fix(android): gate the latency overhaul behind an experimental toggle, default off

The 27c53a4 low-latency overhaul regressed badly on some phones. Every piece
of it — decoder ranking, per-SoC vendor keys, the async decode loop, pipeline
thread boosts, the ADPF max-performance bias, game-tagged AAudio, DSCP marking,
the Wi-Fi low-latency lock, HDMI ALLM and the forced TV mode switch — now rides
the "Low-latency mode (experimental)" toggle, default OFF. Off restores the
pre-overhaul pipeline byte-for-byte: the sync poll loop, the platform-default
decoder, and the original format keys (standard low-latency + blind Qualcomm
twin + priority=0 + operating-rate=MAX together).

- New pref key (low_latency_mode_experimental): the old key shipped default-ON,
  so any install that ever saved settings persisted true — flipping the default
  under the old key would leave exactly the regressed devices stuck on.
- DSCP is applied at socket creation, so the toggle reaches the transport via
  NativeBridge.nativeSetLowLatencyMode → transport::set_dscp_default, called in
  the connect choke point before nativeConnect; the core DSCP default reverts
  to off everywhere.
- nativeStartAudio(handle, lowLatencyMode) gates AAudio usage=Game.
- VideoDecoders.pickDecoder now skips `.secure` decoder twins and decoders that
  require FEATURE_SecurePlayback: they need a secure surface, and a secure twin
  could out-score its plain sibling (only it advertising FEATURE_LowLatency),
  which black-screens a clear stream.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

clients/android/native/src/adpf.rs

@@ -103,8 +103,10 @@ pub struct HintSession {
 impl HintSession {
     /// Open a session hinting `tids` with an initial per-frame target of `target_ns` nanoseconds.
     /// `None` when ADPF is unavailable (device API < 33) or the platform declines — the caller then
-    /// runs unhinted (a no-op, not an error).
-    pub fn create(target_ns: i64, tids: &[i32]) -> Option<Self> {
+    /// runs unhinted (a no-op, not an error). `prefer_performance` (the experimental low-latency
+    /// mode) additionally biases the governor away from power efficiency (API 35+); off, the
+    /// session runs with the platform default, as it did before the overhaul.
+    pub fn create(target_ns: i64, tids: &[i32], prefer_performance: bool) -> Option<Self> {
         if target_ns <= 0 || tids.is_empty() {
             return None;
         }
@@ -119,9 +121,11 @@ impl HintSession {
         // Tell the governor NOT to bias this session toward power efficiency (API 35+): our loop is
         // latency-critical, so we want it kept on fast cores at high clocks over battery savings.
         // Best-effort; absent below API 35.
-        if let Some(f) = api.set_prefer_power_efficiency {
-            // SAFETY: `session` is the live session just created; the fn takes it + a bool.
-            unsafe { f(session, false) };
+        if prefer_performance {
+            if let Some(f) = api.set_prefer_power_efficiency {
+                // SAFETY: `session` is the live session just created; the fn takes it + a bool.
+                unsafe { f(session, false) };
+            }
         }
         Some(Self { api, session })
     }

clients/android/native/src/audio.rs

@@ -116,8 +116,10 @@ pub struct AudioPlayback {
 impl AudioPlayback {
     /// 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> {
+    /// caller leaves video streaming). `game_audio` (the experimental low-latency mode) tags the
+    /// stream usage=Game for the HAL's game-audio routing; off, the stream is untagged as it was
+    /// before the overhaul.
+    pub fn start(client: Arc<NativeClient>, game_audio: bool) -> 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;
@@ -226,7 +228,7 @@ impl AudioPlayback {
                 AudioCallbackResult::Continue
             };
 
