feat(practice): run realtime practice on App-Plus through renderjs

App-Plus has no WebRTC or getUserMedia in the logic layer, so realtime
practice was H5-only and the native entry had to advertise a record-then-
transcribe downgrade.

Move the media/WebRTC engine into `realtime-browser-engine.js` and drive it
from `RealtimePracticeAppBridge.vue`, whose renderjs script runs inside the
system WebView where those APIs do exist. The logic layer keeps the
authenticated calls: SDP exchange and `search_knowledge` tool invocation stay
server-proxied, so the access token is never handed to the view layer. Both
sides talk over the renderjs bridge only in session payloads the server
already assembled.

Verified against a real App build (`app-renderjs.js` holds RTCPeerConnection
and getUserMedia; `app-service.js` holds the SDP endpoint, renderjs side has
zero hits). Microphone permission, live transcription, remote playback,
foreground/background switching and disconnect fallback still require Android
and iOS device verification.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-25 23:58:10 +08:00
co-authored by Claude Opus 5
parent 3055d2bec9
commit 5cf7ce5847
10 changed files with 673 additions and 390 deletions
@@ -0,0 +1,220 @@
<template>
<view
class="realtime-app-bridge"
:bridge-command="bridgeCommand"
:change:bridge-command="realtimeBridge.onCommand"
/>
</template>
<script>
import { exchangeRealtimeSdp, invokeRealtimeTool } from '@/services/realtime-practice';
const errorMessage = (error, fallback) =>
error instanceof Error ? error.message : fallback;
export default {
emits: [
'status',
'trainee-transcript',
'customer-transcript',
'audio-playback-blocked',
'terminated',
'error'
],
data() {
return {
bridgeCommand: { id: 0, type: 'idle' },
commandId: 0,
activeSessionId: '',
pendingStart: null,
pendingResume: new Map()
};
},
methods: {
sendCommand(type, payload = {}) {
this.commandId += 1;
this.bridgeCommand = { id: this.commandId, type, ...payload };
},
start(sessionUpdate, sessionId) {
this.pendingStart?.resolve();
this.activeSessionId = sessionId || '';
return new Promise((resolve, reject) => {
this.pendingStart = { resolve, reject };
this.sendCommand('start', { sessionUpdate, sessionId: this.activeSessionId });
});
},
stop() {
this.pendingStart?.resolve();
this.pendingStart = null;
this.pendingResume.forEach((resolve) => resolve(false));
this.pendingResume.clear();
this.activeSessionId = '';
this.sendCommand('stop');
},
resumeAudio() {
const requestId = `resume_${Date.now()}_${this.commandId + 1}`;
return new Promise((resolve) => {
this.pendingResume.set(requestId, resolve);
this.sendCommand('resume-audio', { requestId });
});
},
async answerSdp(event) {
const sessionId = this.activeSessionId;
try {
const answerSdp = await exchangeRealtimeSdp(event.offerSdp, sessionId);
this.sendCommand('request-result', { requestId: event.requestId, value: answerSdp });
} catch (error) {
this.sendCommand('request-error', {
requestId: event.requestId,
message: errorMessage(error, '实时语音连接请求失败')
});
}
},
async answerToolCall(event) {
const sessionId = this.activeSessionId;
try {
const response = await invokeRealtimeTool(
sessionId,
event.callId,
event.name,
event.argsJson
);
this.sendCommand('request-result', { requestId: event.requestId, value: response.output });
} catch (error) {
this.sendCommand('request-error', {
requestId: event.requestId,
message: errorMessage(error, '实时工具调用失败')
});
}
},
onBridgeEvent(event) {
if (!event?.type) return;
if (event.type === 'sdp-offer') {
void this.answerSdp(event);
return;
}
if (event.type === 'tool-call') {
void this.answerToolCall(event);
return;
}
if (event.type === 'ready') {
this.pendingStart?.resolve();
this.pendingStart = null;
return;
}
if (event.type === 'fatal-error') {
this.pendingStart?.reject(new Error(event.message || '实时语音启动失败'));
this.pendingStart = null;
return;
}
if (event.type === 'resume-result') {
this.pendingResume.get(event.requestId)?.(Boolean(event.success));
this.pendingResume.delete(event.requestId);
return;
}
if (event.type === 'status') this.$emit('status', event.status);
if (event.type === 'trainee-transcript') this.$emit('trainee-transcript', event.text);
if (event.type === 'customer-transcript') this.$emit('customer-transcript', event.text);
if (event.type === 'audio-playback-blocked') this.$emit('audio-playback-blocked', Boolean(event.blocked));
if (event.type === 'terminated') this.$emit('terminated');
if (event.type === 'error') this.$emit('error', event.message);
}
}
};
</script>
<script module="realtimeBridge" lang="renderjs">
import { createRealtimeBrowserEngine } from '../../services/realtime-browser-engine.js';
export default {
mounted() {
this.ownerInstance = this.$ownerInstance;
this.pendingRequests = new Map();
this.requestSequence = 0;
this.startGeneration = 0;
},
methods: {
emit(type, payload = {}) {
const owner = this.ownerInstance || this.$ownerInstance;
owner?.callMethod('onBridgeEvent', { type, ...payload });
},
requestLogic(type, payload) {
this.requestSequence += 1;
const requestId = `render_${Date.now()}_${this.requestSequence}`;
