Files
BizGaze_Remote/mobile/plugins/native-call/ios/Sources/NativeCallPlugin/NativeCallPlugin.swift
T
Sravan 149e32b8d8 Native video Increment 2a: publish local camera + self-view
Wire the camera button on native calls to the plugin instead of a
"not available" toast. New NativeCall.setCamera({on}) calls LiveKit
localParticipant.setCamera(enabled:) so the iOS user's camera is
published to the room — every web/desktop peer renders it via their
existing SFU subscription. Locally the plugin shows a small rounded
self-view (VideoView) pinned top-right over the WebView.

APIs verified against client-sdk-swift 2.15.3 source: setCamera ->
LocalTrackPublication?, TrackPublication.track, VideoView(.track/.layoutMode),
CameraCaptureOptions(position:.front). Front camera only for now.

Rendering the OTHER participants as native tiles synced to the web
meeting grid is Increment 2b (the fragile part) — next build. Until the
new IPA ships, the web branch falls back to an "update the app" toast.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-08-05 23:10:19 +05:30

383 lines
20 KiB
Swift

import Foundation
import Capacitor
import PushKit
import CallKit
import AVFoundation
import LiveKit // SPM product name is 'LiveKit' (Package.swift). (The old CocoaPods module was 'LiveKitClient'.)
// Native calling for Biz Connect (iOS). Registered by `cap sync` as window.Capacitor.Plugins.NativeCall.
//
// ARCHITECTURE (native media):
// * PushKit: registers for VoIP pushes, reports the VoIP token to JS (-> /api/v1/devices 'ios-voip').
// * CallKit: incoming VoIP push -> full-screen system ring (works when force-killed). The CallKit call
// stays ACTIVE for the whole call (that's what foregrounds/unlocks the app on answer and keeps the call
// alive in the background).
// * LiveKit: the call MEDIA runs NATIVELY via the LiveKit iOS SDK — so the mic works with an active CallKit
// call (WebKit's WebRTC could not) and audio survives backgrounding. The VoIP payload carries the
// LiveKit url+token so we can connect immediately on answer, even from a killed state; outgoing calls get
// the token from the WebView via reportOutgoingCall(). The WebView is UI only for native calls (it must
// NOT also join the room — LiveKit allows one connection per identity).
@objc(NativeCallPlugin)
public class NativeCallPlugin: CAPPlugin, CAPBridgedPlugin, PKPushRegistryDelegate, CXProviderDelegate {
public let identifier = "NativeCallPlugin"
public let jsName = "NativeCall"
public let pluginMethods: [CAPPluginMethod] = [
CAPPluginMethod(name: "getToken", returnType: CAPPluginReturnPromise),
CAPPluginMethod(name: "reportOutgoingCall", returnType: CAPPluginReturnPromise),
CAPPluginMethod(name: "reportIncomingCall", returnType: CAPPluginReturnPromise),
CAPPluginMethod(name: "setMuted", returnType: CAPPluginReturnPromise),
CAPPluginMethod(name: "setCamera", returnType: CAPPluginReturnPromise),
CAPPluginMethod(name: "endCall", returnType: CAPPluginReturnPromise)
]
private var pushRegistry: PKPushRegistry?
private var provider: CXProvider?
private let callController = CXCallController()
private var voipToken: String = ""
// callUUID -> the call's data (room, kind, callerId, livekitUrl, livekitToken, …).
private var calls: [UUID: [String: Any]] = [:]
// Calls we've already ended locally — so a LATE cancel push doesn't re-report (which briefly re-rang).
private var endedCalls = Set<UUID>()
private var room: Room?
private var activeUUID: UUID?
