959 lines
37 KiB
JavaScript
959 lines
37 KiB
JavaScript
// Voice Assistant — LiveKit client
|
||
const { Room, RoomEvent } = LivekitClient;
|
||
|
||
// ── Config ──────────────────────────────────────────────────────────────────
|
||
// LiveKit is reached through the same origin as the page (nginx proxies
|
||
// /livekit -> localhost:7880). Keeps a single HTTPS port and avoids mixed
|
||
// content when the UI is served over HTTPS.
|
||
const LIVEKIT_URL = `${window.location.protocol === "https:" ? "wss" : "ws"}://${window.location.host}/livekit`;
|
||
const ROOM_NAME = "voice-room";
|
||
const AGENT_NAME = "voice-assistant";
|
||
|
||
const VOICES = [
|
||
{ id: "en-US-Ava:DragonHDOmniLatestNeural", name: "Ava", tag: "Dragon HD Omni" },
|
||
{ id: "en-US-JennyNeural", name: "Jenny" },
|
||
{ id: "en-US-GuyNeural", name: "Guy" },
|
||
{ id: "en-US-AndrewNeural", name: "Andrew" },
|
||
{ id: "en-US-AriaNeural", name: "Aria" },
|
||
{ id: "en-US-EmmaNeural", name: "Emma" },
|
||
{ id: "en-US-EricNeural", name: "Eric" },
|
||
{ id: "en-US-BrianNeural", name: "Brian" },
|
||
{ id: "en-US-AshleyNeural", name: "Ashley" },
|
||
{ id: "en-US-RichardNeural", name: "Richard" },
|
||
{ id: "en-US-TinaNeural", name: "Tina" },
|
||
{ id: "en-US-SteffanNeural", name: "Steffan" },
|
||
];
|
||
|
||
const HISTORY_KEY = "voice_history";
|
||
const HISTORY_MAX = 50;
|
||
const MODE_KEY = "hope_conversation_mode";
|
||
|
||
// ── State ───────────────────────────────────────────────────────────────────
|
||
let room = null;
|
||
let agentParticipant = null;
|
||
let agentReady = false;
|
||
let uiState = "idle"; // idle | connecting | listening | thinking | speaking
|
||
let micLevel = 0; // 0..1, smoothed
|
||
let agentAudioLevel = 0; // 0..1, smoothed
|
||
let userSpeaking = false; // local VAD-ish flag from mic level
|
||
let wakeLock = null;
|
||
let conversationMode = localStorage.getItem(MODE_KEY) === "text" ? "text" : "voice";
|
||
let connectionPromise = null;
|
||
|
||
function escapeHtml(s) {
|
||
const d = document.createElement("div");
|
||
d.textContent = s || "";
|
||
return d.innerHTML;
|
||
}
|
||
|
||
// ── DOM ─────────────────────────────────────────────────────────────────────
|
||
const startBtn = document.getElementById("startBtn");
|
||
const stopBtn = document.getElementById("stopBtn");
|
||
const muteBtn = document.getElementById("muteBtn");
|
||
let micMuted = false;
|
||
const statusEl = document.getElementById("status");
|
||
const messagesEl = document.getElementById("messages");
|
||
const orbEl = document.getElementById("orb");
|
||
const stateLabelEl = document.getElementById("stateLabel");
|
||
const thinkingChipEl = document.getElementById("thinkingChip");
|
||
const bargeHintEl = document.getElementById("bargeHint");
|
||
const micMeterFillEl = document.getElementById("micMeterFill");
|
||
const settingsBtn = document.getElementById("settingsBtn");
|
||
const settingsSheet = document.getElementById("settingsSheet");
|
||
const sheetBackdrop = document.getElementById("sheetBackdrop");
|
||
const closeSheetBtn = document.getElementById("closeSheetBtn");
|
||
const voiceListEl = document.getElementById("voiceList");
|
||
const clearBtn = document.getElementById("clearBtn");
|
||
const tasksBtn = document.getElementById("tasksBtn");
|
||
const tasksPanel = document.getElementById("tasksPanel");
|
||
const tasksList = document.getElementById("tasksList");
|
||
const tasksBadge = document.getElementById("tasksBadge");
|
||
const closeTasksBtn = document.getElementById("closeTasksBtn");
|
||
const voiceModeBtn = document.getElementById("voiceModeBtn");
|
||
const textModeBtn = document.getElementById("textModeBtn");
|
||
const modeDescriptionEl = document.getElementById("modeDescription");
|
||
const transcriptModeLabelEl = document.getElementById("transcriptModeLabel");
|
||
const chatComposer = document.getElementById("chatComposer");
|
||
const chatInput = document.getElementById("chatInput");
|
||
const sendChatBtn = document.getElementById("sendChatBtn");
|
||
|
||
// ── Background tasks state ──────────────────────────────────────────────────
|
||
const tasks = new Map(); // task_id -> {id, description, status, steps: [], result, error}
|
||
|
||
function updateTasksBadge() {
|
||
const active = [...tasks.values()].filter(t => t.status === "running" || t.status === "pending").length;
|
||
if (active > 0) {
|
||
