perf(android): low-latency decode overhaul — vendor keys, async loop, system tuning

Close the latency gap on the Android client with per-SoC decoder tuning, an
event-driven decode loop, and full system integration.

- Decoder selection: rank MediaCodecList decoders in Kotlin (hardware/vendor
  preferred, software avoided, FEATURE_LowLatency probed) and create the chosen
  one by name. Per-SoC low-latency keys gated on the codec-name prefix: Qualcomm
  picture-order + low-latency, Exynos (also Google Tensor), Amlogic, HiSilicon;
  MediaTek vdec-lowlatency set unconditionally. operating-rate = MAX (Qualcomm)
  vs priority = 0 (else) are mutually exclusive. NVIDIA/Rockchip/Realtek have no
  vendor key — covered by ranking + the standard low-latency key.

- Async decode loop: AMediaCodec async-notify replaces the poll loop, presenting a
  decoded frame the instant it is ready instead of waiting out a poll interval.
  Behind USE_ASYNC_DECODE with the synchronous loop kept for A/B during bring-up.

- System integration: Wi-Fi FULL_LOW_LATENCY lock and HDMI ALLM
  (setPreferMinimalPostProcessing) for the stream's lifetime; game_mode_config.xml
  opting out of OEM downscaling / FPS overrides.

- Pipeline: boost the data-plane pump + audio thread priorities, AAudio usage=Game,
  DSCP marking on by default on Android, ADPF setPreferPowerEfficiency(false),
  and setFrameRateWithChangeStrategy(ALWAYS) to force the HDMI mode switch on TV.

- lowLatencyMode master toggle (default on) as the escape hatch; the stats HUD now
  shows the resolved decoder name.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

clients/android/app/src/main/AndroidManifest.xml

@@ -43,6 +43,14 @@
         android:supportsRtl="true"
         android:theme="@style/Theme.PunktfunkAndroid">
 
+        <!-- Game Mode config (Android 13+): declare we support Performance mode and opt OUT of the
+             OEM interventions that would fight the negotiated stream — resolution downscaling and
+             FPS overrides. A game-streaming client renders exactly the host's mode; a platform
+             downscale/FPS-cap corrupts that. Ignored below API 33. -->
+        <meta-data
+            android:name="android.game_mode_config"
+            android:resource="@xml/game_mode_config" />
+
         <activity
             android:name=".MainActivity"
             android:exported="true"

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

@@ -54,6 +54,14 @@ data class Settings(
      * client's `libraryEnabled`.
      */
     val libraryEnabled: Boolean = true,
+    /**
+     * Aggressive decoder latency tuning — the master escape hatch. On (default): the decoder runs
+     * the full low-latency profile (per-SoC vendor keys + max-clock operating-rate on Qualcomm).
+     * Off: a conservative profile (the standard `low-latency` key only), for a device that thermally
+     * throttles or misbehaves under the aggressive clocks. Decoder ranking, the Wi-Fi low-latency
+     * lock and HDMI game-mode signalling stay on regardless — they're harmless.
+     */
+    val lowLatencyMode: Boolean = true,
 )
 
 /** [Settings.touchMode] values; persisted by name. */
@@ -82,6 +90,7 @@ class SettingsStore(context: Context) {
             ?: if (prefs.getBoolean(K_TRACKPAD, true)) TouchMode.TRACKPAD else TouchMode.POINTER,
         gamepadUiEnabled = prefs.getBoolean(K_GAMEPAD_UI, true),
         libraryEnabled = prefs.getBoolean(K_LIBRARY, true),
+        lowLatencyMode = prefs.getBoolean(K_LOW_LATENCY, true),
     )
 
     fun save(s: Settings) {
@@ -100,6 +109,7 @@ class SettingsStore(context: Context) {
             .putString(K_TOUCH_MODE, s.touchMode.name)
             .putBoolean(K_GAMEPAD_UI, s.gamepadUiEnabled)
             .putBoolean(K_LIBRARY, s.libraryEnabled)
+            .putBoolean(K_LOW_LATENCY, s.lowLatencyMode)
             .apply()
     }
 
@@ -118,6 +128,7 @@ class SettingsStore(context: Context) {
         const val K_TOUCH_MODE = "touch_mode"
         const val K_GAMEPAD_UI = "gamepad_ui_enabled"
         const val K_LIBRARY = "library_enabled"
+        const val K_LOW_LATENCY = "low_latency_mode"
 
         /** Legacy Boolean the enum replaced — read once as the migration default, never written. */
         const val K_TRACKPAD = "trackpad_mode"

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

@@ -324,6 +324,14 @@ private fun DisplaySettings(s: Settings, update: (Settings) -> Unit, context: an
             options = COMPOSITOR_OPTIONS.mapIndexed { i, lbl -> i to lbl },
             selected = s.compositor,
         ) { c -> update(s.copy(compositor = c)) }
+
+        ToggleRow(
+            title = "Low-latency mode",
+            subtitle = "Run the decoder at max clocks for the lowest latency. Turn off only if a " +
+                "device overheats or glitches during long sessions.",
+            checked = s.lowLatencyMode,
+            onCheckedChange = { on -> update(s.copy(lowLatencyMode = on)) },
+        )
     }
 }
 

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

@@ -27,7 +27,7 @@ import kotlin.math.roundToInt
  * older layouts just omit those lines.
  */
 @Composable
-internal fun StatsOverlay(s: DoubleArray, modifier: Modifier = Modifier) {
+internal fun StatsOverlay(s: DoubleArray, decoderLabel: String = "", modifier: Modifier = Modifier) {
     if (s.size < 10) return
     val w = s[6].toInt()
     val h = s[7].toInt()
@@ -46,6 +46,14 @@ internal fun StatsOverlay(s: DoubleArray, modifier: Modifier = Modifier) {
             fontFamily = FontFamily.Monospace,
             fontSize = 12.sp,
         )
+        if (decoderLabel.isNotEmpty()) {
+            Text(
+                decoderLabel,
+                color = Color(0xFFB0D0FF),
+                fontFamily = FontFamily.Monospace,
+                fontSize = 12.sp,
+            )
+        }
         videoFeedLine(s)?.let { feed ->
             Text(
                 feed,

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

@@ -1,8 +1,11 @@
 package io.unom.punktfunk
 
 import android.Manifest
+import android.content.Context
 import android.content.pm.ActivityInfo
 import android.content.pm.PackageManager
+import android.net.wifi.WifiManager
+import android.os.Build
 import android.view.SurfaceHolder
 import android.view.SurfaceView
 import android.view.WindowManager
@@ -30,6 +33,7 @@ import androidx.core.view.WindowInsetsControllerCompat
 import io.unom.punktfunk.kit.Gamepad
 import io.unom.punktfunk.kit.GamepadFeedback
 import io.unom.punktfunk.kit.NativeBridge
+import io.unom.punktfunk.kit.VideoDecoders
 import java.util.concurrent.atomic.AtomicBoolean
 import kotlinx.coroutines.delay
 
@@ -55,15 +59,23 @@ fun StreamScreen(handle: Long, micEnabled: Boolean, onDisconnect: () -> Unit) {
     // comes from Settings.
     val initialSettings = remember { SettingsStore(context).load() }
     var stats by remember { mutableStateOf<DoubleArray?>(null) }
+    var decoderLabel by remember { mutableStateOf("") }
     var showStats by remember { mutableStateOf(initialSettings.statsHudEnabled) }
     // Touch model is fixed per session (re-keys the gesture handler below if it ever changes).
     val touchMode = initialSettings.touchMode
+    // Master low-latency toggle, resolved once for the session and passed to the decoder at start.
+    val lowLatencyMode = initialSettings.lowLatencyMode
+    // TV form factor (leanback): the decoder actively switches the HDMI output mode to the stream
+    // refresh; a phone/tablet gets the softer seamless frame-rate hint instead.
+    val isTv = remember { context.packageManager.hasSystemFeature(PackageManager.FEATURE_LEANBACK) }
     LaunchedEffect(handle, showStats) {
         NativeBridge.nativeSetVideoStatsEnabled(handle, showStats)
         if (showStats) {
             while (true) {
                 delay(1000)
                 stats = NativeBridge.nativeVideoStats(handle)
+                // The decoder is fixed for the session; fetch its label once it's resolved.
+                if (decoderLabel.isEmpty()) decoderLabel = NativeBridge.nativeVideoDecoderLabel(handle)
             }
         } else {
             stats = null // drop the last snapshot so a re-show never flashes stale numbers
@@ -76,8 +88,29 @@ fun StreamScreen(handle: Long, micEnabled: Boolean, onDisconnect: () -> Unit) {
     // main thread, so a plain flag is race-free; AtomicBoolean just makes the intent explicit.
     val closed = remember { AtomicBoolean(false) }
 