// Native video (Increment 2a): the local camera is published to the room (so everyone else sees this
// user) and mirrored into a small self-view (PiP) drawn over the WebView. Rendering the OTHER
// participants as native tiles synced to the web meeting grid is Increment 2b. VideoView is a UIKit
// view — only ever touched on the main thread (helpers below dispatch there).
private var localVideoView: VideoView?
override public func load() {
let config = CXProviderConfiguration(localizedName: "Biz Connect")
config.supportsVideo = true
config.maximumCallGroups = 1
config.maximumCallsPerCallGroup = 1
config.supportedHandleTypes = [.generic]
let p = CXProvider(configuration: config)
p.setDelegate(self, queue: nil)
provider = p
let registry = PKPushRegistry(queue: .main)
registry.delegate = self
registry.desiredPushTypes = [.voIP]
pushRegistry = registry
// CallKit audio coordination (LiveKit 2.15+, pinned to the git tag in ios-patch.sh). LiveKit's automatic
// AVAudioSession config RACES CallKit's own activation → intermittent dead mic / no audio + the output
// route only settling once audio flows ("speaker turns on late"). Fix: turn auto-config OFF and keep the
// engine OFF; we configure the session and enable the engine ONLY in didActivate.
AudioManager.shared.audioSession.isAutomaticConfigurationEnabled = false
try? AudioManager.shared.setEngineAvailability(.none)
}
// MARK: - LiveKit media
private func connectRoom(url: String, token: String) {
guard !url.isEmpty, !token.isEmpty else { return }
// Ask for mic permission now (we still connect MUTED). If it stays "undetermined", enabling the audio
// engine in didActivate can block on first use — determining it up front avoids that.
AVAudioSession.sharedInstance().requestRecordPermission { _ in }
let old = room
let r = Room()
room = r
Task { [weak self] in
await old?.disconnect() // drop any previous/stale connection so we never leave DUPLICATE participants
do {
try await r.connect(url: url, token: token)
// House rule: answer MUTED. Not enabling the mic here means nothing is captured/published
// until the user taps Mic in the meeting UI (→ setMuted(false) → setMicrophone(true)), which
// is also when iOS asks for mic permission. Playback (hearing others) is unaffected.
try await r.localParticipant.setMicrophone(enabled: false)
self?.notifyListeners("callConnected", data: ["ok": true])
} catch {
self?.notifyListeners("callError", data: ["error": String(describing: error)])
}
}
}
private func disconnectRoom() {
let r = room
room = nil
Task { await r?.disconnect() }
hideSelfView()
}
// MARK: - Native video (local self-view)
// Show the local camera as a small rounded self-view pinned to the top-right safe area, above the WebView.
// Increment 2b will render the REMOTE participants as native views synced to the web meeting tiles.
private func showSelfView(track: VideoTrack?) {
DispatchQueue.main.async { [weak self] in
guard let self = self, let track = track, let host = self.bridge?.viewController?.view else { return }
let vv = self.localVideoView ?? VideoView()
vv.layoutMode = .fill // fill the PiP box (crop) instead of letterboxing
vv.track = track
if vv.superview == nil {
vv.backgroundColor = .black
vv.clipsToBounds = true
vv.layer.cornerRadius = 10
vv.translatesAutoresizingMaskIntoConstraints = false
host.addSubview(vv)
NSLayoutConstraint.activate([
vv.widthAnchor.constraint(equalToConstant: 96),
vv.heightAnchor.constraint(equalToConstant: 132),
vv.topAnchor.constraint(equalTo: host.safeAreaLayoutGuide.topAnchor, constant: 16),
vv.trailingAnchor.constraint(equalTo: host.safeAreaLayoutGuide.trailingAnchor, constant: -12),
])
}
self.localVideoView = vv
}
}
private func hideSelfView() {
DispatchQueue.main.async { [weak self] in
self?.localVideoView?.removeFromSuperview()
self?.localVideoView = nil
}
}
// Route call audio to the LOUDSPEAKER when we'd otherwise be on the quiet earpiece. Guarded so a connected
// wired/Bluetooth headset (any non-receiver route) still wins. Re-asserted on mute toggles because enabling
// the mic can flip the route back to the earpiece.
private func preferSpeaker() {
let s = AVAudioSession.sharedInstance()
if s.currentRoute.outputs.contains(where: { $0.portType == .builtInReceiver }) {
try? s.overrideOutputAudioPort(.speaker)
}
}
// MARK: - JS-callable methods
@objc func getToken(_ call: CAPPluginCall) { call.resolve(["token": voipToken]) }
// Outgoing call from the web app: start a CallKit outgoing call AND connect the LiveKit room natively.