tasksBadge.hidden = false;
|
||
tasksBadge.textContent = String(active);
|
||
} else {
|
||
tasksBadge.hidden = true;
|
||
}
|
||
}
|
||
|
||
function renderTasks() {
|
||
const items = [...tasks.values()].sort((a, b) => (b.created_at || 0) - (a.created_at || 0));
|
||
if (items.length === 0) {
|
||
tasksList.innerHTML = '<div class="tasks-empty"><strong>Nothing running</strong><span>Ask Hope to research or compare something.</span></div>';
|
||
return;
|
||
}
|
||
tasksList.innerHTML = "";
|
||
for (const t of items) {
|
||
const card = document.createElement("div");
|
||
card.className = "task-card";
|
||
const statusClass = t.status || "pending";
|
||
card.innerHTML = `
|
||
<div class="task-card-header">
|
||
<span class="task-status-dot ${statusClass}"></span>
|
||
<span class="task-desc">${escapeHtml(t.description)}</span>
|
||
</div>
|
||
<ul class="task-steps">${t.steps.map(s => `<li class="task-step ${s.role}">${escapeHtml(s.content)}</li>`).join("")}</ul>
|
||
${t.result ? `<div class="task-result">${escapeHtml(t.result)}</div>` : ""}
|
||
${t.error ? `<div class="task-error">${escapeHtml(t.error)}</div>` : ""}
|
||
`;
|
||
tasksList.appendChild(card);
|
||
}
|
||
}
|
||
|
||
function handleTaskEvent(data) {
|
||
const { task_id, event, role, content, result, error, task } = data;
|
||
if (event === "created" && task) {
|
||
tasks.set(task_id, { ...task, steps: [] });
|
||
} else if (event === "step") {
|
||
const t = tasks.get(task_id);
|
||
if (t) {
|
||
t.steps.push({ role, content });
|
||
t.status = "running";
|
||
}
|
||
} else if (event === "completed") {
|
||
const t = tasks.get(task_id);
|
||
if (t) { t.status = "completed"; t.result = result; }
|
||
} else if (event === "failed") {
|
||
const t = tasks.get(task_id);
|
||
if (t) { t.status = "failed"; t.error = error; }
|
||
}
|
||
updateTasksBadge();
|
||
renderTasks();
|
||
}
|
||
|
||
function setTasksOpen(open) {
|
||
tasksPanel.classList.toggle("open", open);
|
||
tasksBtn.setAttribute("aria-expanded", String(open));
|
||
}
|
||
|
||
tasksBtn.setAttribute("aria-expanded", "false");
|
||
tasksBtn.addEventListener("click", () => setTasksOpen(!tasksPanel.classList.contains("open")));
|
||
closeTasksBtn.addEventListener("click", () => setTasksOpen(false));
|
||
|
||
// ── Voice / text mode ──────────────────────────────────────────────────────
|
||
function updateModeUI() {
|
||
const isText = conversationMode === "text";
|
||
document.body.dataset.mode = conversationMode;
|
||
voiceModeBtn.classList.toggle("active", !isText);
|
||
textModeBtn.classList.toggle("active", isText);
|
||
voiceModeBtn.setAttribute("aria-pressed", String(!isText));
|
||
textModeBtn.setAttribute("aria-pressed", String(isText));
|
||
modeDescriptionEl.textContent = isText
|
||
? "Type when quiet is better. Switch back to voice without losing the thread."
|
||
: "Speak naturally. I’ll listen, remember, and answer in real time.";
|
||
transcriptModeLabelEl.textContent = isText ? "Shared voice and text history" : "Live voice transcript";
|
||
startBtn.innerHTML = isText
|
||
? '<span class="button-spark" aria-hidden="true"></span>Connect to Hope'
|
||
: '<span class="button-spark" aria-hidden="true"></span>Start conversation';
|
||
if (isText) {
|
||
setState(room ? "listening" : "idle");
|
||
window.setTimeout(() => chatInput.focus(), 0);
|
||
}
|
||
}
|
||
|
||
async function setConversationMode(mode) {
|
||
if (mode !== "voice" && mode !== "text") return;
|
||
const previousMode = conversationMode;
|
||
conversationMode = mode;
|
||
localStorage.setItem(MODE_KEY, mode);
|
||
updateModeUI();
|
||
if (mode === "voice" && previousMode === "text") {
|
||
chatInput.blur();
|
||
window.setTimeout(() => {
|
||
document.querySelector(".workspace").scrollIntoView({ block: "start", behavior: "smooth" });
|
||
}, 0);
|
||
}
|
||
|
||
if (!room || !room.localParticipant) return;
|
||
sendModeMessage(mode);
|
||
if (mode === "text") {
|
||
await room.localParticipant.setMicrophoneEnabled(false);
|
||
micMuted = true;
|
||
muteBtn.disabled = true;
|
||
updateMuteIcon();
|
||
stopVisualLoop();
|
||
statusEl.textContent = "Secure room · Text mode";
|
||
} else {
|
||
await room.startAudio();
|
||
await room.localParticipant.setMicrophoneEnabled(true);
|
||
micMuted = false;
|
||
muteBtn.disabled = false;
|
||
updateMuteIcon();
|
||
setupMicAnalyser();
|
||
startVisualLoop();
|
||
statusEl.textContent = "Secure room · Microphone on";