+    // A Wi-Fi low-latency lock held for the stream's duration: asks the Wi-Fi firmware to drop its
+    // power-save polling (a common source of tens-of-ms jitter). WIFI_MODE_FULL_LOW_LATENCY (API
+    // 29+) is the strongest; older releases fall back to FULL_HIGH_PERF. Needs no extra permission
+    // beyond ACCESS_WIFI_STATE (already declared). Non-reference-counted: one explicit acquire/release.
+    val wifiLock = remember(handle) {
+        val wm = context.applicationContext.getSystemService(Context.WIFI_SERVICE) as? WifiManager
+        val mode = if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.Q) {
+            WifiManager.WIFI_MODE_FULL_LOW_LATENCY
+        } else {
+            @Suppress("DEPRECATION")
+            WifiManager.WIFI_MODE_FULL_HIGH_PERF
+        }
+        wm?.createWifiLock(mode, "punktfunk:stream")?.apply { setReferenceCounted(false) }
+    }
+
     DisposableEffect(handle) {
         window?.addFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON)
+        runCatching { wifiLock?.acquire() }
+        // HDMI Auto Low-Latency Mode: ask the display to drop its post-processing (game mode) —
+        // the biggest panel-side latency win on the TV boxes. No-op where ALLM isn't supported. API 30+.
+        if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.R) {
+            window?.setPreferMinimalPostProcessing(true)
+        }
         controller?.let {
             it.systemBarsBehavior = WindowInsetsControllerCompat.BEHAVIOR_SHOW_TRANSIENT_BARS_BY_SWIPE
             it.hide(WindowInsetsCompat.Type.systemBars())
@@ -105,6 +138,10 @@ fun StreamScreen(handle: Long, micEnabled: Boolean, onDisconnect: () -> Unit) {
             activity?.setConsoleHighRefreshRate(true) // back to the console UI's max refresh
             controller?.show(WindowInsetsCompat.Type.systemBars())
             window?.clearFlags(WindowManager.LayoutParams.FLAG_KEEP_SCREEN_ON)
+            if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.R) {
+                window?.setPreferMinimalPostProcessing(false)
+            }
+            runCatching { if (wifiLock?.isHeld == true) wifiLock.release() }
             // Release the landscape lock so the rest of the app follows the device/system again.
             activity?.requestedOrientation =
                 priorOrientation ?: ActivityInfo.SCREEN_ORIENTATION_UNSPECIFIED
@@ -125,7 +162,19 @@ fun StreamScreen(handle: Long, micEnabled: Boolean, onDisconnect: () -> Unit) {
                 SurfaceView(ctx).apply {
                     holder.addCallback(object : SurfaceHolder.Callback {
                         override fun surfaceCreated(holder: SurfaceHolder) {
-                            NativeBridge.nativeStartVideo(handle, holder.surface)
+                            // Rank MediaCodecList decoders for the negotiated MIME (framework-only
+                            // API) and hand the chosen one to Rust, which creates it by name and
+                            // applies the per-SoC vendor low-latency keys.
+                            val mime = NativeBridge.nativeVideoMime(handle)
+                            val choice = VideoDecoders.pickDecoder(mime)
+                            NativeBridge.nativeStartVideo(
+                                handle,
+                                holder.surface,
+                                choice?.name ?: "",
+                                lowLatencyMode,
+                                choice?.lowLatencyFeature ?: false,
+                                isTv,
+                            )
                             NativeBridge.nativeStartAudio(handle)
                             if (micWanted) NativeBridge.nativeStartMic(handle)
                         }
@@ -150,7 +199,7 @@ fun StreamScreen(handle: Long, micEnabled: Boolean, onDisconnect: () -> Unit) {
         // Live stats HUD (FPS / throughput / capture→client latency), drawn over the video but
         // BEFORE the transparent gesture layer below, so it shows through and never eats touches.
         if (showStats) {
-            stats?.let { StatsOverlay(it, Modifier.align(Alignment.TopStart).padding(12.dp)) }
+            stats?.let { StatsOverlay(it, decoderLabel, Modifier.align(Alignment.TopStart).padding(12.dp)) }
         }
         // Touch input per the Settings model: trackpad/direct-pointer mouse (the shared gesture
         // vocabulary) or real multi-touch passthrough — see TouchInput.kt.

clients/android/app/src/main/res/xml/game_mode_config.xml

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!--
+  Game Mode config (Android 13 / API 33+). We support the Performance game mode; and we opt OUT of
+  the two OEM interventions that would corrupt a game-streaming session:
+    - allowGameDownscaling=false: the client renders exactly the host's negotiated resolution; a
+      platform downscale would blur the stream.
+    - allowGameFpsOverride=false: the stream is paced to the host's frame rate; a platform FPS cap
+      would drop frames / add judder.
+  Ignored on releases below API 33.
+-->
+<game-mode-config xmlns:android="http://schemas.android.com/apk/res/android"
+    android:supportsPerformanceGameMode="true"
+    android:allowGameDownscaling="false"
+    android:allowGameFpsOverride="false" />

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

@@ -104,14 +104,40 @@ object NativeBridge {
     external fun nativeWakeOnLan(macsCsv: String, lastIp: String): Boolean
 
     /**
-     * Start the HEVC decode thread rendering onto [surface] (a SurfaceView's surface). Decode runs
+     * The MediaCodec MIME the host resolved for this session (`"video/hevc"` / `"video/avc"` /
-     * entirely in Rust (NDK AMediaCodec → ANativeWindow) — no per-frame JNI. No-op if already started.
+     * `"video/av01"`), or `""` on a `0` handle. Kotlin ranks `MediaCodecList` decoders for this
+     * MIME (see [io.unom.punktfunk.kit.VideoDecoders]) before [nativeStartVideo]. Cheap; UI-safe.
      */
-    external fun nativeStartVideo(handle: Long, surface: android.view.Surface)
+    external fun nativeVideoMime(handle: Long): String
+
+    /**
+     * Start the decode thread rendering onto [surface] (a SurfaceView's surface). Decode runs
+     * entirely in Rust (NDK AMediaCodec → ANativeWindow) — no per-frame JNI. [decoderName] is the
+     * decoder Kotlin ranked from `MediaCodecList` (`""` = let the platform resolve the default for
+     * the MIME); [lowLatencyMode] is the user's master toggle (default on → aggressive per-SoC
+     * tuning; off → conservative); [lowLatencyFeature] is whether [decoderName] advertised
+     * `FEATURE_LowLatency` (HUD label only). [isTv] drives an active HDMI mode switch to the stream
+     * refresh on TV boxes (vs. the softer seamless hint on phones). No-op if already started.
+     */
+    external fun nativeStartVideo(
+        handle: Long,
+        surface: android.view.Surface,
+        decoderName: String,
+        lowLatencyMode: Boolean,
+        lowLatencyFeature: Boolean,
+        isTv: Boolean,
+    )
 
     /** Stop + join the decode thread without closing the session. No-op on `0`. */
     external fun nativeStopVideo(handle: Long)
 
+    /**
+     * The resolved decoder identity for the HUD, e.g. `c2.qti.avc.decoder · low-latency`, or `""`
+     * before the decode thread has resolved one. One-shot (fixed for the session); poll once after
+     * the HUD appears.
+     */
+    external fun nativeVideoDecoderLabel(handle: Long): String
+
     /**
      * Drain ~1 s of live decode stats for the on-stream HUD, or `null` when no decode thread runs.
      * Returns 18 doubles (unified stats spec, `design/stats-unification.md`):