-            let stream = AudioStreamBuilder::new()?
+            let builder = AudioStreamBuilder::new()?
                 .direction(AudioDirection::Output)
                 .sample_rate(SAMPLE_RATE)
                 // The wire order (FL FR FC LFE RL RR SL SR) is the standard AAudio/Android channel
@@ -234,12 +236,19 @@ impl AudioPlayback {
                 // 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)
-                // Tag the stream as game audio (usage=Game / content=Movie): the audio HAL applies
-                // its low-latency game-audio routing/policy and it's grouped correctly with the
-                // game-mode profile. Advisory — ignored where the device has no such policy.
-                .usage(AudioUsage::Game)
-                .content_type(AudioContentType::Movie)
+                .format(AudioFormat::PCM_Float);
+            // Tag the stream as game audio (usage=Game / content=Movie): the audio HAL applies
+            // its low-latency game-audio routing/policy and it's grouped correctly with the
+            // game-mode profile. Advisory — ignored where the device has no such policy. Part of
+            // the experimental low-latency stack; off, the stream stays untagged.
+            let builder = if game_audio {
+                builder
+                    .usage(AudioUsage::Game)
+                    .content_type(AudioContentType::Movie)
+            } else {
+                builder
+            };
+            let stream = builder
                 .performance_mode(AudioPerformanceMode::LowLatency)
                 .sharing_mode(sharing)
                 .data_callback(Box::new(callback))

clients/android/native/src/decode.rs

@@ -36,9 +36,11 @@ const IN_FLIGHT_CAP: usize = 64;
 /// this deep is a lost datagram (or an old host that never sends any) and gets evicted.
 const PENDING_SPLIT_CAP: usize = 256;
 
-/// Whether to run the event-driven async decode loop (default) or the synchronous poll loop kept as
-/// a bring-up fallback. Flip to `false` to A/B the two on the HUD (`design/…`); the async loop
-/// presents a decoded frame the instant it's ready instead of waiting out a poll interval.
+/// Whether low-latency mode uses the event-driven async decode loop (default) or the synchronous
+/// poll loop. Flip to `false` to A/B the two on the HUD (`design/…`); the async loop presents a
+/// decoded frame the instant it's ready instead of waiting out a poll interval. Only consulted when
+/// the user's "Low-latency mode (experimental)" toggle is ON — off, the sync loop always runs (the
+/// original pipeline).
 const USE_ASYNC_DECODE: bool = true;
 
 /// Per-session decode configuration, resolved by the JNI layer (`nativeStartVideo`) and passed to
@@ -50,8 +52,10 @@ pub(crate) struct DecodeOptions {
     /// Whether Kotlin found the chosen decoder advertises `FEATURE_LowLatency` (queryable only via
     /// the Java `CodecCapabilities` API) — surfaced on the HUD next to the decoder name.
     pub ll_feature: bool,
-    /// The user's "Low-latency mode" master toggle (default on ⇒ full aggressive profile; off ⇒
-    /// conservative, an escape hatch for a device that throttles under the clocks).
+    /// The user's "Low-latency mode (experimental)" master toggle. On ⇒ the full overhaul: async
+    /// decode loop, per-SoC vendor keys, pipeline thread boosts, ADPF max-performance, forced TV
+    /// mode switch. Off (default) ⇒ the original pre-overhaul pipeline, kept as the known-good
+    /// baseline while the overhaul is experimental.
     pub low_latency_mode: bool,
     /// TV form factor (Kotlin's `UiModeManager`): actively drive the HDMI output into the stream's
     /// refresh mode, vs. the softer seamless hint on a phone/tablet.
@@ -67,17 +71,16 @@ pub fn run(
     stats: Arc<crate::stats::VideoStats>,
     opts: DecodeOptions,
 ) {
-    if USE_ASYNC_DECODE {
+    if opts.low_latency_mode && USE_ASYNC_DECODE {
         run_async(client, window, shutdown, stats, opts);
     } else {
         run_sync(client, window, shutdown, stats, opts);
     }
 }
 