|
||
}
|
||
}
|
||
|
||
voiceModeBtn.addEventListener("click", () => setConversationMode("voice"));
|
||
textModeBtn.addEventListener("click", () => setConversationMode("text"));
|
||
|
||
// ── Audio analysers (mic + remote agent audio) ─────────────────────────────
|
||
let micCtx = null;
|
||
let micAnalyser = null;
|
||
let micBuf = null;
|
||
let remoteCtx = null;
|
||
let remoteAnalyser = null;
|
||
let remoteFreqBuf = null;
|
||
|
||
function setupMicAnalyser() {
|
||
try {
|
||
const pub = room.localParticipant.getTrackPublication(LivekitClient.Track.Source.Microphone);
|
||
const mst = pub && pub.track && pub.track.mediaStreamTrack;
|
||
if (mst) {
|
||
micCtx = new AudioContext();
|
||
micAnalyser = micCtx.createAnalyser();
|
||
micAnalyser.fftSize = 512;
|
||
micBuf = new Float32Array(micAnalyser.fftSize);
|
||
micCtx.createMediaStreamSource(new MediaStream([mst])).connect(micAnalyser);
|
||
}
|
||
} catch (e) { /* fall back to SDK audioLevel in the meter loop */ }
|
||
}
|
||
|
||
function setupRemoteAudioAnalyser(audioEl) {
|
||
try {
|
||
if (!audioEl.srcObject) return;
|
||
remoteCtx = new AudioContext();
|
||
remoteAnalyser = remoteCtx.createAnalyser();
|
||
remoteAnalyser.fftSize = 256;
|
||
remoteFreqBuf = new Uint8Array(remoteAnalyser.frequencyBinCount);
|
||
remoteCtx.createMediaStreamSource(audioEl.srcObject).connect(remoteAnalyser);
|
||
} catch (e) { /* analyser optional */ }
|
||
}
|
||
|
||
function teardownAudio() {
|
||
for (const ctx of [micCtx, remoteCtx]) {
|
||
if (ctx && ctx.state !== "closed") ctx.close().catch(() => {});
|
||
}
|
||
micCtx = micAnalyser = micBuf = null;
|
||
remoteCtx = remoteAnalyser = remoteFreqBuf = null;
|
||
}
|
||
|
||
function readMicLevel() {
|
||
let level = 0;
|
||
if (micAnalyser && micBuf) {
|
||
micAnalyser.getFloatTimeDomainData(micBuf);
|
||
for (let i = 0; i < micBuf.length; i++) level = Math.max(level, Math.abs(micBuf[i]));
|
||
} else if (room && room.localParticipant) {
|
||
level = room.localParticipant.audioLevel || 0;
|
||
}
|
||
// Smooth so the orb pulses rather than flickers
|
||
micLevel = micLevel * 0.6 + level * 0.4;
|
||
return micLevel;
|
||
}
|
||
|
||
function readAgentAudioLevel() {
|
||
let level = 0;
|
||
if (remoteAnalyser && remoteFreqBuf) {
|
||
remoteAnalyser.getByteFrequencyData(remoteFreqBuf);
|
||
for (let i = 0; i < remoteFreqBuf.length; i++) level = Math.max(level, remoteFreqBuf[i]);
|
||
level /= 255;
|
||
} else if (agentParticipant && agentParticipant.audioLevel !== undefined) {
|
||
level = agentParticipant.audioLevel || 0;
|
||
}
|
||
agentAudioLevel = agentAudioLevel * 0.6 + level * 0.4;
|
||
return agentAudioLevel;
|
||
}
|
||
|
||
// ── State machine ───────────────────────────────────────────────────────────
|
||
const STATE_LABELS = {
|
||
voice: {
|
||
idle: "Ready when you are",
|
||
connecting: "Opening a secure room",
|
||
listening: "Listening",
|
||
thinking: "Thinking it through",
|
||
speaking: "Hope is speaking",
|
||
},
|
||
text: {
|
||
idle: "Ready to type",
|
||
connecting: "Opening a secure room",
|
||
listening: "Text chat ready",
|
||
thinking: "Hope is writing",
|
||
speaking: "Hope replied",
|
||
},
|
||
};
|
||
|
||
function setState(next) {
|
||
uiState = next;
|
||
orbEl.dataset.state = next;
|
||
stateLabelEl.textContent = STATE_LABELS[conversationMode][next] || next;
|
||
|
||
// Thinking timer: show the "thinking..." chip if it lingers past 2s
|
||
if (next === "thinking") {
|
||
thinkingChipEl.hidden = true;
|
||
setTimeout(() => {
|
||
if (uiState === "thinking") thinkingChipEl.hidden = false;
|
||
}, 2000);
|
||
} else {
|
||
thinkingChipEl.hidden = true;
|
||
}
|
||
|
||
// Barge-in hint only while the agent is speaking
|
||
bargeHintEl.hidden = next !== "speaking";
|
||
|
||
if (next === "idle") {
|
||
micLevel = 0;
|
||
agentAudioLevel = 0;
|
||
userSpeaking = false;
|
||
}
|
||
}
|
||
|
||
updateModeUI();
|
||
|
||
function inferState() {
|
||
if (!room || !room.localParticipant) return "idle";
|
||
if (!agentParticipant) return "connecting";
|
||
readMicLevel();
|
||
readAgentAudioLevel();
|
||
userSpeaking = micLevel > 0.035;
|
||
if (agentAudioLevel > 0.02) return "speaking";
|
||
if (userSpeaking) return "listening";
|
||
// Once agent audio ends, return to listening. The previous implementation
|
||
// converted speaking → thinking forever, leaving the UI apparently frozen.
