cancelled
Docker Tests (Consolidated) / LLM Unit Tests (push) Has been cancelled
Docker Tests (Consolidated) / LLM Example Tests (push) Has been cancelled
Docker Tests (Consolidated) / Production Image Smoke Test (push) Has been cancelled
Docker Tests (Consolidated) / Infrastructure Tests (push) Has been cancelled
OSSF Scorecard / OSSF Security Scorecard Analysis (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [mobile] (push) Has been cancelled
Backwards Compatibility / Verify Encryption Constants (push) Has been cancelled
Backwards Compatibility / PyPI Version Compatibility (push) Has been cancelled
Backwards Compatibility / Database Migration Tests (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Docker Tests (Consolidated) / detect-changes (push) Has been cancelled
Docker Tests (Consolidated) / Build Test Image (push) Has been cancelled
Docker Tests (Consolidated) / All Pytest Tests + Coverage (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [accessibility] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [api-crud] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-login] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-pages] (push) Has been cancelled
Docker Tests (Consolidated) / UI Tests (Puppeteer) [auth-register] (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:08:55 +08:00

592 lines
25 KiB
JavaScript

#!/usr/bin/env node
/**
* Benchmark UI Tests
*
* Tests for the benchmark dashboard and results pages.
*
* Run: node test_benchmark_ci.js
*/
const { setupTest, teardownTest, TestResults, log, delay, navigateTo, withTimeout } = require('./test_lib');
// ============================================================================
// Benchmark Dashboard Tests
// ============================================================================
const BenchmarkDashboardTests = {
async benchmarkPageLoads(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
return {
hasContent: !!document.querySelector('.benchmark-container, .ldr-benchmark, #benchmark, .benchmark'),
hasHeader: !!document.querySelector('h1, .benchmark-header, .page-title'),
headerText: document.querySelector('h1, .benchmark-header, .page-title')?.textContent?.trim(),
hasForm: !!document.querySelector('form, .benchmark-form, .config-form')
};
});
const passed = result.hasContent || result.hasHeader || result.hasForm;
return {
passed,
message: passed
? `Benchmark page loaded (header: "${result.headerText}", form: ${result.hasForm})`
: 'Benchmark page failed to load'
};
},
async benchmarkFormStructure(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
const form = document.querySelector('form, .benchmark-form, .config-form');
if (!form) return { hasForm: false };
const inputs = form.querySelectorAll('input, select, textarea');
const selects = form.querySelectorAll('select');
const buttons = form.querySelectorAll('button[type="submit"], .btn-primary, .start-btn');
return {
hasForm: true,
inputCount: inputs.length,
selectCount: selects.length,
hasSubmitButton: buttons.length > 0,
buttonText: buttons[0]?.textContent?.trim()
};
});
if (!result.hasForm) {
return { passed: null, skipped: true, message: 'No benchmark form found' };
}
return {
passed: result.inputCount > 0 || result.selectCount > 0,
message: `Benchmark form: ${result.inputCount} inputs, ${result.selectCount} selects, submit="${result.buttonText}"`
};
},
async configDropdowns(page, baseUrl) {
// The benchmark form (benchmark.html) has #evaluation_provider (a <select>)
// and #evaluation_model (a custom-dropdown input). On load,
// populateEvaluationProviders() (benchmark.html) fills the select with the
// built-in provider list (ollama/openai/anthropic/...), which renders
// client-side with no LLM — the async /settings/api/available-models call
// only *replaces* that list if it returns providers. So this asserts the
// select is actually populated with non-empty options (a render/contract
// check that catches the script not running), not that discovery succeeded.