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

@@ -0,0 +1,85 @@
+package io.unom.punktfunk.kit
+
+import android.media.MediaCodecInfo.CodecCapabilities
+import android.media.MediaCodecList
+import android.os.Build
+
+/** The decoder Kotlin ranked for a MIME, handed to [NativeBridge.nativeStartVideo]. */
+data class DecoderChoice(val name: String, val lowLatencyFeature: Boolean)
+
+/**
+ * Rank the platform's `MediaCodecList` decoders for a video MIME and pick the best one for
+ * low-latency streaming, the way Moonlight-Android does. There is no NDK `MediaCodecList`, so this
+ * enumeration must live on the Kotlin (framework) side; Rust then creates the chosen decoder by
+ * name (`AMediaCodec_createCodecByName`) and derives the per-SoC vendor low-latency keys from it.
+ *
+ * Ranking (best first): hardware over software; a real SoC-vendor decoder (Qualcomm/Amlogic/…) over
+ * the generic AOSP software fallback; a decoder advertising `FEATURE_LowLatency` over one that
+ * doesn't. Known-bad software decoders (`omx.google.*`, `c2.android.*`, Qualcomm/Samsung SW HEVC)
+ * are dropped outright — matching Moonlight's blacklist.
+ */
+object VideoDecoders {
+    /** Decoder-name prefixes/names we never want, mirroring Moonlight's blacklist. */
+    private val BLOCKED_PREFIXES = listOf("omx.google.", "c2.android.", "avcdecoder", "omx.ffmpeg.")
+    private val BLOCKED_EXACT = listOf("omx.qcom.video.decoder.hevcswvdec", "omx.sec.hevc.sw.dec")
+
+    /**
+     * Real SoC-vendor decoder prefixes we prefer over the generic AOSP fallback, covering the common
+     * targets: Qualcomm Snapdragon and MediaTek (most phones + many TV boxes), Samsung Exynos (+
+     * Google Tensor, whose decoder is `c2.exynos.*`), NVIDIA Tegra (Shield TV), Amlogic / Rockchip /
+     * Realtek (TV boxes & smart TVs), and HiSilicon Kirin (older Huawei).
+     */
+    private val VENDOR_PREFIXES = listOf(
+        "omx.qcom", "c2.qti",
+        "omx.mtk", "c2.mtk",
+        "omx.exynos", "c2.exynos",
+        "omx.nvidia", "c2.nvidia",
+        "omx.amlogic", "c2.amlogic",
+        "omx.rk", "c2.rk",
+        "omx.realtek", "c2.realtek",
+        "omx.hisi", "c2.hisi",
+    )
+
+    /**
+     * Pick the best decoder for [mime] (`"video/hevc"` / `"video/avc"` / `"video/av01"`), or `null`
+     * to let the platform resolve its default. Enumerates once — call at stream start.
+     */
+    fun pickDecoder(mime: String): DecoderChoice? {
+        if (mime.isEmpty()) return null
+        val infos = runCatching { MediaCodecList(MediaCodecList.REGULAR_CODECS).codecInfos }
+            .getOrNull() ?: return null
+
+        var bestName: String? = null
+        var bestLowLatency = false
+        var bestScore = Int.MIN_VALUE
+        for (info in infos) {
+            if (info.isEncoder) continue
+            val name = info.name
+            val lower = name.lowercase()
+            if (BLOCKED_PREFIXES.any { lower.startsWith(it) } || lower in BLOCKED_EXACT) continue
+            val caps = runCatching { info.getCapabilitiesForType(mime) }.getOrNull() ?: continue
+
+            val hardware = if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.Q) {
+                info.isHardwareAccelerated
+            } else {
+                // Pre-Q heuristic: the software decoders are the ones we can name (already blocked
+                // above), so anything surviving the blacklist is treated as hardware.
+                true
+            }
+            val lowLatency = Build.VERSION.SDK_INT >= Build.VERSION_CODES.R &&
+                runCatching { caps.isFeatureSupported(CodecCapabilities.FEATURE_LowLatency) }
+                    .getOrDefault(false)
+            val vendor = VENDOR_PREFIXES.any { lower.startsWith(it) }
+
+            val score = (if (hardware) 100 else 0) +
+                (if (vendor) 40 else 0) +
+                (if (lowLatency) 20 else 0)
+            if (score > bestScore) {
+                bestScore = score
+                bestName = name
+                bestLowLatency = lowLatency
+            }
+        }
+        return bestName?.let { DecoderChoice(it, bestLowLatency) }
+    }
+}

clients/android/native/src/adpf.rs

@@ -28,6 +28,7 @@ type CreateSessionFn = unsafe extern "C" fn(*mut c_void, *const i32, usize, i64)
 type ReportFn = unsafe extern "C" fn(*mut c_void, i64) -> c_int;
 type UpdateTargetFn = unsafe extern "C" fn(*mut c_void, i64) -> c_int;
 type CloseFn = unsafe extern "C" fn(*mut c_void);
+type SetPreferPowerEfficiencyFn = unsafe extern "C" fn(*mut c_void, bool) -> c_int;
 
 /// The entry points we use, resolved once from `libandroid.so`, plus the process-wide manager.
 struct Api {
@@ -35,6 +36,9 @@ struct Api {
     report: ReportFn,
     update_target: UpdateTargetFn,
     close: CloseFn,
+    /// `APerformanceHint_setPreferPowerEfficiency` — NDK **API 35**, so `Option`al even when the
+    /// rest of ADPF resolved (a 33/34 device has the session API but not this one).
+    set_prefer_power_efficiency: Option<SetPreferPowerEfficiencyFn>,
     manager: *mut c_void,
 }
 
@@ -70,11 +74,20 @@ fn resolve_api() -> Option<Api> {
         if manager.is_null() {
             return None;
         }
+        // Optional (API 35): resolve if present, else `None` — the session still works without it.
+        let set_prefer_power_efficiency =
+            libc::dlsym(lib, c"APerformanceHint_setPreferPowerEfficiency".as_ptr());
+        let set_prefer_power_efficiency = (!set_prefer_power_efficiency.is_null()).then(|| {
+            std::mem::transmute::<*mut c_void, SetPreferPowerEfficiencyFn>(
+                set_prefer_power_efficiency,
+            )
+        });
         Some(Api {
             create_session: std::mem::transmute::<*mut c_void, CreateSessionFn>(create_session),
             report: std::mem::transmute::<*mut c_void, ReportFn>(report),
             update_target: std::mem::transmute::<*mut c_void, UpdateTargetFn>(update_target),
             close: std::mem::transmute::<*mut c_void, CloseFn>(close),
+            set_prefer_power_efficiency,
             manager,
         })
     }
@@ -103,6 +116,13 @@ impl HintSession {
         if session.is_null() {
             return None;
         }
+        // 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) };
+        }
         Some(Self { api, session })
     }
 

clients/android/native/src/audio.rs

@@ -18,8 +18,8 @@
 //! grown on XRuns (Google's anti-glitch technique).
 
 use ndk::audio::{
-    AudioCallbackResult, AudioDirection, AudioFormat, AudioPerformanceMode, AudioSharingMode,
+    AudioCallbackResult, AudioContentType, AudioDirection, AudioFormat, AudioPerformanceMode,
-    AudioStream, AudioStreamBuilder,
+    AudioSharingMode, AudioStream, AudioStreamBuilder, AudioUsage,
 };
 use punktfunk_core::client::NativeClient;
 use punktfunk_core::error::PunktfunkError;
@@ -235,6 +235,11 @@ impl AudioPlayback {
                 // 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)
                 .performance_mode(AudioPerformanceMode::LowLatency)
                 .sharing_mode(sharing)
                 .data_callback(Box::new(callback))

clients/android/native/src/decode.rs

@@ -8,8 +8,8 @@
 
 use ndk::data_space::DataSpace;
 use ndk::media::media_codec::{
-    DequeuedInputBufferResult, DequeuedOutputBufferInfoResult, MediaCodec, MediaCodecDirection,
+    AsyncNotifyCallback, DequeuedInputBufferResult, DequeuedOutputBufferInfoResult, MediaCodec,
-    OutputBuffer,
+    MediaCodecDirection, OutputBuffer,
 };
 use ndk::media::media_format::MediaFormat;
 use ndk::native_window::NativeWindow;
@@ -19,9 +19,14 @@ use punktfunk_core::session::Frame;
 use std::collections::VecDeque;
 use std::ffi::c_void;
 use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
+use std::sync::{mpsc, Arc, Mutex};
 use std::time::{Duration, Instant};
 
+/// Cap on AUs parked in the async loop awaiting a free codec input slot. Matches the connector's
+/// own frame-channel depth; on sustained overflow the oldest is dropped and a keyframe requested
+/// (same recovery as a reassembler drop). In steady state this stays near-empty.
+const FRAME_PARK_CAP: usize = 16;
+
 /// Cap on the pts→received-timestamp map below: MediaCodec holds only a handful of frames in
 /// flight, so anything beyond this is stale (codec flushed / HUD toggled) and gets evicted.
 const IN_FLIGHT_CAP: usize = 64;
@@ -31,29 +36,80 @@ 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;
 
-/// The decode loop. Runs on the `pf-decode` thread until `shutdown` is set or the session closes.
+/// 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.
+const USE_ASYNC_DECODE: bool = true;
+
+/// Per-session decode configuration, resolved by the JNI layer (`nativeStartVideo`) and passed to
+/// the decode loop. Bundled so the loop entry points don't sprout a wide argument list.
+pub(crate) struct DecodeOptions {
+    /// The decoder Kotlin ranked from `MediaCodecList` (`VideoDecoders.pickDecoder`). `None`/empty ⇒
+    /// let the platform resolve the default decoder for the MIME.
+    pub decoder_name: Option<String>,
+    /// 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).
+    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.
+    pub is_tv: bool,
+}
+
+/// The decode entry point on the `pf-decode` thread: dispatches to the async or synchronous loop.
+/// Both run until `shutdown` is set or the session closes.
 pub fn run(
     client: Arc<NativeClient>,
     window: NativeWindow,
     shutdown: Arc<AtomicBool>,
     stats: Arc<crate::stats::VideoStats>,
+    opts: DecodeOptions,
 ) {
+    if 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)]
+fn run_sync(
+    client: Arc<NativeClient>,
+    window: NativeWindow,
+    shutdown: Arc<AtomicBool>,
+    stats: Arc<crate::stats::VideoStats>,
+    opts: DecodeOptions,
+) {
+    let DecodeOptions {
+        decoder_name,
+        ll_feature,
+        low_latency_mode,
+        is_tv,
+    } = opts;
     boost_thread_priority();
     let mode = client.mode();
-    // The MediaCodec MIME for the codec the host resolved (`Welcome.codec`): HEVC or H.264. AMediaCodec
+    // The MediaCodec MIME for the codec the host resolved (`Welcome.codec`). AMediaCodec needs no
-    // needs no out-of-band extradata — the in-band VPS/SPS/PPS on every IDR configure it either way.
+    // out-of-band extradata — the in-band VPS/SPS/PPS on every IDR configure it either way.
-    let mime = match client.codec {
+    let mime = codec_mime(client.codec);
-        punktfunk_core::quic::CODEC_H264 => "video/avc",
+    let codec = match create_codec(mime, decoder_name.as_deref()) {
-        _ => "video/hevc",
-    };
-    let codec = match MediaCodec::from_decoder_type(mime) {
         Some(c) => c,
         None => {
             log::error!("decode: no {mime} decoder on this device");
             return;
         }
     };
-    log::info!("decode: codec mime = {mime}");
+    // The decoder's *actual* resolved name (Kotlin's pick, or the platform default when it fell
+    // back) drives both the HUD label and which vendor low-latency keys apply below.
+    let codec_name = codec.name().unwrap_or_default();
+    stats.set_decoder(&codec_name, ll_feature);
+    log::info!(
+        "decode: codec mime = {mime}, decoder = {codec_name} (low-latency feature: {ll_feature})"
+    );
 
