mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-30 19:49:14 +00:00
613da94093
* fix(minions): honest attempt accounting + cooperative abort-honoring + per-handler timeouts (#1737) - Wall-clock and stall dead-letter paths now increment attempts_made (terminal, no retry — wall-clock fires at 2x cumulative timeout; retrying non-idempotent embed/subagent work would duplicate side effects). Surface stalled_counter in jobs get so 'started 3 / stalled 2 / attempts 0' reads true instead of looking like broken accounting. - Thread AbortSignal through embed-backfill/autopilot-cycle -> runPhaseEmbed -> runEmbedCore -> embedAll(Stale)/embedPage, checking it on BOTH --stale and --all paths and between embed batches. A timed-out embed phase now bails within a batch, so the cycle finally releases gbrain_cycle_locks instead of running the full 10-15 min after the job was killed (the daily cycle-wedge). New shared src/core/abort-check.ts (isAborted/throwIfAborted/anySignal). - Per-handler default wall-clock budget (handler-timeouts.ts) stamped at submit for long handlers without an explicit timeout_ms. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * fix(minions): queue-scoped DB supervisor singleton + canonical pidfile + doctor max-rss check (#1849) - Acquire a queue-scoped DB lock (tryAcquireDbLock, keyed on the raw DB identity + queue) on supervisor.start(): a second supervisor on the same (db, queue) fails fast with exit 2 regardless of $HOME/--pid-file. Refresh on a dedicated timer; on refresh failure past the threshold, fail SAFE (exit non-zero) before the TTL could lapse and let a second supervisor take over. Release on shutdown. - Canonical default pidfile keyed on brain id (currentBrainId, config-only, no DB connect) so two brains under one HOME no longer share supervisor.pid. - doctor: new supervisor_singleton check surfaces the effective --max-rss (from the started audit event) and warns when the lock holder's (host,pid) differs from the local pidfile — comparing host+pid, not bare pid. Registered in doctor-categories. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(agent-voice): topic-aware persona context via server-resolved topicId (#1851) Summon Mars/Venus into a specific conversation topic so they boot already knowing the recent thread. A per-topic call link carries only topicId (+ optional display topicName); the server resolves the recent-conversation context from the brain (topics/<topicId>.md) — topic CONTENT is never accepted over the wire (that would be prompt injection + a leak into URLs/referrers/logs). topicId is a strict slug with a path-traversal guard. New '# Topic Context' prompt slot injected after the persona body so identity-first ordering still wins; persona identity unchanged. No topicId -> generic behavior. Contract doc + persona skill docs updated. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: file #1737 slot-reservation fair-scheduling follow-up TODO (F7) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * chore: bump version and changelog (v0.42.29.0) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * docs: sync KEY_FILES.md for v0.42.29.0 minions + abort wave (#1737, #1849) Fold the #1737/#1849 behavior into the existing per-file entries and add the two new core files, keeping the doc at current-state truth: - queue.ts: honest attempt accounting on wall-clock + stall dead-letter paths; defaultTimeoutMsFor stamping at submit. - supervisor.ts: queue-scoped DB singleton lock (supervisorLockId, classifySupervisorSingleton, LOCK_LOST, refresh-fail-safe, brain-id pidfile, max_rss_mb audit). - worker-registry.ts: currentDbIdentity(). - New entries: src/core/abort-check.ts, src/core/minions/handler-timeouts.ts. - New doctor.ts extension: supervisor_singleton check. - cycle.ts / embed.ts extensions: AbortSignal threading note. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
