Merge origin/main; the presenter rebuild's four settings join the sidebar

`#20` landed while this branch was open and added four settings the
console screen groups under a new "Presentation" header: Prioritize,
Smoothness buffer, V-Sync and Follow variable refresh. A branch whose
whole claim is "everything the store holds is reachable" cannot merge
past those, so they get a Presentation page of their own, in the console
screen's position (after Video, before Audio) and with its wording.
Smoothness buffer is indented under Prioritize and disabled until the
intent is Smoothness — the same relationship the console's `enabled`
gate draws.

The docs conflict resolves to main's side plus this branch's correction:
the 4:4:4 advertisement claim main rewrote is the current one and stays,
while "Android, Decky and the console home don't offer it" was wrong
about two of the three before this branch and about all three after it.
The four new settings' paragraphs pick up the console home and Decky the
same way.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

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

@@ -401,8 +401,15 @@ private fun buildSettingsRows(
             s.echoCancel,
         ) { update(s.copy(echoCancel = it)) },
 
+        toggle(
+            "padForward", "Controllers", "Forward controllers",
+            "Send this device's controllers to the host. Turn it off when your controller " +
+                "already reaches the host another way — USB passthrough such as VirtualHere — " +
+                "so games don't see two of them.",
+            s.gamepadForwarding,
+        ) { update(s.copy(gamepadForwarding = it)) },
         choice(
-            "padType", "Controllers", "Controller type",
+            "padType", null, "Controller type",
             "The virtual pad the host creates — Automatic matches this controller.",
             GAMEPAD_OPTIONS, s.gamepad,
         ) { update(s.copy(gamepad = it)) },

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

@@ -43,6 +43,7 @@ data class SettingsOverlay(
     val mouseMode: MouseMode? = null,
     val invertScroll: Boolean? = null,
     val gamepad: Int? = null,
+    val gamepadForwarding: Boolean? = null,
     val statsVerbosity: StatsVerbosity? = null,
     /**
      * Android-only tier-P addition (design §3): the decode pipeline is a device fact everywhere
@@ -76,6 +77,7 @@ data class SettingsOverlay(
         mouseMode = mouseMode ?: base.mouseMode,
         invertScroll = invertScroll ?: base.invertScroll,
         gamepad = gamepad ?: base.gamepad,
+        gamepadForwarding = gamepadForwarding ?: base.gamepadForwarding,
         statsVerbosity = statsVerbosity ?: base.statsVerbosity,
         lowLatencyMode = lowLatencyMode ?: base.lowLatencyMode,
         presentPriority = presentPriority ?: base.presentPriority,
@@ -110,6 +112,9 @@ data class SettingsOverlay(
         mouseMode = if (after.mouseMode != before.mouseMode) after.mouseMode else mouseMode,
         invertScroll = if (after.invertScroll != before.invertScroll) after.invertScroll else invertScroll,
         gamepad = if (after.gamepad != before.gamepad) after.gamepad else gamepad,
+        gamepadForwarding =
+            if (after.gamepadForwarding != before.gamepadForwarding) after.gamepadForwarding
+            else gamepadForwarding,
         statsVerbosity = if (after.statsVerbosity != before.statsVerbosity) after.statsVerbosity else statsVerbosity,
         lowLatencyMode = if (after.lowLatencyMode != before.lowLatencyMode) after.lowLatencyMode else lowLatencyMode,
         presentPriority = if (after.presentPriority != before.presentPriority) after.presentPriority else presentPriority,
@@ -136,6 +141,7 @@ data class SettingsOverlay(
         "mouse_mode" -> copy(mouseMode = null)
         "invert_scroll" -> copy(invertScroll = null)
         "gamepad" -> copy(gamepad = null)
+        "gamepad_forwarding" -> copy(gamepadForwarding = null)
         "stats_verbosity" -> copy(statsVerbosity = null)
         "low_latency_mode" -> copy(lowLatencyMode = null)
         "present_priority" -> copy(presentPriority = null)
@@ -159,6 +165,7 @@ data class SettingsOverlay(
         if (mouseMode != null) add("mouse_mode")
         if (invertScroll != null) add("invert_scroll")
         if (gamepad != null) add("gamepad")
+        if (gamepadForwarding != null) add("gamepad_forwarding")
         if (statsVerbosity != null) add("stats_verbosity")
         if (lowLatencyMode != null) add("low_latency_mode")
         if (presentPriority != null) add("present_priority")
@@ -190,6 +197,7 @@ data class SettingsOverlay(
         mouseMode?.let { j.put("mouse_mode", it.storedName) }
         invertScroll?.let { j.put("invert_scroll", it) }
         gamepad?.let { j.put("gamepad", it) }
+        gamepadForwarding?.let { j.put("gamepad_forwarding", it) }
         statsVerbosity?.let { j.put("stats_verbosity", it.name) }
         lowLatencyMode?.let { j.put("low_latency_mode", it) }
         presentPriority?.let { j.put("present_priority", it) }
@@ -205,7 +213,8 @@ data class SettingsOverlay(
         private val KNOWN = setOf(
             "width", "height", "refresh_hz", "bitrate_kbps", "render_scale", "codec",
             "hdr_enabled", "compositor", "audio_channels", "mic_enabled", "echo_cancel",
-            "touch_mode", "mouse_mode", "invert_scroll", "gamepad", "stats_verbosity",
+            "touch_mode", "mouse_mode", "invert_scroll", "gamepad", "gamepad_forwarding",
+            "stats_verbosity",
             "low_latency_mode", "present_priority", "smooth_buffer",
         )
 
@@ -227,6 +236,7 @@ data class SettingsOverlay(
                 ?.let { n -> MouseMode.entries.firstOrNull { it.storedName == n } },
             invertScroll = j.optBooleanOrNull("invert_scroll"),
             gamepad = j.optIntOrNull("gamepad"),
+            gamepadForwarding = j.optBooleanOrNull("gamepad_forwarding"),
             statsVerbosity = j.optStringOrNull("stats_verbosity")
                 ?.let { n -> StatsVerbosity.entries.firstOrNull { it.name == n } },
             lowLatencyMode = j.optBooleanOrNull("low_latency_mode"),

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

@@ -34,6 +34,17 @@ data class Settings(
     val hdrEnabled: Boolean = true,
     val compositor: Int = 0,
     val gamepad: Int = 0,
+    /**
+     * Forward this device's controllers to the host at all. Default on — that was the
+     * unconditional behaviour before this became a setting.
+     *
+     * Off is for a couch whose controller reaches the host another way: a USB passthrough tool
+     * (VirtualHere and friends), or a pad simply plugged into the host itself. Leaving it on
+     * there gives the host two controllers for one pair of hands, and games read both. It also
+     * stops this device CLAIMING the pad — a device held open is one a passthrough tool can't
+     * bind — which is why it gates the USB capture paths, not just the wire sends.
+     */
+    val gamepadForwarding: Boolean = true,
     /** Requested audio channel count: 2 (stereo), 6 (5.1) or 8 (7.1). The host clamps to what it
      * can capture; the resolved count drives the decoder + AAudio layout. */
     val audioChannels: Int = 2,
@@ -216,6 +227,7 @@ class SettingsStore(context: Context) {
         hdrEnabled = prefs.getBoolean(K_HDR, true),
         compositor = prefs.getInt(K_COMPOSITOR, 0),
         gamepad = prefs.getInt(K_GAMEPAD, 0),
+        gamepadForwarding = prefs.getBoolean(K_GAMEPAD_FORWARDING, true),
         audioChannels = prefs.getInt(K_AUDIO_CH, 2),
         codec = prefs.getString(K_CODEC, "auto") ?: "auto",
         micEnabled = prefs.getBoolean(K_MIC, false),
@@ -262,6 +274,7 @@ class SettingsStore(context: Context) {
             .putBoolean(K_HDR, s.hdrEnabled)
             .putInt(K_COMPOSITOR, s.compositor)
             .putInt(K_GAMEPAD, s.gamepad)
+            .putBoolean(K_GAMEPAD_FORWARDING, s.gamepadForwarding)
             .putInt(K_AUDIO_CH, s.audioChannels)
             .putString(K_CODEC, s.codec)
             .putBoolean(K_MIC, s.micEnabled)
@@ -291,6 +304,7 @@ class SettingsStore(context: Context) {
         const val K_HDR = "hdr_enabled"
         const val K_COMPOSITOR = "compositor"
         const val K_GAMEPAD = "gamepad"
+        const val K_GAMEPAD_FORWARDING = "gamepad_forwarding"
         const val K_AUDIO_CH = "audio_channels"
         const val K_CODEC = "codec"
         const val K_MIC = "mic_enabled"

