feat: consolidate iOS with API and web preserving history

ios/Sources/LiveKit/ConversationState.swift

@@ -0,0 +1,94 @@
+import Foundation
+import os
+
+enum ConversationPhase: String {
+    case idle
+    case connecting
+    case listening
+    case thinking
+    case speaking
+}
+
+/// Ports the web UI's `inferState` + EMA smoothing (app.js): mic/agent levels
+/// are smoothed with `prev * 0.6 + raw * 0.4`, thresholds are user > 0.035 and
+/// agent > 0.02. When remote audio ends, the state returns to listening
+/// (matching the current web reference at app.js:414-426) rather than becoming
+/// "thinking" forever.
+@MainActor
+final class ConversationStateModel: ObservableObject {
+    @Published private(set) var phase: ConversationPhase = .idle
+    @Published private(set) var micLevel: Double = 0
+    @Published private(set) var agentLevel: Double = 0
+    @Published private(set) var isThinkingChipVisible = false
+
+    static let userThreshold = 0.035
+    static let agentThreshold = 0.02
+    static let thinkingDelay: Duration = .seconds(2)
+
+    private var smoothedMic: Double = 0
+    private var smoothedAgent: Double = 0
+    private var lastTransition = Date()
+    private var chipTask: Task<Void, Never>?
+
+    func start() {
+        stop()
+        setPhase(.connecting)
+    }
+
+    func stop() {
+        chipTask?.cancel()
+        chipTask = nil
+        smoothedMic = 0
+        smoothedAgent = 0
+        micLevel = 0
+        agentLevel = 0
+        isThinkingChipVisible = false
+        setPhase(.idle)
+    }
+
+    func tick(localAudioLevel: Float, remoteAudioLevel: Float) {
+        guard phase != .idle else { return }
+        smoothedMic = smoothedMic * 0.6 + Double(localAudioLevel) * 0.4
+        smoothedAgent = smoothedAgent * 0.6 + Double(remoteAudioLevel) * 0.4
+        micLevel = smoothedMic
+        agentLevel = smoothedAgent
+
+        let userSpeaking = smoothedMic > Self.userThreshold
+        let next: ConversationPhase
+        if smoothedAgent > Self.agentThreshold {
+            next = .speaking
+        } else if userSpeaking {
+            next = .listening
+        } else {
+            // Both silent: return to listening. The previous implementation
+            // converted speaking → thinking forever, leaving the UI apparently
+            // frozen after an agent response (matches current web reference).
+            next = .listening
+        }
+        setPhase(next)
+    }
+
+    private func setPhase(_ next: ConversationPhase) {
+        guard next != phase else { return }
+        let old = phase
+        logger.log("state \(old.rawValue, privacy: .public) -> \(next.rawValue, privacy: .public)")
+        phase = next
+        lastTransition = Date()
+        if next == .thinking {
+            chipTask?.cancel()
+            chipTask = Task { [weak self] in
+                try? await Task.sleep(for: Self.thinkingDelay)
+                guard !Task.isCancelled, let self else { return }
+                if self.phase == .thinking {
+                    self.isThinkingChipVisible = true
+                }
+            }
+        } else {
+            chipTask?.cancel()
+            chipTask = nil
+            isThinkingChipVisible = false
+        }
+    }
+}
+
+private let logger = Logger(subsystem: "dev.shane.voice", category: "state")