return new Promise((resolve, reject) => {
this.pendingRequests.set(requestId, { resolve, reject });
this.emit(type, { requestId, ...payload });
});
},
ensureEngine() {
if (this.engine) return;
this.engine = createRealtimeBrowserEngine({
onStatus: (status) => this.emit('status', { status }),
onTraineeTranscript: (text) => this.emit('trainee-transcript', { text }),
onCustomerTranscript: (text) => this.emit('customer-transcript', { text }),
onAudioPlaybackBlocked: (blocked) => this.emit('audio-playback-blocked', { blocked }),
onToolCall: (callId, name, argsJson) =>
this.requestLogic('tool-call', { callId, name, argsJson }),
onTerminated: () => this.emit('terminated'),
onError: (message) => this.emit('error', { message })
}, (offerSdp, sessionId) =>
this.requestLogic('sdp-offer', { offerSdp, sessionId: sessionId || '' }));
},
settleRequest(command) {
const pending = this.pendingRequests.get(command.requestId);
if (!pending) return;
this.pendingRequests.delete(command.requestId);
if (command.type === 'request-error') {
pending.reject(new Error(command.message || '实时语音请求失败'));
} else {
pending.resolve(command.value);
}
},
cancelRequests() {
this.pendingRequests.forEach(({ reject }) => reject(new Error('实时陪练已结束')));
this.pendingRequests.clear();
},
onCommand(command, previous, ownerInstance) {
if (!command?.id || command.id === previous?.id) return;
this.ownerInstance = ownerInstance || this.ownerInstance || this.$ownerInstance;
if (command.type === 'request-result' || command.type === 'request-error') {
this.settleRequest(command);
return;
}
this.ensureEngine();
if (command.type === 'stop') {
this.startGeneration += 1;
this.cancelRequests();
this.engine.stop();
return;
}
if (command.type === 'resume-audio') {
void this.engine.resumeAudio()
.then((success) => this.emit('resume-result', { requestId: command.requestId, success }))
.catch(() => this.emit('resume-result', { requestId: command.requestId, success: false }));
return;
}
if (command.type !== 'start') return;
const generation = ++this.startGeneration;
void this.engine.start(command.sessionUpdate || {}, command.sessionId || '')
.then(() => {
if (generation === this.startGeneration) this.emit('ready');
})
.catch((error) => {
if (generation !== this.startGeneration) return;
this.emit('fatal-error', {
message: error instanceof Error ? error.message : '实时语音启动失败'
});
});
}
}
};
</script>
<style scoped>
.realtime-app-bridge {
width: 0;
height: 0;
overflow: hidden;
}
</style>
+57 -29
View File
@@ -485,6 +485,18 @@
<button class="secondary-button" @click="openPracticeHistory">查看训练记录</button>
<button class="primary-button tabbar-safe-action" :disabled="!canStartPractice || busy" @click="start(selectedScenarioId)">再练一次</button>
</view>
<!-- #ifdef APP-PLUS -->
<RealtimePracticeAppBridge
ref="realtimeAppBridge"
@status="handleRealtimeStatus"
@trainee-transcript="handleRealtimeTraineeTranscript"
@customer-transcript="handleRealtimeCustomerTranscript"
@audio-playback-blocked="handleRealtimeAudioPlaybackBlocked"
@terminated="handleRealtimeTerminated"
@error="handleRealtimeError"
/>
<!-- #endif -->
</view>
</template>
@@ -492,6 +504,7 @@
import { computed, nextTick, ref } from 'vue';
import { onHide, onShow, onUnload } from '@dcloudio/uni-app';
import ChatComposer from '@/components/chat/ChatComposer.vue';
import RealtimePracticeAppBridge from '@/components/practice/RealtimePracticeAppBridge.vue';
import type {
PracticeFinishResponse,
PracticePrepCard,
@@ -513,7 +526,7 @@ import { searchKnowledge } from '@/services/knowledge';
import { resetPageScroll } from '@/services/navigation';
import { ensureEmployeePosition } from '@/services/position';
import { chooseSpeechAudio, createSpeechPlaybackController, customerVoiceProfile, measureAudioDuration, MENTOR_VOICE_PROFILE, normalizeOssId, transcribeSpeechCapture, transcribeSpeechFile } from '@/services/speech';
import { startSpeechCapture } from '@/services/speech-capture';
import { isNativeAppRuntime, startSpeechCapture } from '@/services/speech-capture';
import type { SpeechCapture, SpeechCaptureSession } from '@/services/speech-capture';
import { createPageRequestScope, currentAccountKey, type RequestScopeTicket } from '@/services/request-scope';
import { createRealtimePracticeController, createRealtimeSession, fetchRealtimePersonas, invokeRealtimeTool, type RealtimePersonaOption } from '@/services/realtime-practice';
@@ -572,6 +585,11 @@ const realtimeAudioBlocked = ref(false);
const realtimeSessionId = ref('');
const realtimePersonaOptions = ref<RealtimePersonaOption[]>([]);
const selectedRealtimePersonaId = ref(typeof storedRealtimePersona === 'string' ? storedRealtimePersona : '');
const realtimeAppBridge = ref<{
start: (sessionUpdate: Record<string, unknown>, sessionId?: string) => Promise<void>;
stop: () => void;
resumeAudio: () => Promise<boolean>;
} | null>(null);
const growthDetailsExpanded = ref(false);
const assignments = ref<PracticeAssignment[]>([]);
const practiceHistory = ref<PracticeRecord[]>([]);
@@ -1010,34 +1028,40 @@ const appendTurn = (role: PracticeRole, text?: string, emotion = 0, synthesizeCu
scrollThreadToBottom();
};