     let mut format = MediaFormat::new();
     format.set_str("mime", mime);
@@ -64,23 +120,9 @@ pub fn run(
         "max-input-size",
         (mode.width * mode.height).max(2_000_000) as i32,
     );
-    // Ask for the low-latency decode path where the decoder supports it (no reordering buffer).
+    // Standard + per-SoC vendor low-latency keys and the clock hints, gated on the resolved decoder
-    format.set_i32("low-latency", 1);
+    // name and the master toggle (see `configure_low_latency`).
-    // Best-effort vendor twin of the standard key: older Qualcomm decoders only honor their own
+    configure_low_latency(&mut format, &codec_name, low_latency_mode);
-    // extension. Unknown keys are ignored by other vendors' codecs, so this is safe to set blind.
-    format.set_i32("vendor.qti-ext-dec-low-latency.enable", 1);
-    // Advisory low-latency hints (KEY_PRIORITY / KEY_OPERATING_RATE), ignored where unsupported:
-    // realtime priority + the target frame rate, so vendor decoders (e.g. Qualcomm) run at full
-    // clocks instead of a power-saving cadence that adds dequeue latency.
-    format.set_i32("priority", 0); // 0 = realtime
-                                   // Operating rate = the codec's clock hint. Setting it to the display rate merely asks the
-                                   // decoder to *sustain* that cadence — a Qualcomm decoder can meet 60/120 fps at a power-saving
-                                   // clock that adds a millisecond-plus of decode latency per frame. Setting it to the AOSP
-                                   // "unbounded" sentinel (Short.MAX) instead asks the decoder to run each frame at max clocks and
-                                   // finish ASAP, minimising per-frame decode latency — the right trade for a real-time stream
-                                   // (costs power/heat; the dial to lower if a device thermally throttles over a long session).
-                                   // Ignored where unsupported.
-    format.set_i32("operating-rate", i16::MAX as i32); // 32767 = "as fast as possible"
 
     // HDR static metadata (ST.2086 mastering + content light level): when an HDR session was
     // negotiated, set KEY_HDR_STATIC_INFO so the display tone-maps from the source's real grade.
@@ -118,7 +160,7 @@ pub fn run(
     // 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) {
+    if mode.refresh_hz > 0 && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv) {
         log::debug!(
             "decode: set_frame_rate({} Hz) unavailable/declined (non-fatal)",
             mode.refresh_hz
@@ -277,6 +319,7 @@ pub fn run(
                 // 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);
                 log::info!(
                     "decode: ADPF hint session {} — {} hot thread(s), target {frame_period_ns} ns",
@@ -326,6 +369,609 @@ fn now_realtime_ns() -> i128 {
         .unwrap_or(0)
 }
 
