feat(audio): end-to-end 5.1/7.1 surround across the native path + all clients

Adds negotiated 5.1/7.1 surround to the punktfunk/1 protocol and every client
(previously stereo-only):

- core: new shared `audio` layout table (LAYOUT_51/71 + identity multistream
  mapping, canonical wire order FL FR FC LFE RL RR SL SR); Hello/Welcome
  `audio_channels` negotiation via the trailing-byte back-compat pattern (old
  peers fall back to stereo); C-ABI `punktfunk_connect_ex6`,
  `punktfunk_connection_audio_channels`, and in-core multistream decode
  `punktfunk_connection_next_audio_pcm` for embedders without a multistream
  Opus decoder. Real-libopus channel-identity round-trip test.
- host: native audio thread captures + Opus-(multi)stream-encodes at the
  negotiated count (with a cross-session cached-capturer channel-mismatch fix);
  GameStream surround unified onto the safe `opus::MSEncoder`, dropping
  `audiopus_sys` (~4 unsafe blocks) and un-gating Windows GameStream surround;
  WASAPI loopback capture relaxed to 2/6/8 with the correct dwChannelMask.
- clients: Linux (PipeWire), Windows (WASAPI), Android (AAudio) decode via
  `opus::MSDecoder` + render multichannel; Apple decodes in-core to PCM →
  AVAudioEngine with an explicit wire-order channel layout; each gains a
  Stereo/5.1/7.1 setting. `punktfunk-probe --audio-channels N` is the headless
  validator.

Verified on Linux: core/host/linux/probe test suites + the Android Rust
(cargo-ndk) build, clippy -D warnings, and rustfmt all green. Windows/Apple
builds, all on-glass checks, and the live native loopback are pending (CI / a
free box).

Also lands the concurrent in-tree HEVC 4:4:4 host work (PUNKTFUNK_444): it
shares the same touched files (quic.rs, punktfunk1.rs, encode/*, ...) and so
cannot be committed separately from the surround changes.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

clients/android/app/src/main/kotlin/io/unom/punktfunk/ConnectScreen.kt

@@ -163,7 +163,7 @@ fun ConnectScreen(settings: Settings, onConnected: (Long) -> Unit) {
                     targetHost, targetPort, w, h, hz,
                     id.certPem, id.privateKeyPem, pinHex ?: "",
                     settings.bitrateKbps, settings.compositor, gamepadPref,
-                    hdrEnabled,
+                    hdrEnabled, settings.audioChannels,
                 )
             }
             connecting = false

clients/android/app/src/main/kotlin/io/unom/punktfunk/Settings.kt

@@ -16,6 +16,9 @@ data class Settings(
     val bitrateKbps: Int = 0,
     val compositor: Int = 0,
     val gamepad: Int = 0,
+    /** Requested audio channel count: 2 (stereo), 6 (5.1) or 8 (7.1). The host clamps to what it
+     * can capture; the resolved count drives the decoder + AAudio layout. */
+    val audioChannels: Int = 2,
     val micEnabled: Boolean = false,
     /** Show the live stats overlay (FPS / throughput / latency) during a stream. */
     val statsHudEnabled: Boolean = true,
@@ -39,6 +42,7 @@ class SettingsStore(context: Context) {
         bitrateKbps = prefs.getInt(K_BITRATE, 0),
         compositor = prefs.getInt(K_COMPOSITOR, 0),
         gamepad = prefs.getInt(K_GAMEPAD, 0),
+        audioChannels = prefs.getInt(K_AUDIO_CH, 2),
         micEnabled = prefs.getBoolean(K_MIC, false),
         statsHudEnabled = prefs.getBoolean(K_HUD, true),
         trackpadMode = prefs.getBoolean(K_TRACKPAD, true),
@@ -52,6 +56,7 @@ class SettingsStore(context: Context) {
             .putInt(K_BITRATE, s.bitrateKbps)
             .putInt(K_COMPOSITOR, s.compositor)
             .putInt(K_GAMEPAD, s.gamepad)
+            .putInt(K_AUDIO_CH, s.audioChannels)
             .putBoolean(K_MIC, s.micEnabled)
             .putBoolean(K_HUD, s.statsHudEnabled)
             .putBoolean(K_TRACKPAD, s.trackpadMode)
@@ -65,6 +70,7 @@ class SettingsStore(context: Context) {
         const val K_BITRATE = "bitrate_kbps"
         const val K_COMPOSITOR = "compositor"
         const val K_GAMEPAD = "gamepad"
+        const val K_AUDIO_CH = "audio_channels"
         const val K_MIC = "mic_enabled"
         const val K_HUD = "stats_hud_enabled"
         const val K_TRACKPAD = "trackpad_mode"
@@ -133,6 +139,13 @@ val REFRESH_OPTIONS = listOf(
     240 to "240 Hz",
 )
 