@objc func reportOutgoingCall(_ call: CAPPluginCall) {
guard let uuidStr = call.getString("callUUID"), let uuid = UUID(uuidString: uuidStr) else {
call.reject("callUUID required"); return
}
let url = call.getString("url") ?? ""
let token = call.getString("token") ?? ""
let video = call.getBool("hasVideo") ?? false
calls[uuid] = ["room": call.getString("room") ?? "", "kind": call.getString("kind") ?? "dm",
"livekitUrl": url, "livekitToken": token]
activeUUID = uuid
let handle = CXHandle(type: .generic, value: call.getString("peerName") ?? "Call")
let start = CXStartCallAction(call: uuid, handle: handle)
start.isVideo = video
callController.request(CXTransaction(action: start)) { [weak self] error in
if let error = error { call.reject(error.localizedDescription); return }
self?.connectRoom(url: url, token: token)
// Start muted (house rule) — also reflect it on the CallKit system call screen.
self?.callController.request(CXTransaction(action: CXSetMutedCallAction(call: uuid, muted: true))) { _ in }
self?.provider?.reportOutgoingCall(with: uuid, connectedAt: Date())
call.resolve()
}
}
// Ring CallKit from a WEBSOCKET call event (a 2nd path alongside the VoIP push). When the app is open the
// WS is connected and reliable, but the VoIP push can be delayed/dropped → "sometimes it doesn't ring".
// Deduped by UUID: if the VoIP push already reported this call, this is a no-op (and vice-versa).
@objc func reportIncomingCall(_ call: CAPPluginCall) {
guard let uuidStr = call.getString("callUUID"), let uuid = UUID(uuidString: uuidStr) else {
call.reject("callUUID required"); return
}
// Already handled (ended, ringing, or active) → don't re-report (CallKit would reject a dup anyway).
if endedCalls.contains(uuid) || calls[uuid] != nil || activeUUID == uuid { call.resolve(); return }
let callerName = call.getString("callerName") ?? call.getString("groupName") ?? "Incoming call"
let hasVideo = call.getBool("hasVideo") ?? false
calls[uuid] = [
"callUUID": uuidStr, "room": call.getString("room") ?? "", "kind": call.getString("kind") ?? "dm",
"callerId": call.getString("callerId") ?? "", "callerName": callerName,
"groupId": call.getString("groupId") ?? "", "groupName": call.getString("groupName") ?? "",
"hasVideo": hasVideo, "livekitUrl": call.getString("url") ?? "", "livekitToken": call.getString("token") ?? "",
]
let update = CXCallUpdate()
update.remoteHandle = CXHandle(type: .generic, value: callerName)
update.localizedCallerName = callerName
update.hasVideo = hasVideo
update.supportsHolding = false; update.supportsGrouping = false; update.supportsUngrouping = false
provider?.reportNewIncomingCall(with: uuid, update: update) { _ in }
call.resolve()
}
@objc func setMuted(_ call: CAPPluginCall) {
let muted = call.getBool("muted") ?? false
// Drive mute THROUGH CallKit so the system call screen and the in-app meeting UI stay in sync (the
// CXSetMutedCallAction handler does the actual setMicrophone). Fall back to a direct call if somehow
// there's no active CallKit call.
if let uuid = activeUUID {
callController.request(CXTransaction(action: CXSetMutedCallAction(call: uuid, muted: muted))) { _ in }
} else {
let r = room
Task { try? await r?.localParticipant.setMicrophone(enabled: !muted) }
}
call.resolve()
}
// Native video (Increment 2a): enable/disable the local camera. Publishing it makes this user's video
// appear for everyone else (their web/desktop clients render it via their own SFU subscription); locally
// we mirror it into a small self-view. Seeing the OTHER participants' video (native tiles) is Increment 2b.