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

@@ -818,11 +818,23 @@ private fun AudioSettings(s: Settings, update: (Settings) -> Unit, onMicChange:
 @Composable
 private fun ControllerSettings(s: Settings, update: (Settings) -> Unit, onOpenControllers: () -> Unit) {
     SettingsGroup(footer = "Applies from the next session.") {
+        // The master switch, above everything it governs. Profileable, so it shows in both
+        // scopes: a "Work" profile can decline to forward what "Game" forwards.
+        ToggleRow(
+            title = "Forward controllers",
+            subtitle = "Send this device's controllers to the host. Turn it off when your " +
+                "controller already reaches the host another way — USB passthrough such as " +
+                "VirtualHere, or a pad plugged into the host — so games don't see two of them",
+            checked = s.gamepadForwarding,
+            field = "gamepad_forwarding",
+            onCheckedChange = { on -> update(s.copy(gamepadForwarding = on)) },
+        )
         SettingDropdown(
             label = "Controller type",
             options = GAMEPAD_OPTIONS,
             selected = s.gamepad,
             field = "gamepad",
+            enabled = s.gamepadForwarding,
             caption = "The virtual pad the host creates. Automatic matches your controller; " +
                 "every connected one is forwarded as its own player.",
         ) { g -> update(s.copy(gamepad = g)) }
@@ -852,6 +864,7 @@ private fun ControllerSettings(s: Settings, update: (Settings) -> Unit, onOpenCo
                 subtitle = "Stream a Steam Controller 2 as-is — Steam on the host drives its " +
                     "trackpads, gyro and haptics directly",
                 checked = s.sc2Capture,
+                enabled = s.gamepadForwarding,
                 onCheckedChange = { on -> update(s.copy(sc2Capture = on)) },
             )
             // Same no-vibrator-gate reasoning as the SC2 row: this capture renders feedback on
@@ -861,6 +874,7 @@ private fun ControllerSettings(s: Settings, update: (Settings) -> Unit, onOpenCo
                 subtitle = "Drive a USB-connected Sony pad directly — rumble on any phone, " +
                     "plus adaptive triggers, lightbar and gyro",
                 checked = s.dsCapture,
+                enabled = s.gamepadForwarding,
                 onCheckedChange = { on -> update(s.copy(dsCapture = on)) },
             )
         }
@@ -1013,6 +1027,7 @@ private fun <T> SettingDropdown(
     selected: T,
     field: String? = null,
     caption: String? = null,
+    enabled: Boolean = true,
     onSelect: (T) -> Unit,
 ) {
     var expanded by remember { mutableStateOf(false) }
@@ -1020,18 +1035,25 @@ private fun <T> SettingDropdown(
         ?: options.firstOrNull()?.second.orEmpty()
     Column {
         OverrideBadge(field)
-        ExposedDropdownMenuBox(expanded = expanded, onExpandedChange = { expanded = it }) {
+        ExposedDropdownMenuBox(
+            expanded = expanded && enabled,
+            onExpandedChange = { if (enabled) expanded = it },
+        ) {
             OutlinedTextField(
                 value = selectedLabel,
                 onValueChange = {},
                 readOnly = true,
+                enabled = enabled,
                 label = { Text(label) },
                 trailingIcon = { ExposedDropdownMenuDefaults.TrailingIcon(expanded = expanded) },
                 modifier = Modifier
                     .menuAnchor(ExposedDropdownMenuAnchorType.PrimaryNotEditable)
                     .fillMaxWidth(),
             )
-            ExposedDropdownMenu(expanded = expanded, onDismissRequest = { expanded = false }) {
+            ExposedDropdownMenu(
+                expanded = expanded && enabled,
+                onDismissRequest = { expanded = false },
+            ) {
                 options.forEach { (value, lbl) ->
                     DropdownMenuItem(
                         text = { Text(lbl) },

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

@@ -321,7 +321,9 @@ fun StreamScreen(session: ActiveSession, onDisconnect: () -> Unit) {
         // Multi-controller router: a stable wire pad index per connected controller, per-device axis
         // state, Arrival/Remove on hot-plug, and feedback routed back by pad index. Forwards every
         // controller (Automatic). Built here, released on dispose.
-        val router = GamepadRouter(context, handle, initialSettings.gamepad)
+        val router = GamepadRouter(
+            context, handle, initialSettings.gamepad, initialSettings.gamepadForwarding,
+        )
         activity?.gamepadRouter = router
         // Select+Start+L1+R1 chord leaves the stream — a deliberate quit (signal it so the host skips
         // the keep-alive linger), unlike a host-ended / backgrounded drop. The router debounces it
@@ -442,7 +444,11 @@ fun StreamScreen(session: ActiveSession, onDisconnect: () -> Unit) {
         // The menu-time capture (UI navigation) must let go before the stream-mode capture can
         // claim the interfaces; it resumes in onDispose once the stream releases them.
         activity?.stopSc2MenuNav()
-        val sc2 = if (initialSettings.sc2Capture) Sc2Capture(context, router) else null
+        val sc2 = if (initialSettings.sc2Capture && initialSettings.gamepadForwarding) {
+            Sc2Capture(context, router)
+        } else {
+            null
+        }
         var sc2UsbReceiver: BroadcastReceiver? = null
         if (sc2 != null) {
             feedback.onHidRaw = sc2::onHidRaw
@@ -492,7 +498,11 @@ fun StreamScreen(session: ActiveSession, onDisconnect: () -> Unit) {
         // the automatic fallback. Host feedback routes back through feedback.sink; the claim
         // frees the pad's InputDevice slot itself (see DsCapture.startUsb), so the wire index
         // hands over deterministically.
-        val ds = if (initialSettings.dsCapture) DsCapture(context, router) else null
+        val ds = if (initialSettings.dsCapture && initialSettings.gamepadForwarding) {
+            DsCapture(context, router)
+        } else {
+            null
+        }
         var dsUsbReceiver: BroadcastReceiver? = null
         if (ds != null) {
             feedback.sink = ds

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

@@ -33,7 +33,24 @@ import java.util.concurrent.ConcurrentHashMap
  * InputManager hot-plug callbacks both land there). [deviceForPad] is read from the feedback poll
  * threads, so the slot table is a [ConcurrentHashMap].
  */
-class GamepadRouter(context: Context, private val handle: Long, private val setting: Int) {
+class GamepadRouter(
+    context: Context,
+    private val handle: Long,
+    private val setting: Int,
+    /**
+     * Forward this device's controllers to the host at all (`Settings.gamepadForwarding`,
+     * default true). Off is for a couch whose controller reaches the host another way — USB
+     * passthrough such as VirtualHere, or a pad plugged into the host itself — where forwarding
+     * as well would give the host two pads for one pair of hands.
+     *
+     * Off still opens slots and tracks held state; it only stops the wire sends. That is
+     * deliberate: the exit and mic chords are read off the same slots, and a couch that lost its
+     * quit shortcut because a forwarding preference was off would be the worse bug. Nothing is
+     * claimed by keeping a slot — the Android input stack shares controllers — unlike the USB
+     * capture links, which `StreamScreen` does not start at all while this is off.
+     */
+    private val forwarding: Boolean = true,
+) {
 
     /** One forwarded controller: its stable wire pad index, per-device axis state, and held buttons. */
     private class Slot(val index: Int, val mapper: Gamepad.AxisMapper) {
@@ -123,7 +140,9 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
      */
     private fun slotButton(slot: Slot, bit: Int, down: Boolean, send: Boolean) {
         if (down) {
-            if (send) NativeBridge.nativeSendGamepadButton(handle, bit, true, slot.index)
+            if (send && forwarding) {
+                NativeBridge.nativeSendGamepadButton(handle, bit, true, slot.index)
+            }
             val wasHeld = slot.held
             slot.held = slot.held or bit
             // Full chord now held on this pad → start the hold countdown (idempotent while held).
@@ -136,7 +155,9 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
                 onMicChord?.invoke()
             }
         } else {
-            if (send) NativeBridge.nativeSendGamepadButton(handle, bit, false, slot.index)
+            if (send && forwarding) {
+                NativeBridge.nativeSendGamepadButton(handle, bit, false, slot.index)
+            }
             slot.held = slot.held and bit.inv()
             // A chord button lifted before the hold elapsed → cancel, unless another pad still
             // holds the full chord.
@@ -186,7 +207,7 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
         val dev = event.device ?: return false
         if (!isForwardable(dev)) return false
         val slot = slotFor(dev) ?: return false
-        slot.mapper.onMotion(event)
+        if (forwarding) slot.mapper.onMotion(event)
         return true
     }
 
@@ -221,24 +242,26 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
 
         /** One axis update ([Gamepad].AXIS_*: stick i16 +y=up / trigger 0..255). On-change only. */
         fun axis(id: Int, value: Int) {
-            if (slot != null) NativeBridge.nativeSendGamepadAxis(handle, id, value, index)
+            if (slot != null && forwarding) NativeBridge.nativeSendGamepadAxis(handle, id, value, index)
         }
 
         /** One raw HID report, forwarded verbatim for the host's as-is virtual pad. */
         fun hidReport(buf: java.nio.ByteBuffer, len: Int) {
-            if (slot != null) NativeBridge.nativeSendPadHidReport(handle, index, buf, len)
+            if (slot != null && forwarding) NativeBridge.nativeSendPadHidReport(handle, index, buf, len)
         }
 
         /** One touchpad contact on the rich plane: [finger] 0/1, x/y normalized 0..65535 in
          *  SCREEN convention (+y down); `active = false` lifts the finger. On-change only. */
         fun touch(finger: Int, active: Boolean, x: Int, y: Int) {
-            if (slot != null) NativeBridge.nativeSendPadTouch(handle, index, finger, active, x, y)
+            if (slot != null && forwarding) {
+                NativeBridge.nativeSendPadTouch(handle, index, finger, active, x, y)
+            }
         }
 
         /** One motion sample on the rich plane (gyro pitch/yaw/roll + accel, raw device i16
          *  units — the host passes them straight into the virtual pad's report). Per report. */
         fun motion(gyro: IntArray, accel: IntArray) {
-            if (slot != null) {
+            if (slot != null && forwarding) {
                 NativeBridge.nativeSendPadMotion(
                     handle, index,
                     gyro[0], gyro[1], gyro[2],
@@ -260,7 +283,7 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
         // Synthetic ids live below any real InputDevice id (those are positive), so they can't
         // collide and InputDevice.getDevice(id) resolves them to null for the feedback path.
         val syntheticId = EXTERNAL_ID_BASE - index
-        NativeBridge.nativeSendGamepadArrival(handle, pref, index)
+        if (forwarding) NativeBridge.nativeSendGamepadArrival(handle, pref, index)
         slots[syntheticId] = Slot(index, Gamepad.AxisMapper(handle, index))
         return ExternalPad(syntheticId, index)
     }
@@ -317,7 +340,7 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
         // Automatic resolves the pad's type from its VID/PID; an explicit setting forces every pad
         // to that type (a single global choice — matches the handshake's session-default pref).
         val pref = if (setting == Gamepad.PREF_AUTO) Gamepad.prefFor(dev) else setting
-        NativeBridge.nativeSendGamepadArrival(handle, pref, index)
+        if (forwarding) NativeBridge.nativeSendGamepadArrival(handle, pref, index)
         val slot = Slot(index, Gamepad.AxisMapper(handle, index))
         slots[dev.id] = slot
         return slot
@@ -330,7 +353,7 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
     private fun closeSlot(deviceId: Int) {
         val slot = slots.remove(deviceId) ?: return
         releaseHeld(slot)
-        NativeBridge.nativeSendGamepadRemove(handle, slot.index)
+        if (forwarding) NativeBridge.nativeSendGamepadRemove(handle, slot.index)
         // If this pad was mid-exit-chord, its removal may have left no pad holding it — drop the timer.
         if (slots.values.none { it.held and EXIT_CHORD == EXIT_CHORD }) disarmExit()
         // Release this controller's feedback bindings (close its lights session / cancel rumble).
@@ -342,11 +365,11 @@ class GamepadRouter(context: Context, private val handle: Long, private val sett
         var bits = slot.held
         while (bits != 0) {
             val bit = bits and -bits // lowest set bit
-            NativeBridge.nativeSendGamepadButton(handle, bit, false, slot.index)
+            if (forwarding) NativeBridge.nativeSendGamepadButton(handle, bit, false, slot.index)
             bits = bits and bit.inv()
         }
         slot.held = 0
-        slot.mapper.reset() // zero sticks/triggers + release the HAT dpad
+        if (forwarding) slot.mapper.reset() // zero sticks/triggers + release the HAT dpad
     }
 