|
||
if (uiState === "speaking") return "listening";
|
||
if (uiState === "thinking") return "thinking";
|
||
return "listening";
|
||
}
|
||
|
||
// ── Visual loop: drives orb + meter + state inference ───────────────────────
|
||
let visualTimer = null;
|
||
function startVisualLoop() {
|
||
if (visualTimer) clearInterval(visualTimer);
|
||
visualTimer = setInterval(() => {
|
||
if (!room || !room.localParticipant) return;
|
||
setState(inferState());
|
||
|
||
// Mic meter (thin bar under the status line)
|
||
micMeterFillEl.style.width = `${Math.min(100, Math.round(micLevel * 250))}%`;
|
||
|
||
// Orb pulse: scale/opacity from whichever stream is active
|
||
if (uiState === "speaking") {
|
||
orbEl.style.setProperty("--pulse-scale", (1 + agentAudioLevel * 0.35).toFixed(3));
|
||
orbEl.style.setProperty("--pulse-opacity", Math.min(1, 0.55 + agentAudioLevel).toFixed(3));
|
||
} else if (uiState === "listening" && userSpeaking) {
|
||
orbEl.style.setProperty("--pulse-scale", (1 + micLevel * 0.4).toFixed(3));
|
||
orbEl.style.setProperty("--pulse-opacity", Math.min(1, 0.5 + micLevel).toFixed(3));
|
||
} else {
|
||
orbEl.style.setProperty("--pulse-scale", "1");
|
||
orbEl.style.setProperty("--pulse-opacity", "");
|
||
}
|
||
|
||
// Agent audio visualizer bars on the latest agent bubble
|
||
const viz = messagesEl.querySelector(".message-row.agent:last-of-type .audio-viz");
|
||
if (viz) {
|
||
let level = 0;
|
||
if (remoteAnalyser && remoteFreqBuf) {
|
||
for (let i = 0; i < remoteFreqBuf.length; i++) level = Math.max(level, remoteFreqBuf[i]);
|
||
level /= 255;
|
||
}
|
||
const bars = viz.children;
|
||
for (let i = 0; i < bars.length; i++) {
|
||
// Per-bar phase offset so the bars dance rather than move in lockstep
|
||
const h = Math.max(0.15, level * (0.6 + 0.4 * Math.sin(Date.now() / 120 + i * 1.3)));
|
||
bars[i].style.height = `${h * 100}%`;
|
||
}
|
||
}
|
||
}, 80);
|
||
}
|
||
|
||
function stopVisualLoop() {
|
||
if (visualTimer) clearInterval(visualTimer);
|
||
visualTimer = null;
|
||
micMeterFillEl.style.width = "0%";
|
||
orbEl.style.setProperty("--pulse-scale", "1");
|
||
orbEl.style.setProperty("--pulse-opacity", "");
|
||
}
|
||
|
||
// ── Conversation history (localStorage) ─────────────────────────────────────
|
||
function loadHistory() {
|
||
try {
|
||
const raw = localStorage.getItem(HISTORY_KEY);
|
||
if (!raw) return [];
|
||
const arr = JSON.parse(raw);
|
||
return Array.isArray(arr) ? arr.slice(-HISTORY_MAX) : [];
|
||
} catch (e) { return []; }
|
||
}
|
||
|
||
function persistHistory() {
|
||
try {
|
||
localStorage.setItem(HISTORY_KEY, JSON.stringify(history.slice(-HISTORY_MAX)));
|
||
} catch (e) { /* storage full or unavailable */ }
|
||
}
|
||
|
||
let history = loadHistory();
|
||
|
||
const DELIVERY_MARKERS = /\[(?:appreciative|calm|concerned|curious|encouraging|excited|happy|joking|quiet|reassuring|reflective|sad|serious|surprised|sympathetic|urgent|whispering|laughter|sighing|breathing|neutral)\]\s*/gi;
|
||
|
||
function cleanSpokenText(text) {
|
||
return String(text || "").replace(DELIVERY_MARKERS, "").trim();
|
||
}
|
||
|
||
function formatTimestamp(ts) {
|
||
if (!ts) return "";
|
||
return new Date(ts).toLocaleTimeString([], { hour: "numeric", minute: "2-digit" });
|
||
}
|
||
|
||
function renderMessage(msg) {
|
||
const wrap = document.createElement("div");
|
||
wrap.className = `message-row ${msg.role}`;
|
||
wrap.dataset.ts = formatTimestamp(msg.ts);
|
||
|
||
if (msg.role === "agent") {
|
||
const dot = document.createElement("span");
|
||
dot.className = "avatar-dot";
|
||
wrap.appendChild(dot);
|
||
}
|
||
|
||
const bubble = document.createElement("div");
|
||
bubble.className = "bubble";
|
||
bubble.textContent = cleanSpokenText(msg.text);
|
||
if (msg.role === "agent") {
|
||
const viz = document.createElement("span");
|
||
viz.className = "audio-viz";
|
||
for (let i = 0; i < 5; i++) viz.appendChild(document.createElement("i"));
|
||
bubble.appendChild(viz);
|
||
}
|
||
wrap.appendChild(bubble);
|
||
messagesEl.appendChild(wrap);
|
||
messagesEl.scrollTop = messagesEl.scrollHeight;
|
||
}
|
||
|
||
function addMessage(role, text) {
|
||
clearPartials();
|
||
const msg = { role, text, ts: Date.now() };
|
||
history.push(msg);
|
||
persistHistory();
|
||
renderMessage(msg);
|
||
return msg;
|
||
}
|
||
|
||
// Partial transcripts render greyed and update in place until a final arrives.