+/** (channel count, label). 2 = stereo (default), 6 = 5.1, 8 = 7.1. */
+val AUDIO_CHANNEL_OPTIONS = listOf(
+    2 to "Stereo",
+    6 to "5.1 Surround",
+    8 to "7.1 Surround",
+)
+
 /** (kbps, label). `0` = host default. */
 val BITRATE_OPTIONS = listOf(
     0 to "Automatic",

clients/android/app/src/main/kotlin/io/unom/punktfunk/SettingsScreen.kt

@@ -104,6 +104,12 @@ fun SettingsScreen(initial: Settings, onChange: (Settings) -> Unit, onBack: () -
         }
 
         SettingsGroup("Audio") {
+            SettingDropdown(
+                label = "Audio channels",
+                options = AUDIO_CHANNEL_OPTIONS,
+                selected = s.audioChannels,
+            ) { ch -> update(s.copy(audioChannels = ch)) }
+
             ToggleRow(
                 title = "Microphone",
                 subtitle = "Send your mic to the host's virtual microphone",

clients/android/kit/src/main/kotlin/io/unom/punktfunk/kit/NativeBridge.kt

@@ -45,6 +45,7 @@ object NativeBridge {
         compositorPref: Int,
         gamepadPref: Int,
         hdrEnabled: Boolean,
+        audioChannels: Int,
     ): Long
 
     /** 64-hex SHA-256 of the cert the host presented on [handle]; valid after a successful connect. */

clients/android/native/src/audio.rs

@@ -1,7 +1,11 @@
 //! Android audio playback (android-only): pull Opus packets from the connector, decode to
-//! interleaved f32 stereo, and feed AAudio (LowLatency) via its realtime data callback through a
-//! jitter ring. Mirrors [`crate::decode`]: one thread we own (the Opus decode producer) plus a
-//! shutdown flag; the realtime callback thread is owned by AAudio.
+//! interleaved f32 (stereo or 5.1/7.1 surround), and feed AAudio (LowLatency) via its realtime data
+//! callback through a jitter ring. Mirrors [`crate::decode`]: one thread we own (the Opus decode
+//! producer) plus a shutdown flag; the realtime callback thread is owned by AAudio.
+//!
+//! The layout is the host-RESOLVED channel count (`NativeClient::audio_channels`, negotiated at
+//! connect), so an older/clamping host that can only capture stereo is decoded + played as stereo.
+//! 2 = stereo / 6 = 5.1 / 8 = 7.1, in the canonical wire order FL FR FC LFE RL RR SL SR.
 //!
 //! The ring started as a port of `punktfunk-client-linux/src/audio.rs`, but AAudio — unlike
 //! PipeWire, which adaptively rate-matches the stream and absorbs a shallow buffer — hands us a raw
@@ -26,36 +30,72 @@ use std::sync::mpsc::{sync_channel, Receiver, SyncSender, TrySendError};
 use std::sync::Arc;
 use std::time::Duration;
 
-const CHANNELS: usize = 2;
 const SAMPLE_RATE: i32 = 48_000;
 /// Decoded-chunk hand-off depth: 64 × 5 ms = 320 ms slack (matches the core's AUDIO_QUEUE).
 const RING_CHUNKS: usize = 64;
-/// Opus decode scratch: worst-case 120 ms stereo frame (5760 samples/ch × 2 ch).
-const PCM_SCRATCH: usize = 5760 * CHANNELS;
 