     /** Lowest wire index 0..[MAX_PADS) not held by a slot, or null when full — stable lowest-free keeps indices from shuffling on hot-plug. */

clients/android/native/src/decode/async_loop.rs

@@ -392,7 +392,7 @@ pub(super) fn run_async(
         // even when the choreographer clock is absent.
         if let Some(p) = presenter.as_mut() {
             let clock = vsync.as_ref().map(|v| v.shared().as_ref());
-            if p.pump(&codec, clock, &tracker, &stats, now_monotonic_ns()) {
+            if p.pump(&codec, clock, &tracker, &meter, &stats, now_monotonic_ns()) {
                 rendered += 1;
             }
             // The 1 Hz window flush doubles as the phase-lock report tick. v3 sensor: the
@@ -822,8 +822,21 @@ fn feed_ready(
             }
         }
         let Some(dst) = codec.input_buffer(idx) else {
-            log::warn!("decode: input_buffer({idx}) returned None — dropping AU");
-            continue;
+            // Nothing was written and nothing was queued, so BOTH stay ours. Dropping the slot
+            // here leaked one of the codec's input buffers per occurrence — we forget it and the
+            // codec never frees what it never received, so the pipeline quietly runs out of input
+            // slots, `pending_aus` overflows, and the resulting drop storm reads as a decode
+            // fault. Dropping the AU on top of that punched a hole in the reference chain with no
+            // keyframe request behind it, unlike every sibling path here.
+            //
+            // `break`, not `continue`: a codec that cannot hand out an input buffer it just
+            // advertised is in no state to be fed the rest of the parked queue this pass, and
+            // retrying the same index against every parked AU would burn the whole backlog. The
+            // loop re-runs within the housekeeping wake (≤ 5 ms) if it was transient.
+            log::warn!("decode: input_buffer({idx}) returned None — retrying next pass");
+            free_inputs.push_front(idx);
+            pending_aus.push_front(frame);
+            break;
         };
         let au = &frame.data;
         if au.len() > dst.len() {

clients/android/native/src/decode/mod.rs

@@ -115,9 +115,14 @@ pub(crate) struct DecodeOptions {
     /// The smoothness buffer depth (`smooth_buffer` setting): 0 = automatic (2), else 1..=3.
     /// Only meaningful with `present_priority` = smooth.
     pub smooth_buffer: i32,
-    /// The display mode's own refresh rate (Kotlin's `display.refreshRate` at stream start;
-    /// 0 = unknown) — the latch grid the presenter subdivides onto when the app's choreographer
-    /// stream is down-rated below the panel (see `vsync.rs`).
+    /// SEED for the panel's refresh period — the latch grid the presenter subdivides onto when
+    /// the app's choreographer stream is down-rated below the panel (see `vsync.rs`). Kotlin
+    /// resolves it from the display mode TABLE (`MainActivity.streamPanelFps`), not
+    /// `display.refreshRate`, which reports a per-uid override rather than the panel. 0 = unknown.
+    ///
+    /// ⚠ Only a seed: `preferredDisplayModeId` is a REQUEST the system may refuse, so the mode
+    /// named here is not necessarily the one the panel ends up in. The measured timeline spacing
+    /// corrects it in both directions ([`punktfunk_core::phase::PanelGrid`]).
     pub panel_hz: i32,
 }
 

clients/android/native/src/decode/presenter.rs

@@ -4,10 +4,12 @@
 //!  * a **newest-wins slot** (or a small smoothing FIFO, by user intent) between decode and
 //!    release, so a burst coalesces in the app — as an explicit, counted drop — instead of
 //!    queueing behind the display;
-//!  * a **glass budget of exactly one**: at most one undisplayed release in flight to
-//!    SurfaceFlinger, reopened on the clock-predicted latch (with a 100 ms stale force-open as
-//!    the liveness backstop, mirroring Apple's `PresentGate.staleAfter`). The BufferQueue can
-//!    hold at most the frame being scanned out plus one — a standing queue is unconstructible;
+//!  * a **glass budget of one**: at most one undisplayed release in flight to SurfaceFlinger,
+//!    reopened on the clock-predicted latch (with a 100 ms stale force-open as the liveness
+//!    backstop, mirroring Apple's `PresentGate.staleAfter`), and bounded underneath by what
+//!    `OnFrameRendered` actually confirmed reached glass ([`UNDISPLAYED_CAP`]) — because the
+//!    prediction is only as good as the panel grid behind it, and 0.23.0 shipped a grid that
+//!    could be wrong in one direction forever;
 //!  * a **timed release**: `AMediaCodec_releaseOutputBufferAtTime` targeting the platform's own
 //!    frame timeline (API 33+, via [`super::vsync`]), so the latch phase is deterministic instead
 //!    of inheriting network + decode jitter. On the 31/32 fallback the release is ASAP —
@@ -20,6 +22,7 @@
 
 use ndk::media::media_codec::MediaCodec;
 use std::collections::VecDeque;
+use std::sync::atomic::{AtomicBool, AtomicI32, Ordering};
 use std::sync::Mutex;
 use std::time::Instant;
 
@@ -36,9 +39,9 @@ use super::vsync::VsyncShared;
 ///
 /// 2.5 ms: SF's latch runs ~1-2 ms before present on modern devices (its `sfOffset`), and the
 /// release itself is a binder call well under a ms. 4 ms measured latch p50 8-10; each ms cut
-/// here is a ms off every frame's display stage. If a device misses at this margin the `paced`
-/// counter shows it (a miss presents one vsync later, coalescing the next frame) — that is the
-/// signal to widen, not stutter.
+/// here is a ms off every frame's display stage. A device that misses at the live margin shows it
+/// as a measured latch beyond one panel period (see the adaptation in
+/// [`Presenter::flush_log`]) — that, not a drop counter, is the signal to widen.
 const LATCH_MARGIN_NS: i64 = 2_500_000;
 
 /// `debug.punktfunk.latch_margin_us` (0..=8000 µs): PIN the submit margin for a sweep —
@@ -71,6 +74,26 @@ fn latch_margin_ns() -> Option<i64> {
 /// `forced` — reads 0 on healthy systems (Apple's `PresentGate.staleAfter`, same value).
 const STALE_REOPEN_NS: i64 = 100_000_000;
 
+/// Releases still unconfirmed by `OnFrameRendered` at which the presenter stops handing
+/// SurfaceFlinger more work.
+///
+/// The reopen above is a PREDICTION off the learned panel grid. A grid finer than the panel
+/// (0.23.0 could pin one permanently — see [`punktfunk_core::phase::PanelGrid`]) reopens the
+/// budget before the display has consumed anything, and the presenter then releases faster than
+/// the panel scans: the BufferQueue fills, MediaCodec runs out of output buffers, the decoder
+/// stalls, and the no-output backstop starts begging for keyframes. The render callback is the
+/// ground truth about what actually reached glass, so it bounds the prediction.
+///
+/// Six, not one: the platform is explicitly allowed to deliver these callbacks BATCHED, and this
+/// module's own `RENDERED_CAP` note records them trailing a release by a vsync or two — so a
+/// healthy device sits at 1-3 outstanding and a tight cap would throttle it for nothing (a held
+/// frame in the newest-wins slot is a DROPPED frame the moment a fresher one decodes). This is
+/// not a pacing knob; it is the "something is structurally wrong" rail, and a presenter genuinely
+/// out-running its display climbs past any fixed cap within a second. If a device's BufferQueue
+/// is shallower than this the rail simply never engages and the no-output backstop handles it,
+/// exactly as before — best-effort, never worse than not having it.
+const UNDISPLAYED_CAP: i32 = 6;
+
 /// Fallback latch-prediction period while the vsync clock is unmeasured/absent: one 120 Hz frame.
 const FALLBACK_PERIOD_NS: i64 = 8_333_333;
 
@@ -121,6 +144,14 @@ struct InFlight {
 /// a HUD-off wireless A/B readable from logcat.
 pub(super) struct PresentMeter {
     inner: Mutex<PresentMeterInner>,
+    /// Frames released to SurfaceFlinger that `OnFrameRendered` has not yet confirmed reached
+    /// glass. The presenter's structural rail (see [`UNDISPLAYED_CAP`]) and the pf-present line's
+    /// queue-depth readout. Lock-free because the release side runs on the decode loop and the
+    /// confirm side on the codec's callback thread, once per frame each.
+    undisplayed: AtomicI32,
+    /// This device delivers render callbacks at all (API ≥ 33 and the platform accepted the
+    /// registration). Until one arrives, `undisplayed` is meaningless and the rail stays down.
+    confirms: AtomicBool,
 }
 
 struct PresentMeterInner {
@@ -147,11 +178,23 @@ impl PresentMeter {
                 codec_us: Vec::with_capacity(256),
                 e2e_us: Vec::with_capacity(256),
             }),
+            undisplayed: AtomicI32::new(0),
+            confirms: AtomicBool::new(false),
         }
     }
 
     /// One displayed frame's release→displayed latch, µs. Callback thread; poison-proof.
+    ///
+    /// Also the glass budget's CONFIRM: this frame left the BufferQueue, so one outstanding
+    /// release is settled. Clamped at zero — the legacy `arrival` path renders without going
+    /// through [`Presenter::pump`], so confirms can outnumber counted releases.
     pub(super) fn note_latch(&self, latch_us: Option<u64>) {
+        self.confirms.store(true, Ordering::Relaxed);
+        let _ = self
+            .undisplayed
+            .fetch_update(Ordering::Relaxed, Ordering::Relaxed, |v| {
+                Some((v - 1).max(0))
+            });
         let mut g = self
             .inner
             .lock()
@@ -164,6 +207,26 @@ impl PresentMeter {
         }
     }
 