336 lines
12 KiB
HTML
336 lines
12 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="utf-8" />
|
|
<title>Voice Agent</title>
|
|
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
|
<style>
|
|
:root {
|
|
color-scheme: dark;
|
|
font-family: ui-sans-serif, system-ui, -apple-system, "Segoe UI", Inter, Roboto, "Helvetica Neue", sans-serif;
|
|
}
|
|
body {
|
|
margin: 0;
|
|
min-height: 100vh;
|
|
display: grid;
|
|
place-items: center;
|
|
background: radial-gradient(circle at top, #1a1a25, #0a0a0f);
|
|
color: #eaeaf0;
|
|
}
|
|
.card {
|
|
width: min(420px, 92vw);
|
|
padding: 32px;
|
|
border-radius: 16px;
|
|
background: rgba(30, 30, 40, 0.6);
|
|
backdrop-filter: blur(12px);
|
|
border: 1px solid rgba(255, 255, 255, 0.06);
|
|
box-shadow: 0 16px 48px rgba(0, 0, 0, 0.4);
|
|
}
|
|
h1 {
|
|
margin: 0 0 8px;
|
|
font-size: 24px;
|
|
font-weight: 600;
|
|
letter-spacing: -0.01em;
|
|
}
|
|
.subtitle { color: #9c9caa; font-size: 14px; margin-bottom: 24px; }
|
|
.status {
|
|
font-family: ui-monospace, "JetBrains Mono", Menlo, monospace;
|
|
font-size: 12px;
|
|
color: #9c9caa;
|
|
padding: 12px;
|
|
border-radius: 8px;
|
|
background: rgba(0, 0, 0, 0.3);
|
|
margin-bottom: 16px;
|
|
min-height: 60px;
|
|
white-space: pre-wrap;
|
|
}
|
|
.call-btn {
|
|
width: 100%;
|
|
padding: 14px 20px;
|
|
border-radius: 999px;
|
|
border: none;
|
|
background: linear-gradient(180deg, #4f46e5, #4338ca);
|
|
color: white;
|
|
font-size: 16px;
|
|
font-weight: 500;
|
|
cursor: pointer;
|
|
transition: transform 0.05s ease, background 0.2s ease;
|
|
}
|
|
.call-btn:hover:not(:disabled) { background: linear-gradient(180deg, #5b52ec, #4d42d4); }
|
|
.call-btn:active:not(:disabled) { transform: scale(0.98); }
|
|
.call-btn:disabled { background: #2b2b36; cursor: not-allowed; }
|
|
.call-btn.active { background: linear-gradient(180deg, #dc2626, #b91c1c); }
|
|
.meta {
|
|
margin-top: 16px;
|
|
font-size: 12px;
|
|
color: #6c6c7a;
|
|
display: flex;
|
|
gap: 12px;
|
|
flex-wrap: wrap;
|
|
}
|
|
.badge {
|
|
padding: 2px 8px;
|
|
border-radius: 4px;
|
|
background: rgba(255, 255, 255, 0.06);
|
|
}
|
|
</style>
|
|
</head>
|
|
<body>
|
|
<div class="card">
|
|
<h1>Voice Agent</h1>
|
|
<div class="subtitle" id="subtitle">Press connect to start a voice session.</div>
|
|
<div class="status" id="status">idle</div>
|
|
<button class="call-btn" id="callBtn">Connect</button>
|
|
<div class="meta">
|
|
<span class="badge" id="personaBadge">persona: venus</span>
|
|
<span class="badge" id="testBadge" style="display:none">?test=1 active</span>
|
|
</div>
|
|
</div>
|
|
|
|
<audio id="remoteAudio" autoplay playsinline></audio>
|
|
|
|
<script type="module">
|
|
// ── Configuration from query params ─────────────────────────
|
|
const params = new URLSearchParams(location.search);
|
|
const persona = (params.get('persona') || 'venus').toLowerCase();
|
|
const TEST_MODE = params.get('test') === '1';
|
|
// #1851: a per-topic call link carries topicId (+ optional topicName). We
|
|
// forward ONLY these to /session — the server resolves the topic's recent
|
|
// conversation from the brain. Topic content never travels in a URL.
|
|
const topicId = params.get('topicId') || '';
|
|
const topicName = params.get('topicName') || '';
|
|
|
|
document.getElementById('personaBadge').textContent = `persona: ${persona}`;
|
|
if (TEST_MODE) document.getElementById('testBadge').style.display = '';
|
|
|
|
// ── D5-A: ?test=1-gated instrumentation namespace ───────────
|
|
// Production load of /call has ZERO window._gbrainTest. The MediaRecorder
|
|
// never instantiates. No audio Blob lives in browser memory unless the
|
|
// test harness explicitly opts in via the query param.