+/// The MediaCodec MIME for the codec the host resolved (`Welcome.codec`). Shared by the decode
+/// thread and `nativeVideoMime` (which tells Kotlin what to rank decoders for). AV1 uses the
+/// AOSP `video/av01` type; anything not H.264/AV1 is treated as HEVC (every pre-negotiation host
+/// emitted HEVC).
+pub(crate) fn codec_mime(codec: u8) -> &'static str {
+    match codec {
+        punktfunk_core::quic::CODEC_H264 => "video/avc",
+        punktfunk_core::quic::CODEC_AV1 => "video/av01",
+        _ => "video/hevc",
+    }
+}
+
+/// Create the decoder: prefer the specific codec Kotlin ranked from `MediaCodecList`
+/// (`from_codec_name`), falling back to the platform's default decoder for the MIME
+/// (`from_decoder_type`) if that name can't be created (codec busy / renamed across an OS update).
+fn create_codec(mime: &str, preferred: Option<&str>) -> Option<MediaCodec> {
+    if let Some(name) = preferred.filter(|n| !n.is_empty()) {
+        if let Some(c) = MediaCodec::from_codec_name(name) {
+            return Some(c);
+        }
+        log::warn!(
+            "decode: from_codec_name({name}) failed — falling back to default {mime} decoder"
+        );
+    }
+    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.
+///
+/// Vendor keys mirror Moonlight's `MediaCodecHelper` (verified against current source): Qualcomm
+/// picture-order + low-latency, Exynos (also Google Tensor), Amlogic, HiSilicon, MediaTek. NVIDIA
+/// Tegra / Rockchip / Realtek expose no such key (nor does Moonlight) — they're covered by the
+/// standard key + clock hint + being ranked first in `VideoDecoders`.
+fn configure_low_latency(format: &mut MediaFormat, codec_name: &str, aggressive: bool) {
+    // Standard key: request the no-reorder low-latency path where the platform decoder supports it.
+    format.set_i32("low-latency", 1);
+    if !aggressive {
+        return;
+    }
+    // MediaTek's low-latency key — very common (mid/budget phones + many Google TV / Fire TV boxes).
+    // Set unconditionally like the standard key: MediaTek decoders honour it, others ignore it, so it
+    // covers MediaTek whatever the exact decoder name (omx.mtk / c2.mtk / an OEM rename). Moonlight
+    // does the same, and also relies on it for Amazon's Amlogic fork.
+    format.set_i32("vdec-lowlatency", 1);
+    let name = codec_name.to_ascii_lowercase();
+    let is = |prefix: &str| name.starts_with(prefix);
+    // Qualcomm Snapdragon (the most common phone SoC): picture-order forces decode-order output
+    // (kills the reorder buffer on decoders that predate the standard key); low-latency is the older
+    // vendor twin.
+    if is("omx.qcom") || is("c2.qti") {
+        format.set_i32("vendor.qti-ext-dec-picture-order.enable", 1);
+        format.set_i32("vendor.qti-ext-dec-low-latency.enable", 1);
+    }
+    // Samsung Exynos — also covers Google Tensor (Pixel 6+), whose hardware decoder is `c2.exynos.*`.
+    if is("omx.exynos") || is("c2.exynos") {
+        format.set_i32("vendor.rtc-ext-dec-low-latency.enable", 1);
+    }
+    // Amlogic — the Android TV boxes (onn 4K, Chromecast w/ Google TV, Homatics).
+    if is("omx.amlogic") || is("c2.amlogic") {
+        format.set_i32("vendor.low-latency.enable", 1);
+    }
+    // HiSilicon / Kirin (older Huawei; paired req/rdy keys).
+    if is("omx.hisi") || is("c2.hisi") {
+        format.set_i32(
+            "vendor.hisi-ext-low-latency-video-dec.video-scene-for-low-latency-req",
+            1,
+        );
+        format.set_i32(
+            "vendor.hisi-ext-low-latency-video-dec.video-scene-for-low-latency-rdy",
+            -1,
+        );
+    }
+    // NVIDIA Tegra (Shield TV) and Rockchip/Realtek (budget TV boxes / smart TVs) expose no
+    // low-latency vendor key (Moonlight has none either) — their decoders are already low-latency
+    // oriented, so the standard `low-latency` key + the clock hint below + being ranked first
+    // (see `VideoDecoders`) is their treatment.
+    //
+    // Clock hint, mutually exclusive (matching Moonlight): the AOSP "unbounded" operating-rate
+    // sentinel (Short.MAX) tells the decoder to run each frame at max clocks and finish ASAP rather
+    // than pace to the frame rate — shaving per-frame decode latency at a power/heat cost. Only
+    // Qualcomm is known to handle the sentinel; every other vendor mis-paces on it, so they get the
+    // plain realtime `priority` hint instead.
+    if decoder_supports_max_operating_rate(&name) {
+        format.set_i32("operating-rate", i16::MAX as i32); // 32767 = "as fast as possible"
+    } else {
+        format.set_i32("priority", 0); // 0 = realtime
+    }
+}
+
+/// Whether a decoder tolerates `operating-rate = Short.MAX` rather than regressing on it. Follows
+/// Moonlight's allowlist: Qualcomm decoders honour the sentinel (the Adreno 620 generation is the
+/// known exception Moonlight excludes by GPU model — undetectable from native code here, so it
+/// rides the master toggle as its escape hatch). Other vendors fall back to the plain `priority`
+/// hint above.
+fn decoder_supports_max_operating_rate(name_lower: &str) -> bool {
+    name_lower.starts_with("omx.qcom") || name_lower.starts_with("c2.qti")
+}
+
+/// One decoded output buffer ready to release: its codec buffer index + the pts the codec echoed
+/// (from the output callback's `BufferInfo`), used to pair the `decode` HUD stat.
+struct OutputReady {
+    index: usize,
+    pts_us: u64,
+}
+
+/// Events the async decode loop reacts to. The codec's async-notify callbacks (which run on its
+/// internal looper thread) push the codec ones; the feeder thread pushes `Au`. Each carries only
+/// owned/`Copy` data so the callback closures satisfy the `Send` bound and never touch the codec.
+enum DecodeEvent {
+    /// A received access unit from the feeder, ready to queue into the decoder.
+    Au(Frame),
+    /// An input buffer slot freed (index) — we can queue an AU into it.
+    InputAvailable(usize),
+    /// A decoded frame is ready (buffer index + echoed pts).
+    OutputAvailable { index: usize, pts_us: u64 },
+    /// The output format changed — re-check the stream's colour signalling (HDR DataSpace).
+    FormatChanged,
+    /// The codec reported an error; `fatal` when neither recoverable nor transient.
+    Error { fatal: bool },
+}
+
+/// The event-driven async decode loop (default; see [`run`]/[`USE_ASYNC_DECODE`]). The codec drives
+/// us: an async-notify callback fires the instant an input buffer frees or a frame finishes
+/// decoding, so a decoded frame is presented immediately instead of waiting out a poll interval (the
+/// latency the sync loop left on the table). The callbacks run on the codec's internal looper thread
+/// and only *push events* — every `AMediaCodec` buffer op stays on this thread, which owns the codec,
+/// sidestepping the self-reference that would arise from a callback calling back into the codec it's
+/// stored in. A small `pf-decode-feed` thread blocks on the network so this loop never does.
+fn run_async(
+    client: Arc<NativeClient>,
+    window: NativeWindow,
+    shutdown: Arc<AtomicBool>,
+    stats: Arc<crate::stats::VideoStats>,
+    opts: DecodeOptions,
+) {
+    let DecodeOptions {
+        decoder_name,
+        ll_feature,
+        low_latency_mode,
+        is_tv,
+    } = opts;
+    boost_thread_priority();
+    let mode = client.mode();
+    let mime = codec_mime(client.codec);
+    let mut codec = match create_codec(mime, decoder_name.as_deref()) {
+        Some(c) => c,
+        None => {
+            log::error!("decode: no {mime} decoder on this device");
+            return;
+        }
+    };
+    let codec_name = codec.name().unwrap_or_default();
+    stats.set_decoder(&codec_name, ll_feature);
+    log::info!(
+        "decode: codec mime = {mime}, decoder = {codec_name} (async, low-latency feature: {ll_feature})"
+    );
+
+    // The event channel: the callbacks + feeder push, this loop pulls. `Sender` is `Send`, so the
+    // callback closures (each capturing a clone) satisfy the async-notify `Send` bound.
+    let (ev_tx, ev_rx) = mpsc::channel::<DecodeEvent>();
+    // Install the callbacks BEFORE configure()/start() so we're in async mode from the first buffer.
+    // Each just forwards an index/flag — no codec access here (the codec owns these closures).
+    {
+        let out_tx = ev_tx.clone();
+        let in_tx = ev_tx.clone();
+        let fmt_tx = ev_tx.clone();
+        let err_tx = ev_tx.clone();
+        let cb = AsyncNotifyCallback {
+            on_input_available: Some(Box::new(move |idx| {
+                let _ = in_tx.send(DecodeEvent::InputAvailable(idx));
+            })),
+            on_output_available: Some(Box::new(move |idx, info| {
+                let _ = out_tx.send(DecodeEvent::OutputAvailable {
+                    index: idx,
+                    pts_us: info.presentation_time_us().max(0) as u64,
+                });
+            })),
+            on_format_changed: Some(Box::new(move |_fmt| {
+                let _ = fmt_tx.send(DecodeEvent::FormatChanged);
+            })),
+            on_error: Some(Box::new(move |e, code, _detail| {
+                let fatal = !code.is_recoverable() && !code.is_transient();
+                log::warn!("decode: codec error {e:?} (fatal={fatal})");
+                let _ = err_tx.send(DecodeEvent::Error { fatal });
+            })),
+        };
+        if let Err(e) = codec.set_async_notify_callback(Some(cb)) {
+            log::error!("decode: set_async_notify_callback failed: {e}");
+            return;
+        }
+    }
+
+    // Build the low-latency format (identical keys to the sync path).
+    let mut format = MediaFormat::new();
+    format.set_str("mime", mime);
+    format.set_i32("width", mode.width as i32);
+    format.set_i32("height", mode.height as i32);
+    format.set_i32(
+        "max-input-size",
+        (mode.width * mode.height).max(2_000_000) as i32,
+    );
+    configure_low_latency(&mut format, &codec_name, low_latency_mode);
+    if client.color.is_hdr() {
+        match client.next_hdr_meta(Duration::from_millis(250)) {
+            Ok(meta) => {
+                format.set_buffer("hdr-static-info", &android_hdr_static_info(&meta));
+                log::info!("decode: HDR static metadata applied (KEY_HDR_STATIC_INFO)");
+            }
+            Err(_) => {
+                log::info!("decode: HDR session but no mastering metadata yet — DataSpace only")
+            }
+        }
+    }
+    if let Err(e) = codec.configure(&format, Some(&window), MediaCodecDirection::Decoder) {
+        log::error!("decode: configure failed: {e}");
+        return;
+    }
+    if let Err(e) = codec.start() {
+        log::error!("decode: start failed: {e}");
+        return;
+    }
+    log::info!(
+        "decode: decoder started (async) at {}x{}",
+        mode.width,
+        mode.height
+    );
+    if mode.refresh_hz > 0 && !try_set_frame_rate(&window, mode.refresh_hz as f32, is_tv) {
+        log::debug!(
+            "decode: set_frame_rate({} Hz) unavailable/declined (non-fatal)",
+            mode.refresh_hz
+        );
+    }
+
+    // Skew-corrected latency stats (spec: design/stats-unification.md). Receipt stamps (keyed by the
+    // pts we queue) live in a shared map: the feeder writes them at receipt, this loop pairs decoded
+    // output back to them. Behind a `Mutex` since two threads touch it — only ever locked while the
+    // HUD is visible.
+    let clock_offset = client.clock_offset_ns;
+    let in_flight = Arc::new(Mutex::new(VecDeque::<(u64, i128)>::new()));
+
+    // Feeder thread: block on the network so this loop doesn't (an AU's arrival becomes an event that
+    // wakes us immediately, with no input-side poll latency). It also records the `received` HUD stat.
+    let feeder = {
+        let client = client.clone();
+        let stats = stats.clone();
+        let in_flight = in_flight.clone();
+        let shutdown = shutdown.clone();
+        let ev_tx = ev_tx.clone();
+        std::thread::Builder::new()
+            .name("pf-decode-feed".into())
+            .spawn(move || {
+                feeder_loop(
+                    client,
+                    stats,
+                    in_flight,
+                    clock_offset as i128,
+                    shutdown,
+                    ev_tx,
+                );
+            })
+            .ok()
+    };
+    drop(ev_tx); // only the feeder + callbacks keep the channel alive now
+
+    // ADPF: same as the sync path — register this thread now, create the session lazily on the first
+    // presented frame (by when the pump + audio + feeder threads have registered their tids too).
+    let frame_period_ns = if mode.refresh_hz > 0 {
+        1_000_000_000i64 / mode.refresh_hz as i64
+    } else {
+        0
+    };
+    client.register_hot_thread();
+    let mut hint: Option<crate::adpf::HintSession> = None;
+    let mut hint_tried = false;
+
+    let mut free_inputs: VecDeque<usize> = VecDeque::new();
+    let mut pending_aus: VecDeque<Frame> = VecDeque::new();
+    let mut ready: Vec<OutputReady> = Vec::new();
+    let mut applied_ds: Option<DataSpace> = None;
+    let mut fed: u64 = 0;
+    let mut rendered: u64 = 0;
+    let mut discarded: u64 = 0;
+    let mut last_dropped = client.frames_dropped();
+    let mut last_kf_req: Option<Instant> = None;