+    /// One frame handed to SurfaceFlinger, awaiting its confirm. Decode thread.
+    fn note_released(&self) {
+        self.undisplayed.fetch_add(1, Ordering::Relaxed);
+    }
+
+    /// Releases still unconfirmed, and whether confirms happen on this device at all.
+    fn outstanding(&self) -> (i32, bool) {
+        (
+            self.undisplayed.load(Ordering::Relaxed),
+            self.confirms.load(Ordering::Relaxed),
+        )
+    }
+
+    /// Write off the outstanding releases: the platform stopped confirming (it is allowed to
+    /// drop callbacks under load) or SurfaceFlinger discarded the buffers without presenting
+    /// them. Never stall the stream on a ledger we cannot audit.
+    fn forgive_outstanding(&self) {
+        self.undisplayed.store(0, Ordering::Relaxed);
+    }
+
     /// One decoded frame's always-on measurements: the `decode`-stage split (feed =
     /// received→queued when a receipt stamp matched; codec = queued→decoded when the queued
     /// stamp did) and the capture→decoded end-to-end, µs. Decode thread; poison-proof.
@@ -239,6 +302,13 @@ pub(super) struct Presenter {
     no_budget: u64,
     forced: u64,
     dry: u64,
+    /// Pump passes that held a frame back because too many earlier releases were still
+    /// unconfirmed ([`UNDISPLAYED_CAP`]) — reads 0 on a healthy device, and a climbing value is
+    /// the signature of a presenter out-running its display.
+    queue_waits: u64,
+    /// When the unconfirmed-release rail first engaged, so it can be forgiven if the confirms
+    /// simply stopped coming. `None` while the rail is down.
+    backed_up_since: Option<i64>,
     pace_us: Vec<u64>,
     last_flush: Instant,
     /// The live submit margin. Starts at 0 (P2e on-glass: SurfaceFlinger latched every
@@ -280,6 +350,8 @@ impl Presenter {
             no_budget: 0,
             forced: 0,
             dry: 0,
+            queue_waits: 0,
+            backed_up_since: None,
             pace_us: Vec::with_capacity(256),
             last_flush: Instant::now(),
             margin_ns,
@@ -334,6 +406,7 @@ impl Presenter {
         codec: &MediaCodec,
         clock: Option<&VsyncShared>,
         tracker: &DisplayTracker,
+        meter: &PresentMeter,
         stats: &crate::stats::VideoStats,
         now_mono_ns: i64,
     ) -> bool {
@@ -346,6 +419,10 @@ impl Presenter {
                 self.inflight = None;
             }
         }
+        // The measured rail beneath that prediction (see `UNDISPLAYED_CAP`). Evaluated on every
+        // pass — frame waiting or not — so its forgiveness timer measures real elapsed time
+        // rather than how often a frame happened to be ready.
+        let backlogged = self.unconfirmed_backlog(meter, now_mono_ns);
         // Pick the frame this pump may release.
         let frame = if self.fifo_capacity == 0 {
             self.frames.pop_back() // submit() kept it a single slot; back == the newest
@@ -373,9 +450,12 @@ impl Presenter {
             self.frames.pop_front()
         };
         let Some(frame) = frame else { return false };
-        if self.inflight.is_some() {
+        if self.inflight.is_some() || backlogged {
             // Budget closed — park it back; a fresher submit replaces it (newest-wins), the next
             // vsync tick / loop pass retries the pairing.
+            if backlogged {
+                self.queue_waits += 1;
+            }
             self.no_budget += 1;
             match self.fifo_capacity {
                 0 => self.frames.push_back(frame),
@@ -412,6 +492,7 @@ impl Presenter {
             released_at_ns: now_mono_ns,
         });
         self.released += 1;
+        meter.note_released();
         let release_real_ns = now_realtime_ns();
         let pace_us = ((release_real_ns - frame.decoded_ns).max(0) / 1000) as u64;
         if self.pace_us.len() < 4096 {
@@ -422,6 +503,33 @@ impl Presenter {
         true
     }
 
+    /// Whether SurfaceFlinger is sitting on too many unconfirmed releases to be handed another.
+    ///
+    /// The predicted reopen is only as good as the panel grid behind it; this is the measured
+    /// rail underneath it (see [`UNDISPLAYED_CAP`]). It self-clears two ways — the confirms catch
+    /// up, or [`STALE_REOPEN_NS`] passes with the backlog stuck, which means the ledger itself is
+    /// unreliable (callbacks dropped under load, or SF discarded the buffers) and is written off
+    /// rather than allowed to wedge the stream.
+    fn unconfirmed_backlog(&mut self, meter: &PresentMeter, now_ns: i64) -> bool {
+        let (outstanding, confirms_live) = meter.outstanding();
+        if !confirms_live || outstanding < UNDISPLAYED_CAP {
+            self.backed_up_since = None;
+            return false;
+        }
+        match self.backed_up_since {
+            Some(t) if now_ns - t > STALE_REOPEN_NS => {
+                meter.forgive_outstanding();
+                self.backed_up_since = None;
+                self.forced += 1;
+                false
+            }
+            _ => {
+                self.backed_up_since.get_or_insert(now_ns);
+                true
+            }
+        }
+    }
+
     /// Release every held buffer unrendered — the teardown path, BEFORE `codec.stop()`.
     pub(super) fn release_all(&mut self, codec: &MediaCodec) {
         while let Some(f) = self.frames.pop_front() {
@@ -434,7 +542,9 @@ impl Presenter {
     /// `pf-present` line, so a HUD-off on-device A/B is readable wirelessly:
     /// `released` (to glass) / `displays` (OnFrameRendered confirms) / `paced` (policy drops) /
     /// `noBudget` (waits on the closed budget) / `forced` (stale force-opens — 0 when healthy) /
-    /// `qDry` (FIFO underflows) / `pace` (decoded→release) / `latch` (release→displayed) /
+    /// `qDry` (FIFO underflows) / `qWait` (pumps held back by unconfirmed releases — 0 when
+    /// healthy) / `unconfirmed` (releases OnFrameRendered hasn't settled) /
+    /// `pace` (decoded→release) / `latch` (release→displayed) /
     /// `feed`+`codec` (the decode stage split: received→queued hand-off/slot wait + the
     /// codec-pure queued→decoded time) / `e2e` (capture→decoded, skew-corrected — the wireless
     /// A/B headline) / `vsync` (the measured panel period).
@@ -462,14 +572,15 @@ impl Presenter {
         let circ = clock.and_then(|c| {
             punktfunk_core::phase::circular_latch(&latch, c.panel_period_ns().max(c.period_ns()))
         });
+        let latch_samples = latch.len();
         let (latch_p50, latch_max) = p50_max_ms(latch);
         let period_ms = clock.map(|c| c.period_ns() as f64 / 1e6).unwrap_or(0.0);
-        let panel_ms = clock
-            .map(|c| c.panel_period_ns() as f64 / 1e6)
-            .unwrap_or(0.0);
+        let panel_ns = clock.map(|c| c.panel_period_ns()).unwrap_or(0);
+        let (outstanding, _) = meter.outstanding();
         log::info!(
             target: "pf.present",
             "released={} displays={} paced={} noBudget={} forced={} qDry={} \
+             qWait={} unconfirmed={} \
              paceMs p50={:.2} max={:.2} latchMs p50={:.2} max={:.2} \
              feedMs p50={:.2} max={:.2} codecMs p50={:.2} max={:.2} \
              e2eMs p50={:.2} max={:.2} circ={:.2}ms coh={} \
@@ -480,6 +591,8 @@ impl Presenter {
             self.no_budget,
             self.forced,
             self.dry,
+            self.queue_waits,
+            outstanding,
             pace_p50,
             pace_max,
             latch_p50,
@@ -493,25 +606,48 @@ impl Presenter {
             circ.map(|(m, _)| m as f64 / 1e6).unwrap_or(0.0),
             circ.map(|(_, c)| c).unwrap_or(0),
             period_ms,
-            panel_ms,
+            panel_ns as f64 / 1e6,
         );
         self.released = 0;
-        // Margin adaptation: repeated latch misses in one window (a miss presents a vsync
-        // late and coalesces the next frame into `paced`) mean this device's SF does need
-        // lead — widen toward the pre-sweep ceiling. One-way by design: a margin that once
-        // proved necessary is never re-gambled mid-stream (the next stream restarts at 0).
-        if !self.margin_pinned && self.paced_drops > 2 && self.margin_ns < LATCH_MARGIN_NS {
+        // Margin adaptation, off the MEASURED latch. A release targets the first grid point past
+        // `now + margin`, so a frame that makes its vsync is on glass within one panel period of
+        // that margin; beyond it, SurfaceFlinger wanted more lead and the frame waited out an
+        // extra refresh. Widen toward the pre-sweep ceiling. One-way by design: a margin that
+        // once proved necessary is never re-gambled mid-stream (the next stream restarts at 0).
+        //
+        // ⚠ NOT `paced_drops`, which 0.23.0 used: those are the newest-wins store's own policy
+        // evictions — a second frame decoding while one is held — which happen whenever the
+        // stream out-runs the panel and say nothing at all about SF's latch lead. Driving the
+        // margin from them widened it to the ceiling on healthy devices, re-imposing the 2.5 ms
+        // of pure display latency the P2e sweep had just measured away.
+        let latch_p50_ns = (latch_p50 * 1e6) as i64;
+        if !self.margin_pinned
+            && self.margin_ns < LATCH_MARGIN_NS
+            && panel_ns > 0
+            && latch_samples >= 8
+            && latch_p50_ns > panel_ns + self.margin_ns
+        {
             self.margin_ns = (self.margin_ns + 500_000).min(LATCH_MARGIN_NS);
             log::warn!(
-                "presenter: {} latch misses in 1s — margin widened to {}us",
-                self.paced_drops,
+                "presenter: latch p50 {:.2}ms over the {:.2}ms panel period — margin widened to {}us",
+                latch_p50,
+                panel_ns as f64 / 1e6,
                 self.margin_ns / 1_000
             );
         }
+        if self.queue_waits > 0 {
+            log::warn!(
+                "presenter: {} pump(s) held back — {} release(s) still unconfirmed by \
+                 OnFrameRendered (the display is not keeping up with the release rate)",
+                self.queue_waits,
+                outstanding
+            );
+        }
         self.paced_drops = 0;
         self.no_budget = 0;
         self.forced = 0;
         self.dry = 0;
+        self.queue_waits = 0;
         circ
     }
 }