const handleRealtimeStatus = (nextStatus: typeof realtimeStatus.value) => {
realtimeStatus.value = nextStatus;
};
const handleRealtimeTraineeTranscript = (text: string) => {
if (realtimeActive.value) appendTurn('trainee', text);
};
const handleRealtimeCustomerTranscript = (text: string) => {
if (realtimeActive.value) appendTurn('customer', text, 0, false);
};
const handleRealtimeAudioPlaybackBlocked = (blocked: boolean) => {
if (realtimeActive.value) realtimeAudioBlocked.value = blocked;
};
const handleRealtimeTerminated = () => {
if (!realtimeActive.value) return;
realtimeActive.value = false;
realtimeStatus.value = 'idle';
realtimeAudioBlocked.value = false;
realtimeSessionId.value = '';
sessionId.value = '';
activeAssignmentId.value = undefined;
status.value = 'idle';
};
const handleRealtimeError = (text: string) => {
if (realtimeActive.value) message.value = text;
};
const realtimePractice = createRealtimePracticeController({
onStatus: (nextStatus) => {
realtimeStatus.value = nextStatus;
},
onTraineeTranscript: (text) => {
if (realtimeActive.value) appendTurn('trainee', text);
},
onCustomerTranscript: (text) => {
if (realtimeActive.value) appendTurn('customer', text, 0, false);
},
onAudioPlaybackBlocked: (blocked) => {
if (realtimeActive.value) realtimeAudioBlocked.value = blocked;
},
onStatus: handleRealtimeStatus,
onTraineeTranscript: handleRealtimeTraineeTranscript,
onCustomerTranscript: handleRealtimeCustomerTranscript,
onAudioPlaybackBlocked: handleRealtimeAudioPlaybackBlocked,
onToolCall: (callId, name, argsJson) =>
invokeRealtimeTool(realtimeSessionId.value, callId, name, argsJson).then((res) => res.output),
onTerminated: () => {
if (!realtimeActive.value) return;
realtimeActive.value = false;
realtimeStatus.value = 'idle';
realtimeAudioBlocked.value = false;
realtimeSessionId.value = '';
sessionId.value = '';
activeAssignmentId.value = undefined;
status.value = 'idle';
},
onError: (text) => {
if (realtimeActive.value) message.value = text;
}
onTerminated: handleRealtimeTerminated,
onError: handleRealtimeError
});
const selectRealtimePersona = (item: RealtimePersonaOption) => {
@@ -1062,7 +1086,8 @@ const loadRealtimePersonas = async (request: RequestScopeTicket = requests.begin
const stopRealtime = () => {
if (!realtimeActive.value && realtimeStatus.value === 'idle') return;
realtimePractice.stop();
if (isNativeAppRuntime()) realtimeAppBridge.value?.stop();
else realtimePractice.stop();
realtimeActive.value = false;
realtimeStatus.value = 'idle';
realtimeAudioBlocked.value = false;
@@ -1093,7 +1118,9 @@ const startRealtime = async () => {
if (!realtimeActive.value) return;
realtimeSessionId.value = session.sessionId;
activeScenarioName.value = session.personaName || '实时陪练';
await realtimePractice.start(session.sessionUpdate, session.sessionId);
const controller = isNativeAppRuntime() ? realtimeAppBridge.value : realtimePractice;
if (!controller) throw new Error('实时语音模块尚未就绪,请稍后重试');
await controller.start(session.sessionUpdate, session.sessionId);
if (!realtimeActive.value) return;
status.value = 'active';
message.value = `已连接「${session.personaName}」,请直接开口说话。`;
@@ -1107,7 +1134,8 @@ const startRealtime = async () => {
};
const resumeRealtimeAudio = async () => {
if (await realtimePractice.resumeAudio()) {
const controller = isNativeAppRuntime() ? realtimeAppBridge.value : realtimePractice;
if (controller && await controller.resumeAudio()) {
message.value = '已恢复实时语音播放。';
} else {
message.value = '仍无法播放实时语音,请确认设备媒体权限后重试。';
+30
View File
@@ -0,0 +1,30 @@
export type RealtimeBrowserStatus =
| 'idle'
| 'connecting'
| 'connected'
| 'listening'
| 'speaking'
| 'calling-tool';
export interface RealtimeBrowserCallbacks {
onStatus: (status: RealtimeBrowserStatus) => void;
onTraineeTranscript: (text: string) => void;
onCustomerTranscript: (text: string) => void;
onAudioPlaybackBlocked: (blocked: boolean) => void;
onToolCall: (callId: string, name: string, argsJson: string) => Promise<string>;
onTerminated: () => void;
onError: (message: string) => void;
}
export interface RealtimeBrowserEngine {
start: (sessionUpdate: Record<string, unknown>, sessionId?: string) => Promise<void>;
stop: () => void;
resumeAudio: () => Promise<boolean>;
}
export const isRealtimeBrowserSupported: () => boolean;
export const createRealtimeBrowserEngine: (
callbacks: RealtimeBrowserCallbacks,
exchangeSdp: (offerSdp: string, sessionId?: string) => Promise<string>
) => RealtimeBrowserEngine;
@@ -0,0 +1,302 @@
const trimTranscript = (value) => (value || '').trim();
const normalizeSdp = (sdp) => `${sdp.replace(/\r\n|\r|\n/g, '\r\n').replace(/\r\n$/, '')}\r\n`;
const TOOL_CALL_FALLBACK_OUTPUT = '工具暂时不可用,请直接回应员工';
export const isRealtimeBrowserSupported = () =>
typeof navigator !== 'undefined'
&& Boolean(navigator.mediaDevices?.getUserMedia)
&& typeof RTCPeerConnection !== 'undefined';
const waitForIceComplete = (connection) =>
new Promise((resolve) => {
if (connection.iceGatheringState === 'complete') {
resolve();
return;
}
const previous = connection.onicegatheringstatechange;
let timeout;
const done = () => {
clearTimeout(timeout);