|
|
if (TEST_MODE) {
|
|
window._gbrainTest = {
|
|
setupDone: false,
|
|
audioSendCount: 0,
|
|
audioPlayCount: 0,
|
|
lastResponseBlob: null,
|
|
log: [],
|
|
};
|
|
}
|
|
|
|
const callBtn = document.getElementById('callBtn');
|
|
const statusEl = document.getElementById('status');
|
|
const remoteAudio = document.getElementById('remoteAudio');
|
|
|
|
let pc = null; // RTCPeerConnection
|
|
let dc = null; // RTCDataChannel
|
|
let localStream = null; // microphone MediaStream
|
|
let mediaRecorder = null;
|
|
let recorderChunks = [];
|
|
let audioContext = null;
|
|
let teeDestination = null;
|
|
let callActive = false;
|
|
|
|
function setStatus(text) {
|
|
statusEl.textContent = text;
|
|
if (TEST_MODE) window._gbrainTest.log.push({ t: Date.now(), text });
|
|
}
|
|
|
|
async function startCall() {
|
|
callBtn.disabled = true;
|
|
callBtn.textContent = 'Connecting...';
|
|
setStatus('requesting microphone...');
|
|
|
|
try {
|
|
// 1. Mic.
|
|
localStream = await navigator.mediaDevices.getUserMedia({ audio: true, video: false });
|
|
setStatus('microphone OK; creating peer connection...');
|
|
|
|
// 2. RTCPeerConnection.
|
|
pc = new RTCPeerConnection({
|
|
iceServers: [{ urls: 'stun:stun.l.google.com:19302' }],
|
|
});
|
|
|
|
for (const track of localStream.getAudioTracks()) {
|
|
pc.addTrack(track, localStream);
|
|
}
|
|
|
|
// 3. Data channel for tool calls.
|
|
dc = pc.createDataChannel('oai-events');
|
|
dc.onopen = () => {
|
|
setStatus('data channel open');
|
|
};
|
|
dc.onmessage = (ev) => handleDataChannelMessage(ev.data);
|
|
|
|
// 4. Remote track handler — D12-A WebAudio-tee for capture in test mode.
|
|
pc.ontrack = (ev) => {
|
|
const stream = ev.streams[0];
|
|
remoteAudio.srcObject = stream;
|
|
if (TEST_MODE) {
|
|
try {
|
|
audioContext = new (window.AudioContext || window.webkitAudioContext)();
|
|
const src = audioContext.createMediaStreamSource(stream);
|
|
teeDestination = audioContext.createMediaStreamDestination();
|
|
// Connect ONLY to the tee destination. The <audio> element
|
|
// handles playback via its own srcObject above; we don't
|
|
// double-connect to audioContext.destination (would cause
|
|
// a 2x playback echo).
|
|
src.connect(teeDestination);
|
|
mediaRecorder = new MediaRecorder(teeDestination.stream, {
|
|
mimeType: 'audio/webm; codecs=opus',
|
|
});
|
|
recorderChunks = [];
|
|
mediaRecorder.ondataavailable = (e) => {
|
|
if (e.data && e.data.size > 0) recorderChunks.push(e.data);
|
|
};
|
|
mediaRecorder.onstop = () => {
|
|
window._gbrainTest.lastResponseBlob = new Blob(recorderChunks, {
|
|
type: 'audio/webm',
|
|
});
|
|
};
|
|
mediaRecorder.start(250); // 250ms chunks
|
|
} catch (err) {
|
|
setStatus(`tee setup failed: ${err.message}`);
|
|
}
|
|
}
|
|
// Hook playback counter.
|
|
const audio = stream.getAudioTracks()[0];
|
|
if (audio) {
|
|
audio.onunmute = () => {
|
|
if (TEST_MODE) window._gbrainTest.audioPlayCount++;
|
|
};
|
|
}
|
|
};
|
|
|
|
// 5. Outbound counter — fires whenever we send audio frames.
|
|
// RTCPeerConnection doesn't expose a "frame sent" event natively,
|
|
// but we can poll getStats() on a short interval and count
|
|
// outbound-rtp packets.
|
|
if (TEST_MODE) {
|
|
const statsTimer = setInterval(async () => {
|
|
if (!pc || pc.connectionState === 'closed') {
|
|
clearInterval(statsTimer);
|
|
return;
|
|
}
|
|
try {
|
|
const stats = await pc.getStats();
|
|
stats.forEach((report) => {
|
|
if (report.type === 'outbound-rtp' && report.kind === 'audio') {
|
|
// Each packetsSent tick is roughly 20ms of audio.