-// --- Jitter-ring depths, in interleaved-f32 samples (all expressed in ms via `MS`). -----------
+// --- Jitter-ring depths, in MILLISECONDS (scaled to interleaved-f32 samples at runtime). --------
+// The channel count is negotiated, not a compile-time const, so these are kept in ms and multiplied
+// by `ms` (interleaved-f32 samples per millisecond at the resolved layout) inside `start`.
 // Unlike the Linux client (PipeWire adaptively rate-matches the stream to the graph clock, masking
 // host↔DAC drift + a shallow ring), AAudio hands us a raw callback and we own the buffer: drift and
 // WiFi power-save bunching land as underruns/overflows = crackle. So Android runs a deliberately
 // deeper, smoothly-managed ring than Linux — keep the two clients' depths intentionally divergent.
-/// Interleaved f32 samples per millisecond (48 kHz × 2 ch).
-const MS: usize = (SAMPLE_RATE as usize / 1000) * CHANNELS; // 96
 /// Prime/target floor: fill to ~40 ms before playing (and after a sustained drain). Deep enough to
 /// ride out WiFi arrival jitter + clock drift; the dominant Android-only anti-crackle lever.
-const PRIME_FLOOR: usize = 40 * MS;
+const PRIME_FLOOR_MS: usize = 40;
 /// Ceiling for the burst-scaled target (so a large quantum can't push the prime depth too high).
-const PRIME_CEIL: usize = 80 * MS;
+const PRIME_CEIL_MS: usize = 80;
 /// Drop-oldest headroom above the target before trimming — a ~80 ms band swallows an arrival burst
 /// without overflowing.
-const JITTER_HEADROOM: usize = 80 * MS;
+const JITTER_HEADROOM_MS: usize = 80;
 /// Hard latency bound: never let the ring exceed ~150 ms (the only thing that caps added latency).
-const HARD_CAP: usize = 150 * MS;
+const HARD_CAP_MS: usize = 150;
 /// Re-prime (go silent to refill) only after this many CONSECUTIVE empty callbacks, so one transient
 /// drain doesn't manufacture a fresh 40 ms silence (the old `if ring.is_empty()` re-primed instantly).
 const DEPRIME_AFTER_CALLBACKS: u32 = 5;
 /// Throttle the AAudio XRun-driven HW-buffer grow check (cheap, but no need to poll every quantum).
 const XRUN_CHECK_EVERY: u32 = 128;
 
+/// Opus decoder for the audio plane: a plain stereo decoder (the validated path) or a multistream
+/// decoder for 5.1/7.1, both behind one `decode_float`. Built from the host-RESOLVED channel count
+/// via the shared layout table. Mirrors the Linux client's `AudioDec`.
+enum AudioDec {
+    Stereo(opus::Decoder),
+    Surround(opus::MSDecoder),
+}
+
+impl AudioDec {
+    fn new(channels: u8) -> Result<AudioDec, opus::Error> {
+        if channels == 2 {
+            Ok(AudioDec::Stereo(opus::Decoder::new(
+                SAMPLE_RATE as u32,
+                opus::Channels::Stereo,
+            )?))
+        } else {
+            let l = punktfunk_core::audio::layout_for(channels, false);
+            Ok(AudioDec::Surround(opus::MSDecoder::new(
+                SAMPLE_RATE as u32,
+                l.streams,
+                l.coupled,
+                l.mapping,
+            )?))
+        }
+    }
+
+    fn decode_float(
+        &mut self,
+        input: &[u8],
+        out: &mut [f32],
+        fec: bool,
+    ) -> Result<usize, opus::Error> {
+        match self {
+            AudioDec::Stereo(d) => d.decode_float(input, out, fec),
+            AudioDec::Surround(d) => d.decode_float(input, out, fec),
+        }
+    }
+}
+
 /// Diagnostics — written by the decode thread + the realtime callback, logged periodically. The
 /// audio analogue of the video `fed`/`rendered` counters (we can't "screenshot" sound).
 #[derive(Default)]
@@ -74,9 +114,20 @@ pub struct AudioPlayback {
 }
 