connection.onicegatheringstatechange = previous;
resolve();
};
timeout = setTimeout(done, 3000);
connection.onicegatheringstatechange = () => {
previous?.call(connection, new Event('icegatheringstatechange'));
if (connection.iceGatheringState === 'complete') done();
};
});
export const createRealtimeBrowserEngine = (callbacks, exchangeSdp) => {
let activeAttempt = 0;
let connection = null;
let microphone = null;
let speaker = null;
let controlChannel = null;
let cancelSessionWait = null;
let sessionWaitAttempt = null;
let toolCallChain = Promise.resolve();
const isCurrent = (attempt) => activeAttempt === attempt;
const releaseResources = () => {
controlChannel?.close();
controlChannel = null;
microphone?.getTracks().forEach((track) => track.stop());
microphone = null;
if (speaker) {
speaker.pause();
speaker.srcObject = null;
speaker = null;
}
connection?.close();
connection = null;
};
const sendSessionUpdate = (channel, sessionUpdate) => {
if (channel.readyState !== 'open') return;
channel.send(JSON.stringify({ event_id: `event_${Date.now()}`, ...sessionUpdate }));
};
const handleToolCall = (attempt, event) => {
const callId = trimTranscript(event.call_id);
const name = trimTranscript(event.name);
if (!callId || !name) return;
const argsJson = typeof event.arguments === 'string' ? event.arguments : '{}';
toolCallChain = toolCallChain.then(async () => {
if (!isCurrent(attempt)) return;
const channel = controlChannel;
if (!channel || channel.readyState !== 'open') return;
callbacks.onStatus('calling-tool');
let output;
try {
output = await callbacks.onToolCall(callId, name, argsJson);
} catch {
output = TOOL_CALL_FALLBACK_OUTPUT;
}
if (!isCurrent(attempt) || channel.readyState !== 'open') return;
channel.send(JSON.stringify({
event_id: `event_${Date.now()}`,
type: 'conversation.item.create',
item: { type: 'function_call_output', call_id: callId, output }
}));
channel.send(JSON.stringify({ event_id: `event_${Date.now()}`, type: 'response.create' }));
callbacks.onStatus('connected');
}).catch(() => {
// 链内任何意外抛错不得毒化后续工具调用;本次调用软失败,对话继续
});
};
const handleEvent = (raw, attempt, provider) => {
if (!isCurrent(attempt)) return;
let event;
try {
event = JSON.parse(raw);
} catch {
return;
}
if (event.type === 'session.created') provider.onSessionCreated();
if (event.type === 'session.updated') provider.onSessionUpdated();
if (event.type === 'input_audio_buffer.speech_started') callbacks.onStatus('listening');
if (event.type === 'response.created') callbacks.onStatus('speaking');
if (event.type === 'response.done') callbacks.onStatus('connected');
if (event.type === 'conversation.item.input_audio_transcription.completed') {
const transcript = trimTranscript(event.transcript);
if (transcript) callbacks.onTraineeTranscript(transcript);
}
if (event.type === 'response.audio_transcript.done') {
const transcript = trimTranscript(event.transcript);
if (transcript) callbacks.onCustomerTranscript(transcript);
}
if (event.type === 'response.function_call_arguments.done') {
handleToolCall(attempt, event);
}
if (event.type === 'error') {
const error = new Error(event.error?.message || '实时陪练连接异常,请改用录音对练');
callbacks.onError(error.message);
provider.onSessionError(error);
}
};
const bindChannel = (channel, attempt, provider) => {
channel.onmessage = (event) => handleEvent(String(event.data || ''), attempt, provider);
channel.onerror = () => {
if (!isCurrent(attempt)) return;
const error = new Error('实时陪练数据通道异常,请改用录音对练');
callbacks.onError(error.message);
provider.onSessionError(error);
};
};
const stop = () => {
activeAttempt += 1;
cancelSessionWait?.();
cancelSessionWait = null;
sessionWaitAttempt = null;
toolCallChain = Promise.resolve();
releaseResources();
callbacks.onAudioPlaybackBlocked(false);
callbacks.onStatus('idle');
};
const terminate = (attempt, message) => {
if (!isCurrent(attempt)) return;
callbacks.onError(message);
stop();
callbacks.onTerminated();
};
const resumeAudio = async () => {
if (!speaker) return false;
try {
await speaker.play();
callbacks.onAudioPlaybackBlocked(false);
return true;
} catch {
callbacks.onAudioPlaybackBlocked(true);
return false;
}
};
const start = async (sessionUpdate, sessionId) => {
if (!isRealtimeBrowserSupported()) throw new Error('当前设备的 WebView 不支持实时语音,请更新系统 WebView 后重试');
stop();
const attempt = ++activeAttempt;
callbacks.onStatus('connecting');
let localMicrophone = null;
let localConnection = null;
let localChannel = null;
let localSpeaker = null;
let readyTimeout;
let disconnectTimeout;
let sessionUpdateSent = false;
let resolveReady;
let rejectReady;
let sessionReady = null;
const releaseLocalResources = () => {
if (disconnectTimeout) clearTimeout(disconnectTimeout);
localChannel?.close();
localMicrophone?.getTracks().forEach((track) => track.stop());
if (localSpeaker) {
localSpeaker.pause();
localSpeaker.srcObject = null;
}
localConnection?.close();
};
const ensureCurrent = () => {
if (isCurrent(attempt)) return true;
releaseLocalResources();
return false;
};
try {
localMicrophone = await navigator.mediaDevices.getUserMedia({ audio: true });
if (!ensureCurrent()) return;
microphone = localMicrophone;
