feat: upgrade voice pipeline — MLX Whisper STT (20x faster), Qwen3.5 MoE LLM, fix HA tool calling

- Replace faster-whisper with wyoming-mlx-whisper (whisper-large-v3-turbo, MLX Metal GPU)
  STT latency: 8.4s → 400ms for short voice commands
- Add Qwen3.5-35B-A3B (MoE, 3B active params, Q8_0) to Ollama — 26.7 tok/s vs 5.4 tok/s (70B)
- Add model preload launchd service to pin voice model in VRAM permanently
- Fix HA tool calling: set commands.native=true, symlink ha-ctl to PATH
- Add pipeline benchmark script (STT/LLM/TTS latency profiling)
- Add service restart buttons and STT endpoint to dashboard
- Bind Vite dev server to 0.0.0.0 for LAN access

Total estimated pipeline latency: ~27s → ~4s

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Aodhan Collins
2026-03-13 18:03:12 +00:00
parent 1bfd7fbd08
commit af6b7bd945
10 changed files with 721 additions and 27 deletions

View File

@@ -53,6 +53,70 @@ function healthCheckPlugin() {
res.end(JSON.stringify({ status: 'offline', responseTime: null }));
}
});
// Service restart — runs launchctl or docker restart
server.middlewares.use('/api/service/restart', async (req, res) => {
if (req.method === 'OPTIONS') {
res.writeHead(204, { 'Access-Control-Allow-Origin': '*', 'Access-Control-Allow-Methods': 'POST', 'Access-Control-Allow-Headers': 'Content-Type' });
res.end();
return;
}
if (req.method !== 'POST') {
res.writeHead(405);
res.end();
return;
}
try {
const chunks = [];
for await (const chunk of req) chunks.push(chunk);
const { type, id } = JSON.parse(Buffer.concat(chunks).toString());
if (!type || !id) {
res.writeHead(400, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, error: 'Missing type or id' }));
return;
}
// Whitelist valid service IDs to prevent command injection
const ALLOWED_LAUNCHD = [
'gui/501/com.homeai.ollama',
'gui/501/com.homeai.openclaw',
'gui/501/com.homeai.openclaw-bridge',
'gui/501/com.homeai.wyoming-stt',
'gui/501/com.homeai.wyoming-tts',
'gui/501/com.homeai.wyoming-satellite',
'gui/501/com.homeai.character-dashboard',
];
const ALLOWED_DOCKER = [
'homeai-open-webui',
'homeai-uptime-kuma',
'homeai-n8n',
'homeai-code-server',
];
let cmd;
if (type === 'launchd' && ALLOWED_LAUNCHD.includes(id)) {
cmd = ['launchctl', 'kickstart', '-k', id];
} else if (type === 'docker' && ALLOWED_DOCKER.includes(id)) {
cmd = ['docker', 'restart', id];
} else {
res.writeHead(403, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, error: 'Service not in allowed list' }));
return;
}
const { execFile } = await import('child_process');
const { promisify } = await import('util');
const execFileAsync = promisify(execFile);
const { stdout, stderr } = await execFileAsync(cmd[0], cmd.slice(1), { timeout: 30000 });
res.writeHead(200, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: true, stdout: stdout.trim(), stderr: stderr.trim() }));
} catch (err) {
res.writeHead(500, { 'Content-Type': 'application/json' });
res.end(JSON.stringify({ ok: false, error: err.message }));
}
});
// TTS preview proxy — forwards POST to OpenClaw bridge, returns audio
server.middlewares.use('/api/tts', async (req, res) => {
if (req.method !== 'POST') {
@@ -99,4 +163,7 @@ export default defineConfig({
tailwindcss(),
react(),
],
server: {
host: '0.0.0.0',
},
})