Speech to speech: Mute functionality #5688
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -32,6 +32,7 @@ export function setupMockMediaDevices() { | |||||
| const node = context.createGain(); | ||||||
| const channel = new MessageChannel(); | ||||||
| let recording = false; | ||||||
| let muted = false; | ||||||
| let intervalId = null; | ||||||
|
|
||||||
| node.port = channel.port1; | ||||||
|
|
@@ -42,13 +43,21 @@ export function setupMockMediaDevices() { | |||||
| channel.port2.onmessage = ({ data }) => { | ||||||
| if (data.command === 'START') { | ||||||
| recording = true; | ||||||
| muted = false; | ||||||
| const bufferSize = options?.processorOptions?.bufferSize || 2400; | ||||||
|
|
||||||
| // Send chunks at ~100ms intervals while recording | ||||||
| // Use port2.postMessage so port1.onmessage (set by real code) receives it | ||||||
| intervalId = setInterval(() => { | ||||||
| if (recording) { | ||||||
| // Float32Array defaults to zeros (silent), fill with sine wave when not muted | ||||||
| const audioData = new Float32Array(bufferSize); | ||||||
| if (!muted) { | ||||||
| for (let i = 0; i < bufferSize; i++) { | ||||||
| audioData[+i] = Math.sin(i * 0.1) * 0.5; | ||||||
|
There was a problem hiding this comment. In the mock sine-wave generator,
Suggested change
|
||||||
| } | ||||||
| } | ||||||
| channel.port2.postMessage({ eventType: 'audio', audioData }); | ||||||
| } | ||||||
| }, 100); | ||||||
| } else if (data.command === 'STOP') { | ||||||
|
|
@@ -57,6 +66,10 @@ export function setupMockMediaDevices() { | |||||
| clearInterval(intervalId); | ||||||
| intervalId = null; | ||||||
| } | ||||||
| } else if (data.command === 'MUTE') { | ||||||
| muted = true; | ||||||
| } else if (data.command === 'UNMUTE') { | ||||||
| muted = false; | ||||||
| } | ||||||
| }; | ||||||
|
|
||||||
|
|
||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,214 @@ | ||
| <!doctype html> | ||
| <html lang="en-US"> | ||
| <head> | ||
| <link href="/assets/index.css" rel="stylesheet" type="text/css" /> | ||
| <script crossorigin="anonymous" src="https://unpkg.com/@babel/standalone@7.8.7/babel.min.js"></script> | ||
| <script crossorigin="anonymous" src="https://unpkg.com/react@16.8.6/umd/react.production.min.js"></script> | ||
| <script crossorigin="anonymous" src="https://unpkg.com/react-dom@16.8.6/umd/react-dom.production.min.js"></script> | ||
| <script crossorigin="anonymous" src="/test-harness.js"></script> | ||
| <script crossorigin="anonymous" src="/test-page-object.js"></script> | ||
| <script crossorigin="anonymous" src="/__dist__/webchat-es5.js"></script> | ||
| <script crossorigin="anonymous" src="/__dist__/botframework-webchat-fluent-theme.production.min.js"></script> | ||
| </head> | ||
| <body> | ||
| <main id="webchat"></main> | ||
| <!-- | ||
| Test: Mute/Unmute functionality for Speech-to-Speech | ||
|
|
||
| This test validates: | ||
| 1. Listening state can transition to muted and back to listening | ||
| 2. Other states (idle) cannot transition to muted | ||
| 3. Muted chunks contain all zeros (silent audio) | ||
| 4. Uses useVoiceRecordingMuted hook via Composer pattern for mute/unmute control | ||
| --> | ||
| <script type="module"> | ||
| import { setupMockMediaDevices } from '/assets/esm/speechToSpeech/mockMediaDevices.js'; | ||
| import { setupMockAudioPlayback } from '/assets/esm/speechToSpeech/mockAudioPlayback.js'; | ||
|
|
||
| setupMockMediaDevices(); | ||
| setupMockAudioPlayback(); | ||
| </script> | ||
| <script type="text/babel"> | ||
| run(async function () { | ||
| const { | ||
| React: { useEffect }, | ||
| ReactDOM: { render }, | ||
| WebChat: { | ||
| FluentThemeProvider, | ||
| testIds, | ||
| hooks: { useVoiceRecordingMuted }, | ||