localConnection = new RTCPeerConnection({ iceServers: [] });
connection = localConnection;
const audioSender = localConnection.addTransceiver('audio', { direction: 'sendrecv' }).sender;
const provider = {
onSessionCreated: () => {
if (!isCurrent(attempt) || !localChannel || sessionUpdateSent) return;
sessionUpdateSent = true;
sendSessionUpdate(localChannel, sessionUpdate);
},
onSessionUpdated: () => {
if (!isCurrent(attempt) || !sessionUpdateSent) return;
const track = localMicrophone?.getAudioTracks()[0] || null;
void audioSender.replaceTrack(track)
.then(() => {
if (isCurrent(attempt)) resolveReady?.();
})
.catch((error) => rejectReady?.(error instanceof Error ? error : new Error('实时陪练麦克风启动失败')));
},
onSessionError: (error) => {
rejectReady?.(error);
terminate(attempt, error.message);
}
};
localChannel = localConnection.createDataChannel('oai-events');
controlChannel = localChannel;
bindChannel(localChannel, attempt, provider);
localConnection.ondatachannel = (event) => bindChannel(event.channel, attempt, provider);
localConnection.ontrack = (event) => {
if (!isCurrent(attempt)) return;
const stream = event.streams[0] || new MediaStream([event.track]);
localSpeaker = new Audio();
speaker = localSpeaker;
localSpeaker.autoplay = true;
localSpeaker.setAttribute('playsinline', 'true');
localSpeaker.srcObject = stream;
void localSpeaker.play()
.then(() => {
if (isCurrent(attempt)) callbacks.onAudioPlaybackBlocked(false);
})
.catch(() => {
if (isCurrent(attempt)) callbacks.onAudioPlaybackBlocked(true);
});
};
localConnection.onconnectionstatechange = () => {
if (!isCurrent(attempt)) return;
if (localConnection?.connectionState === 'failed' || localConnection?.connectionState === 'closed') {
terminate(attempt, '实时陪练已断开,请改用录音对练');
return;
}
if (localConnection?.connectionState === 'disconnected') {
disconnectTimeout ??= setTimeout(() => {
if (localConnection?.connectionState === 'disconnected') {
terminate(attempt, '实时陪练已断开,请改用录音对练');
}
}, 3000);
} else if (disconnectTimeout) {
clearTimeout(disconnectTimeout);
disconnectTimeout = undefined;
}
};
const offer = await localConnection.createOffer();
if (!ensureCurrent()) return;
await localConnection.setLocalDescription(offer);
if (!ensureCurrent()) return;
await waitForIceComplete(localConnection);
if (!ensureCurrent()) return;
const offerSdp = localConnection.localDescription?.sdp;
if (!offerSdp) throw new Error('实时陪练连接请求创建失败');
const answerSdp = await exchangeSdp(normalizeSdp(offerSdp), sessionId);
if (!ensureCurrent()) return;
sessionReady = new Promise((resolve, reject) => {
resolveReady = resolve;
rejectReady = reject;
readyTimeout = setTimeout(() => reject(new Error('实时陪练会话初始化超时,请使用录音对练')), 15000);
});
void sessionReady.catch(() => undefined);
sessionWaitAttempt = attempt;
cancelSessionWait = () => {
if (readyTimeout) clearTimeout(readyTimeout);
rejectReady?.(new Error('实时陪练已结束'));
};
await localConnection.setRemoteDescription({ type: 'answer', sdp: normalizeSdp(answerSdp) });
if (!ensureCurrent()) return;
await sessionReady;
if (!ensureCurrent()) return;
callbacks.onStatus('connected');
} catch (error) {
if (!isCurrent(attempt)) {
releaseLocalResources();
return;
}
stop();
throw error instanceof Error ? error : new Error('实时陪练连接失败,请改用录音对练');
} finally {
if (readyTimeout) clearTimeout(readyTimeout);
if (sessionWaitAttempt === attempt) {
sessionWaitAttempt = null;
cancelSessionWait = null;
}
}
};
return { start, stop, resumeAudio };
};
+28 -338
View File
@@ -1,7 +1,11 @@
import { apiRequest } from './api';
import { isNativeAppRuntime } from './speech-capture';
type RealtimeStatus = 'idle' | 'connecting' | 'connected' | 'listening' | 'speaking' | 'calling-tool';
import { createRealtimeBrowserEngine } from './realtime-browser-engine.js';
import type {
RealtimeBrowserCallbacks,
RealtimeBrowserEngine,
RealtimeBrowserStatus
} from './realtime-browser-engine.js';
export interface RealtimePersonaOption {
id: string;
@@ -28,36 +32,11 @@ interface RealtimeSdpResponse {
model: string;
}
interface RealtimeEvent {
type?: string;
transcript?: string;
call_id?: string;
name?: string;
arguments?: string;
error?: { message?: string };
export interface RealtimePracticeCallbacks extends RealtimeBrowserCallbacks {
onStatus: (status: RealtimeBrowserStatus) => void;
}
interface ProviderEventHandlers {
onSessionCreated: () => void;
onSessionUpdated: () => void;
onSessionError: (error: Error) => void;
}
export interface RealtimePracticeCallbacks {
onStatus: (status: RealtimeStatus) => void;
onTraineeTranscript: (text: string) => void;
onCustomerTranscript: (text: string) => void;
onAudioPlaybackBlocked: (blocked: boolean) => void;
onToolCall: (callId: string, name: string, argsJson: string) => Promise<string>;
onTerminated: () => void;
onError: (message: string) => void;
}
export interface RealtimePracticeController {
start: (sessionUpdate: Record<string, unknown>, sessionId?: string) => Promise<void>;
stop: () => void;
resumeAudio: () => Promise<boolean>;
}
export interface RealtimePracticeController extends RealtimeBrowserEngine {}
export const fetchRealtimePersonas = () =>