// Front camera only for now.
@objc func setCamera(_ call: CAPPluginCall) {
guard let r = room else { call.reject("no active call"); return }
let on = call.getBool("on") ?? false
Task { [weak self] in
do {
let pub = try await r.localParticipant.setCamera(
enabled: on,
captureOptions: CameraCaptureOptions(position: .front))
if on { self?.showSelfView(track: pub?.track as? VideoTrack) } else { self?.hideSelfView() }
call.resolve(["on": on])
} catch {
call.reject("camera failed: \(String(describing: error))")
}
}
}
// End the CallKit call (remote hung up / user ended from the web UI). No callUUID -> end all.
@objc func endCall(_ call: CAPPluginCall) {
if let uuidStr = call.getString("callUUID"), let uuid = UUID(uuidString: uuidStr) {
requestEnd(uuid)
} else {
for uuid in calls.keys { requestEnd(uuid) }
if let a = activeUUID { requestEnd(a) }
}
call.resolve()
}
private func requestEnd(_ uuid: UUID) {
callController.request(CXTransaction(action: CXEndCallAction(call: uuid))) { _ in }
calls.removeValue(forKey: uuid)
endedCalls.insert(uuid)
}
// MARK: - PushKit (VoIP)
public func pushRegistry(_ registry: PKPushRegistry, didUpdate pushCredentials: PKPushCredentials, for type: PKPushType) {
let token = pushCredentials.token.map { String(format: "%02x", $0) }.joined()
voipToken = token
notifyListeners("voipToken", data: ["token": token])
}
public func pushRegistry(_ registry: PKPushRegistry, didInvalidatePushTokenFor type: PKPushType) {
voipToken = ""
}
// Incoming VoIP push. iOS 13+: we MUST reportNewIncomingCall for EVERY push before completion(), or the
// app is terminated.
public func pushRegistry(_ registry: PKPushRegistry, didReceiveIncomingPushWith payload: PKPushPayload, for type: PKPushType, completion: @escaping () -> Void) {
var dict: [String: Any] = [:]
for (k, v) in payload.dictionaryPayload { if let ks = k as? String { dict[ks] = v } }
let uuid = UUID(uuidString: (dict["callUUID"] as? String) ?? "") ?? UUID()
// CANCEL: caller hung up / declined / timed out. iOS requires a reported call per push, but blindly
// reporting a NEW incoming call is what caused the "rings back for a second" blip on a call we've
// already handled. So:
if (dict["type"] as? String) == "cancel" {
// iOS 13+ TERMINATES the app if a VoIP push doesn't result in reportNewIncomingCall before
// completion() — that's the crash after several calls (my earlier "no-blip" optimization SKIPPED
// the report for known/ended calls, which iOS kills for). So ALWAYS report, then immediately end:
// * uuid already ringing/active → the report errors harmlessly (NO second ring), reportCall ends it.
// * late/duplicate cancel (done) → a brief, unavoidable blip (acceptable; a crash is not).
let u = CXCallUpdate()
u.remoteHandle = CXHandle(type: .generic, value: (dict["callerName"] as? String) ?? "Call")
let wasActive = (activeUUID == uuid)
var ev = calls[uuid] ?? [:]; ev["callUUID"] = uuid.uuidString
calls.removeValue(forKey: uuid)
endedCalls.insert(uuid)
if wasActive { disconnectRoom(); activeUUID = nil }
provider?.reportNewIncomingCall(with: uuid, update: u) { [weak self] _ in
self?.provider?.reportCall(with: uuid, endedAt: Date(), reason: .remoteEnded)
if wasActive { self?.notifyListeners("endCall", data: ev) } // active call cancelled → leave the meeting
completion()
}
return
}
let callerName = (dict["callerName"] as? String) ?? (dict["groupName"] as? String) ?? "Incoming call"
let hasVideo = (dict["hasVideo"] as? Bool) ?? false
calls[uuid] = dict
let update = CXCallUpdate()
update.remoteHandle = CXHandle(type: .generic, value: callerName)
update.localizedCallerName = callerName
update.hasVideo = hasVideo
update.supportsHolding = false
update.supportsGrouping = false
update.supportsUngrouping = false
provider?.reportNewIncomingCall(with: uuid, update: update) { _ in completion() }
}
// MARK: - CXProviderDelegate
public func providerDidReset(_ provider: CXProvider) {
disconnectRoom()
calls.removeAll(); endedCalls.removeAll(); activeUUID = nil
}
public func provider(_ provider: CXProvider, perform action: CXAnswerCallAction) {
let uuid = action.callUUID
let data = calls[uuid] ?? [:]
activeUUID = uuid
action.fulfill()
// Keep the CallKit call ACTIVE (foregrounds the app + keeps the call alive). Connect the LiveKit room
// NATIVELY so the mic works with the active CallKit call and audio survives backgrounding.