+    // Productive (dispatch+feed+present) time between displayed frames; reported to ADPF once one is
+    // presented. The blocking event wait is excluded (idle, not work) — same accounting as the sync loop.
+    let mut work_accum_ns: i64 = 0;
+    let mut fatal = false;
+
+    while !shutdown.load(Ordering::Relaxed) && !fatal {
+        // Block for the next event (idle wait — excluded from the work tally). The short timeout
+        // drives loss-recovery housekeeping when the pipeline is momentarily quiet.
+        let ev0 = match ev_rx.recv_timeout(Duration::from_millis(5)) {
+            Ok(ev) => Some(ev),
+            Err(mpsc::RecvTimeoutError::Timeout) => None,
+            Err(mpsc::RecvTimeoutError::Disconnected) => break,
+        };
+        let work_t0 = Instant::now();
+        let mut fmt_dirty = false;
+        let mut au_dropped = false;
+        if let Some(ev) = ev0 {
+            au_dropped |= dispatch_event(
+                ev,
+                &mut pending_aus,
+                &mut free_inputs,
+                &mut ready,
+                &mut fmt_dirty,
+                &mut fatal,
+            );
+        }
+        // Coalesce every other event already queued into this one work pass — correct newest-only
+        // presentation across a decode burst, and batched feeding.
+        while let Ok(ev) = ev_rx.try_recv() {
+            au_dropped |= dispatch_event(
+                ev,
+                &mut pending_aus,
+                &mut free_inputs,
+                &mut ready,
+                &mut fmt_dirty,
+                &mut fatal,
+            );
+        }
+        if fmt_dirty {
+            apply_hdr_dataspace(&codec, &window, &mut applied_ds);
+        }
+        feed_ready(&codec, &mut pending_aus, &mut free_inputs, &mut fed);
+        let had_output = !ready.is_empty();
+        present_ready(
+            &codec,
+            &mut ready,
+            &stats,
+            &in_flight,
+            clock_offset,
+            &mut rendered,
+            &mut discarded,
+        );
+
+        work_accum_ns += work_t0.elapsed().as_nanos() as i64;
+        if had_output {
+            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);
+                log::info!(
+                    "decode: ADPF hint session {} — {} hot thread(s), target {frame_period_ns} ns",
+                    if hint.is_some() {
+                        "active"
+                    } else {
+                        "unavailable"
+                    },
+                    tids.len(),
+                );
+            }
+            if let Some(h) = &hint {
+                h.report_actual(work_accum_ns);
+            }
+            work_accum_ns = 0;
+            if rendered > 0 && rendered % 300 == 0 {
+                log::info!("decode: fed={fed} rendered={rendered} discarded={discarded}");
+            }
+        }
+        // Loss recovery: request an IDR when the reassembler's unrecoverable-drop count climbs (or we
+        // dropped a parked AU on overflow), throttled so a multi-frame recovery gap doesn't flood the
+        // control stream.
+        let dropped = client.frames_dropped();
+        if dropped > last_dropped || au_dropped {
+            last_dropped = dropped;
+            let now = Instant::now();
+            if last_kf_req.is_none_or(|t| now.duration_since(t) >= Duration::from_millis(100)) {
+                last_kf_req = Some(now);
+                let _ = client.request_keyframe();
+            }
+        }
+    }
+
+    let _ = codec.stop();
+    shutdown.store(true, Ordering::SeqCst); // ensure the feeder wakes and exits, then join it
+    if let Some(j) = feeder {
+        let _ = j.join();
+    }
+    log::info!("decode: stopped (async, fed={fed} rendered={rendered} discarded={discarded})");
+}
+
+/// The `pf-decode-feed` thread: block on the connector for the next access unit so the async loop
+/// never has to. Records the `received` HUD stat (receipt point) — including the Phase-2 host/network
+/// split from any matching 0xCF host timings — then hands the AU to the loop via the event channel.
+/// Exits when `shutdown` is set, the session closes, or the loop's receiver is gone.
+fn feeder_loop(
+    client: Arc<NativeClient>,
+    stats: Arc<crate::stats::VideoStats>,
+    in_flight: Arc<Mutex<VecDeque<(u64, i128)>>>,
+    clock_offset: i128,
+    shutdown: Arc<AtomicBool>,
+    ev_tx: mpsc::Sender<DecodeEvent>,
+) {
+    // Received AUs awaiting their 0xCF host timing (Phase-2 split), as (pts_ns, capture→received µs).
+    let mut pending_split: VecDeque<(u64, u64)> = VecDeque::new();
+    while !shutdown.load(Ordering::Relaxed) {
+        match client.next_frame(Duration::from_millis(5)) {
+            Ok(frame) => {
+                if stats.enabled() {
+                    let received_ns = now_realtime_ns();
+                    let lat_ns = received_ns + clock_offset - frame.pts_ns as i128;
+                    let lat_us =
+                        (lat_ns > 0 && lat_ns < 10_000_000_000).then_some((lat_ns / 1000) as u64);
+                    stats.note_received(frame.data.len(), lat_us, clock_offset != 0);
+                    {
+                        let mut g = in_flight
+                            .lock()
+                            .unwrap_or_else(std::sync::PoisonError::into_inner);
+                        g.push_back((frame.pts_ns / 1000, received_ns));
+                        if g.len() > IN_FLIGHT_CAP {
+                            g.pop_front(); // stale — codec never echoed it back
+                        }
+                    }
+                    if let Some(hostnet_us) = lat_us {
+                        pending_split.push_back((frame.pts_ns, hostnet_us));
+                        if pending_split.len() > PENDING_SPLIT_CAP {
+                            pending_split.pop_front();
+                        }
+                    }
+                    while let Ok(t) = client.next_host_timing(Duration::ZERO) {
+                        if let Some(i) = pending_split.iter().position(|&(p, _)| p == t.pts_ns) {
+                            let (_, hostnet_us) = pending_split.remove(i).unwrap();
+                            stats.note_host_split(
+                                t.host_us as u64,
+                                hostnet_us.saturating_sub(t.host_us as u64),
+                            );
+                        }
+                    }
+                }
+                if ev_tx.send(DecodeEvent::Au(frame)).is_err() {
+                    break; // the decode loop is gone
+                }
+            }
+            Err(PunktfunkError::NoFrame) => {} // timeout — re-check shutdown and poll again
+            Err(_) => break,                   // session closed
+        }
+    }
+}
+
+/// Route one [`DecodeEvent`] into the loop's working sets. Returns `true` only when a parked AU was
+/// dropped on overflow (the caller then requests a keyframe).
+fn dispatch_event(
+    ev: DecodeEvent,
+    pending_aus: &mut VecDeque<Frame>,
+    free_inputs: &mut VecDeque<usize>,
+    ready: &mut Vec<OutputReady>,
+    fmt_dirty: &mut bool,
+    fatal: &mut bool,
+) -> bool {
+    match ev {
+        DecodeEvent::Au(f) => {
+            pending_aus.push_back(f);
+            if pending_aus.len() > FRAME_PARK_CAP {
+                pending_aus.pop_front(); // sustained overflow — drop oldest, signal a keyframe request
+                return true;
+            }
+        }
+        DecodeEvent::InputAvailable(i) => free_inputs.push_back(i),
+        DecodeEvent::OutputAvailable { index, pts_us } => ready.push(OutputReady { index, pts_us }),
+        DecodeEvent::FormatChanged => *fmt_dirty = true,
+        DecodeEvent::Error { fatal: f } => {
+            if f {
+                *fatal = true;
+            }
+        }
+    }
+    false
+}
+
+/// Queue as many parked AUs as there are free input buffer slots (async mode: the indices come from
+/// `InputAvailable` callbacks, not a dequeue). Each AU is copied into its codec input buffer and
+/// submitted; a too-large AU is truncated (logged) rather than dropped.
+fn feed_ready(
+    codec: &MediaCodec,
+    pending_aus: &mut VecDeque<Frame>,
+    free_inputs: &mut VecDeque<usize>,
+    fed: &mut u64,
+) {
+    while !pending_aus.is_empty() && !free_inputs.is_empty() {
+        let idx = free_inputs.pop_front().unwrap();
+        let frame = pending_aus.pop_front().unwrap();
+        let pts_us = frame.pts_ns / 1000;
+        let Some(dst) = codec.input_buffer(idx) else {
+            log::warn!("decode: input_buffer({idx}) returned None — dropping AU");
+            continue;
+        };
+        let au = &frame.data;
+        let n = au.len().min(dst.len());
+        if n < au.len() {
+            log::warn!(
+                "decode: AU {} > input buffer {}, truncated",
+                au.len(),
+                dst.len()
+            );
+        }
+        // SAFETY: `au` (wire AU) and `dst` (codec input buffer) are distinct allocations, both valid
+        // for `n` bytes; `MaybeUninit<u8>` is layout-identical to `u8`, so this initializes dst[..n].
+        unsafe {
+            std::ptr::copy_nonoverlapping(au.as_ptr(), dst.as_mut_ptr().cast::<u8>(), n);
+        }
+        if let Err(e) = codec.queue_input_buffer_by_index(idx, 0, n, pts_us, 0) {
+            log::warn!("decode: queue_input_buffer_by_index: {e}");
+        } else {
+            *fed += 1;
+        }
+    }
+}
+
+/// Present only the NEWEST ready output (render = true) and release the rest without rendering — a
+/// burst of stale frames on glass is worse than skipping to the freshest (the sync loop's newest-ready
+/// policy, callback-driven). Every dequeued buffer, rendered or not, is the HUD's `decoded`
+/// measurement point (it finished decoding either way); samples are recorded in pts order so the
+/// receipt-map eviction stays monotonic. `ready` is drained.
+fn present_ready(
+    codec: &MediaCodec,
+    ready: &mut Vec<OutputReady>,
+    stats: &crate::stats::VideoStats,
+    in_flight: &Mutex<VecDeque<(u64, i128)>>,
+    clock_offset: i64,
+    rendered: &mut u64,
+    discarded: &mut u64,
+) {
+    if ready.is_empty() {
+        return;
+    }
+    if stats.enabled() {
+        let mut g = in_flight
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        for o in ready.iter() {
+            note_decoded_pts(stats, &mut g, clock_offset, o.pts_us);
+        }
+    }
+    let last = ready.len() - 1;
+    for (i, o) in ready.drain(..).enumerate() {
+        let render = i == last;
+        match codec.release_output_buffer_by_index(o.index, render) {
+            Ok(()) if render => *rendered += 1,
+            Ok(()) => *discarded += 1,
+            Err(e) => {
+                log::warn!(
+                    "decode: release_output_buffer_by_index({}, {render}): {e}",
+                    o.index
+                )
+            }
+        }
+    }
+}
+
+/// React to an output-format change by signalling the stream's HDR dataspace on the Surface (SDR
+/// streams leave the default alone). The AMediaCodec analogue of the sync loop's `OutputFormatChanged`
+/// handling; safe to call repeatedly (`applied_ds` dedups).
+fn apply_hdr_dataspace(
+    codec: &MediaCodec,
+    window: &NativeWindow,
+    applied_ds: &mut Option<DataSpace>,
+) {
+    if let Some(ds) = hdr_dataspace(codec) {
+        if *applied_ds != Some(ds) {
+            match window.set_buffers_data_space(ds) {
+                Ok(()) => {
+                    *applied_ds = Some(ds);
+                    log::info!("decode: HDR stream → Surface dataspace {ds}");
+                }
+                Err(e) => {
+                    log::warn!("decode: set_buffers_data_space({ds}) failed (non-fatal): {e}")
+                }
+            }
+        }
+    }
+}
+
+/// Raise the pipeline's OTHER hot threads — the core's data-plane pump (UDP receive + FEC
+/// reassembly) and the audio decode thread — toward the display band, matching this decode thread's
+/// own boost. `setpriority(PRIO_PROCESS, tid)` targets any task in the process, so we do it from
+/// here once their tids are known (the same set ADPF hints), without a per-platform priority hook
+/// in the shared core. Slightly below the decode thread's -10 so the display path still wins.
+/// Best-effort; skips this thread (already boosted) and is non-fatal if the platform refuses.
+fn boost_hot_threads(tids: &[i32]) {
+    // SAFETY: `gettid` is an always-safe syscall on the calling thread.
+    let self_tid = unsafe { libc::gettid() };
+    for &tid in tids {
+        if tid == self_tid {
+            continue;
+        }
+        // SAFETY: `setpriority` with PRIO_PROCESS + a live tid in our own process is an always-safe
+        // syscall; a refusal is reported via the return value, not UB.
+        unsafe {
+            if libc::setpriority(libc::PRIO_PROCESS, tid as libc::id_t, -8) != 0 {
+                log::debug!("decode: setpriority(-8) on hot tid {tid} failed (non-fatal)");
+            }
+        }
+    }
+}
+
 /// Best-effort: raise the decode thread toward Android's URGENT_DISPLAY band so background work
 /// can't preempt it under load (which shows up as late/dropped frames). Non-fatal if the platform
 /// refuses (foreground apps may set their own threads; the exact floor is policy-dependent).
@@ -343,23 +989,48 @@ fn boost_thread_priority() {
     }
 }
 