clients/android/native/src/decode/vsync.rs

@@ -58,8 +58,10 @@ pub(super) struct VsyncShared {
     /// video to THIS rate would cap the stream — hence `panel_period_ns` + the subdivision in
     /// [`Self::next_target`].
     period_ns: AtomicI64,
-    /// The panel's own refresh period (from the display mode Kotlin resolved at stream start;
-    /// 0 = unknown). The grid SurfaceFlinger actually latches on.
+    /// The panel's own refresh period — the grid SurfaceFlinger actually latches on (0 = unknown).
+    /// Seeded from the display mode Kotlin resolved at stream start and then corrected by
+    /// measurement; the learner itself is [`punktfunk_core::phase::PanelGrid`], owned by the
+    /// choreographer thread (see [`CallbackCtx::panel`]) and published here for the decode loop.
     panel_period_ns: AtomicI64,
     /// Callback count, for the one-shot cadence diagnostic log.
     ticks: std::sync::atomic::AtomicU32,
@@ -231,6 +233,11 @@ struct CallbackCtx {
     choreographer: *mut c_void,
     shared: Arc<VsyncShared>,
     on_tick: Box<dyn Fn() + Send>,
+    /// The panel-period learner. `Cell` rather than an atomic because it is touched from exactly
+    /// one thread — callbacks only ever fire inside this thread's looper poll (see the struct
+    /// doc) — and its streak state is nobody else's business; only the settled period is
+    /// published, to `shared.panel_period_ns`.
+    panel: std::cell::Cell<punktfunk_core::phase::PanelGrid>,
 }
 
 impl CallbackCtx {
@@ -240,22 +247,25 @@ impl CallbackCtx {
             .shared
             .last_vsync_ns
             .swap(frame_time_ns, Ordering::Relaxed);
-        // Panel-grid learner: timeline spacing is SurfaceFlinger's own grid, and the finest
-        // spacing ever observed is the panel's true period — trustworthy where the configured
-        // value is not (under a per-uid frame-rate override, `Display.getRefreshRate` REPORTS
-        // THE OVERRIDE, observed on-glass: a 120 Hz panel read back as 60 while early timelines
-        // ran at 8.28 ms). Corrects DOWNWARD only: subdividing onto a finer real grid is always
-        // valid, widening on a later down-rated window never is.
+        // Panel-grid learner: timeline spacing is SurfaceFlinger's own grid, and therefore the
+        // only honest witness to what the panel is doing — the configured mode is not (under a
+        // per-uid frame-rate override `Display.getRefreshRate` REPORTS THE OVERRIDE, observed
+        // on-glass: a 120 Hz panel read back as 60 while its timelines ran at 8.28 ms), and
+        // neither is the mode Kotlin *requested* (`preferredDisplayModeId` is a hint the system
+        // may refuse). Both directions matter and the asymmetry lives in `PanelGrid`.
         if timelines.len() >= 2 {
             let spacing = timelines[1].expected_present_ns - timelines[0].expected_present_ns;
-            if (2_000_000..=42_000_000).contains(&spacing) {
-                let cur = self.shared.panel_period_ns.load(Ordering::Relaxed);
-                if cur == 0 || spacing < cur - 200_000 {
-                    self.shared
-                        .panel_period_ns
-                        .store(spacing, Ordering::Relaxed);
-                }
+            let mut grid = self.panel.get();
+            if grid.observe(spacing) {
+                self.shared
+                    .panel_period_ns
+                    .store(grid.period_ns(), Ordering::Relaxed);
+                log::info!(
+                    "vsync: panel grid now {:.2}ms",
+                    grid.period_ns() as f64 / 1e6
+                );
             }
+            self.panel.set(grid);
         }
         // One-shot cadence diagnostic (3rd tick, once deltas exist): the callback cadence vs the
         // panel period is exactly the down-rating question, and this line answers it on-glass.
@@ -372,8 +382,9 @@ pub(super) struct VsyncClock {
 impl VsyncClock {
     /// Spawn the choreographer thread. `on_tick` fires once per vsync ON THAT THREAD — it must
     /// only do something cheap and `Send` (the decode loop passes an event-channel send).
-    /// `panel_hz` is the display mode's own refresh rate (0 = unknown), the latch grid that
-    /// [`VsyncShared::next_target`] subdivides onto. `None` when the platform surface is missing
+    /// `panel_hz` SEEDS the panel-grid learner (0 = unknown) — the latch grid that
+    /// [`VsyncShared::next_target`] subdivides onto. A seed, not a fact: it names the display
+    /// mode Kotlin *requested*, and the observed timeline spacing is what settles it. `None` when the platform surface is missing
     /// (very old device) — the presenter then runs clock-less (ASAP targets, predicted-latch
     /// budget).
     pub(super) fn start(panel_hz: i32, on_tick: Box<dyn Fn() + Send>) -> Option<VsyncClock> {
@@ -383,11 +394,9 @@ impl VsyncClock {
             stop: AtomicBool::new(false),
             last_vsync_ns: AtomicI64::new(0),
             period_ns: AtomicI64::new(0),
-            panel_period_ns: AtomicI64::new(if panel_hz > 0 {
-                1_000_000_000 / panel_hz as i64
-            } else {
-                0
-            }),
+            panel_period_ns: AtomicI64::new(
+                punktfunk_core::phase::PanelGrid::seeded(panel_hz).period_ns(),
+            ),
             ticks: std::sync::atomic::AtomicU32::new(0),
             timelines: Mutex::new(Vec::new()),
         });
@@ -408,6 +417,7 @@ impl VsyncClock {
                     choreographer,
                     shared: thread_shared,
                     on_tick,
+                    panel: std::cell::Cell::new(punktfunk_core::phase::PanelGrid::seeded(panel_hz)),
                 };
                 ctx.repost();
                 // The bounded poll doubles as the stop check: no cross-thread wake needed, worst

clients/apple/Sources/PunktfunkClient/Session/SessionModel.swift

@@ -672,7 +672,11 @@ final class SessionModel: ObservableObject {
         // back to the pad it's addressed to (rumble always; lightbar/player-LEDs/adaptive-triggers
         // when a pad's virtual device is a DualSense). Same trust gate as audio — nothing is
         // forwarded during the trust prompt.
-        let capture = GamepadCapture(connection: conn, manager: .shared)
+        // `gamepadForwarding` off means the host gets this device's pads from somewhere else
+        // (USB passthrough, or a pad plugged into the host) — capture still runs, and still
+        // watches for the escape chord, but puts nothing on the wire.
+        let capture = GamepadCapture(
+            connection: conn, manager: .shared, forwarding: settings.gamepadForwarding)
         // The cross-client escape chord (hold L1+R1+Start+Select 1.5 s) — on tvOS the only
         // controller way out of a stream (B/Menu is swallowed during sessions; see ContentView).
         capture.onDisconnectRequest = { [weak self] in self?.disconnect() }

clients/apple/Sources/PunktfunkClient/Settings/GamepadSettingsView.swift

@@ -26,6 +26,7 @@ struct GamepadSettingsView: View {
     @AppStorage(DefaultsKey.streamHz) private var hz = 60
     @AppStorage(DefaultsKey.compositor) private var compositor = 0
     @AppStorage(DefaultsKey.gamepadType) private var gamepadType = 0
+    @AppStorage(DefaultsKey.gamepadForwarding) private var gamepadForwarding = true
     @AppStorage(DefaultsKey.bitrateKbps) private var bitrateKbps = 0
     @AppStorage(DefaultsKey.audioChannels) private var audioChannels = 2
     @AppStorage(DefaultsKey.hdrEnabled) private var hdrEnabled = true
@@ -323,8 +324,15 @@ struct GamepadSettingsView: View {
                     + "speaker setups feeding the game back to the host.",
                 value: $echoCancel),
 
+            toggleRow(
+                id: "padForward", header: "Controller", icon: "gamecontroller",
+                label: "Forward controllers",
+                detail: "Send this device's controllers to the host. Turn it off when your "
+                    + "controller already reaches the host another way — USB passthrough such "
+                    + "as VirtualHere — so games don't see two of them.",
+                value: $gamepadForwarding),
             choiceRow(
-                id: "pad", header: "Controller", icon: "gamecontroller", label: "Use controller",
+                id: "pad", icon: "gamecontroller", label: "Use controller",
                 detail: "Which pad is forwarded to the host, as player 1.",
                 options: controllers, current: gamepads.preferredID
             ) { gamepads.preferredID = $0 },

clients/apple/Sources/PunktfunkClient/Settings/SettingsView+Scope.swift

@@ -122,6 +122,10 @@ enum SettingsFields {
         .init(name: "gamepad", key: DefaultsKey.gamepadType,
               overlay: \.gamepadType, effective: \.gamepadType)
     }
+    static var gamepadForwarding: SettingsField<Bool> {
+        .init(name: "gamepad_forwarding", key: DefaultsKey.gamepadForwarding,
+              overlay: \.gamepadForwarding, effective: \.gamepadForwarding)
+    }
     static var statsVerbosity: SettingsField<String> {
         .init(name: "stats_verbosity", key: DefaultsKey.statsVerbosity,
               overlay: \.statsVerbosity, effective: \.statsVerbosity)
@@ -181,6 +185,7 @@ extension SettingsView {
         base.micEnabled = micEnabled
         base.echoCancel = echoCancel
         base.gamepadType = gamepadType
+        base.gamepadForwarding = gamepadForwarding
         base.statsVerbosity = statsVerbosityRaw
         base.fullscreenWhileStreaming = fullscreenWhileStreaming
         base.presentPriority = presentPriority

clients/apple/Sources/PunktfunkClient/Settings/SettingsView+Sections.swift

@@ -641,6 +641,15 @@ extension SettingsView {
 
     @ViewBuilder var controllersSection: some View {
         Section {
+            // The master switch, above everything it governs. Profileable, so it renders in
+            // both scopes: a "Work" profile can decline to forward what "Game" forwards.
+            described("Sends controllers connected to this device to the host. Turn it off when "
+                + "your controller already reaches the host another way — USB passthrough such "
+                + "as VirtualHere, or a pad plugged into the host itself — so games don't see "
+                + "two of them.",
+                field: "gamepad_forwarding") {
+                Toggle("Forward controllers", isOn: scoped(SettingsFields.gamepadForwarding))
+            }
             // Which physical pad this device forwards, and what its own haptics do, are facts
             // about THIS device (tier G) — only the virtual pad the host creates is profileable.
             if !inProfileScope {
@@ -659,6 +668,7 @@ extension SettingsView {
                             Text(option.label).tag(option.tag)
                         }
                     }
+                    .disabled(!effective.gamepadForwarding)
                 }
             }
             described("The virtual pad created on the host. Automatic matches your controller "
@@ -669,6 +679,7 @@ extension SettingsView {
                         Text(option.label).tag(option.tag)
                     }
                 }
+                .disabled(!effective.gamepadForwarding)
             }
             #if os(iOS)
             // iPhone only in practice: hidden where the device itself can't play haptics (iPad).

