Add Athena WebRTC bridge for OpenClaw Talk

integrations/openclaw-athena-talk/README.md

@@ -1,7 +1,8 @@
 # Athena Local Talk for OpenClaw
 
-This private OpenClaw provider connects browser/Desktop Talk to the existing
-Athena speech stack:
+This private OpenClaw provider connects Gateway-relay Talk sessions to the
+existing Athena speech stack. An experimental browser WebRTC path is available
+through the separate `services/athena-realtime-voice` service:
 
 1. local VAD collects a spoken utterance,
 2. Athena Whisper transcribes it,
@@ -9,8 +10,8 @@ Athena speech stack:
    tools,
 4. Athena Qwen3-TTS returns PCM audio to the Talk client.
 
-Long replies are synthesized incrementally. The first short phrase starts
-playing as soon as it is ready while the next phrase is generated in parallel.
+The older `gateway-relay` path synthesizes long replies incrementally. The
+experimental WebRTC path currently synthesizes each agent reply as one clip.
 
 The provider intentionally uses half-duplex audio: microphone input is paused
 while a response is being transcribed, generated, synthesized, or played. This
@@ -30,11 +31,12 @@ Recommended `talk.realtime` configuration:
   "model": "athena-local",
   "speakerVoice": "alloy",
   "mode": "realtime",
-  "transport": "gateway-relay",
+  "transport": "webrtc",
   "brain": "agent-consult",
   "providers": {
     "athena-talk": {
       "modelProvider": "llama-cpp",
+      "realtimeUpstreamUrl": "http://192.168.1.212:8090/v1/realtime/calls",
       "language": "de",
       "vadThreshold": 0.018,
       "silenceDurationMs": 750,
@@ -59,4 +61,32 @@ openclaw plugins inspect athena-talk --runtime --json
 Restart the gateway once if the installation does not trigger an automatic
 reload. The managed plugin copy is stored in OpenClaw's persistent data
 directory, so normal image updates do not remove it. Hermes remains unchanged;
-both clients reuse the same OpenAI-compatible Athena speech endpoints.
+the provider reuses the same OpenAI-compatible Athena speech endpoints.
+
+## Browser and Mac app status (OpenClaw 2026.9.4)
+
+The original 1.0.0 provider implements `gateway-relay` only. A direct Gateway call to
+`talk.session.create` with `mode=realtime`, `transport=gateway-relay`, and
+`brain=agent-consult` creates an Athena Talk session successfully. The Control
+UI and Mac app first call `talk.client.create`, which rejects that transport
+with `talk.client.create is client-owned; use talk.session.create for
+gateway-relay`. Their fallback to `talk.session.create` is not observed in the
+affected installation, so the UI still reports a misleading authentication
+error. A successfully created test session is tied to its Gateway connection
+and disappears when that connection closes.
+
+The 2026.9.4 browser `provider-websocket` client accepts only the built-in
+`google-live-bidi` protocol and validates the Google WebSocket hostname.
+Version 1.1.0 adds a separate `webrtc` browser session using the UI's
+OpenAI-style WebRTC protocol and the Athena realtime voice bridge. The plugin
+proxies the SDP offer through the existing OpenClaw HTTPS origin. On
+2026-09-16, the installed plugin created a browser session successfully; a
+synthetic spoken request traversed the real OpenClaw offer route, private
+WireGuard media connection, Athena Whisper, and Qwen3-TTS and returned audio.
+The installed browser code also recognizes the bridge's
+`openclaw_agent_consult` call. A real UI microphone-to-agent-to-speaker call
+has **not** yet been observed, so this remains experimental. The Mac setting
+“Echtzeitweiterleitung über Gateway verwenden” must be off for the browser-owned
+WebRTC path. `gateway-relay` remains available as a reversible fallback. Never
+select `provider-websocket` for this service. See
+`services/athena-realtime-voice/README.md` for setup and limits.