// The old test scanned all <select>s and passed if any name contained
// "provider" — true for #evaluation_provider regardless of its options.
await navigateTo(page, `${baseUrl}/benchmark/`);
await page.waitForSelector('#evaluation_provider', { timeout: 15000 });
// Providers populate synchronously on DOMContentLoaded; wait briefly for a
// real (non-stub) option in case the inline script hasn't finished when we
// first query. 5s is ample for a synchronous fill, so a genuine "script
// never ran" failure surfaces fast rather than after a long timeout.
await page.waitForFunction(
() => {
const sel = document.querySelector('#evaluation_provider');
return sel && Array.from(sel.options).some(o => o.value && o.value.length > 0);
},
{ timeout: 5000 }
).catch(() => {});
const result = await page.evaluate(() => {
const provider = document.querySelector('#evaluation_provider');
const model = document.querySelector('#evaluation_model');
const opts = provider ? Array.from(provider.options).map(o => o.value).filter(Boolean) : [];
return {
hasProvider: !!provider,
providerOptionCount: opts.length,
providerOptions: opts.slice(0, 6),
// #evaluation_model is a custom-dropdown <input> (render_dropdown),
// not a <select>; assert the type and that it lives in the form.
modelIsInput: model?.tagName === 'INPUT',
modelInForm: !!model?.closest('form#benchmark-form'),
};
});
const passed = result.hasProvider && result.providerOptionCount > 0
&& result.modelIsInput && result.modelInForm;
return {
passed,
message: passed
? `Benchmark config: #evaluation_provider has ${result.providerOptionCount} options (${result.providerOptions.join(', ')}) + #evaluation_model is an input inside #benchmark-form`
: `Benchmark config incomplete (provider=${result.hasProvider}, providerOptions=${result.providerOptionCount}, modelIsInput=${result.modelIsInput}, modelInForm=${result.modelInForm})`
};
},
async startBenchmarkButton(page, baseUrl) {
// The real start control is #start-benchmark-btn: a submit button inside
// form#benchmark-form labelled "Start Benchmark" (benchmark.html:296). The
// old test fuzzy-matched any button whose text contained start/run/begin.
await navigateTo(page, `${baseUrl}/benchmark/`);
await page.waitForSelector('#start-benchmark-btn', { timeout: 15000 });
const result = await page.evaluate(() => {
const btn = document.querySelector('#start-benchmark-btn');
if (!btn) return { found: false };
return {
found: true,
tag: btn.tagName.toLowerCase(),
type: btn.type,
text: btn.textContent?.trim() || '',
inForm: !!btn.closest('form#benchmark-form'),
};
});
if (!result.found) {
return { passed: false, message: '#start-benchmark-btn not found' };
}
const passed = result.tag === 'button' && result.type === 'submit'
&& /start benchmark/i.test(result.text) && result.inForm;
return {
passed,
message: passed
? `Start button is a submit button in #benchmark-form ("${result.text}")`
: `Start button contract failed (tag=${result.tag}, type=${result.type}, text="${result.text}", inForm=${result.inForm})`
};
},
async runningBenchmarksSection(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
const runningSection = document.querySelector(
'[class*="running"], ' +
'[id*="running"], ' +
'.active-benchmarks, ' +
'.in-progress'
);
const hasRunningText = document.body.textContent?.toLowerCase().includes('running') ||
document.body.textContent?.toLowerCase().includes('in progress');
return {
hasSection: !!runningSection,
hasRunningText
};
});
if (!result.hasSection && !result.hasRunningText) {
return { passed: null, skipped: true, message: 'No running benchmarks section found' };
}
return {
passed: true,
message: 'Running benchmarks section found'
};
},
async benchmarkHistoryTable(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
const table = document.querySelector('table, .benchmark-history, .history-list');
if (!table) return { hasTable: false };
const rows = table.querySelectorAll('tbody tr, .history-item');
const headers = Array.from(table.querySelectorAll('th')).map(th => th.textContent?.toLowerCase().trim());
return {
hasTable: true,
rowCount: rows.length,
hasDateColumn: headers.some(h => h.includes('date') || h.includes('time') || h.includes('created')),
hasStatusColumn: headers.some(h => h.includes('status') || h.includes('state')),
headers: headers.slice(0, 6)
};
});
if (!result.hasTable) {
return { passed: null, skipped: true, message: 'No benchmark history table found' };
}
return {
passed: true,
message: `History table: ${result.rowCount} rows (columns: ${result.headers.join(', ')})`
};
}
};
// ============================================================================
// Benchmark Results Tests
// ============================================================================
const BenchmarkResultsTests = {