clients/apple/Sources/PunktfunkClient/Settings/SettingsView.swift

@@ -49,6 +49,7 @@ struct SettingsView: View {
     @AppStorage(DefaultsKey.renderScale) var renderScale = 1.0
     @AppStorage(DefaultsKey.compositor) var compositor = 0
     @AppStorage(DefaultsKey.gamepadType) var gamepadType = 0
+    @AppStorage(DefaultsKey.gamepadForwarding) var gamepadForwarding = true
     @AppStorage(DefaultsKey.bitrateKbps) var bitrateKbps = 0
     @AppStorage(DefaultsKey.presentPriority) var presentPriority =
         SettingsOptions.presentPriorityDefault

clients/apple/Sources/PunktfunkKit/Gamepad/GamepadCapture.swift

@@ -98,9 +98,27 @@ public final class GamepadCapture {
     /// gameplay can't end it (see ContentView's tvOS session branch).
     public var onDisconnectRequest: (() -> Void)?
 
-    public init(connection: PunktfunkConnection, manager: GamepadManager) {
+    /// Forward this device's controllers to the host at all (`Settings.gamepadForwarding`,
+    /// default true). Off is for a couch whose controller reaches the host another way — USB
+    /// passthrough such as VirtualHere, or a pad plugged into the host itself — where
+    /// forwarding as well would give the host two pads for one pair of hands.
+    ///
+    /// Off still opens slots and tracks button state; it just sends nothing (see `wire`). That
+    /// is deliberate, not laziness: the escape chord is read off the same slots, and on tvOS it
+    /// is the ONLY controller way out of a stream — a session that silently lost its exit
+    /// because a forwarding preference was off would be a worse bug than the one this fixes.
+    /// Unlike pf-client-core's slots, GameController claims nothing exclusive, so holding one
+    /// open costs the host nothing and blocks no passthrough tool.
+    public let forwarding: Bool
+
+    /// The connection, or nil while forwarding is off — every wire send goes through this, so
+    /// "don't forward" is one fact in one place rather than a condition at twelve call sites.
+    private var wire: PunktfunkConnection? { forwarding ? connection : nil }
+
+    public init(connection: PunktfunkConnection, manager: GamepadManager, forwarding: Bool = true) {
         self.connection = connection
         self.manager = manager
+        self.forwarding = forwarding
     }
 
     public func start() {
@@ -205,8 +223,8 @@ public final class GamepadCapture {
         // core re-sends it a few times against datagram loss; an older host ignores it and uses
         // the session-default kind. Then wake the host pad (pads are created lazily from the first
         // event; a DualSense's UHID handshake + initial lightbar write only start then).
-        connection.send(.gamepadArrival(pref: slot.pref.rawValue, pad: slot.pad))
-        connection.send(.gamepadAxis(GamepadWire.axisLSX, value: 0, pad: slot.pad))
+        wire?.send(.gamepadArrival(pref: slot.pref.rawValue, pad: slot.pad))
+        wire?.send(.gamepadAxis(GamepadWire.axisLSX, value: 0, pad: slot.pad))
         sync(slot, ext)
 
         if let tp = Self.touchpad(ext) {
@@ -233,7 +251,7 @@ public final class GamepadCapture {
         flush(slot)
         // Sent after the flush so the core stamps it with a seq past the zeroing snapshots; the host
         // seq-gates it, so a reordered snapshot can't resurrect the removed pad.
-        connection.send(.gamepadRemove(pad: slot.pad))
+        wire?.send(.gamepadRemove(pad: slot.pad))
         let c = slot.controller
         if let ext = c.extendedGamepad {
             ext.valueChangedHandler = nil
@@ -275,7 +293,7 @@ public final class GamepadCapture {
         let changed = newButtons ^ slot.buttons
         if changed != 0 {
             for bit in GamepadWire.allButtons where changed & bit != 0 {
-                connection.send(.gamepadButton(bit, down: newButtons & bit != 0, pad: slot.pad))
+                wire?.send(.gamepadButton(bit, down: newButtons & bit != 0, pad: slot.pad))
             }
             slot.buttons = newButtons
         }
@@ -288,7 +306,7 @@ public final class GamepadCapture {
             Int32(g.rightTrigger.value * 255),
         ]
         for (i, v) in newAxes.enumerated() where v != slot.axes[i] {
-            connection.send(.gamepadAxis(UInt32(i), value: v, pad: slot.pad))
+            wire?.send(.gamepadAxis(UInt32(i), value: v, pad: slot.pad))
             slot.axes[i] = v
         }
         updateEscapeChord()
@@ -302,7 +320,7 @@ public final class GamepadCapture {
         let bit = GamepadWire.guide
         let now = down ? (slot.buttons | bit) : (slot.buttons & ~bit)
         guard now != slot.buttons else { return }
-        connection.send(.gamepadButton(bit, down: down, pad: slot.pad))
+        wire?.send(.gamepadButton(bit, down: down, pad: slot.pad))
         slot.buttons = now
     }
 
@@ -365,13 +383,13 @@ public final class GamepadCapture {
         if lifted {
             if slot.fingerActive[finger] {
                 slot.fingerActive[finger] = false
-                connection.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(finger), active: false, x: 0, y: 0)
+                wire?.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(finger), active: false, x: 0, y: 0)
             }
             return
         }
         slot.fingerActive[finger] = true
         let w = GamepadWire.touchpad(x: x, y: y)
-        connection.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(finger), active: true, x: w.x, y: w.y)
+        wire?.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(finger), active: true, x: w.x, y: w.y)
     }
 
     private func forwardMotion(_ slot: Slot, _ m: GCMotion) {
@@ -394,7 +412,7 @@ public final class GamepadCapture {
         }
         let gs = GamepadWire.gyroLSBPerRadS
         let as_ = GamepadWire.accelLSBPerG
-        connection.sendMotion(
+        wire?.sendMotion(
             pad: UInt8(slot.pad),
             gyro: (
                 GamepadWire.motionRaw(Float(m.rotationRate.x), scale: gs),
@@ -432,15 +450,15 @@ public final class GamepadCapture {
     /// GamepadRemove (that's `closeSlot`).
     private func flush(_ slot: Slot) {
         for bit in GamepadWire.allButtons where slot.buttons & bit != 0 {
-            connection.send(.gamepadButton(bit, down: false, pad: slot.pad))
+            wire?.send(.gamepadButton(bit, down: false, pad: slot.pad))
         }
         slot.buttons = 0
         for (i, v) in slot.axes.enumerated() where v != 0 {
-            connection.send(.gamepadAxis(UInt32(i), value: 0, pad: slot.pad))
+            wire?.send(.gamepadAxis(UInt32(i), value: 0, pad: slot.pad))
             slot.axes[i] = 0
         }
         for (f, active) in slot.fingerActive.enumerated() where active {
-            connection.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(f), active: false, x: 0, y: 0)
+            wire?.sendTouchpad(pad: UInt8(slot.pad), finger: UInt8(f), active: false, x: 0, y: 0)
             slot.fingerActive[f] = false
         }
     }

clients/apple/Sources/PunktfunkKit/Views/StreamViewIOS.swift

@@ -175,6 +175,46 @@ public final class StreamViewController: StreamViewControllerBase {
     /// renegotiates the host mode (1:1, no presenter resample). iOS only (iPhone naturally no-ops
     /// its fixed full-screen scene; tvOS drives display modes via AVDisplayManager instead).
     private var matchFollower: MatchWindowFollower?
+    // MARK: Escape-drop re-lock
+    //
+    // iPadOS releases the pointer lock BY ITSELF when the user presses Escape — the platform's
+    // built-in "let me out", mirroring the web Pointer Lock API's default unlock gesture. Nothing
+    // in our code does it: a bare Esc never touches `captured`, so it keeps forwarding to the host
+    // as the game key it is. But the lock going away flips the mouse onto the absolute UIKit path
+    // and un-hides the iPadOS cursor, so hitting Esc for an in-game menu silently costs the capture
+    // until the user clicks to win it back. Esc is a GAME key here, not a request to hand the
+    // pointer back to iPadOS, so an unwanted drop is re-requested below. The DELIBERATE releases
+    // (⌘⎋, ⌃⌥⇧Q, the Stream menu, backgrounding) all clear `captured` first, so `wantsPointerLock`
+    // is already false when their drop is observed and none of them are fought here.
+    /// Whether this capture ever actually held the lock. Only a lock we HELD is worth winning back
+    /// — never having been granted one means the scene doesn't qualify, not that Esc took it.
+    /// Cleared when capture ends, so each capture starts from a clean slate.
+    private var pointerLockWasEngaged = false
+    /// Attempts spent in the current re-lock burst, and when the burst began.
+    private var pointerRelockAttempt = 0
+    private var pointerRelockBurstStart: CFTimeInterval = 0
+    /// True from an unwanted drop until the lock is back (or the burst gives up). While pending,
+    /// the local cursor stays hidden and absolute pointer MOTION stays muted, so a re-lock that
+    /// lands a frame or two later is invisible instead of flashing the iPadOS cursor and
+    /// teleporting the host's to the pointer's absolute position.
+    private var pointerRelockPending = false
+    /// Forces `prefersPointerLocked` to report false for one resolve pass, so the escalated attempt
+    /// presents the system with a genuine false→true transition instead of re-asserting a value it
+    /// already holds. See `requestPointerRelock()`.
+    private var pointerLockForcedOff = false
+    /// A burst is 3 attempts, and a burst can't restart inside 2 s. A scene the system will never
+    /// lock (Stage Manager, Split View) therefore costs three cheap re-resolves and then falls back
+    /// to today's click-to-recapture, rather than retrying forever.
+    private static let pointerRelockAttemptLimit = 3
+    private static let pointerRelockBurstWindow: CFTimeInterval = 2
+    /// Gap between attempts in a burst — long enough for the system to answer the previous
+    /// re-resolve, short enough that the whole burst fits in ~0.6 s. Must exceed
+    /// `pointerLockForcedOffHold` so an escalated attempt is back to preferring the lock before the
+    /// next attempt evaluates.
+    private static let pointerRelockRetryDelay: TimeInterval = 0.2
+    /// How long an escalated attempt reports `prefersPointerLocked == false` before flipping back,
+    /// so the system observes a real transition instead of coalescing the flip away.
+    private static let pointerLockForcedOffHold: TimeInterval = 0.05
     #endif
 
