Plan 3 fix: GA turn_detection auto-create_response + reset state on WS reconnect

GA Realtime API requires create_response:true and interrupt_response:true
inside turn_detection — without them the model never auto-generates a
reply after VAD detects speech_stopped, so the relay idles out at 30s
with no assistant audio. Add both.

Client side: when the /device WS drops (Coolify rolling deploy, etc.),
Session.run_forever reconnects but the StateMachine kept whatever state
it was in — usually LISTENING, which permanently disables the wakeword.
Add StateMachine.force_idle() and a Callbacks.on_disconnected() hook;
main.py wires it to force the state back to IDLE on every disconnect.
Also harden Session's fire-and-forget send_* helpers to swallow
ConnectionClosed instead of bubbling up as unhandled task exceptions.

backend/Realtime/RealtimeEvents.cs

@@ -50,6 +50,11 @@ public static class RealtimeEvents
                             ["threshold"] = 0.5,
                             ["prefix_padding_ms"] = 300,
                             ["silence_duration_ms"] = 500,
+                            // GA requires both explicitly — without them the
+                            // model never auto-generates a reply after VAD
+                            // detects speech_stopped.
+                            ["create_response"] = true,
+                            ["interrupt_response"] = true,
                         },
                     },
                     ["output"] = new JsonObject