async benchmarkResultsPageLoads(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/results`);
const result = await page.evaluate(() => {
return {
hasContent: !!document.querySelector('.benchmark-results, .results-container, #results'),
hasHeader: !!document.querySelector('h1, .page-title'),
headerText: document.querySelector('h1, .page-title')?.textContent?.trim(),
hasResults: document.querySelectorAll('.result-card, .benchmark-result, table').length > 0
};
});
const passed = result.hasContent || result.hasHeader || result.hasResults;
return {
passed,
message: passed
? `Benchmark results page loaded (header: "${result.headerText}")`
: 'Benchmark results page failed to load'
};
},
async resultsMetricsCards(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/results`);
const result = await page.evaluate(() => {
const cards = document.querySelectorAll('.metric-card, .stats-card, .card, .result-metric');
const cardTexts = Array.from(cards).map(c => c.textContent?.toLowerCase() || '');
return {
cardCount: cards.length,
hasAccuracyCard: cardTexts.some(t => t.includes('accuracy') || t.includes('correct')),
hasSpeedCard: cardTexts.some(t => t.includes('speed') || t.includes('time') || t.includes('latency')),
hasQualityCard: cardTexts.some(t => t.includes('quality') || t.includes('score'))
};
});
if (result.cardCount === 0) {
return { passed: null, skipped: true, message: 'No metrics cards found on results page' };
}
return {
passed: true,
message: `Results metrics: ${result.cardCount} cards (accuracy=${result.hasAccuracyCard}, speed=${result.hasSpeedCard}, quality=${result.hasQualityCard})`
};
},
async comparisonCharts(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/results`);
await delay(1000);
const result = await page.evaluate(() => {
const charts = document.querySelectorAll('canvas, svg, .chart, .recharts-wrapper');
const comparisonSection = document.querySelector('[class*="comparison"], [id*="comparison"]');
return {
hasCharts: charts.length > 0,
chartCount: charts.length,
hasComparisonSection: !!comparisonSection
};
});
if (!result.hasCharts && !result.hasComparisonSection) {
return { passed: null, skipped: true, message: 'No comparison charts found' };
}
return {
passed: true,
message: `Comparison visualization: ${result.chartCount} charts found`
};
},
async qualityScoreDisplay(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/results`);
const result = await page.evaluate(() => {
const scoreElement = document.querySelector(
'[class*="quality-score"], ' +
'[class*="overall-score"], ' +
'.score-display'
);
// Look for percentage or score pattern
const scorePattern = /(\d+(?:\.\d*)?)\s*(?:%|\/\s*100|points?|score)/i;
const bodyText = document.body.textContent || '';
const scoreMatch = bodyText.match(scorePattern);
return {
hasScoreElement: !!scoreElement,
scoreText: scoreElement?.textContent?.trim(),
foundScoreInText: !!scoreMatch,
scoreValue: scoreMatch ? scoreMatch[1] : null
};
});
if (!result.hasScoreElement && !result.foundScoreInText) {
return { passed: null, skipped: true, message: 'No quality score display found' };
}
return {
passed: true,
message: result.hasScoreElement
? `Quality score displayed: "${result.scoreText}"`
: `Score found: ${result.scoreValue}`
};
},
async cancelBenchmarkButton(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
const buttons = Array.from(document.querySelectorAll('button, a.btn'));
const cancelBtn = buttons.find(b => {
const text = b.textContent?.toLowerCase() || '';
return text.includes('cancel') || text.includes('stop') || text.includes('abort');
});
return {
found: !!cancelBtn,
text: cancelBtn?.textContent?.trim(),
disabled: cancelBtn?.disabled
};
});
if (!result.found) {
return { passed: null, skipped: true, message: 'No cancel button found (may only appear during active benchmark)' };
}
return {
passed: true,
message: `Cancel button found: "${result.text}"`
};
},
async deleteBenchmarkButton(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(() => {
const buttons = Array.from(document.querySelectorAll('button, a.btn'));
const deleteBtn = buttons.find(b => {
const text = b.textContent?.toLowerCase() || '';
return text.includes('delete') || text.includes('remove');
});
// Also check for trash icons
const trashIcon = document.querySelector('.fa-trash, .delete-icon, [class*="trash"]');
return {
found: !!deleteBtn || !!trashIcon,
text: deleteBtn?.textContent?.trim(),
hasIcon: !!trashIcon
};
});
if (!result.found) {
return { passed: null, skipped: true, message: 'No delete button found (may require existing benchmarks)' };
}
return {
passed: true,
message: result.text ? `Delete button found: "${result.text}"` : 'Delete icon found'
};
},
async exportDropdown(page, baseUrl) {
// The per-run Export dropdown only renders for COMPLETED runs.
