mirror of
https://github.com/permissionlesstech/bitchat.git
synced 2026-07-26 09:05:20 +00:00
Live push-to-talk voice for DMs (streams while you talk, voice note as fallback) (#1403)
* Live push-to-talk voice for DMs: stream while you talk, voice note as fallback Holding the mic in a DM now streams AAC frames live over the Noise session (walkie-talkie style, ~0.5s mouth-to-ear at one hop) while recording the same audio as a normal voice note. On release the note ships through the existing fileTransfer pipeline; receivers that heard the live stream absorb it silently into the same bubble (matched by the burst ID embedded in the file name), so reliability comes for free and nobody sees duplicates. Protocol: - NoisePayloadType.voiceFrame = 0x08 carrying VoiceBurstPacket (burstID + seq + START/data/END/CANCELED, length-prefixed AAC frames) - 210-byte burst-content budget keeps each Noise packet inside the 256-byte padding bucket: one BLE frame, never the fragment scheduler - fire-and-forget: frames are dropped (never queued) without an established session; live is only offered when the peer is mesh-reachable Receive: - ChatLiveVoiceCoordinator assembles bursts (jitter-ordered, 0.5s gap skip, 3s idle end, flood/size caps), persists progressively as ADTS .aac so even a partial burst is a replayable bubble - live autoplay only when the conversation is on screen, app active, and the new app-info "live voice messages" toggle is on (also gates live sending) - one-playback-at-a-time via a shared ExclusivePlayback slot Capture: - PTTCaptureEngine taps AVAudioEngine, dual-encodes: live AAC frames + the finalized .m4a (same 16kHz/mono/16kbps settings as VoiceRecorder) - VoiceRecordingViewModel now drives a pluggable VoiceCaptureSession; the composer HUD shows a pulsing LIVE treatment when streaming Includes the push-to-talk design doc, 6 new localization keys across all 29 locales, and unit tests for framing, packetizer budget, ADTS output, codec round-trip, and the assembly/absorb lifecycle. Public-mesh PTT (MessageType 0x29) lands separately on top of this. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * PTT follow-ups from review + field test: peer-ID normalization, toggle gates inbound, drop-path diagnostics Codex review fixes (#1403): - makeVoiceCaptureSession normalizes the selected peer with toShort() before the reachability/session checks and binds the send target to that same routing ID — a conversation selected under the stable 64-hex Noise key no longer silently falls back to a classic note while the short-ID session is established - the live-voice toggle now gates inbound bursts too: off means classic-notes-only in both directions (no live bubble, partial file, or early notification; the finalized note still arrives), with a test Field-test diagnostics (first device run: DM frames decrypted but no bubble appeared, with no log evidence of which guard dropped them): - coordinator logs undecodable frames (size + hex prefix) and blocked drops - makeAssembly logs directory/file-handle failures instead of returning nil silently - PTTLiveVoiceSession logs capture start and finish (packet/frame/duration counts); PTTCaptureEngine logs engine start success/failure with the input format; BLEService.sendVoiceFrame logs no-session drops Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> * Fix iPhone live-capture failure: dead input unit (AURemoteIO -10851, 0 Hz) Field testing showed the phone's live capture failing at mic enable with AURemoteIO -10851 and an input format of 0 Hz / 2 ch — an input unit bound to an earlier (playback-only or settling) audio session. The Mac, which has no session lifecycle, captured fine, which is why public bursts from the Mac worked while phone-side sends degraded from working (first hold) to sporadic to dead across holds. Three layers of defense: - PTTCaptureEngine recreates its AVAudioEngine on every start(), after the session is configured, so the input unit binds to the session that is active now; a dead input (0 Hz or 0 channels) is now a distinct, logged error instead of a silent setup failure - PTTLiveVoiceSession retries the capture start once after a 150 ms route-settle pause - VoiceRecordingViewModel falls back to the classic VoiceRecorder within the same hold if the live engine still cannot start — a route glitch now costs the live stream, never the voice note Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: jack <jackjackbits@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
jack
co-authored by
jack
Claude Fable 5
jack
Claude Fable 5
parent
6886035632
commit
eacd8f0750
@@ -0,0 +1,144 @@
|
||||
//
|
||||
// PTTBurstPlayer.swift
|
||||
// bitchat
|
||||
//
|
||||
// This is free and unencumbered software released into the public domain.
|
||||
// For more information, see <https://unlicense.org>
|
||||
//
|
||||
|
||||
import AVFoundation
|
||||
import BitLogger
|
||||
import Foundation
|
||||
|
||||
/// Plays one inbound live voice burst with a small jitter buffer.
|
||||
///
|
||||
/// Frames are decoded and scheduled back-to-back on an `AVAudioPlayerNode`;
|
||||
/// an underrun (missing/late packets) simply pauses output until the next
|
||||
/// buffer arrives, which self-heals timing without explicit silence
|
||||
/// insertion. Playback starts once `TransportConfig.pttJitterBufferSeconds`
|
||||
/// of audio is queued or `pttJitterDeadlineSeconds` has elapsed.
