pediatric-ai-scribe-v3/test/assistant-voice-mode.test.js

// ============================================================
// ASSISTANT VOICE MODE
// ============================================================
// The hands-free overlay: tap, speak, hear the answer. Two things about it were
// wrong in ways a person notices immediately.

const test = require('node:test');
const assert = require('node:assert');
const fs = require('fs');
const path = require('path');
const read = p => fs.readFileSync(path.join(__dirname, '..', p), 'utf8');
const src = read('public/js/clinicalAssistant.js');

// The function under test is a closure inside a browser IIFE, so it is pulled
// out by source rather than imported.
const speakableText = (() => {
  const from = src.indexOf('function speakableText');
  const to = src.indexOf('function speakAnswerVoice');
  // eslint-disable-next-line no-eval
  return eval(src.slice(from, to) + '; speakableText');
})();

test('ending the call stops the voice', () => {
  // It stopped listening and aborted the request but never stopped playback,
  // and the <audio> element was a local with no handle kept — so the answer
  // talked on until the page was reloaded.
  assert.match(src, /function conversationStopSpeaking\(\)/);
  assert.match(src, /if \(window\.speechSynthesis\) window\.speechSynthesis\.cancel\(\)/);
  assert.match(src, /playing\.pause\(\); playing\.src = '';/);

  const end = src.slice(src.indexOf('function endConversationMode'));
  assert.ok(end.indexOf('conversationStopSpeaking()') < end.indexOf('conversationStopListening()'),
    'hanging up silences the answer');
  // Speaking over the previous answer is how an assistant talks past you.
  assert.match(src, /unlockAudioPlayback\(\);\s*\n\s*\/\/[^\n]*\n\s*conversationStopSpeaking\(\);/);
  // A reply that arrives after the overlay closed must not start talking.
  assert.match(src, /if \(!conversationMode\.active\) \{ URL\.revokeObjectURL\(url\); return; \}/);
  // Both players are tracked, or only one of them can be stopped.
  assert.match(src, /conversationMode\.speaking = utter;/);
  assert.match(src, /conversationMode\.speaking = audio;/);
});

test('the answer is read only once it exists', () => {
  // setBusy(false) announces assistant-answer-done, and it used to run before
  // lastAnswer was assigned — so every listener, voice mode included, was handed
  // the previous answer. Tested by position, because that is the whole bug.
  const body = src.slice(src.indexOf('if (request && request.cancelled) return;'));
  const assigned = body.indexOf("lastAnswer = finalData.answer");
  const rendered = body.indexOf('replaceLoadingMessage(loading, lastAnswer');
  const announced = body.indexOf("setBusy(false, 'Ready')");
  assert.ok(assigned < announced, 'the answer is assigned before it is announced');
  assert.ok(rendered < announced, 'and rendered before it is announced');
});

test('voice mode reads what the page shows', () => {
  // The rendered bubble is the answer with its markup already resolved, so
  // reading it is both simpler than unpicking markdown and impossible to drift
  // from what the reader is looking at.
  assert.match(src, /function renderedAnswerText\(\)/);
  assert.match(src, /speakAnswerVoice\(renderedAnswerText\(\) \|\| String\(detail\.answer \|\| ''\)\)/);
  // Never the bubble that is still thinking.
  assert.match(src, /last\.classList\.contains\('assistant-loading-msg'\)\) return '';/);
  // A clone: the things that are not the answer are removed from a copy, not
  // from the page.
  assert.match(src, /var copy = bubble\.cloneNode\(true\);/);
  assert.match(src, /assistant-msg-actions, \.assistant-sources, \.assistant-suggestions, button, pre, table/);
});

test('the markdown fallback is still reduced before it is spoken', () => {
  // The raw answer went straight to the speaker. It is markdown, and a browser
  // voice reads "#" and "**" aloud or stumbles over them.
  assert.match(src, /var text = speakableText\(markdown\);/);

  assert.equal(speakableText('## Croup\n\nA **viral** illness.'), 'Croup\nA viral illness.');
  assert.equal(speakableText('- One\n- Two'), 'One\nTwo');
  assert.equal(speakableText('1. First\n2. Second'), 'First\nSecond');
  assert.equal(speakableText('See [the guideline](https://x.y).'), 'See the guideline.');
  assert.equal(speakableText('Use `epinephrine` now.'), 'Use epinephrine now.');
  // A table read aloud is noise; the prose around it survives.
  assert.equal(speakableText('| A | B |\n|---|---|\n| 1 | 2 |\n\nAfter.'), 'After.');
  // Citation markers leave no gap before the punctuation they preceded.
  assert.equal(speakableText('Clear [1] and also [^2].'), 'Clear and also.');
  assert.equal(speakableText('---\n\n> Quoted.'), 'Quoted.');
  assert.equal(speakableText('```\ncode\n```\n\nThen.'), 'Then.');
  assert.equal(speakableText(''), '');
  assert.equal(speakableText(null), '');
});