apiRequest<RealtimePersonaOption[]>({
@@ -82,316 +61,27 @@ export const invokeRealtimeTool = (sessionId: string, callId: string, name: stri
timeout: 20000
});
const isSupported = () =>
!isNativeAppRuntime()
&& typeof navigator !== 'undefined'
&& Boolean(navigator.mediaDevices?.getUserMedia)
&& typeof RTCPeerConnection !== 'undefined';
const waitForIceComplete = (connection: RTCPeerConnection) =>
new Promise<void>((resolve) => {
if (connection.iceGatheringState === 'complete') {
resolve();
return;
}
const previous = connection.onicegatheringstatechange;
let timeout: ReturnType<typeof setTimeout>;
const done = () => {
clearTimeout(timeout);
connection.onicegatheringstatechange = previous;
resolve();
};
timeout = setTimeout(done, 3000);
connection.onicegatheringstatechange = () => {
previous?.call(connection, new Event('icegatheringstatechange'));
if (connection.iceGatheringState === 'complete') done();
};
export const exchangeRealtimeSdp = async (offerSdp: string, sessionId?: string) => {
const response = await apiRequest<RealtimeSdpResponse>({
url: '/api/train/practice/realtime/sdp',
method: 'POST',
data: { offerSdp, sessionId: sessionId || null },
timeout: 30000
});
const normalizeSdp = (sdp: string) => `${sdp.replace(/\r\n|\r|\n/g, '\r\n').replace(/\r\n$/, '')}\r\n`;
const trimTranscript = (value?: string) => (value || '').trim();
const TOOL_CALL_FALLBACK_OUTPUT = '工具暂时不可用,请直接回应员工';
export const createRealtimePracticeController = (callbacks: RealtimePracticeCallbacks): RealtimePracticeController => {
let activeAttempt = 0;
let connection: RTCPeerConnection | null = null;
let microphone: MediaStream | null = null;
let speaker: HTMLAudioElement | null = null;
let controlChannel: RTCDataChannel | null = null;
let cancelSessionWait: (() => void) | null = null;
let sessionWaitAttempt: number | null = null;
let toolCallChain: Promise<void> = Promise.resolve();
const isCurrent = (attempt: number) => activeAttempt === attempt;
const releaseResources = () => {
controlChannel?.close();
controlChannel = null;
microphone?.getTracks().forEach((track) => track.stop());
microphone = null;
if (speaker) {
speaker.pause();
speaker.srcObject = null;
speaker = null;
}
connection?.close();
connection = null;
};
// 服务端下发的 session.update 载荷原样转发,仅补 event_id
const sendSessionUpdate = (channel: RTCDataChannel, sessionUpdate: Record<string, unknown>) => {
if (channel.readyState !== 'open') return;
channel.send(JSON.stringify({ event_id: `event_${Date.now()}`, ...sessionUpdate }));
};
const handleToolCall = (attempt: number, event: RealtimeEvent) => {
const callId = trimTranscript(event.call_id);
const name = trimTranscript(event.name);
if (!callId || !name) return;
const argsJson = typeof event.arguments === 'string' ? event.arguments : '{}';
// 多次工具调用串行化,避免打断竞态下回传交错
toolCallChain = toolCallChain.then(async () => {
if (!isCurrent(attempt)) return;
const channel = controlChannel;
if (!channel || channel.readyState !== 'open') return;
callbacks.onStatus('calling-tool');
let output: string;
try {
output = await callbacks.onToolCall(callId, name, argsJson);
} catch {
output = TOOL_CALL_FALLBACK_OUTPUT;
}
if (!isCurrent(attempt) || channel.readyState !== 'open') return;
channel.send(JSON.stringify({
event_id: `event_${Date.now()}`,
type: 'conversation.item.create',
item: { type: 'function_call_output', call_id: callId, output }
}));
channel.send(JSON.stringify({ event_id: `event_${Date.now()}`, type: 'response.create' }));
callbacks.onStatus('connected');
}).catch(() => {
// 链内任何意外抛错不得毒化后续工具调用;本次调用软失败,对话继续
});
};
const handleEvent = (raw: string, attempt: number, provider: ProviderEventHandlers) => {
if (!isCurrent(attempt)) return;
let event: RealtimeEvent;
try {
event = JSON.parse(raw) as RealtimeEvent;
} catch {
return;
}
if (event.type === 'session.created') provider.onSessionCreated();
if (event.type === 'session.updated') provider.onSessionUpdated();
if (event.type === 'input_audio_buffer.speech_started') callbacks.onStatus('listening');
if (event.type === 'response.created') callbacks.onStatus('speaking');
if (event.type === 'response.done') callbacks.onStatus('connected');
if (event.type === 'conversation.item.input_audio_transcription.completed') {
const transcript = trimTranscript(event.transcript);
if (transcript) callbacks.onTraineeTranscript(transcript);
}
if (event.type === 'response.audio_transcript.done') {
const transcript = trimTranscript(event.transcript);
if (transcript) callbacks.onCustomerTranscript(transcript);
}
if (event.type === 'response.function_call_arguments.done') {
handleToolCall(attempt, event);
}
if (event.type === 'error') {
const error = new Error(event.error?.message || '实时陪练连接异常,请改用录音对练');
callbacks.onError(error.message);
provider.onSessionError(error);
}
};
const bindChannel = (channel: RTCDataChannel, attempt: number, provider: ProviderEventHandlers) => {
channel.onmessage = (event) => handleEvent(String(event.data || ''), attempt, provider);
channel.onerror = () => {
if (!isCurrent(attempt)) return;
const error = new Error('实时陪练数据通道异常,请改用录音对练');
callbacks.onError(error.message);
provider.onSessionError(error);
};
};