-/// The synchronous poll loop — the original decode path, kept as a bring-up fallback behind
-/// [`USE_ASYNC_DECODE`]. Feeds and drains on this one thread; the only blocking wait is a short
-/// output dequeue while input is backed up.
-#[allow(dead_code)]
+/// The synchronous poll loop — the original decode path: the only one when low-latency mode is off,
+/// and the [`USE_ASYNC_DECODE`] A/B fallback when it's on. Feeds and drains on this one thread; the
+/// only blocking wait is a short output dequeue while input is backed up.
 fn run_sync(
     client: Arc<NativeClient>,
     window: NativeWindow,
@@ -160,7 +163,11 @@ fn run_sync(
     // above our API-28 floor, so we resolve it at runtime (see `try_set_frame_rate`) rather than link
     // it — a hard import would stop `libpunktfunk_android.so` loading at all on API 28/29. Absent
     // there ⇒ we simply skip the hint (non-fatal; the stream renders fine without it).
-    if mode.refresh_hz > 0 && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv) {
+    // The forced TV mode switch (`is_tv` ⇒ ALWAYS strategy) is part of the experimental stack;
+    // off, every form factor gets the original soft seamless hint.
+    if mode.refresh_hz > 0
+        && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv && low_latency_mode)
+    {
         log::debug!(
             "decode: set_frame_rate({} Hz) unavailable/declined (non-fatal)",
             mode.refresh_hz
@@ -319,8 +326,12 @@ fn run_sync(
                 // or where the platform declines → `None`, and the loop runs unhinted).
                 hint_tried = true;
                 let tids = client.hot_thread_ids();
-                boost_hot_threads(&tids);
-                hint = crate::adpf::HintSession::create(frame_period_ns, &tids);
+                // The pump/audio priority boost is part of the experimental low-latency stack; the
+                // ADPF session itself predates it and always runs (max-performance bias gated inside).
+                if low_latency_mode {
+                    boost_hot_threads(&tids);
+                }
+                hint = crate::adpf::HintSession::create(frame_period_ns, &tids, low_latency_mode);
                 log::info!(
                     "decode: ADPF hint session {} — {} hot thread(s), target {frame_period_ns} ns",
                     if hint.is_some() {
@@ -396,12 +407,15 @@ fn create_codec(mime: &str, preferred: Option<&str>) -> Option<MediaCodec> {
     MediaCodec::from_decoder_type(mime)
 }
 
-/// Apply the low-latency MediaFormat keys for `codec_name`. The standard AOSP `low-latency` key is
-/// always set (API 30+, harmless/ignored elsewhere). When `aggressive` (the "Low-latency mode"
-/// master toggle) we additionally set MediaTek's `vdec-lowlatency` (unconditionally — ignored off
-/// MediaTek), the per-SoC vendor extension keys (gated on the decoder-name prefix the way
-/// Moonlight-Android does, since a key one vendor honours is meaningless on another), and one clock
-/// hint. Off ⇒ the standard key only, a gentler profile for a device that throttles under max clocks.
+/// Apply the low-latency MediaFormat keys for `codec_name`.
+///
+/// `aggressive` = the "Low-latency mode (experimental)" master toggle. **Off** (default) ⇒ the
+/// pre-overhaul key set, byte-for-byte — the standard `low-latency` key, the blind Qualcomm vendor
+/// twin, `priority = 0` AND `operating-rate = MAX` set together — kept as the known-good baseline
+/// (the profile every device streamed with before the overhaul). **On** ⇒ the Moonlight-parity
+/// profile: MediaTek's `vdec-lowlatency` (unconditionally — ignored off MediaTek), the per-SoC
+/// vendor extension keys (gated on the decoder-name prefix the way Moonlight-Android does, since a
+/// key one vendor honours is meaningless on another), and one *mutually exclusive* clock hint.
 ///
 /// Vendor keys mirror Moonlight's `MediaCodecHelper` (verified against current source): Qualcomm
 /// picture-order + low-latency, Exynos (also Google Tensor), Amlogic, HiSilicon, MediaTek. NVIDIA
@@ -411,6 +425,12 @@ fn configure_low_latency(format: &mut MediaFormat, codec_name: &str, aggressive:
     // Standard key: request the no-reorder low-latency path where the platform decoder supports it.
     format.set_i32("low-latency", 1);
     if !aggressive {
+        // The original profile: the Qualcomm vendor twin set blind (unknown keys are ignored by
+        // other vendors' codecs), realtime priority, and the AOSP "unbounded" operating-rate
+        // sentinel — decode each frame at max clocks rather than pacing to the frame rate.
+        format.set_i32("vendor.qti-ext-dec-low-latency.enable", 1);
+        format.set_i32("priority", 0); // 0 = realtime
+        format.set_i32("operating-rate", i16::MAX as i32); // 32767 = "as fast as possible"
         return;
     }
     // MediaTek's low-latency key — very common (mid/budget phones + many Google TV / Fire TV boxes).
@@ -600,7 +620,11 @@ fn run_async(
         mode.width,
         mode.height
     );
-    if mode.refresh_hz > 0 && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv) {
+    // The forced TV mode switch (`is_tv` ⇒ ALWAYS strategy) is part of the experimental stack;
+    // off, every form factor gets the original soft seamless hint.
+    if mode.refresh_hz > 0
+        && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv && low_latency_mode)
+    {
         log::debug!(
             "decode: set_frame_rate({} Hz) unavailable/declined (non-fatal)",
             mode.refresh_hz
@@ -716,8 +740,12 @@ fn run_async(
             if !hint_tried {
                 hint_tried = true;
                 let tids = client.hot_thread_ids();
-                boost_hot_threads(&tids);
-                hint = crate::adpf::HintSession::create(frame_period_ns, &tids);
+                // The pump/audio priority boost is part of the experimental low-latency stack; the
+                // ADPF session itself predates it and always runs (max-performance bias gated inside).
+                if low_latency_mode {
+                    boost_hot_threads(&tids);
+                }
+                hint = crate::adpf::HintSession::create(frame_period_ns, &tids, low_latency_mode);
                 log::info!(
                     "decode: ADPF hint session {} — {} hot thread(s), target {frame_period_ns} ns",
                     if hint.is_some() {