 impl AudioPlayback {
-    /// Open AAudio (LowLatency, 48 kHz/stereo/f32) with a realtime callback draining a jitter ring,
-    /// then spawn the Opus decode thread. `None` on failure (the caller leaves video streaming).
+    /// Open AAudio (LowLatency, 48 kHz/f32, the host-resolved channel layout) with a realtime
+    /// callback draining a jitter ring, then spawn the Opus decode thread. `None` on failure (the
+    /// caller leaves video streaming).
     pub fn start(client: Arc<NativeClient>) -> Option<AudioPlayback> {
+        // Build playback from the host-RESOLVED channel count (never the request): 2 = stereo /
+        // 6 = 5.1 / 8 = 7.1, canonical wire order FL FR FC LFE RL RR SL SR.
+        let channels = punktfunk_core::audio::normalize_channels(client.audio_channels) as usize;
+        // Interleaved f32 samples per millisecond at this layout (48 kHz × channels); the ms-
+        // denominated jitter-ring depths scale by it.
+        let ms = (SAMPLE_RATE as usize / 1000) * channels;
+        let prime_floor = PRIME_FLOOR_MS * ms;
+        let prime_ceil = PRIME_CEIL_MS * ms;
+        let jitter_headroom = JITTER_HEADROOM_MS * ms;
+        let hard_cap_max = HARD_CAP_MS * ms;
         let counters = Arc::new(Counters::default());
         let (tx, rx) = sync_channel::<Vec<f32>>(RING_CHUNKS);
         // Recycle free-list: drained PCM buffers go BACK to the decode thread to be refilled, so the
@@ -92,13 +143,13 @@ impl AudioPlayback {
         // before the trim below = the hard cap plus one full channel of 5 ms (480-f32) frames — the
         // punktfunk protocol always sends 5 ms Opus frames (host `audio_thread`); a larger frame
         // would force a one-time realloc, asserted (not silently corrupted) in `decode_loop`.
-        let mut ring: VecDeque<f32> = VecDeque::with_capacity(HARD_CAP + RING_CHUNKS * 5 * MS);
+        let mut ring: VecDeque<f32> = VecDeque::with_capacity(hard_cap_max + RING_CHUNKS * 5 * ms);
         let mut primed = false;
         let mut empties: u32 = 0; // consecutive empty callbacks (de-prime hysteresis)
         let mut cb_count: u32 = 0; // callbacks since open (throttles the XRun grow check)
         let mut last_xrun: i32 = 0; // last AAudio XRun count we grew the buffer for
         let callback = move |s: &AudioStream, data: *mut c_void, num_frames: i32| {
-            let want = num_frames as usize * CHANNELS;
+            let want = num_frames as usize * channels;
             // SAFETY: AAudio provides `num_frames * channel_count` F32 slots at `data`.
             let out = unsafe { std::slice::from_raw_parts_mut(data as *mut f32, want) };
             // Drain decoded chunks into the ring WITHOUT freeing on the RT thread: `drain(..)` empties
@@ -108,11 +159,11 @@ impl AudioPlayback {
                 ring.extend(chunk.drain(..));
                 let _ = free_tx.try_send(chunk);
             }
-            // Jitter buffer: prime to ~40 ms (PRIME_FLOOR) before playing and after a sustained drain;
+            // Jitter buffer: prime to ~40 ms (prime_floor) before playing and after a sustained drain;
             // drop-oldest only above a wide ~120 ms band. Decoupled from the AAudio burst `want` (tiny
             // on the LowLatency MMAP path) so the depth doesn't collapse to a single quantum.
-            let target = (3 * want).clamp(PRIME_FLOOR, PRIME_CEIL);
-            let hard_cap = (target + JITTER_HEADROOM).min(HARD_CAP);
+            let target = (3 * want).clamp(prime_floor, prime_ceil);
+            let hard_cap = (target + jitter_headroom).min(hard_cap_max);
             while ring.len() > hard_cap {
                 ring.pop_front();
             }
@@ -166,7 +217,11 @@ impl AudioPlayback {
             .ok()?
             .direction(AudioDirection::Output)
             .sample_rate(SAMPLE_RATE)
-            .channel_count(CHANNELS as i32)
+            // The wire order (FL FR FC LFE RL RR SL SR) is the standard AAudio/Android channel
+            // order, so this is an IDENTITY mapping — no permute. AAudio infers the 5.1/7.1 mask
+            // from `channel_count` (the ndk crate's builder exposes no setChannelMask); the host
+            // captures + Opus-encodes in exactly this order.
+            .channel_count(channels as i32)
             .format(AudioFormat::PCM_Float)
             .performance_mode(AudioPerformanceMode::LowLatency)
             .sharing_mode(AudioSharingMode::Shared)
@@ -206,7 +261,7 @@ impl AudioPlayback {
         let sd = shutdown.clone();
         let join = std::thread::Builder::new()
             .name("pf-audio".into())
-            .spawn(move || decode_loop(client, tx, free_rx, sd, counters))
+            .spawn(move || decode_loop(client, tx, free_rx, sd, counters, channels))
             .ok();
 
