feat: LiveKit voice session, control channel, transcripts (Phase 2)

- VoiceSession: token->connect with fresh-room retry on timeout, agent
  discovery, agent_ready wait, mic enable/mute, text send over lk.chat
- ControlChannel: outbound set_voice/set_model/get_models/set_mode/
  media_state; inbound agent_ready/models/model_changed/task_event
- TranscriptHandler: transcription segments + transcript topic finals,
  partial/final dedupe per role
- ConversationView/OrbView: status orb, mic/text-mode toggles, composer
- ServerConfig: plain ws:// signaling for private IPs (self-signed TLS
  not injectable into SDK WebSocket); Info.plist local networking

Sources/LiveKit/AgentMonitor.swift

@@ -0,0 +1,38 @@
+import Foundation
+import LiveKit
+
+/// Observes the agent participant's audio level for UI state inference.
+@MainActor
+final class AgentMonitor: ObservableObject {
+    @Published private(set) var agentSpeaking = false
+    @Published private(set) var localSpeaking = false
+
+    private let session: VoiceSession
+    private var pollTask: Task<Void, Never>?
+
+    init(session: VoiceSession) {
+        self.session = session
+    }
+
+    func start() {
+        stop()
+        pollTask = Task { [weak self] in
+            while !Task.isCancelled {
+                guard let self else { return }
+                let remote = self.session.room.remoteParticipants.values.first(where: {
+                    $0.kind == .agent || $0.identity?.stringValue == "voice-assistant"
+                })
+                self.agentSpeaking = remote?.isSpeaking ?? false
+                self.localSpeaking = self.session.room.localParticipant.isSpeaking
+                try? await Task.sleep(for: .milliseconds(250))
+            }
+        }
+    }
+
+    func stop() {
+        pollTask?.cancel()
+        pollTask = nil
+        agentSpeaking = false
+        localSpeaking = false
+    }
+}