const stop = () => {
activeAttempt += 1;
cancelSessionWait?.();
cancelSessionWait = null;
sessionWaitAttempt = null;
toolCallChain = Promise.resolve();
releaseResources();
callbacks.onAudioPlaybackBlocked(false);
callbacks.onStatus('idle');
};
const terminate = (attempt: number, message: string) => {
if (!isCurrent(attempt)) return;
callbacks.onError(message);
stop();
callbacks.onTerminated();
};
const resumeAudio = async () => {
if (!speaker) return false;
try {
await speaker.play();
callbacks.onAudioPlaybackBlocked(false);
return true;
} catch {
callbacks.onAudioPlaybackBlocked(true);
return false;
}
};
const start = async (sessionUpdate: Record<string, unknown>, sessionId?: string) => {
if (!isSupported()) throw new Error('当前设备不支持实时语音,请使用录音对练');
stop();
const attempt = ++activeAttempt;
callbacks.onStatus('connecting');
let localMicrophone: MediaStream | null = null;
let localConnection: RTCPeerConnection | null = null;
let localChannel: RTCDataChannel | null = null;
let localSpeaker: HTMLAudioElement | null = null;
let readyTimeout: ReturnType<typeof setTimeout> | undefined;
let disconnectTimeout: ReturnType<typeof setTimeout> | undefined;
let sessionUpdateSent = false;
let resolveReady: (() => void) | undefined;
let rejectReady: ((error: Error) => void) | undefined;
let sessionReady: Promise<void> | null = null;
const releaseLocalResources = () => {
if (disconnectTimeout) clearTimeout(disconnectTimeout);
localChannel?.close();
localMicrophone?.getTracks().forEach((track) => track.stop());
if (localSpeaker) {
localSpeaker.pause();
localSpeaker.srcObject = null;
return response.answerSdp;
};
export const createRealtimePracticeController = (
callbacks: RealtimePracticeCallbacks
): RealtimePracticeController => {
const engine = createRealtimeBrowserEngine(callbacks, exchangeRealtimeSdp);
return {
...engine,
start: async (sessionUpdate, sessionId) => {
if (isNativeAppRuntime()) {
throw new Error('APP 实时语音应由 WebView 桥接启动');
}
localConnection?.close();
};
const ensureCurrent = () => {
if (isCurrent(attempt)) return true;
releaseLocalResources();
return false;
};
try {
localMicrophone = await navigator.mediaDevices.getUserMedia({ audio: true });
if (!ensureCurrent()) return;
microphone = localMicrophone;
localConnection = new RTCPeerConnection({ iceServers: [] });
connection = localConnection;
const audioSender = localConnection.addTransceiver('audio', { direction: 'sendrecv' }).sender;
const provider: ProviderEventHandlers = {
onSessionCreated: () => {
if (!isCurrent(attempt) || !localChannel || sessionUpdateSent) return;
sessionUpdateSent = true;
sendSessionUpdate(localChannel, sessionUpdate);
},
onSessionUpdated: () => {
if (!isCurrent(attempt) || !sessionUpdateSent) return;
const track = localMicrophone?.getAudioTracks()[0] || null;
void audioSender.replaceTrack(track)
.then(() => {
if (isCurrent(attempt)) resolveReady?.();
})
.catch((error: unknown) => rejectReady?.(error instanceof Error ? error : new Error('实时陪练麦克风启动失败')));
},
onSessionError: (error) => {
rejectReady?.(error);
terminate(attempt, error.message);
}
};
localChannel = localConnection.createDataChannel('oai-events');
controlChannel = localChannel;
bindChannel(localChannel, attempt, provider);
localConnection.ondatachannel = (event) => bindChannel(event.channel, attempt, provider);
localConnection.ontrack = (event) => {
if (!isCurrent(attempt)) return;
const stream = event.streams[0] || new MediaStream([event.track]);
localSpeaker = new Audio();
speaker = localSpeaker;
localSpeaker.autoplay = true;
localSpeaker.setAttribute('playsinline', 'true');
localSpeaker.srcObject = stream;
void localSpeaker.play()
.then(() => {
if (isCurrent(attempt)) callbacks.onAudioPlaybackBlocked(false);
})
.catch(() => {
if (isCurrent(attempt)) callbacks.onAudioPlaybackBlocked(true);
});
};
localConnection.onconnectionstatechange = () => {
if (!isCurrent(attempt)) return;
if (localConnection?.connectionState === 'failed' || localConnection?.connectionState === 'closed') {
terminate(attempt, '实时陪练已断开,请改用录音对练');
return;
}
if (localConnection?.connectionState === 'disconnected') {
disconnectTimeout ??= setTimeout(() => {
if (localConnection?.connectionState === 'disconnected') {
terminate(attempt, '实时陪练已断开,请改用录音对练');
}
}, 3000);
} else if (disconnectTimeout) {
clearTimeout(disconnectTimeout);
disconnectTimeout = undefined;
}
};
const offer = await localConnection.createOffer();
if (!ensureCurrent()) return;
await localConnection.setLocalDescription(offer);
if (!ensureCurrent()) return;
await waitForIceComplete(localConnection);
if (!ensureCurrent()) return;
const offerSdp = localConnection.localDescription?.sdp;
if (!offerSdp) throw new Error('实时陪练连接请求创建失败');
const response = await apiRequest<RealtimeSdpResponse>({
url: '/api/train/practice/realtime/sdp',
method: 'POST',
data: { offerSdp: normalizeSdp(offerSdp), sessionId: sessionId || null },
timeout: 30000
});
if (!ensureCurrent()) return;
sessionReady = new Promise<void>((resolve, reject) => {
resolveReady = resolve;
rejectReady = reject;
readyTimeout = setTimeout(() => reject(new Error('实时陪练会话初始化超时,请使用录音对练')), 15000);