     /// Reads whether the scene's pointer is actually locked right now; nil = state
@@ -260,7 +300,7 @@ public final class StreamViewController: StreamViewControllerBase {
         captured && pointerCaptureEnabled && UIDevice.current.userInterfaceIdiom == .pad
     }
 
-    public override var prefersPointerLocked: Bool { wantsPointerLock }
+    public override var prefersPointerLocked: Bool { wantsPointerLock && !pointerLockForcedOff }
     public override var prefersHomeIndicatorAutoHidden: Bool { true }
 
     // NOTE: we deliberately do NOT override `childViewControllerForPointerLock`. The default
@@ -383,6 +423,11 @@ public final class StreamViewController: StreamViewControllerBase {
         // is the exact mirror of the GCMouse handlers, which fire only while locked.
         streamView.onPointerMoveAbs = { [weak self] p in
             guard let self, self.inputCapture?.gcMouseForwarding == false else { return }
+            // A re-lock is in flight after an Esc-drop: the absolute path would teleport the host
+            // cursor to wherever the local pointer sits, undoing the relative aiming we're about to
+            // resume. Motion only — BUTTONS still forward (they carry no position, so a click during
+            // the couple of frames a re-lock takes must not be swallowed mid-firefight).
+            guard !self.pointerRelockPending else { return }
             self.inputCapture?.sendMouseAbs(
                 x: p.x, y: p.y, surfaceWidth: p.w, surfaceHeight: p.h)
         }
@@ -693,6 +738,24 @@ public final class StreamViewController: StreamViewControllerBase {
     /// change and capture toggle. Main queue.
     private func syncPointerLock() {
         let locked = pointerLockEngaged() == true
+        // Wanted, previously HELD, and now gone is the Esc-drop signature. The "previously held"
+        // half matters: a lock that was never granted is a scene that doesn't qualify (Stage
+        // Manager, Split View), and burst-requesting there would hide the cursor for the burst's
+        // duration to win a lock that isn't coming. A first grant is already driven by the chain
+        // engage in setCaptured/viewDidAppear.
+        if locked {
+            pointerLockWasEngaged = true
+            pointerRelockPending = false
+            pointerRelockAttempt = 0
+        } else if wantsPointerLock, pointerLockWasEngaged {
+            requestPointerRelock()
+        } else {
+            // Capture is gone (or the lock was never ours) — settle, and let the next capture
+            // start from a clean "never held" slate.
+            if !wantsPointerLock { pointerLockWasEngaged = false }
+            pointerRelockPending = false
+            pointerRelockAttempt = 0
+        }
         let useGCMouse = captured && locked
         // Lock dropped (or capture ended) while the GCMouse path held a button down: once
         // gcMouseForwarding flips false its release handler is gated off, so flush any held
@@ -704,7 +767,83 @@ public final class StreamViewController: StreamViewControllerBase {
         pointerInteraction?.invalidate() // re-resolve the hidden/visible cursor for the state
         if iosInputDebug {
             iosInputLog.debug(
-                "pointer lock isLocked=\(locked, privacy: .public) captured=\(self.captured, privacy: .public)")
+                """
+                pointer lock isLocked=\(locked, privacy: .public) \
+                captured=\(self.captured, privacy: .public) \
+                relockPending=\(self.pointerRelockPending, privacy: .public) \
+                relockAttempt=\(self.pointerRelockAttempt, privacy: .public)
+                """)
+        }
+    }
+
+    /// Ask the system for the lock back after it dropped one we still want (see the Escape-drop
+    /// note on the state above). Bounded to a short burst; idempotent within it. Main queue.
+    private func requestPointerRelock() {
+        // Only a frontmost scene can hold the lock at all. Anywhere else the drop is the system
+        // saying we don't qualify, not the Esc key — re-asking would be noise, and the qualifying
+        // states (foreground, appearance, reparent) each re-resolve on their own already.
+        guard view.window?.windowScene?.activationState == .foregroundActive else {
+            pointerRelockPending = false
+            return
+        }
+        let now = CACurrentMediaTime()
+        // attempt == 0 is a fresh burst (first drop, or one the settle branch cleared); the window
+        // is the backstop for the pathological case where a grant is immediately revoked again and
+        // re-arms us. Even then this stays timer-driven at a few Hz — never a spin.
+        if pointerRelockAttempt == 0 || now - pointerRelockBurstStart > Self.pointerRelockBurstWindow {
+            pointerRelockBurstStart = now
+            pointerRelockAttempt = 0
+        }
+        guard pointerRelockAttempt < Self.pointerRelockAttemptLimit else {
+            // Out of budget: fall back to exactly today's behavior — the iPadOS cursor comes back
+            // and a click into the video re-captures. The caller invalidates the interaction, so
+            // the cursor can never stay hidden on a lock the system won't grant.
+            pointerRelockPending = false
+            return
+        }
+        pointerRelockAttempt += 1
+        pointerRelockPending = true
+        let escalate = pointerRelockAttempt > 1
+        // Deferred a turn so a ⌘⎋ whose GC keystroke lands after the system's unlock notification
+        // has already cleared `captured` — then the guard below drops this attempt instead of
+        // fighting the user's own release.
+        DispatchQueue.main.async { [weak self] in
+            guard let self, self.pointerRelockPending else { return }
+            guard self.wantsPointerLock, self.pointerLockEngaged() != true else {
+                // The grant landed, or the capture went away under us (⌘⎋ / ⌃⌥⇧Q / resign).
+                // Settle through the one decision point rather than returning with `pending` still
+                // set — that flag hides the cursor, so it must never outlive the burst.
+                self.syncPointerLock()
+                return
+            }
+            if escalate {
+                // Re-asserting a value the system already holds didn't take. Present a real
+                // false→true transition instead — the documented way to change your mind about the
+                // lock — and re-anchor the chain in case a reparent broke the downward walk to us.
+                // Held for a beat rather than cleared on the next turn: the system resolves the
+                // property asynchronously, and a same-turn flip back to true can be coalesced into
+                // no transition at all. We are already unlocked, so the false pass costs nothing.
+                self.pointerLockForcedOff = true
+                self.setNeedsUpdateOfPrefersPointerLocked()
+                self.updatePointerLockChain()
+                DispatchQueue.main.asyncAfter(deadline: .now() + Self.pointerLockForcedOffHold) {
+                    [weak self] in
+                    guard let self else { return }
+                    self.pointerLockForcedOff = false
+                    self.setNeedsUpdateOfPrefersPointerLocked()
+                }
+            } else {
+                self.setNeedsUpdateOfPrefersPointerLocked()
+            }
+            // A GRANT arrives as a didChange → syncPointerLock, which settles the burst and makes
+            // this retry a no-op. Routed back through syncPointerLock (not straight into another
+            // requestPointerRelock) so the give-up path re-resolves the cursor through the one
+            // place that does it.
+            DispatchQueue.main.asyncAfter(deadline: .now() + Self.pointerRelockRetryDelay) {
+                [weak self] in
+                guard let self, self.pointerRelockPending else { return }
+                self.syncPointerLock()
+            }
         }
     }
     #endif
@@ -724,7 +863,11 @@ extension StreamViewController: UIPointerInteractionDelegate {
         // host renders its own cursor from GCMouse deltas and a visible local one would just
         // diverge. When the lock isn't held the cursor stays VISIBLE so the user can aim; the
         // pointer is forwarded as an absolute position, both cursors tracking together.
-        captured && pointerLockEngaged() == true ? .hidden() : nil
+        // …except across an Esc-drop we're actively re-locking (`pointerRelockPending`): staying
+        // hidden for those couple of frames is what turns the fix into "Esc did nothing to my
+        // mouse" rather than a cursor that blinks in and out. The burst is bounded and clears
+        // itself on give-up, so the cursor can never stay hidden on a lock that isn't coming.
+        captured && (pointerLockEngaged() == true || pointerRelockPending) ? .hidden() : nil
     }
 }
 #endif

clients/apple/Sources/PunktfunkShared/DefaultsKeys.swift

@@ -32,6 +32,12 @@ public enum DefaultsKey {
     public static let compositor = "punktfunk.compositor"
     public static let gamepadType = "punktfunk.gamepadType"
     public static let gamepadID = "punktfunk.gamepadID"
+    /// Forward this device's controllers to the host at all (default true). Off is for a
+    /// couch whose controller reaches the host another way — USB passthrough such as
+    /// VirtualHere, or a pad plugged into the host — where forwarding as well would give the
+    /// host two pads for one pair of hands. Read at connect: `SessionModel` then never starts
+    /// `GamepadCapture`, so no slot opens, no arrival is sent and no virtual pad is built.
+    public static let gamepadForwarding = "punktfunk.gamepadForwarding"
     public static let bitrateKbps = "punktfunk.bitrateKbps"
     /// Requested audio channel count: 2 (stereo), 6 (5.1) or 8 (7.1). The host clamps to what it
     /// can capture; the resolved count drives the in-core decode + AVAudioEngine layout.