await navigateTo(page, `${baseUrl}/benchmark/`);
await delay(1500); // let the async history fetch render run cards
const result = await page.evaluate(() => {
const toggle = Array.from(document.querySelectorAll('.dropdown-toggle'))
.find(b => (b.textContent || '').toLowerCase().includes('export'));
if (!toggle) return { found: false };
const menu = toggle.closest('.dropdown')?.querySelector('.dropdown-menu');
const items = menu
? Array.from(menu.querySelectorAll('.dropdown-item')).map(i => (i.textContent || '').toLowerCase())
: [];
const itemText = items.join(' | ');
const checkbox = menu?.querySelector('input[type="checkbox"]');
const checkboxLabel = (checkbox?.closest('label')?.textContent || '').toLowerCase();
return {
found: true,
hasSummary: itemText.includes('summary'),
hasExamples: itemText.includes('examples'),
hasSettingsCheckbox: !!checkbox && checkboxLabel.includes('settings'),
// The opt-in default must be OFF so the default download is lean.
checkboxDefaultOff: checkbox ? checkbox.checked === false : null,
};
});
if (!result.found) {
return { passed: null, skipped: true, message: 'No Export dropdown found (requires a completed benchmark run)' };
}
const ok = result.hasSummary && result.hasExamples
&& result.hasSettingsCheckbox && result.checkboxDefaultOff === true;
return {
passed: ok,
message: ok
? 'Export dropdown has summary/examples items + settings-snapshot checkbox (default off)'
: `Export dropdown incomplete: summary=${result.hasSummary} examples=${result.hasExamples} settingsCheckbox=${result.hasSettingsCheckbox} checkboxDefaultOff=${result.checkboxDefaultOff}`,
};
}
};
// ============================================================================
// Benchmark API Tests
// ============================================================================
const BenchmarkApiTests = {
async benchmarkHistoryApiResponds(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(async (url) => {
try {
const response = await fetch(`${url}/benchmark/api/history`);
if (!response.ok) return { ok: false, status: response.status };
const data = await response.json();
return {
ok: true,
status: response.status,
count: Array.isArray(data) ? data.length : (data.items?.length || 0)
};
} catch (e) {
return { ok: false, error: e.message };
}
}, baseUrl);
if (!result.ok && result.status === 404) {
return { passed: null, skipped: true, message: 'Benchmark history API not found' };
}
return {
passed: result.ok,
message: result.ok
? `Benchmark history API responds (${result.count} items)`
: `Benchmark API failed: ${result.error || 'status ' + result.status}`
};
},
async benchmarkConfigsApiResponds(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(async (url) => {
try {
const response = await fetch(`${url}/benchmark/api/configs`);
if (!response.ok) return { ok: false, status: response.status };
const data = await response.json();
return {
ok: true,
status: response.status,
count: Array.isArray(data) ? data.length : Object.keys(data).length
};
} catch (e) {
return { ok: false, error: e.message };
}
}, baseUrl);
if (!result.ok && result.status === 404) {
return { passed: null, skipped: true, message: 'Benchmark configs API not found' };
}
return {
passed: result.ok,
message: result.ok
? `Benchmark configs API responds (${result.count} configs)`
: `Configs API failed: ${result.error || 'status ' + result.status}`
};
},
async benchmarkRunningApiResponds(page, baseUrl) {
await navigateTo(page, `${baseUrl}/benchmark/`);
const result = await page.evaluate(async (url) => {
try {
const response = await fetch(`${url}/benchmark/api/running`);
if (!response.ok) return { ok: false, status: response.status };