});
void sessionReady.catch(() => undefined);
sessionWaitAttempt = attempt;
cancelSessionWait = () => {
if (readyTimeout) clearTimeout(readyTimeout);
rejectReady?.(new Error('实时陪练已结束'));
};
await localConnection.setRemoteDescription({ type: 'answer', sdp: normalizeSdp(response.answerSdp) });
if (!ensureCurrent()) return;
const waitForSessionReady = sessionReady;
if (!waitForSessionReady) throw new Error('实时陪练会话初始化失败');
await waitForSessionReady;
if (!ensureCurrent()) return;
callbacks.onStatus('connected');
} catch (error) {
if (!isCurrent(attempt)) {
releaseLocalResources();
return;
}
stop();
throw error instanceof Error ? error : new Error('实时陪练连接失败,请改用录音对练');
} finally {
if (readyTimeout) clearTimeout(readyTimeout);
if (sessionWaitAttempt === attempt) {
sessionWaitAttempt = null;
cancelSessionWait = null;
}
await engine.start(sessionUpdate, sessionId);
}
};
return { start, stop, resumeAudio };
};
+32 -19
View File
@@ -5,39 +5,52 @@ import test from 'node:test';
const source = (path) => readFile(new URL(path, import.meta.url), 'utf8');
test('实时陪练通过受认证代理接入,前端不携带供应商密钥、不自组会话配置', async () => {
const [service, page, backendService, backendSessionService, backendPersonaRegistry] = await Promise.all([
const [service, engine, appBridge, page, backendService, backendSessionService, backendPersonaRegistry] = await Promise.all([
source('../src/services/realtime-practice.ts'),
source('../src/services/realtime-browser-engine.js'),
source('../src/components/practice/RealtimePracticeAppBridge.vue'),
source('../src/pages/user/practice/index.vue'),
source('../../backend/ruoyi-modules/ruoyi-aihr/src/main/java/org/dromara/aihr/service/AihrRealtimePracticeService.java'),
source('../../backend/ruoyi-modules/ruoyi-aihr/src/main/java/org/dromara/aihr/service/AihrRealtimeSessionService.java'),
source('../../backend/ruoyi-modules/ruoyi-aihr/src/main/java/org/dromara/aihr/service/AihrRealtimePersonaRegistry.java')
]);
const transport = `${service}\n${engine}`;
// 传输与事件协议
assert.match(service, /\/api\/train\/practice\/realtime\/sdp/);
assert.match(service, /conversation\.item\.input_audio_transcription\.completed/);
assert.match(service, /response\.audio_transcript\.done/);
assert.match(service, /session\.created/);
assert.match(service, /session\.updated/);
assert.match(service, /activeAttempt/);
assert.match(service, /resumeAudio/);
assert.match(transport, /conversation\.item\.input_audio_transcription\.completed/);
assert.match(transport, /response\.audio_transcript\.done/);
assert.match(transport, /session\.created/);
assert.match(transport, /session\.updated/);
assert.match(transport, /activeAttempt/);
assert.match(transport, /resumeAudio/);
// 方案B 架构:session.update 由服务端组装,浏览器只原样转发;instructions/音色不下放前端
assert.match(service, /\/api\/train\/practice\/realtime\/session/);
assert.match(service, /sendSessionUpdate/);
assert.doesNotMatch(service, /instructions/);
assert.doesNotMatch(service, /REALTIME_PRACTICE_VOICES|createRealtimePracticeSessionUpdate|normalizeRealtimePracticeVoice/);
assert.doesNotMatch(service, /semantic_vad/);
assert.doesNotMatch(service, /DASHSCOPE_API_KEY|Authorization:\s*Bearer/);
assert.match(transport, /sendSessionUpdate/);
assert.doesNotMatch(transport, /instructions/);
assert.doesNotMatch(transport, /REALTIME_PRACTICE_VOICES|createRealtimePracticeSessionUpdate|normalizeRealtimePracticeVoice/);
assert.doesNotMatch(transport, /semantic_vad/);
assert.doesNotMatch(transport, /DASHSCOPE_API_KEY|Authorization:\s*Bearer/);
// function calling 工具桥:事件分支、串行链、软着陆兜底、回传协议
assert.match(service, /\/api\/train\/practice\/realtime\/tools\/invoke/);
assert.match(service, /response\.function_call_arguments\.done/);
assert.match(service, /function_call_output/);
assert.match(service, /response\.create/);
assert.match(service, /toolCallChain/);
assert.match(service, /工具暂时不可用,请直接回应员工/);
assert.match(service, /calling-tool/);
assert.match(transport, /response\.function_call_arguments\.done/);
assert.match(transport, /function_call_output/);
assert.match(transport, /response\.create/);
assert.match(transport, /toolCallChain/);
assert.match(transport, /工具暂时不可用,请直接回应员工/);
assert.match(transport, /calling-tool/);
// App-Plus:WebRTC 在 renderjs/WebView 执行,鉴权 SDP 与工具调用回到逻辑层。
assert.match(appBridge, /lang="renderjs"/);
assert.match(appBridge, /createRealtimeBrowserEngine/);
assert.match(appBridge, /exchangeRealtimeSdp/);
assert.match(appBridge, /invokeRealtimeTool/);
assert.match(appBridge, /owner.*callMethod\('onBridgeEvent'/);
assert.match(page, /RealtimePracticeAppBridge/);
assert.match(page, /isNativeAppRuntime\(\) \? realtimeAppBridge\.value : realtimePractice/);
assert.doesNotMatch(transport, /!isNativeAppRuntime\(\)/);
// 服务端是会话配置的唯一组装点
assert.match(backendSessionService, /session\.update/);
@@ -65,7 +78,7 @@ test('实时陪练通过受认证代理接入,前端不携带供应商密钥
});
test('工具调用串行化与竞态防护:链式执行、attempt 双检、stop 重置', async () => {
const service = await source('../src/services/realtime-practice.ts');
const service = await source('../src/services/realtime-browser-engine.js');
// 串行链必须基于上一次调用收尾,且带末端 catch 防毒化
assert.match(service, /toolCallChain = toolCallChain\.then/);