|
||
function addPartial(role, text) {
|
||
const rows = messagesEl.querySelectorAll(".message-row.partial");
|
||
let last = null;
|
||
for (const r of rows) last = r;
|
||
if (last && last.dataset.role === role) {
|
||
last.querySelector(".bubble").textContent = cleanSpokenText(text);
|
||
messagesEl.scrollTop = messagesEl.scrollHeight;
|
||
return;
|
||
}
|
||
const wrap = document.createElement("div");
|
||
wrap.className = `message-row ${role} partial`;
|
||
wrap.dataset.role = role;
|
||
if (role === "agent") {
|
||
const dot = document.createElement("span");
|
||
dot.className = "avatar-dot";
|
||
wrap.appendChild(dot);
|
||
}
|
||
const bubble = document.createElement("div");
|
||
bubble.className = "bubble partial";
|
||
bubble.textContent = cleanSpokenText(text);
|
||
wrap.appendChild(bubble);
|
||
messagesEl.appendChild(wrap);
|
||
messagesEl.scrollTop = messagesEl.scrollHeight;
|
||
}
|
||
|
||
function clearPartials() {
|
||
messagesEl.querySelectorAll(".message-row.partial").forEach((el) => el.remove());
|
||
}
|
||
|
||
function renderHistory() {
|
||
messagesEl.innerHTML = "";
|
||
for (const msg of history) renderMessage(msg);
|
||
messagesEl.scrollTop = messagesEl.scrollHeight;
|
||
}
|
||
|
||
clearBtn.addEventListener("click", () => {
|
||
history = [];
|
||
persistHistory();
|
||
clearPartials();
|
||
renderHistory();
|
||
});
|
||
|
||
renderHistory();
|
||
|
||
// ── Transcripts ─────────────────────────────────────────────────────────────
|
||
// Primary: livekit-agents built-in text stream (word-by-word when available).
|
||
function registerTranscriptionStream(rm) {
|
||
try {
|
||
rm.registerTextStreamHandler("lk.transcription", async (reader, participantInfo) => {
|
||
const text = await reader.readAll();
|
||
if (!text || !text.trim()) return;
|
||
const attrs = (reader.info && reader.info.attributes) || {};
|
||
const trackId = attrs["lk.transcribed_track_id"] || "";
|
||
// Distinguish user vs agent by the transcribed track's owner.
|
||
let role = "agent";
|
||
if (participantInfo && participantInfo.identity === AGENT_NAME) {
|
||
role = "agent";
|
||
} else if (trackId) {
|
||
for (const p of rm.remoteParticipants.values()) {
|
||
const pub = p.getTrackPublication(trackId);
|
||
if (pub) { role = isAgent(p) ? "agent" : "user"; break; }
|
||
}
|
||
}
|
||
// Use partial rendering: updates the same row in place until final.
|
||
addPartial(role, text.trim());
|
||
});
|
||
} catch (e) {
|
||
// Older SDKs may not support registerTextStreamHandler — the data
|
||
// channel handler below still covers transcripts.
|
||
console.warn("text stream registration failed:", e);
|
||
}
|
||
}
|
||
|
||
// Secondary: agent publishes {type:"transcript"} on topic "transcript".
|
||
function handleDataPacket(payload, participant, topic) {
|
||
try {
|
||
const msg = JSON.parse(new TextDecoder().decode(payload));
|
||
if (msg.type === "agent_ready") {
|
||
agentReady = true;
|
||
} else if (msg.type === "transcript") {
|
||
addMessage(msg.role || "agent", msg.text);
|
||
if (conversationMode === "text" && (msg.role || "agent") === "agent") {
|
||
setState("listening");
|
||
chatInput.focus();
|
||
}
|
||
} else if (msg.type === "task_event") {
|
||
handleTaskEvent(msg);
|
||
}
|
||
// set_voice messages flow the other way; nothing to do client-side.
