A new mode where the user explains a topic in their own words and the AI plays a curious classmate: short reactions, exactly one follow-up question at a time, never "correct"/"wrong", never lecturing, and everything it knows comes from the user's own decks and notes. - Entry points: a sidebar row next to Exam mode and a "Teach it back" action in every deck's menu (which prefills the topic and scope). - Start screen: deck or typed topic, friendly/skeptical student, the same context and model chips as Chat (/teach?deck=<id> pre-selects the deck). - Session: the student prompt is a mode of the existing /api/chat route, so model resolution, allowlists, rate limits and the streaming client are the same code; the personality lives in lib/prompts.ts (TEACH_*). The deck's cards travel as a numbered checklist and the student is told to ask about the ideas that were skipped; it must say so rather than guess when the notes cover nothing. One constant (TEACH_MAX_EXCHANGES = 10) ends the session, or the Finish button does. - Recap: a teach_summary call (JSON, one repair retry) yields well / gaps with card references / next steps; each gap links to the card it means. "Add missed cards to review" schedules those activities due now; "Turn gaps into cards" generates one flashcard per gap from the deck's notes and shows an editable review list before saving. - Sessions are chat conversations with a mode:"teach" marker + session record: same IndexedDB history, backup and sync, filtered out of the Chat screens; the recent list reopens a recap or continues a session. - Reused pieces: MessageRow, Composer (now optional attach/scope chips and a mic), Markdown/KaTeX, AiDisclaimer, ContextPicker/ModelPicker, plus a shared useChatModels hook and useKeyboardInset extracted from Chat. - Dictation: Web Speech API recognition (lib/speech-input.ts); the mic only renders where the browser supports it, and dictated phrases land in the draft. - All strings in en + cs. teach-test: 44 checks (API prompts and guards, both entry points, the session, recap actions, history, exchange limit, 360/390px layouts, mic on/off). Version 0.8.1, SW v103.
52 lines
1.5 KiB
JavaScript
52 lines
1.5 KiB
JavaScript
/**
|
|
* Runs every Freezmo browser suite in order.
|
|
*
|
|
* npm run test:e2e # everything
|
|
* npm run test:e2e -- phase1 # only suites whose name contains "phase1"
|
|
*
|
|
* Each suite is a standalone script that talks to the running app on :3207
|
|
* (FREEZMO_URL overrides). Suites that need a stub Ollama or extra server
|
|
* instance start their own on their own port and clean up after themselves.
|
|
*/
|
|
import { spawn } from "node:child_process";
|
|
import path from "node:path";
|
|
|
|
const SUITES = [
|
|
"regression",
|
|
"activities-test",
|
|
"aero-music-test",
|
|
"bubbles-test",
|
|
"mobile-test",
|
|
"wizard-test",
|
|
"native-test",
|
|
"i18n-test",
|
|
"freeze-loading-test",
|
|
"phase1-test",
|
|
"phase2-test",
|
|
"phase3-test",
|
|
"podcast-test",
|
|
"teach-test",
|
|
"security-test",
|
|
"chat-test",
|
|
"providers-test",
|
|
"review-test",
|
|
];
|
|
|
|
const filters = process.argv.slice(2);
|
|
const list = filters.length ? SUITES.filter((name) => filters.some((f) => name.includes(f))) : SUITES;
|
|
|
|
const here = path.dirname(new URL(import.meta.url).pathname);
|
|
const repo = path.resolve(here, "..");
|
|
|
|
let failed = 0;
|
|
for (const suite of list) {
|
|
console.log(`\n===== ${suite} =====`);
|
|
const code = await new Promise((resolve) => {
|
|
const child = spawn(process.execPath, [path.join(here, `${suite}.mjs`)], { cwd: repo, stdio: "inherit" });
|
|
child.on("close", resolve);
|
|
});
|
|
if (code !== 0) failed += 1;
|
|
}
|
|
|
|
console.log(`\n${list.length - failed}/${list.length} suites passed`);
|
|
process.exit(failed ? 1 : 0);
|