clients/android/native/src/session/connect.rs

@@ -32,6 +32,20 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeGenerateIde
     }
 }
 
+/// `NativeBridge.nativeSetLowLatencyMode(enabled)` — apply the user's "Low-latency mode
+/// (experimental)" toggle to the process-wide transport defaults, today just DSCP/QoS marking on
+/// the media sockets. Must be called BEFORE `nativeConnect` (the tag is applied at socket
+/// creation); Kotlin's one connect choke point (`HostConnect.connectToHost`) does. The rest of the
+/// toggle rides explicit per-session parameters (`nativeStartVideo` / `nativeStartAudio`).
+#[no_mangle]
+pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeSetLowLatencyMode(
+    _env: JNIEnv,
+    _this: JObject,
+    enabled: jboolean,
+) {
+    punktfunk_core::transport::set_dscp_default(enabled != 0);
+}
+
 /// `NativeBridge.nativeConnect(host, port, w, h, hz, certPem, keyPem, pinHex, bitrateKbps,
 /// compositorPref, gamepadPref, hdrEnabled, audioChannels, preferredCodec, timeoutMs, launch): Long`.
 /// `launch` (empty ⇒ none) is a store-qualified library id to boot straight into a game.

clients/android/native/src/session/planes.rs

@@ -233,14 +233,17 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeSetVideoSta
     })
 }
 
-/// `NativeBridge.nativeStartAudio(handle)` — start the Opus→AAudio playback thread. No-op if already
-/// started or on a `0` handle. Best-effort: a failure leaves video streaming.
+/// `NativeBridge.nativeStartAudio(handle, lowLatencyMode)` — start the Opus→AAudio playback thread.
+/// `lowLatencyMode` (the experimental toggle) tags the stream usage=Game for the HAL's game-audio
+/// routing. No-op if already started or on a `0` handle. Best-effort: a failure leaves video
+/// streaming.
 #[cfg(target_os = "android")]
 #[no_mangle]
 pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStartAudio(
     _env: JNIEnv,
     _this: JObject,
     handle: jlong,
+    low_latency_mode: jboolean,
 ) {
     if handle == 0 {
         return;
@@ -251,7 +254,7 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStartAudio(
     if guard.is_some() {
         return; // already playing
     }
-    match crate::audio::AudioPlayback::start(h.client.clone()) {
+    match crate::audio::AudioPlayback::start(h.client.clone(), low_latency_mode != 0) {
         Some(p) => *guard = Some(p),
         None => log::error!("nativeStartAudio: playback init failed (video unaffected)"),
     }