const data = await response.json();
return {
ok: true,
status: response.status,
hasData: data !== null && data !== undefined
};
} catch (e) {
return { ok: false, error: e.message };
}
}, baseUrl);
if (!result.ok && result.status === 404) {
return { passed: null, skipped: true, message: 'Benchmark running API not found' };
}
return {
passed: result.ok,
message: result.ok
? `Benchmark running API responds`
: `Running API failed: ${result.error || 'status ' + result.status}`
};
}
};
// ============================================================================
// Main Test Runner
// ============================================================================
async function main() {
log.section('Benchmark Tests');
const ctx = await setupTest({ authenticate: true });
const results = new TestResults('Benchmark Tests');
const { page } = ctx;
const { baseUrl } = ctx.config;
const subTestTimeout = ctx.config.isCI ? 60000 : 30000;
async function run(category, name, testFn) {
try {
const result = await withTimeout(
testFn(page, baseUrl),
subTestTimeout,
`${category}/${name}`
);
if (result.skipped) {
results.skip(category, name, result.message);
} else {
results.add(category, name, result.passed, result.message);
}
} catch (error) {
results.add(category, name, false, `Error: ${error.message}`);
}
}
try {
// Benchmark Dashboard Tests
log.section('Benchmark Dashboard');
await run('Dashboard', 'Benchmark Page Loads', (p, u) => BenchmarkDashboardTests.benchmarkPageLoads(p, u));
await run('Dashboard', 'Benchmark Form Structure', (p, u) => BenchmarkDashboardTests.benchmarkFormStructure(p, u));
await run('Dashboard', 'Config Dropdowns', (p, u) => BenchmarkDashboardTests.configDropdowns(p, u));
await run('Dashboard', 'Start Benchmark Button', (p, u) => BenchmarkDashboardTests.startBenchmarkButton(p, u));
await run('Dashboard', 'Running Benchmarks Section', (p, u) => BenchmarkDashboardTests.runningBenchmarksSection(p, u));
await run('Dashboard', 'Benchmark History Table', (p, u) => BenchmarkDashboardTests.benchmarkHistoryTable(p, u));
// Benchmark Results Tests
log.section('Benchmark Results');
await run('Results', 'Benchmark Results Page Loads', (p, u) => BenchmarkResultsTests.benchmarkResultsPageLoads(p, u));
await run('Results', 'Results Metrics Cards', (p, u) => BenchmarkResultsTests.resultsMetricsCards(p, u));
await run('Results', 'Comparison Charts', (p, u) => BenchmarkResultsTests.comparisonCharts(p, u));
await run('Results', 'Quality Score Display', (p, u) => BenchmarkResultsTests.qualityScoreDisplay(p, u));
await run('Results', 'Cancel Benchmark Button', (p, u) => BenchmarkResultsTests.cancelBenchmarkButton(p, u));
await run('Results', 'Delete Benchmark Button', (p, u) => BenchmarkResultsTests.deleteBenchmarkButton(p, u));
await run('Results', 'Export Dropdown', (p, u) => BenchmarkResultsTests.exportDropdown(p, u));
// Benchmark API Tests
log.section('Benchmark APIs');
await run('API', 'Benchmark History API', (p, u) => BenchmarkApiTests.benchmarkHistoryApiResponds(p, u));
await run('API', 'Benchmark Configs API', (p, u) => BenchmarkApiTests.benchmarkConfigsApiResponds(p, u));
await run('API', 'Benchmark Running API', (p, u) => BenchmarkApiTests.benchmarkRunningApiResponds(p, u));
} catch (error) {
log.error(`Fatal error: ${error.message}`);
console.error(error.stack);
} finally {
results.print();
results.save();
await teardownTest(ctx);
process.exit(results.exitCode());
}
}
// Run if executed directly
if (require.main === module) {
main().catch(error => {
console.error('Test runner failed:', error);
process.exit(1);
});
}
module.exports = { BenchmarkDashboardTests, BenchmarkResultsTests, BenchmarkApiTests };