-/// `ANativeWindow_setFrameRate` (NDK **API 30**) resolved from `libandroid.so` at runtime, so the lib
+/// Set the surface's frame-rate hint to the stream's refresh so SurfaceFlinger picks a matching
-/// still loads on our API-28 floor — a hard import of a >floor symbol makes `dlopen`/`System.load`
+/// display mode and aligns vsync (no 60-in-120 judder). Both NDK entry points sit above our API-28
-/// fail on every API-28/29 device, even where this path is never hit. Mirrors the dlsym approach in
+/// floor, so both are dlsym-resolved at runtime (a hard import of a >floor symbol makes
-/// [`crate::adpf`]. Returns `true` when the platform accepted the hint; `false` on API < 30 (symbol
+/// `dlopen`/`System.load` fail on every API-28/29 device, even where this path is never hit —
-/// absent) or when the platform declined. `compatibility` is fixed to the DEFAULT (0) policy.
+/// mirrors [`crate::adpf`]):
-fn try_set_frame_rate(window: &NativeWindow, frame_rate: f32) -> bool {
+///   - On a **TV** (`is_tv`): `ANativeWindow_setFrameRateWithChangeStrategy` (**API 31**) with
+///     `changeFrameRateStrategy = ALWAYS`, which actively drives the HDMI output into the matching
+///     mode (e.g. 60↔120) instead of leaving the panel at its default and judder-matching. The
+///     forced switch may blank the panel briefly — acceptable once at stream start, not wanted on a
+///     phone. Falls through to the 2-arg hint on API 30.
+///   - Otherwise: `ANativeWindow_setFrameRate` (**API 30**) with `compatibility = DEFAULT` — the
+///     softer, seamless-preferred hint for phones/tablets and the universal fallback.
+///
+/// Returns `true` when the platform accepted a hint; `false` on API < 30 (symbols absent) or a
+/// decline.
+fn try_set_frame_rate(window: &NativeWindow, frame_rate: f32, is_tv: bool) -> bool {
     // int32_t ANativeWindow_setFrameRate(ANativeWindow*, float frameRate, int8_t compatibility)
     type SetFrameRateFn = unsafe extern "C" fn(*mut c_void, f32, i8) -> i32;
+    // int32_t ANativeWindow_setFrameRateWithChangeStrategy(
+    //     ANativeWindow*, float frameRate, int8_t compatibility, int8_t changeFrameRateStrategy)
+    type SetFrameRateStrategyFn = unsafe extern "C" fn(*mut c_void, f32, i8, i8) -> i32;
     // SAFETY: `dlopen` of the always-mapped `libandroid.so` (only bumps its refcount; never closed —
-    // process-lifetime handle). `dlsym` returns null when the symbol is absent (device API < 30),
+    // process-lifetime handle). Each `dlsym` returns null when the symbol is absent (device below the
-    // checked before transmuting the non-null pointer to its fn-pointer type. `window.ptr()` is the
+    // symbol's API level), checked before transmuting the non-null pointer to its fn-pointer type.
-    // live `ANativeWindow` this `NativeWindow` owns for the call's duration.
+    // `window.ptr()` is the live `ANativeWindow` this `NativeWindow` owns for the call's duration.
     unsafe {
         let lib = libc::dlopen(c"libandroid.so".as_ptr(), libc::RTLD_NOW);
         if lib.is_null() {
             return false;
         }
+        // TV: prefer the API-31 change-strategy form to force the mode switch (strategy 1 = ALWAYS,
+        // compatibility 0 = DEFAULT). Absent on API 30 ⇒ fall through to the 2-arg hint below.
+        if is_tv {
+            let sym = libc::dlsym(
+                lib,
+                c"ANativeWindow_setFrameRateWithChangeStrategy".as_ptr(),
+            );
+            if !sym.is_null() {
+                let set = std::mem::transmute::<*mut c_void, SetFrameRateStrategyFn>(sym);
+                return set(window.ptr().as_ptr().cast(), frame_rate, 0, 1) == 0;
+            }
+        }
         let sym = libc::dlsym(lib, c"ANativeWindow_setFrameRate".as_ptr());
         if sym.is_null() {
             return false; // device API < 30 — no per-surface frame-rate hint
@@ -499,7 +1170,22 @@ fn note_decoded(
     clock_offset: i64,
     buf: &OutputBuffer<'_>,
 ) {
-    let pts_us = buf.info().presentation_time_us().max(0) as u64;
+    note_decoded_pts(
+        stats,
+        in_flight,
+        clock_offset,
+        buf.info().presentation_time_us().max(0) as u64,
+    );
+}
+
+/// The [`note_decoded`] body keyed by the echoed `presentationTimeUs` directly — the async loop has
+/// the pts (from the output callback's `BufferInfo`) but no borrowed `OutputBuffer`, so it calls this.
+fn note_decoded_pts(
+    stats: &crate::stats::VideoStats,
+    in_flight: &mut VecDeque<(u64, i128)>,
+    clock_offset: i64,
+    pts_us: u64,
+) {
     let decoded_ns = now_realtime_ns();
     // Pair the echoed pts back to its receipt stamp, evicting stale (older) entries as we go.
     let mut received_ns = None;