|
||
} catch (e) {
|
||
console.warn("bad data packet", e);
|
||
}
|
||
}
|
||
|
||
// ── Voice settings sheet ────────────────────────────────────────────────────
|
||
function currentVoiceId() {
|
||
const saved = localStorage.getItem("preferred_voice");
|
||
return VOICES.some((v) => v.id === saved) ? saved : VOICES[0].id;
|
||
}
|
||
|
||
function renderVoiceList() {
|
||
voiceListEl.innerHTML = "";
|
||
const active = currentVoiceId();
|
||
for (const v of VOICES) {
|
||
const card = document.createElement("div");
|
||
card.className = "voice-card" + (v.id === active ? " active" : "");
|
||
card.dataset.voice = v.id;
|
||
|
||
const name = document.createElement("span");
|
||
name.className = "voice-name";
|
||
name.textContent = v.name + (v.tag ? ` (${v.tag})` : "");
|
||
|
||
const selected = v.id === active;
|
||
card.setAttribute("role", "radio");
|
||
card.setAttribute("aria-checked", String(selected));
|
||
card.tabIndex = 0;
|
||
card.appendChild(name);
|
||
card.addEventListener("click", () => selectVoice(v.id));
|
||
card.addEventListener("keydown", (event) => {
|
||
if (event.key === "Enter" || event.key === " ") {
|
||
event.preventDefault();
|
||
selectVoice(v.id);
|
||
}
|
||
});
|
||
voiceListEl.appendChild(card);
|
||
}
|
||
}
|
||
|
||
function selectVoice(voiceId) {
|
||
localStorage.setItem("preferred_voice", voiceId);
|
||
renderVoiceList();
|
||
if (room && agentParticipant) {
|
||
sendVoiceMessage(voiceId);
|
||
const v = VOICES.find((x) => x.id === voiceId);
|
||
addMessage("system", `Voice changed to ${v ? v.name : voiceId}`);
|
||
}
|
||
}
|
||
|
||
function openSheet() {
|
||
renderVoiceList();
|
||
sheetBackdrop.hidden = false;
|
||
settingsSheet.classList.add("open");
|
||
settingsBtn.setAttribute("aria-expanded", "true");
|
||
settingsSheet.querySelector(".voice-card")?.focus();
|
||
}
|
||
|
||
function closeSheet() {
|
||
settingsSheet.classList.remove("open");
|
||
settingsBtn.setAttribute("aria-expanded", "false");
|
||
window.setTimeout(() => { sheetBackdrop.hidden = true; }, 240);
|
||
settingsBtn.focus();
|
||
}
|
||
|
||
settingsBtn.setAttribute("aria-expanded", "false");
|
||
settingsBtn.addEventListener("click", openSheet);
|
||
closeSheetBtn.addEventListener("click", closeSheet);
|
||
sheetBackdrop.addEventListener("click", closeSheet);
|
||
document.addEventListener("keydown", (event) => {
|
||
if (event.key !== "Escape") return;
|
||
if (settingsSheet.classList.contains("open")) closeSheet();
|
||
if (tasksPanel.classList.contains("open")) setTasksOpen(false);
|
||
});
|
||
// ── Wake lock ───────────────────────────────────────────────────────────────
|
||
async function acquireWakeLock() {
|
||
try {
|
||
if ("wakeLock" in navigator) {
|
||
wakeLock = await navigator.wakeLock.request("screen");
|
||
}
|
||
} catch (e) { /* not critical */ }
|
||
}
|
||
|
||
function releaseWakeLock() {
|
||
if (wakeLock) {
|
||
wakeLock.release().catch(() => {});
|
||
wakeLock = null;
|
||
}
|
||
}
|
||
|
||
// ── Agent detection ─────────────────────────────────────────────────────────
|
||
// The agent may already be in the room before we join (it persists between
|
||
// page loads), so scan remoteParticipants after connect AND watch for new
|
||
// joins — ParticipantConnected does not fire for pre-existing participants.
|
||
function isAgent(participant) {
|
||
// kind is the numeric proto enum; ParticipantKind.AGENT === 4.
|
||
// Prefer the SDK's own getter where available.
|
||
if (participant.isAgent !== undefined && participant.isAgent !== null) {
|
||
return participant.isAgent;
|
||
}
|
||
return participant.identity === AGENT_NAME
|
||
|| participant.kind === LivekitClient.ParticipantKind.AGENT;
|
||
}
|
||
|
||
function findAgent(rm) {
|
||
if (!rm) return null;
|
||
for (const p of rm.remoteParticipants.values()) {
|
||
if (isAgent(p)) return p;
|
||
}
|
||
return null;
|
||
}
|
||
|
||
function markAgentFound(rm, participant) {
|
||
agentParticipant = participant;
|
||
statusEl.textContent = conversationMode === "text"
|
||
? "Hope joined · Text chat ready"
|
||
: "Hope joined · Preparing microphone…";
|
||
// Synchronize voice and interaction mode when the agent joins.
|
||
sendVoiceMessage(currentVoiceId(), rm);
|
||
sendModeMessage(conversationMode, rm);
|
||
}
|
||
|
||
function createRoom(token) {
|
||
const newRoom = new Room({
|
||
adaptiveStream: true,
|
||
dynacast: true,
|
||
});
|
||
|
||
// Listen for the agent joining after us
|
||
newRoom.on(RoomEvent.ParticipantConnected, (participant) => {
|
||
if (isAgent(participant)) markAgentFound(newRoom, participant);
|
||
});
|
||
|
||
// Attach and play incoming audio tracks (agent TTS)
|
||
newRoom.on(RoomEvent.TrackSubscribed, (track, publication, participant) => {
|
||
if (track.kind === LivekitClient.Track.Kind.Audio) {
|
||
const el = track.attach();
|
||
el.id = `audio-${participant.identity}`;
|
||
document.body.appendChild(el);
|
||
// Remote audio analyser drives the orb + visualizer while speaking
|
||
setupRemoteAudioAnalyser(el);
|
||
}
|
||
});
|
||
|
||
newRoom.on(RoomEvent.TrackUnsubscribed, (track) => {
|
||
track.detach().forEach((el) => el.remove());
|
||
});
|
||
|
||
// Browsers block audio playback until a user gesture; show an unlock
|
||
// button if the page loads without one.
