Shane
d3f9f2c4ed
Critical frontend bugs: - Add TrackSubscribed/attach() for agent audio playback - Fix decodeToString TypeError with TextDecoder - XSS fix: innerHTML -> textContent in addMessage - Fresh token on reconnect retry Agent fixes: - GemmaLLM subclass with reasoning_content fallback wrapper - Disable Gemma 4 thinking mode via chat_template_kwargs (6.8s -> 0.5s) - Remove duplicate session-level LLM - Replace global _active_session with closure-based handler - asyncio.create_task instead of deprecated get_event_loop - Explicit silero VAD, topic filter on voice-control Infra: - supervisord: all programs log to /dev/stdout - Dockerfile: uv sync --frozen with committed uv.lock - nginx config moved to real file, token_server.py no longer served - entrypoint.sh: cert persisted, only regenerated on IP change - compose: healthcheck + cert volume - token_server: CORS removed, room pinned to voice-room UI upgrade: - Orb UI with state machine (idle/connecting/listening/thinking/speaking) - Streaming transcripts via lk.transcription text streams - Barge-in hint, thinking chip, audio visualizer - Glassmorphism, chat bubbles, settings sheet, light mode - PWA manifest, favicon, wake-lock, safe-area insets - localStorage conversation history Docs: AGENTS.md drift fixed
88 lines
2.6 KiB
Python
88 lines
2.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Tiny token endpoint for the voice UI.
|
|
|
|
Serves POST /token -> { "token": "<signed JWT>" }
|
|
Signs a LiveKit access token with HS256 using the API key/secret from env.
|
|
|
|
The token carries a roomConfig claim requesting the voice-assistant agent, so
|
|
LiveKit dispatches the agent when the participant joins. Without this, the
|
|
auto-created room would get no agent at all.
|
|
|
|
Runs as a separate supervisord process; nginx proxies /token to it.
|
|
"""
|
|
import base64
|
|
import hashlib
|
|
import hmac
|
|
import json
|
|
import os
|
|
import time
|
|
import uuid
|
|
|
|
from http.server import BaseHTTPRequestHandler, HTTPServer
|
|
|
|
API_KEY = os.environ.get("LIVEKIT_API_KEY", "devkey")
|
|
API_SECRET = os.environ.get("LIVEKIT_API_SECRET", "devsecret")
|
|
AGENT_NAME = os.environ.get("VOICE_AGENT_NAME", "voice-assistant")
|
|
|
|
|
|
def b64url(data: bytes) -> str:
|
|
return base64.urlsafe_b64encode(data).rstrip(b"=").decode()
|
|
|
|
|
|
def make_token(room_name: str, identity: str) -> str:
|
|
now = int(time.time())
|
|
header = {"alg": "HS256", "typ": "JWT"}
|
|
payload = {
|
|
"iss": API_KEY,
|
|
"sub": identity,
|
|
"nbf": now - 5,
|
|
"exp": now + 3600,
|
|
"jti": str(uuid.uuid4()),
|
|
"identity": identity,
|
|
"video": {
|
|
"roomJoin": True,
|
|
"room": room_name,
|
|
"canPublish": True,
|
|
"canSubscribe": True,
|
|
"canPublishData": True,
|
|
},
|
|
"roomConfig": {
|
|
"agents": [{"agentName": AGENT_NAME}],
|
|
},
|
|
}
|
|
h = b64url(json.dumps(header).encode())
|
|
p = b64url(json.dumps(payload).encode())
|
|
signing_input = f"{h}.{p}".encode()
|
|
sig = hmac.new(API_SECRET.encode(), signing_input, hashlib.sha256).digest()
|
|
return f"{h}.{p}.{b64url(sig)}"
|
|
|
|
|
|
class Handler(BaseHTTPRequestHandler):
|
|
def do_POST(self):
|
|
if self.path != "/token":
|
|
self.send_response(404)
|
|
self.end_headers()
|
|
return
|
|
|
|
length = int(self.headers.get("Content-Length", 0))
|
|
body = json.loads(self.rfile.read(length) or b"{}")
|
|
room_name = "voice-room"
|
|
identity = body.get("identity") or f"user-{uuid.uuid4().hex[:8]}"
|
|
|
|
token = make_token(room_name, identity)
|
|
resp = json.dumps({"token": token}).encode()
|
|
self.send_response(200)
|
|
self.send_header("Content-Type", "application/json")
|
|
self.send_header("Content-Length", str(len(resp)))
|
|
self.end_headers()
|
|
self.wfile.write(resp)
|
|
|
|
def log_message(self, format, *args):
|
|
pass # silence request logging
|
|
|
|
|
|
if __name__ == "__main__":
|
|
server = HTTPServer(("127.0.0.1", 8091), Handler)
|
|
print("token endpoint listening on 127.0.0.1:8091")
|
|
server.serve_forever()
|