f08c4b18cf
- phase-c.test.ts (626 lines) → phase-c-ui.test.ts (279), phase-c-tabs.test.ts (272), phase-c-llm.test.ts (76) — all 11 scenarios preserved - agor.test.ts (799 lines) → smoke.test.ts (47), workspace.test.ts (79), settings.test.ts (247), features.test.ts (488) — split in progress - Reset-to-home-state hooks added to stateful before() blocks - wdio.conf.js specs array updated for all new filenames
76 lines
3.2 KiB
TypeScript
76 lines
3.2 KiB
TypeScript
import { browser, expect } from '@wdio/globals';
|
||
import { isJudgeAvailable, assertWithJudge } from '../infra/llm-judge';
|
||
|
||
// Phase C — LLM-Judged Tests (C10–C11)
|
||
// Settings completeness and status bar completeness via LLM judge.
|
||
|
||
// ─── Scenario C10: LLM-Judged Settings Completeness ──────────────────
|
||
|
||
describe('Scenario C10 — LLM-Judged Settings Completeness', () => {
|
||
it('should have comprehensive settings panel', async function () {
|
||
if (!isJudgeAvailable()) {
|
||
console.log('Skipping — LLM judge not available (no CLI or API key)');
|
||
this.skip();
|
||
return;
|
||
}
|
||
|
||
// Open settings
|
||
await browser.execute(() => {
|
||
const btn = document.querySelector('[data-testid="settings-btn"]');
|
||
if (btn) (btn as HTMLElement).click();
|
||
});
|
||
await browser.pause(500);
|
||
|
||
const settingsContent = await browser.execute(() => {
|
||
const panel = document.querySelector('.sidebar-panel, .settings-tab');
|
||
return panel?.textContent ?? '';
|
||
});
|
||
|
||
const verdict = await assertWithJudge(
|
||
'The settings panel should contain configuration options for: (1) theme/appearance, (2) font settings (UI and terminal), (3) default shell, and optionally (4) provider settings. It should look like a real settings UI, not an error message.',
|
||
settingsContent,
|
||
{ context: 'BTerminal v3 settings panel with Appearance section (theme dropdown, UI font, terminal font) and Defaults section (shell, CWD). May also have Providers section.' },
|
||
);
|
||
|
||
expect(verdict.pass).toBe(true);
|
||
if (!verdict.pass) {
|
||
console.log(`LLM Judge: ${verdict.reasoning} (confidence: ${verdict.confidence})`);
|
||
}
|
||
|
||
await browser.keys('Escape');
|
||
await browser.pause(300);
|
||
});
|
||
});
|
||
|
||
// ─── Scenario C11: LLM-Judged Status Bar ──────────────────────────────
|
||
|
||
describe('Scenario C11 — LLM-Judged Status Bar Completeness', () => {
|
||
it('should render a comprehensive status bar', async function () {
|
||
if (!isJudgeAvailable()) {
|
||
console.log('Skipping — LLM judge not available (no CLI or API key)');
|
||
this.skip();
|
||
return;
|
||
}
|
||
|
||
const statusBarContent = await browser.execute(() => {
|
||
const bar = document.querySelector('[data-testid="status-bar"]');
|
||
return bar?.textContent ?? '';
|
||
});
|
||
|
||
const statusBarHtml = await browser.execute(() => {
|
||
const bar = document.querySelector('[data-testid="status-bar"]');
|
||
return bar?.innerHTML ?? '';
|
||
});
|
||
|
||
const verdict = await assertWithJudge(
|
||
'The status bar should display agent fleet information including: agent status counts (idle/running/stalled with numbers), and optionally burn rate ($/hr) and cost tracking. It should look like a real monitoring dashboard status bar.',
|
||
`Text: ${statusBarContent}\n\nHTML structure: ${statusBarHtml.substring(0, 2000)}`,
|
||
{ context: 'BTerminal Mission Control status bar shows running/idle/stalled agent counts, total $/hr burn rate, attention queue, and total cost.' },
|
||
);
|
||
|
||
expect(verdict.pass).toBe(true);
|
||
if (!verdict.pass) {
|
||
console.log(`LLM Judge: ${verdict.reasoning} (confidence: ${verdict.confidence})`);
|
||
}
|
||
});
|
||
});
|