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

@@ -2,20 +2,31 @@
 //! ~1 Hz decode-stats drain for the HUD.
 
 use jni::objects::JObject;
-use jni::sys::{jboolean, jdoubleArray, jlong, jsize};
+// Used only by the android-gated `nativeStartVideo`; on the host build that fn is cfg'd out.
+#[cfg(target_os = "android")]
+use jni::objects::JString;
+use jni::sys::{jboolean, jdoubleArray, jlong, jsize, jstring};
 use jni::JNIEnv;
 
 use super::{jni_guard, SessionHandle};
 
-/// `NativeBridge.nativeStartVideo(handle, surface)` — wrap the SurfaceView's `Surface` as an
+/// `NativeBridge.nativeStartVideo(handle, surface, decoderName, lowLatencyMode, lowLatencyFeature)`
-/// `ANativeWindow` and start the HEVC decode thread rendering onto it. No-op if already started.
+/// — wrap the SurfaceView's `Surface` as an `ANativeWindow` and start the decode thread rendering
+/// onto it. `decoderName` is the codec Kotlin ranked from `MediaCodecList` (`""` = let the platform
+/// resolve the default for the MIME); `lowLatencyMode` is the user's master toggle;
+/// `lowLatencyFeature` is whether that decoder advertised `FEATURE_LowLatency` (HUD label only).
+/// No-op if already started.
 #[cfg(target_os = "android")]
 #[no_mangle]
 pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStartVideo(
-    env: JNIEnv,
+    mut env: JNIEnv,
     _this: JObject,
     handle: jlong,
     surface: JObject,
+    decoder_name: JString,
+    low_latency_mode: jboolean,
+    ll_feature: jboolean,
+    is_tv: jboolean,
 ) {
     use super::VideoThread;
     use std::sync::atomic::AtomicBool;
@@ -24,6 +35,12 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStartVideo(
     if handle == 0 {
         return;
     }
+    // The decoder name Kotlin picked (empty string / read failure ⇒ None ⇒ default resolver).
+    let decoder = env
+        .get_string(&decoder_name)
+        .ok()
+        .map(String::from)
+        .filter(|s| !s.is_empty());
     // SAFETY: live handle per the nativeConnect/nativeClose contract.
     let h = unsafe { &*(handle as *const SessionHandle) };
     let mut guard = h.video.lock().unwrap();
@@ -48,13 +65,67 @@ pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeStartVideo(
     let client = h.client.clone();
     let sd = shutdown.clone();
     let st = h.stats.clone(); // session-lifetime stats (gate survives surface recreate)
+    let opts = crate::decode::DecodeOptions {
+        decoder_name: decoder,
+        ll_feature: ll_feature != 0,
+        low_latency_mode: low_latency_mode != 0,
+        is_tv: is_tv != 0,
+    };
     let join = std::thread::Builder::new()
         .name("pf-decode".into())
-        .spawn(move || crate::decode::run(client, window, sd, st))
+        .spawn(move || crate::decode::run(client, window, sd, st, opts))
         .ok();
     *guard = Some(VideoThread { shutdown, join });
 }
 
+/// `NativeBridge.nativeVideoMime(handle): String` — the MediaCodec MIME for the codec the host
+/// resolved (`"video/hevc"` / `"video/avc"` / `"video/av01"`), so Kotlin can rank `MediaCodecList`
+/// decoders for it before calling [`Java_io_unom_punktfunk_kit_NativeBridge_nativeStartVideo`].
+/// Empty string on a `0` handle. Cheap; safe on the UI thread.
+#[cfg(target_os = "android")]
+#[no_mangle]
+pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeVideoMime<'local>(
+    env: JNIEnv<'local>,
+    _this: JObject<'local>,
+    handle: jlong,
+) -> jstring {
+    jni_guard(std::ptr::null_mut(), || {
+        if handle == 0 {
+            return std::ptr::null_mut();
+        }
+        // SAFETY: live handle per the nativeConnect/nativeClose contract.
+        let h = unsafe { &*(handle as *const SessionHandle) };
+        match env.new_string(crate::decode::codec_mime(h.client.codec)) {
+            Ok(s) => s.into_raw(),
+            Err(_) => std::ptr::null_mut(),
+        }
+    })
+}
+
+/// `NativeBridge.nativeVideoDecoderLabel(handle): String` — the resolved decoder identity for the
+/// HUD, e.g. `c2.qti.avc.decoder · low-latency`, or `""` before the decode thread has resolved one.
+/// One-shot (the decoder is fixed for the session); poll once after the HUD appears. Not
+/// android-gated — pure `jni` + a lock, so it links on the host build too (Kotlin only calls it on
+/// device).
+#[no_mangle]
+pub extern "system" fn Java_io_unom_punktfunk_kit_NativeBridge_nativeVideoDecoderLabel<'local>(
+    env: JNIEnv<'local>,
+    _this: JObject<'local>,
+    handle: jlong,
+) -> jstring {
+    jni_guard(std::ptr::null_mut(), || {
+        if handle == 0 {
+            return std::ptr::null_mut();
+        }
+        // SAFETY: live handle per the nativeConnect/nativeClose contract.
+        let h = unsafe { &*(handle as *const SessionHandle) };
+        match env.new_string(h.stats.decoder_label()) {
+            Ok(s) => s.into_raw(),
+            Err(_) => std::ptr::null_mut(),
+        }
+    })
+}
+
 /// `NativeBridge.nativeStopVideo(handle)` — stop + join the decode thread (without closing the
 /// session). No-op on `0`.
 #[no_mangle]

clients/android/native/src/stats.rs

@@ -22,9 +22,21 @@ pub struct VideoStats {
     /// they (and the caller's latency computation — see `enabled`) early-out on this flag alone.
     /// Off until Kotlin shows the HUD.
     enabled: AtomicBool,
+    /// The resolved decoder identity for the HUD: the codec's actual `AMediaCodec` name (e.g.
+    /// `c2.qti.avc.decoder`) and whether it advertised `FEATURE_LowLatency`. Set once when the
+    /// decode thread creates the codec (`set_decoder`), read one-shot by `nativeVideoDecoderLabel`.
+    /// Separate from `inner` (never touched per-frame) so naming it costs nothing on the hot path.
+    decoder: Mutex<Option<DecoderInfo>>,
     inner: Mutex<Inner>,
 }
 
+/// The chosen decoder's identity, surfaced on the stats HUD so before/after latency comparisons
+/// name the codec that produced them.
+struct DecoderInfo {
+    name: String,
+    low_latency: bool,
+}
+
 struct Inner {
     window_start: Instant,
     frames: u64,
@@ -79,6 +91,7 @@ impl VideoStats {
     pub fn new() -> VideoStats {
         VideoStats {
             enabled: AtomicBool::new(false),
+            decoder: Mutex::new(None),
             inner: Mutex::new(Inner {
                 window_start: Instant::now(),
                 frames: 0,
@@ -121,6 +134,36 @@ impl VideoStats {
         }
     }
 
+    /// Record the resolved decoder identity for the HUD — the codec's real `AMediaCodec` name and
+    /// whether it reported `FEATURE_LowLatency`. Called once from the decode thread right after the
+    /// codec is created (before `configure`), overwriting any prior value on a surface recreate.
+    // Set only by the android-only decode thread; unreferenced on the host build — expected.
+    #[cfg_attr(not(target_os = "android"), allow(dead_code))]
+    pub fn set_decoder(&self, name: &str, low_latency: bool) {
+        let mut g = self
+            .decoder
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        *g = Some(DecoderInfo {
+            name: name.to_owned(),
+            low_latency,
+        });
+    }
+
+    /// The decoder label for the HUD, e.g. `c2.qti.avc.decoder · low-latency`, or `""` before the
+    /// decode thread has resolved one. Cheap (a lock + a string build); safe on the UI thread.
+    pub fn decoder_label(&self) -> String {
+        let g = self
+            .decoder
+            .lock()
+            .unwrap_or_else(std::sync::PoisonError::into_inner);
+        match &*g {
+            Some(d) if d.low_latency => format!("{} · low-latency", d.name),
+            Some(d) => d.name.clone(),
+            None => String::new(),
+        }
+    }
+
     /// Record one received access unit: its wire size and (if in range) its capture→received
     /// `host+network` stage sample. Receipt is the fps/goodput counting point per the spec.
     // Driven only by the android-only decode thread; unreferenced on the host build — expected.

crates/punktfunk-core/src/transport/qos.rs

@@ -66,12 +66,18 @@ impl MediaClass {
     }
 }
 
-/// Whether DSCP/QoS marking is enabled (`PUNKTFUNK_DSCP=1`). Off by default.
+/// Whether DSCP/QoS marking is enabled. Default **on for Android**, **off elsewhere**: on Wi-Fi
+/// (where most Android clients live) access points commonly map DSCP to WMM access categories, so
+/// tagging the video/audio sockets can win real airtime priority against other traffic on the link;
+/// on the wired paths the other clients use it's rarely honoured and some paths bleach or reject
+/// marked packets, so it stays opt-in there. `PUNKTFUNK_DSCP` overrides either way — `1`/`true`/`on`
+/// forces it on, `0`/`false`/`off` forces it off (e.g. to rule QoS out while debugging a flaky AP).
 pub(crate) fn dscp_enabled() -> bool {
-    matches!(
+    match std::env::var("PUNKTFUNK_DSCP").as_deref() {
-        std::env::var("PUNKTFUNK_DSCP").as_deref(),
+        Ok("1") | Ok("true") | Ok("on") => true,
-        Ok("1") | Ok("true") | Ok("on")
+        Ok("0") | Ok("false") | Ok("off") => false,
-    )
+        _ => cfg!(target_os = "android"),
+    }
 }
 
 /// Best-effort: tag `socket`'s outgoing packets for prioritized delivery of its media class. A no-op