connectRoom(url: (data["livekitUrl"] as? String) ?? "", token: (data["livekitToken"] as? String) ?? "")
// We answer muted (house rule) — reflect that on the CallKit system call screen (the mic button there
// showed unmuted before, even though we were functionally muted).
callController.request(CXTransaction(action: CXSetMutedCallAction(call: uuid, muted: true))) { _ in }
var ev = data; ev["callUUID"] = uuid.uuidString
// Answering from a KILLED/locked state launches the app — the WebView's JS listener may not be attached
// yet, so retain the event until it is. Without this the "answered" signal is lost, the server's
// unanswered timer fires, and the call is cancelled ~40s after pickup.
notifyListeners("answerCall", data: ev, retainUntilConsumed: true)
}
public func provider(_ provider: CXProvider, perform action: CXEndCallAction) {
var data: [String: Any] = calls[action.callUUID] ?? [:]
data["callUUID"] = action.callUUID.uuidString
disconnectRoom()
notifyListeners("endCall", data: data)
calls.removeValue(forKey: action.callUUID)
endedCalls.insert(action.callUUID)
if activeUUID == action.callUUID { activeUUID = nil }
action.fulfill()
}
public func provider(_ provider: CXProvider, perform action: CXStartCallAction) {
provider.reportOutgoingCall(with: action.callUUID, startedConnectingAt: Date())
action.fulfill()
}
public func provider(_ provider: CXProvider, perform action: CXSetMutedCallAction) {
let r = room
Task { [weak self] in
try? await r?.localParticipant.setMicrophone(enabled: !action.isMuted)
self?.preferSpeaker() // toggling the mic can flip the route back to the earpiece — re-assert speaker
}
notifyListeners("setMuted", data: ["callUUID": action.callUUID.uuidString, "muted": action.isMuted])
action.fulfill()
}
// CallKit owns the AVAudioSession lifecycle. Since LiveKit auto-config is OFF, configure the session HERE —
// when CallKit activates it — and enable LiveKit's audio engine. This is the fix for the intermittent
// dead mic / no-audio and late speaker routing. Don't call setActive(true): CallKit already activated it.
public func provider(_ provider: CXProvider, didActivate audioSession: AVAudioSession) {
do {
// Route to the LOUDSPEAKER by default (earpiece was the .voiceChat default). .videoChat +
// .defaultToSpeaker prefers the speaker while still letting wired/Bluetooth headsets win.
try audioSession.setCategory(.playAndRecord, mode: .videoChat,
options: [.defaultToSpeaker, .allowBluetooth, .allowBluetoothA2DP])
try AudioManager.shared.setEngineAvailability(.default)
preferSpeaker() // belt-and-braces: if we still landed on the earpiece, force the speaker
let route = audioSession.currentRoute.outputs.first?.portType.rawValue ?? "none"
notifyListeners("audioActivated", data: ["ok": true, "route": route])
} catch {
notifyListeners("audioActivated", data: ["ok": false, "error": String(describing: error)])
}
}
public func provider(_ provider: CXProvider, didDeactivate audioSession: AVAudioSession) {
try? AudioManager.shared.setEngineAvailability(.none)
notifyListeners("audioDeactivated", data: ["ok": true])
}
}