|
||||
@MainActor
|
||||
final class PTTBurstPlayer {
|
||||
private let engine = AVAudioEngine()
|
||||
private let node = AVAudioPlayerNode()
|
||||
private let decoder: PTTFrameDecoder
|
||||
|
||||
private var queuedBuffers: [AVAudioPCMBuffer] = []
|
||||
private var queuedDuration: TimeInterval = 0
|
||||
private var scheduledCount = 0
|
||||
private var engineStarted = false
|
||||
private var finished = false
|
||||
private var stopped = false
|
||||
private var deadlineTask: Task<Void, Never>?
|
||||
|
||||
private(set) var isPlaying = false
|
||||
|
||||
init?() {
|
||||
guard let format = PTTAudioFormat.pcmFormat, let decoder = PTTFrameDecoder() else { return nil }
|
||||
self.decoder = decoder
|
||||
engine.attach(node)
|
||||
engine.connect(node, to: engine.mainMixerNode, format: format)
|
||||
|
||||
deadlineTask = Task { [weak self] in
|
||||
try? await Task.sleep(nanoseconds: UInt64(TransportConfig.pttJitterDeadlineSeconds * 1_000_000_000))
|
||||
self?.startIfReady(force: true)
|
||||
}
|
||||
}
|
||||
|
||||
/// Decodes and queues frames (in burst order). Starts playback when the
|
||||
/// jitter buffer fills.
|
||||
func enqueue(_ frames: [Data]) {
|
||||
guard !stopped else { return }
|
||||
for frame in frames {
|
||||
guard let pcm = decoder.decode(frame) else { continue }
|
||||
if engineStarted {
|
||||
schedule(pcm)
|
||||
} else {
|
||||
queuedBuffers.append(pcm)
|
||||
queuedDuration += Double(pcm.frameLength) / PTTAudioFormat.sampleRate
|
||||
}
|
||||
}
|
||||
startIfReady(force: false)
|
||||
}
|
||||
|
||||
/// The burst ended: stop once everything scheduled has played out.
|
||||
func finishAfterDrain() {
|
||||
finished = true
|
||||
stopIfDrained()
|
||||
}
|
||||
|
||||
/// Immediate stop (cancel, another playback taking over, teardown).
|
||||
func stop() {
|
||||
guard !stopped else { return }
|
||||
stopped = true
|
||||
deadlineTask?.cancel()
|
||||
queuedBuffers = []
|
||||
if engineStarted {
|
||||
node.stop()
|
||||
engine.stop()
|
||||
}
|
||||
isPlaying = false
|
||||
VoiceNotePlaybackCoordinator.shared.deactivate(self)
|
||||
}
|
||||
|
||||
private func startIfReady(force: Bool) {
|
||||
guard !engineStarted, !stopped, !queuedBuffers.isEmpty else { return }
|
||||
guard force || queuedDuration >= TransportConfig.pttJitterBufferSeconds else { return }
|
||||
|
||||
#if os(iOS)
|
||||
do {
|
||||
let session = AVAudioSession.sharedInstance()
|
||||
try session.setCategory(.playback, mode: .spokenAudio, options: [.mixWithOthers])
|
||||
try session.setActive(true, options: [])
|
||||
} catch {
|
||||
SecureLogger.error("PTT playback session activation failed: \(error)", category: .session)
|
||||
}
|
||||
#endif
|
||||
|
||||
engine.prepare()
|
||||
do {
|
||||
try engine.start()
|
||||
} catch {
|
||||
SecureLogger.error("PTT playback engine failed to start: \(error)", category: .session)
|
||||
stopped = true
|
||||
return
|
||||
}
|
||||
engineStarted = true
|
||||
isPlaying = true
|
||||
VoiceNotePlaybackCoordinator.shared.activate(self)
|
||||
node.play()
|
||||
|
||||
let buffered = queuedBuffers
|
||||
queuedBuffers = []
|
||||
queuedDuration = 0
|
||||
for buffer in buffered {
|
||||
schedule(buffer)
|
||||
}
|
||||
}
|
||||
|
||||
private func schedule(_ buffer: AVAudioPCMBuffer) {
|
||||
scheduledCount += 1
|
||||
node.scheduleBuffer(buffer) { [weak self] in
|
||||
Task { @MainActor [weak self] in
|
||||
guard let self else { return }
|
||||
self.scheduledCount -= 1
|
||||
self.stopIfDrained()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private func stopIfDrained() {
|
||||
guard finished, scheduledCount <= 0 else { return }
|
||||
stop()
|
||||
}
|
||||
}
|
||||
|
||||
extension PTTBurstPlayer: ExclusivePlayback {
|
||||
/// A live stream can't meaningfully pause; yielding the floor stops it.
|
||||
/// The burst keeps assembling to file, so nothing is lost.
|
||||
nonisolated func pauseForExclusivity() {
|
||||
Task { @MainActor [weak self] in
|
||||
self?.stop()
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user