|
||
newRoom.on(RoomEvent.AudioPlaybackStatusChanged, () => {
|
||
if (!newRoom.canPlaybackAudio) {
|
||
const existing = document.getElementById("audioUnlockBtn");
|
||
if (!existing) {
|
||
const btn = document.createElement("button");
|
||
btn.id = "audioUnlockBtn";
|
||
btn.className = "btn btn-primary";
|
||
btn.textContent = "Tap to enable audio";
|
||
btn.style.cssText = "position:fixed;bottom:2rem;left:50%;transform:translateX(-50%);z-index:999;padding:1rem 2rem;font-size:1.1rem;border-radius:999px;box-shadow:0 4px 24px rgba(0,0,0,.5)";
|
||
btn.onclick = () => { newRoom.startAudio(); btn.remove(); };
|
||
document.body.appendChild(btn);
|
||
}
|
||
} else {
|
||
const existing = document.getElementById("audioUnlockBtn");
|
||
if (existing) existing.remove();
|
||
}
|
||
});
|
||
|
||
// Live text stream (word-by-word transcripts)
|
||
registerTranscriptionStream(newRoom);
|
||
|
||
// Data channel: transcripts (secondary source) + voice control
|
||
newRoom.on(RoomEvent.DataReceived, (payload, participant, kind, topic) => {
|
||
handleDataPacket(payload, participant, topic);
|
||
});
|
||
|
||
// Guard with `=== room` so a stale (retry-discarded) connection cannot
|
||
// clobber UI state of the active one.
|
||
newRoom.on(RoomEvent.ConnectionQualityChanged, (participant, quality) => {
|
||
if (participant === newRoom.localParticipant && newRoom === room) {
|
||
statusEl.textContent = `Secure room · ${quality} connection`;
|
||
}
|
||
});
|
||
|
||
newRoom.on(RoomEvent.Disconnected, () => {
|
||
if (newRoom !== room) return;
|
||
teardownAudio();
|
||
stopVisualLoop();
|
||
releaseWakeLock();
|
||
statusEl.textContent = "Conversation ended";
|
||
setState("idle");
|
||
startBtn.disabled = false;
|
||
stopBtn.disabled = true;
|
||
agentParticipant = null;
|
||
agentReady = false;
|
||
});
|
||
|
||
return newRoom.connect(LIVEKIT_URL, token, {
|
||
autoSubscribe: true,
|
||
}).then(() => {
|
||
// Pick up an agent that was already in the room before we joined
|
||
const existing = findAgent(newRoom);
|
||
if (existing) markAgentFound(newRoom, existing);
|
||
return newRoom;
|
||
});
|
||
}
|
||
|
||
function waitForAgentReady(timeoutMs) {
|
||
return new Promise((resolve) => {
|
||
if (agentReady) return resolve(true);
|
||
const deadline = Date.now() + timeoutMs;
|
||
const timer = setInterval(() => {
|
||
if (agentReady) {
|
||
clearInterval(timer);
|
||
resolve(true);
|
||
} else if (Date.now() > deadline) {
|
||
clearInterval(timer);
|
||
resolve(false);
|
||
}
|
||
}, 100);
|
||
});
|
||
}
|
||
|
||
function waitForAgent(timeoutMs) {
|
||
return new Promise((resolve) => {
|
||
if (findAgent(room)) return resolve(true);
|
||
const deadline = Date.now() + timeoutMs;
|
||
const timer = setInterval(() => {
|
||
const found = findAgent(room);
|
||
if (found) {
|
||
if (!agentParticipant) markAgentFound(room, found);
|
||
clearInterval(timer);
|
||
resolve(true);
|
||
} else if (Date.now() > deadline) {
|
||
clearInterval(timer);
|
||
resolve(false);
|
||
}
|
||
}, 250);
|
||
});
|
||
}
|
||
|
||
async function connectConversation() {
|
||
if (room && agentParticipant) return room;
|
||
if (connectionPromise) return connectionPromise;
|
||
|
||
connectionPromise = (async () => {
|
||
try {
|
||
setState("connecting");
|
||
statusEl.textContent = "Opening your secure room…";
|
||
await acquireWakeLock();
|
||
|
||
// Get a signed access token from the token endpoint.
|
||
const token = await fetchToken(ROOM_NAME);
|
||
room = await createRoom(token);
|
||
|
||
// The agent is dispatched when we join. If it misses the dispatch
|
||
// (for example during a server restart), reconnect once.