| Components: { Composer, BasicWebChat } | ||
| } | ||
| } = window; | ||
|
|
||
| // Helper to decode base64 audio and check if all zeros | ||
| function isAudioAllZeros(base64Content) { | ||
| const binaryString = atob(base64Content); | ||
| const bytes = new Uint8Array(binaryString.length); | ||
| for (let i = 0; i < binaryString.length; i++) { | ||
| bytes[i] = binaryString.charCodeAt(i); | ||
| } | ||
| return bytes.every(byte => byte === 0); | ||
| } | ||
|
|
||
| // Helper to check if audio has non-zero data (real audio) | ||
| function hasNonZeroAudio(base64Content) { | ||
| const binaryString = atob(base64Content); | ||
| const bytes = new Uint8Array(binaryString.length); | ||
| for (let i = 0; i < binaryString.length; i++) { | ||
| bytes[i] = binaryString.charCodeAt(i); | ||
| } | ||
| return bytes.some(byte => byte !== 0); | ||
| } | ||
|
Contributor
There was a problem hiding this comment. Aren't they simple negation of each other? 🤣
Contributor
There was a problem hiding this comment. It's okay to work on it when we touch it. |
||
|
|
||
| const audioChunks = []; | ||
| let currentVoiceState = 'idle'; | ||
|
|
||
| // Setup Web Chat with Speech-to-Speech | ||
| const { directLine, store } = testHelpers.createDirectLineEmulator(); | ||
| directLine.setCapability('getVoiceConfiguration', { sampleRate: 24000, chunkIntervalMs: 100 }, { emitEvent: false }); | ||
|
|
||
| // Track voiceState changes | ||
| store.subscribe(() => { | ||
| currentVoiceState = store.getState().voice?.voiceState || 'idle'; | ||
| }); | ||
|
|
||
| // Intercept postActivity to capture outgoing voice chunks | ||
| const originalPostActivity = directLine.postActivity.bind(directLine); | ||
| directLine.postActivity = activity => { | ||
| if (activity.name === 'media.chunk' && activity.type === 'event') { | ||
| audioChunks.push({ | ||
| content: activity.value?.content, | ||
| voiceState: currentVoiceState | ||
| }); | ||
| } | ||
| return originalPostActivity(activity); | ||
| }; | ||
|
|
||
| // Component to expose hook functions for testing (inside Composer context) | ||
| let muteControlRef = { setMuted: null, muted: false }; | ||
|
|
||
| const MuteController = () => { | ||
| const [muted, setMuted] = useVoiceRecordingMuted(); | ||
|
|
||
| useEffect(() => { | ||
| muteControlRef.setMuted = setMuted; | ||
| }, [setMuted]); | ||
|
|
||
| // Update muted on every render to capture latest value | ||
| muteControlRef.muted = muted; | ||
|
|
||
| return false; | ||
| }; | ||
|
|
||
| // Helper to get voice state from store | ||
| const getVoiceState = () => store.getState().voice?.voiceState; | ||
|
|
||
| render( | ||
| <FluentThemeProvider variant="fluent"> | ||
| <Composer directLine={directLine} store={store}> | ||
| <BasicWebChat /> | ||
| <MuteController /> | ||
| </Composer> | ||
| </FluentThemeProvider>, | ||
| document.getElementById('webchat') | ||
| ); | ||
|
|
||
| await pageConditions.uiConnected(); | ||
|
|
||
| const micButton = document.querySelector(`[data-testid="${testIds.sendBoxMicrophoneButton}"]`); | ||
| expect(micButton).toBeTruthy(); | ||
|
|
||
| // ===== TEST 1: Muting from idle state should be no-op ===== | ||
| expect(getVoiceState()).toBe('idle'); | ||
| expect(muteControlRef.muted).toBe(false); | ||
|
|
||
| muteControlRef.setMuted(true); | ||
| await new Promise(r => setTimeout(r, 100)); | ||
|
|
||
| expect(getVoiceState()).toBe('idle'); // Still idle, not muted | ||
| expect(muteControlRef.muted).toBe(false); | ||
|
|
||
| // ===== TEST 2: Start recording → listening state ===== | ||
| await host.click(micButton); | ||
|
|
||
| await pageConditions.became( | ||
| 'Voice state is listening', | ||
| () => getVoiceState() === 'listening', | ||
| 2000 | ||
| ); | ||
|
|
||