         Some(AudioPlayback {
@@ -236,29 +291,34 @@ fn decode_loop(
     free_rx: Receiver<Vec<f32>>,
     shutdown: Arc<AtomicBool>,
     counters: Arc<Counters>,
+    channels: usize,
 ) {
-    let mut dec = match opus::Decoder::new(SAMPLE_RATE as u32, opus::Channels::Stereo) {
+    // Interleaved f32 samples per millisecond at this layout — the ring's 5 ms reserve check below.
+    let ms = (SAMPLE_RATE as usize / 1000) * channels;
+    // Opus decode scratch: worst-case 120 ms frame (5760 samples/ch) × channels.
+    let pcm_scratch = 5760 * channels;
+    let mut dec = match AudioDec::new(channels as u8) {
         Ok(d) => d,
         Err(e) => {
             log::error!("audio: opus decoder init: {e} — audio disabled");
             return;
         }
     };
-    let mut pcm = vec![0f32; PCM_SCRATCH];
+    let mut pcm = vec![0f32; pcm_scratch];
     let mut window_peak = 0f32; // loudest |sample| since the last log — tells a tone from silence
     while !shutdown.load(Ordering::Relaxed) {
         match client.next_audio(Duration::from_millis(5)) {
             Ok(pkt) => match dec.decode_float(&pkt.data, &mut pcm, false) {
                 Ok(samples) => {
-                    let n = samples * CHANNELS;
+                    let n = samples * channels;
                     for &s in &pcm[..n] {
                         window_peak = window_peak.max(s.abs());
                     }
-                    // The ring's pre-reservation in `start` assumes the protocol's 5 ms (≤480-f32)
+                    // The ring's pre-reservation in `start` assumes the protocol's 5 ms (≤480-f32/ch)
                     // frames; a larger frame would force a one-time realloc on the RT thread. Catch a
                     // future host frame-size change here in debug, not as a silent audio glitch.
                     debug_assert!(
-                        n <= 5 * MS,
+                        n <= 5 * ms,
                         "audio frame {n} f32 exceeds the 5 ms ring reserve"
                     );
                     let count = counters.opus_decoded.fetch_add(1, Ordering::Relaxed) + 1;
@@ -266,7 +326,7 @@ fn decode_loop(
                     // free-list is momentarily empty (startup / after a backpressure drop).
                     let mut buf = free_rx
                         .try_recv()
-                        .unwrap_or_else(|_| Vec::with_capacity(PCM_SCRATCH));
+                        .unwrap_or_else(|_| Vec::with_capacity(pcm_scratch));
                     buf.clear();
                     buf.extend_from_slice(&pcm[..n]);
                     match tx.try_send(buf) {

clients/android/native/src/session.rs

@@ -140,10 +140,12 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeGenerateIde
 }
 
 /// `NativeBridge.nativeConnect(host, port, w, h, hz, certPem, keyPem, pinHex, bitrateKbps,
-/// compositorPref, gamepadPref): Long`. `certPem`/`keyPem` empty = anonymous, else presented as the
-/// persistent identity. `pinHex` empty = TOFU (read `nativeHostFingerprint` after), else 64-hex
-/// SHA-256 to pin the host (mismatch → 0). `bitrateKbps` 0 = host default. `compositorPref`/
-/// `gamepadPref` are `CompositorPref`/`GamepadPref` wire bytes (0 = Auto; unknown → Auto).
+/// compositorPref, gamepadPref, hdrEnabled, audioChannels): Long`. `certPem`/`keyPem` empty =
+/// anonymous, else presented as the persistent identity. `pinHex` empty = TOFU (read
+/// `nativeHostFingerprint` after), else 64-hex SHA-256 to pin the host (mismatch → 0). `bitrateKbps`
+/// 0 = host default. `compositorPref`/`gamepadPref` are `CompositorPref`/`GamepadPref` wire bytes
+/// (0 = Auto; unknown → Auto). `audioChannels` is the requested surround layout (2/6/8; normalized,
+/// anything else → stereo) — the host clamps it and the resolved count drives playback.
 /// Returns an opaque handle, or 0 on failure (logged).
 #[no_mangle]
 #[allow(clippy::too_many_arguments)]
@@ -162,6 +164,7 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeConnect<'lo
     compositor_pref: jint,
     gamepad_pref: jint,
     hdr_enabled: jboolean,
+    audio_channels: jint,
 ) -> jlong {
     let host: String = match env.get_string(&host) {
         Ok(s) => s.into(),
@@ -213,6 +216,11 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeConnect<'lo
         } else {
             0
         },
+        // Requested surround layout (2 = stereo / 6 = 5.1 / 8 = 7.1). The host clamps to what it can
+        // capture and echoes the resolved count in `connector.audio_channels`, which drives the
+        // decoder + AAudio layout (read in `crate::audio::AudioPlayback::start`). Anything else
+        // normalizes to stereo here.
+        punktfunk_core::audio::normalize_channels(audio_channels.clamp(0, u8::MAX as jint) as u8),
         None,     // launch: default app
         pin,      // Some → Crypto on host-fp mismatch
         identity, // owned (cert, key) PEM, or None (anonymous)