|
||
statusEl.textContent = "Inviting Hope into the room…";
|
||
if (!(await waitForAgent(10000))) {
|
||
statusEl.textContent = "Hope is taking a moment · Retrying…";
|
||
const stale = room;
|
||
room = null;
|
||
agentParticipant = null;
|
||
agentReady = false;
|
||
await stale.disconnect();
|
||
const freshToken = await fetchToken(ROOM_NAME);
|
||
room = await createRoom(freshToken);
|
||
if (!(await waitForAgent(15000))) {
|
||
throw new Error("Assistant did not join — reload the page and try again");
|
||
}
|
||
}
|
||
statusEl.textContent = "Hope joined · Finishing setup…";
|
||
if (!(await waitForAgentReady(10000))) {
|
||
throw new Error("Assistant joined but was not ready — try again");
|
||
}
|
||
|
||
sendModeMessage(conversationMode);
|
||
if (conversationMode === "voice") {
|
||
await room.startAudio();
|
||
statusEl.textContent = "Waiting for microphone permission…";
|
||
await room.localParticipant.setMicrophoneEnabled(true);
|
||
micMuted = false;
|
||
setupMicAnalyser();
|
||
startVisualLoop();
|
||
statusEl.textContent = "Secure room · Microphone on";
|
||
} else {
|
||
await room.localParticipant.setMicrophoneEnabled(false);
|
||
micMuted = true;
|
||
stopVisualLoop();
|
||
statusEl.textContent = "Secure room · Text mode";
|
||
}
|
||
|
||
startBtn.disabled = true;
|
||
stopBtn.disabled = false;
|
||
muteBtn.disabled = conversationMode !== "voice";
|
||
updateMuteIcon();
|
||
setState("listening");
|
||
return room;
|
||
} catch (err) {
|
||
console.error("Connection failed:", err);
|
||
statusEl.textContent = `Error: ${err.message}`;
|
||
setState("idle");
|
||
releaseWakeLock();
|
||
throw err;
|
||
} finally {
|
||
connectionPromise = null;
|
||
}
|
||
})();
|
||
|
||
return connectionPromise;
|
||
}
|
||
|
||
startBtn.addEventListener("click", () => {
|
||
connectConversation().catch(() => {});
|
||
});
|
||
|
||
// ── Text chat ──────────────────────────────────────────────────────────────
|
||
function resizeChatInput() {
|
||
chatInput.style.height = "auto";
|
||
chatInput.style.height = `${Math.min(chatInput.scrollHeight, 144)}px`;
|
||
}
|
||
|
||
chatInput.addEventListener("input", () => {
|
||
resizeChatInput();
|
||
sendChatBtn.disabled = !chatInput.value.trim();
|
||
});
|
||
|
||
chatInput.addEventListener("keydown", (event) => {
|
||
if (event.key === "Enter" && !event.shiftKey) {
|
||
event.preventDefault();
|
||
chatComposer.requestSubmit();
|
||
}
|
||
});
|
||
|
||
chatComposer.addEventListener("submit", async (event) => {
|
||
event.preventDefault();
|
||
const text = chatInput.value.trim();
|
||
if (!text) return;
|
||
|
||
sendChatBtn.disabled = true;
|
||
chatInput.disabled = true;
|
||
try {
|
||
if (conversationMode !== "text") await setConversationMode("text");
|
||
await connectConversation();
|
||
setState("thinking");
|
||
await room.localParticipant.sendText(text, { topic: "lk.chat" });
|
||
chatInput.value = "";
|
||
resizeChatInput();
|
||
} catch (err) {
|
||
console.error("Text message failed:", err);
|
||
statusEl.textContent = `Message not sent: ${err.message}`;
|
||
setState("listening");
|
||
} finally {
|
||
chatInput.disabled = false;
|
||
sendChatBtn.disabled = !chatInput.value.trim();
|
||
chatInput.focus();
|
||
}
|
||
});
|
||
|
||
// ── Stop ────────────────────────────────────────────────────────────────────
|
||
stopBtn.addEventListener("click", () => {
|
||
if (room) {
|
||
room.disconnect();
|
||
room = null;
|
||
agentParticipant = null;
|
||
agentReady = false;
|
||
}
|
||
teardownAudio();
|
||
stopVisualLoop();
|
||
releaseWakeLock();
|
||
document.querySelectorAll('[id^="audio-"]').forEach(el => el.remove());
|
||
statusEl.textContent = "Conversation ended";
|
||
setState("idle");
|
||
startBtn.disabled = false;
|
||
stopBtn.disabled = true;
|
||
muteBtn.disabled = true;
|
||
micMuted = false;
|
||
updateMuteIcon();
|
||
});
|
||
|
||
// ── Mic mute toggle ─────────────────────────────────────────────────────────
|
||
muteBtn.addEventListener("click", async () => {
|
||
if (!room || !room.localParticipant) return;
|
||
micMuted = !micMuted;
|
||
await room.localParticipant.setMicrophoneEnabled(!micMuted);
|
||
updateMuteIcon();
|
||
});
|
||
|
||
function updateMuteIcon() {
|
||
const muted = muteBtn.classList.toggle("muted", micMuted);
|
||
muteBtn.setAttribute("aria-label", muted ? "Unmute microphone" : "Mute microphone");
|
||
muteBtn.title = muted ? "Unmute microphone" : "Mute microphone";
|
||
}
|
||
|
||
// ── Helper: fetch a signed access token from the token endpoint ────────────
|
||
async function fetchToken(roomName) {
|
||
const resp = await fetch("/token", {
|
||
method: "POST",
|
||
headers: { "Content-Type": "application/json" },
|
||
body: JSON.stringify({ room: roomName }),
|
||
});
|
||
if (!resp.ok) throw new Error(`Token endpoint returned ${resp.status}`);
|
||
const data = await resp.json();
|
||
return data.token;
|
||
}
|
||
|
||
// ── Helper: send voice selection to the agent via data channel ─────────────
|
||
function sendVoiceMessage(voice, targetRoom) {
|
||
const r = targetRoom || room;
|
||
if (!r || !r.localParticipant) return;
|
||
const payload = new TextEncoder().encode(JSON.stringify({ type: "set_voice", voice }));
|
||
r.localParticipant.publishData(payload, {
|
||
topic: "voice-control",
|
||
reliable: true,
|
||
});
|
||
}
|
||
|
||
function sendModeMessage(mode, targetRoom) {
|
||
const r = targetRoom || room;
|
||
if (!r || !r.localParticipant) return;
|
||
const payload = new TextEncoder().encode(JSON.stringify({ type: "set_mode", mode }));
|
||
r.localParticipant.publishData(payload, {
|
||
topic: "conversation-control",
|
||
reliable: true,
|
||
});
|
||
}
|