| // Wait for some listening chunks | ||
| await pageConditions.became( | ||
| 'At least 2 listening chunks received', | ||
| () => audioChunks.filter(c => c.voiceState === 'listening').length >= 2, | ||
| 2000 | ||
| ); | ||
|
|
||
| // ===== TEST 3: Mute from listening state → muted state ===== | ||
| muteControlRef.setMuted(true); | ||
|
|
||
| await pageConditions.became( | ||
| 'Voice state is muted', | ||
| () => getVoiceState() === 'muted', | ||
| 1000 | ||
| ); | ||
|
|
||
| expect(muteControlRef.muted).toBe(true); | ||
|
|
||
| // Wait for muted chunks | ||
| await pageConditions.became( | ||
| 'At least 2 muted chunks received', | ||
| () => audioChunks.filter(c => c.voiceState === 'muted').length >= 2, | ||
| 2000 | ||
| ); | ||
|
|
||
| // ===== TEST 4: Verify muted chunks are all zeros ===== | ||
| const mutedChunks = audioChunks.filter(c => c.voiceState === 'muted'); | ||
| expect(mutedChunks.length).toBeGreaterThanOrEqual(2); | ||
| for (const chunk of mutedChunks) { | ||
| expect(isAudioAllZeros(chunk.content)).toBe(true); | ||
| } | ||
|
|
||
| // ===== TEST 5: Unmute → back to listening state ===== | ||
| muteControlRef.setMuted(false); | ||
|
|
||
| await pageConditions.became( | ||
| 'Voice state is listening after unmute', | ||
| () => getVoiceState() === 'listening', | ||
| 1000 | ||
| ); | ||
|
|
||
| expect(muteControlRef.muted).toBe(false); | ||
|
|
||
| // Wait for more chunks after unmute | ||
| const chunksBeforeCheck = audioChunks.length; | ||
| await pageConditions.became( | ||
| 'New chunks received after unmute', | ||
| () => audioChunks.length > chunksBeforeCheck + 1, | ||
| 2000 | ||
| ); | ||
|
|
||
| // ===== TEST 6: Verify listening chunks contain real (non-zero) audio ===== | ||
| const listeningChunks = audioChunks.filter(c => c.voiceState === 'listening'); | ||
| expect(listeningChunks.length).toBeGreaterThanOrEqual(4); // At least 2 before mute + 2 after unmute | ||
|
|
||
| // Verify listening audio is non-zero (real audio) | ||
| for (const chunk of listeningChunks) { | ||
| expect(hasNonZeroAudio(chunk.content)).toBe(true); | ||
| } | ||
|
|
||
| // ===== TEST 7: Stop recording ===== | ||
| await host.click(micButton); | ||
|
|
||
| await pageConditions.became( | ||
| 'Voice state is idle after stop', | ||
| () => getVoiceState() === 'idle', | ||
| 2000 | ||
| ); | ||
|
|
||
| expect(muteControlRef.muted).toBe(false); | ||
| }); | ||
| </script> | ||
| </body> | ||
| </html> | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,20 @@ | ||
| import { muteVoiceRecording, unmuteVoiceRecording } from 'botframework-webchat-core'; | ||
| import { useCallback } from 'react'; | ||
| import { useDispatch, useSelector } from './internal/WebChatReduxContext'; | ||
|
|
||
| /** | ||
| * Hook to get and set voice recording mute state in speech-to-speech mode. | ||
| */ | ||
| export default function useVoiceRecordingMuted(): readonly [boolean, (muted: boolean) => void] { | ||
| const dispatch = useDispatch(); | ||
| const value = useSelector(({ voice }) => voice.voiceState === 'muted'); | ||
|
|
||
| const setter = useCallback( | ||
| (muted: boolean) => { | ||
| dispatch(muted ? muteVoiceRecording() : unmuteVoiceRecording()); | ||
| }, | ||
| [dispatch] | ||
| ); | ||
|
|
||
| return Object.freeze([value, setter]); | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Changelog entry says mute/unmute was added "via
useRecorderhook", butuseRecorderis an internal/private implementation detail underproviders/SpeechToSpeech/private. For consumers, the new public surface appears to beuseVoiceRecordingMuted(and/or themuteVoiceRecording/unmuteVoiceRecordingactions). Consider rewording this entry to reference the public API to avoid confusing integrators.