|
|
window._gbrainTest.audioSendCount = report.packetsSent || 0;
|
|
}
|
|
if (report.type === 'inbound-rtp' && report.kind === 'audio') {
|
|
if (report.packetsReceived > 0 && window._gbrainTest.audioPlayCount === 0) {
|
|
// Mark playback as starting if we've received any packets,
|
|
// since `onunmute` doesn't always fire.
|
|
window._gbrainTest.audioPlayCount = report.packetsReceived;
|
|
}
|
|
}
|
|
});
|
|
} catch {
|
|
// ignore
|
|
}
|
|
}, 500);
|
|
}
|
|
|
|
// 6. SDP offer.
|
|
const offer = await pc.createOffer({ offerToReceiveAudio: true });
|
|
await pc.setLocalDescription(offer);
|
|
|
|
setStatus('sending SDP offer to /session...');
|
|
let sessionUrl = `/session?persona=${encodeURIComponent(persona)}`;
|
|
if (topicId) sessionUrl += `&topicId=${encodeURIComponent(topicId)}`;
|
|
if (topicName) sessionUrl += `&topicName=${encodeURIComponent(topicName)}`;
|
|
const res = await fetch(sessionUrl, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/sdp' },
|
|
body: offer.sdp,
|
|
});
|
|
if (!res.ok) {
|
|
const text = await res.text();
|
|
throw new Error(`/session ${res.status}: ${text.slice(0, 200)}`);
|
|
}
|
|
const answerSdp = await res.text();
|
|
await pc.setRemoteDescription({ type: 'answer', sdp: answerSdp });
|
|
setStatus('SDP exchanged; waiting for media...');
|
|
|
|
callActive = true;
|
|
callBtn.disabled = false;
|
|
callBtn.textContent = 'Hang up';
|
|
callBtn.classList.add('active');
|
|
|
|
if (TEST_MODE) window._gbrainTest.setupDone = true;
|
|
} catch (err) {
|
|
setStatus(`ERROR: ${err.message}`);
|
|
callBtn.disabled = false;
|
|
callBtn.textContent = 'Connect';
|
|
await endCall();
|
|
if (TEST_MODE) {
|
|
window._gbrainTest.error = err.message;
|
|
}
|
|
}
|
|
}
|
|
|
|
// Handle tool-call messages from the WebRTC data channel.
|
|
async function handleDataChannelMessage(raw) {
|
|
let msg;
|
|
try { msg = JSON.parse(raw); } catch { return; }
|
|
// OpenAI Realtime emits various event types. We only act on function calls.
|
|
if (msg.type === 'response.function_call_arguments.done' ||
|
|
msg.type === 'conversation.item.input_audio_transcription.completed') {
|
|
// Function call complete — dispatch to /tool.
|
|
if (msg.name && msg.call_id) {
|
|
try {
|
|
const args = msg.arguments ? JSON.parse(msg.arguments) : {};
|
|
const res = await fetch('/tool', {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({ name: msg.name, arguments: args }),
|
|
});
|
|
const result = await res.json();
|
|
// Return the result via the data channel.
|
|
dc.send(JSON.stringify({
|
|
type: 'conversation.item.create',
|
|
item: {
|
|
type: 'function_call_output',
|
|
call_id: msg.call_id,
|
|
output: JSON.stringify(result),
|
|
},
|
|
}));
|
|
dc.send(JSON.stringify({ type: 'response.create' }));
|
|
} catch (err) {
|
|
setStatus(`tool dispatch error: ${err.message}`);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
async function endCall() {
|
|
callActive = false;
|
|
callBtn.textContent = 'Connect';
|
|
callBtn.classList.remove('active');
|
|
setStatus('hung up');
|
|
if (mediaRecorder && mediaRecorder.state !== 'inactive') {
|
|
try { mediaRecorder.stop(); } catch {}
|
|
}
|
|
if (pc) {
|
|
try { pc.close(); } catch {}
|
|
pc = null;
|
|
}
|
|
if (localStream) {
|
|
for (const track of localStream.getTracks()) track.stop();
|
|
localStream = null;
|
|
}
|
|
if (audioContext) {
|
|
try { await audioContext.close(); } catch {}
|
|
audioContext = null;
|
|
}
|
|
}
|
|
|
|
callBtn.addEventListener('click', () => {
|
|
if (callActive) endCall();
|
|
else startCall();
|
|
});
|
|
</script>
|
|
</body>
|
|
</html>
|