clients/apple/Sources/PunktfunkShared/EffectiveSettings.swift

@@ -34,6 +34,7 @@ public struct EffectiveSettings: Equatable, Sendable {
     public var mouseMode = "capture"
     public var invertScroll = false
     public var gamepadType = 0
+    public var gamepadForwarding = true
     /// A `StatsVerbosity` raw value; the enum lives in PunktfunkKit, which this module can't see.
     public var statsVerbosity = "normal"
     public var fullscreenWhileStreaming = true
@@ -93,6 +94,7 @@ public struct EffectiveSettings: Equatable, Sendable {
         mouseMode = str(DefaultsKey.mouseMode, mouseMode)
         invertScroll = bool(DefaultsKey.invertScroll, invertScroll)
         gamepadType = int(DefaultsKey.gamepadType, gamepadType)
+        gamepadForwarding = bool(DefaultsKey.gamepadForwarding, gamepadForwarding)
         statsVerbosity = Self.storedStatsVerbosity(defaults)
         fullscreenWhileStreaming = bool(
             DefaultsKey.fullscreenWhileStreaming, fullscreenWhileStreaming)
@@ -140,6 +142,7 @@ public struct EffectiveSettings: Equatable, Sendable {
         if let v = overlay.mouseMode { s.mouseMode = v }
         if let v = overlay.invertScroll { s.invertScroll = v }
         if let v = overlay.gamepadType { s.gamepadType = v }
+        if let v = overlay.gamepadForwarding { s.gamepadForwarding = v }
         if let v = overlay.statsVerbosity { s.statsVerbosity = v }
         if let v = overlay.fullscreenWhileStreaming { s.fullscreenWhileStreaming = v }
         if let v = overlay.enable444 { s.enable444 = v }

clients/apple/Sources/PunktfunkShared/StreamProfile.swift

@@ -110,6 +110,7 @@ public struct SettingsOverlay: Codable, Equatable, Sendable {
     public var mouseMode: String?
     public var invertScroll: Bool?
     public var gamepadType: Int?
+    public var gamepadForwarding: Bool?
     /// A `StatsVerbosity` raw value ("off"/"compact"/"normal"/"detailed") — the enum lives in
     /// PunktfunkKit, which this module must not depend on.
     public var statsVerbosity: String?
@@ -151,6 +152,7 @@ public struct SettingsOverlay: Codable, Equatable, Sendable {
         case mouseMode = "mouse_mode"
         case invertScroll = "invert_scroll"
         case gamepadType = "gamepad"
+        case gamepadForwarding = "gamepad_forwarding"
         case statsVerbosity = "stats_verbosity"
         case fullscreenWhileStreaming = "fullscreen_on_stream"
         case enable444 = "enable_444"
@@ -184,6 +186,7 @@ public struct SettingsOverlay: Codable, Equatable, Sendable {
         mouseMode = str(.mouseMode)
         invertScroll = bool(.invertScroll)
         gamepadType = int(.gamepadType)
+        gamepadForwarding = bool(.gamepadForwarding)
         statsVerbosity = str(.statsVerbosity)
         fullscreenWhileStreaming = bool(.fullscreenWhileStreaming)
         enable444 = bool(.enable444)
@@ -219,6 +222,8 @@ public struct SettingsOverlay: Codable, Equatable, Sendable {
         try c.encodeIfPresent(mouseMode, forKey: AnyKey(Key.mouseMode.rawValue))
         try c.encodeIfPresent(invertScroll, forKey: AnyKey(Key.invertScroll.rawValue))
         try c.encodeIfPresent(gamepadType, forKey: AnyKey(Key.gamepadType.rawValue))
+        try c.encodeIfPresent(
+            gamepadForwarding, forKey: AnyKey(Key.gamepadForwarding.rawValue))
         try c.encodeIfPresent(statsVerbosity, forKey: AnyKey(Key.statsVerbosity.rawValue))
         try c.encodeIfPresent(
             fullscreenWhileStreaming, forKey: AnyKey(Key.fullscreenWhileStreaming.rawValue))
@@ -271,6 +276,7 @@ public enum OverlayField {
         case "mouse_mode": overlay.mouseMode = nil
         case "invert_scroll": overlay.invertScroll = nil
         case "gamepad": overlay.gamepadType = nil
+        case "gamepad_forwarding": overlay.gamepadForwarding = nil
         case "stats_verbosity": overlay.statsVerbosity = nil
         case "fullscreen_on_stream": overlay.fullscreenWhileStreaming = nil
         case "enable_444": overlay.enable444 = nil
@@ -306,6 +312,7 @@ public enum OverlayField {
         case "mouse_mode": return o.mouseMode != nil
         case "invert_scroll": return o.invertScroll != nil
         case "gamepad": return o.gamepadType != nil
+        case "gamepad_forwarding": return o.gamepadForwarding != nil
         case "stats_verbosity": return o.statsVerbosity != nil
         case "fullscreen_on_stream": return o.fullscreenWhileStreaming != nil
         case "enable_444": return o.enable444 != nil

clients/decky/README.md

@@ -24,8 +24,15 @@ the panel looks and feels native to Gaming Mode.
    browser (aurora backdrop + poster coverflow; A plays, B returns to Gaming Mode). Pins survive
    plugin reinstalls (stored next to the client's config) and follow a host across IP changes
    (matched by certificate fingerprint).
-5. **Settings** — resolution / refresh / bitrate / gamepad type / host compositor / mic, written
-   to the client's config.
+5. **Settings** — the client's whole settings store, written to its config. Laid out like SteamOS's
+   own Settings: a left rail of categories (`SidebarNavigation`), one page each, so no page needs
+   scrolling. The categories and their order are the console settings screen's — Stream (resolution
+   / refresh / render scale / bitrate / compositor), Video (codec / decoder / GPU / HDR / 4:4:4),
+   Presentation (prioritize / smoothness buffer / V-Sync / VRR), Audio (channels / output + mic
+   device / echo cancellation), Controllers, Touch & mouse, Interface (stats overlay / auto-wake /
+   library / fullscreen). The device pickers are populated
+   from the session binary (`--list-adapters` / `--list-audio`); the GPU row appears only where
+   there is more than one adapter.
 6. **About** — plugin version, an explicit "Check for updates" button, the setup-guide link, and
    a force-stop for a wedged stream client.
 
@@ -93,7 +100,7 @@ restart is required for an out-of-band install to appear.
 | --- | --- |
 | `src/index.tsx` | Plugin entry: the QAM panel + route registration. |
 | `src/page.tsx` | The `/punktfunk` fullscreen page — Hosts (with per-host details) / Settings / About tabs. |
-| `src/settings.tsx` · `src/pair.tsx` | Stream-settings section; the gamepad-navigable PIN-pairing modal. |
+| `src/settings.tsx` · `src/pair.tsx` | The settings screen (a `SidebarNavigation` of seven category pages over one shared settings object); the gamepad-navigable PIN-pairing modal. |
 | `src/library.tsx` | The per-host game picker (pin/unpin, "Open library on screen") + the pinned-game launch helper. |
 | `src/hostmgmt.tsx` | Add / edit host dialogs — mutate the shared known-hosts store (`client-known-hosts.json`) via the flatpak client's headless modes, so a host saved here shows up in the desktop client too. |
 | `src/ui.tsx` | Shared UI primitives for the fullscreen page + modals (right-aligned row actions, consistent Field layout). |

clients/decky/main.py

@@ -21,6 +21,10 @@ The backend's jobs are the things Steam can't do:
   the frontend so it can create/point the Steam shortcut.
 * **get_settings() / set_settings()** — read/write the flatpak client's stream settings JSON
   (resolution / bitrate / gamepad), so the Deck UI configures the stream the client reads.
+  ``set_settings`` MERGES onto the file: it is shared with the desktop client and the console.
+* **list_devices() / refresh_devices()** — the GPUs and audio endpoints the settings tab's
+  device pickers offer, read from the session binary (``--list-adapters`` / ``--list-audio``)
+  and cached, since enumerating them costs a Vulkan + PipeWire init.
 * **kill_stream()** — force-stop a wedged stream (``flatpak kill``).
 * **check_update()** — report pending updates for BOTH the plugin and the client. The plugin's
   comes from the registry's per-channel ``manifest.json`` (the frontend then drives Decky's own
@@ -343,6 +347,9 @@ def _flatpak() -> str | None:
 # settings in the same ~/.config/punktfunk (the flatpak's sandbox HOME resolves to the real
 # home), so nothing else in this file has to care which one answered.
 NATIVE_BIN = "punktfunk-client"
+# The Vulkan session binary the shell execs to stream — and the only thing that can enumerate
+# this device's GPUs and audio endpoints for the settings pickers.
+SESSION_BIN = "punktfunk-session"
 
 # Prefixes to try when PATH doesn't have it. The Decky backend runs with a minimal PATH, and
 # SteamOS's read-only /usr pushes native installs into a sysext or the user's own prefix.
@@ -398,6 +405,25 @@ def _client_argv() -> list[str] | None:
     return [native] if native else None
 
 
+def _session_argv() -> list[str] | None:
+    """The argv PREFIX that runs the SESSION binary headlessly, or None when it isn't there.
+
+    The device enumerations the settings pickers need (`--list-adapters`, `--list-audio`) live on
+    `punktfunk-session`, not on the client: the GTK shell deliberately links no Vulkan itself and
+    shells out to the session for exactly the same two lists (clients/linux/src/app.rs). The
+    flatpak installs both binaries into /app/bin, so `--command=` picks the other one; a native
+    install puts them in the same bindir, so the session is the client's sibling.
+    """
+    prefix = _client_argv()
+    if not prefix:
+        return None
+    if prefix[0] == _flatpak():
+        # `flatpak run --command=<bin> <app>` — the app id must stay LAST.
+        return [*prefix[:-1], f"--command={SESSION_BIN}", prefix[-1]]
+    sibling = Path(prefix[0]).with_name(SESSION_BIN)
+    return [str(sibling)] if sibling.exists() else None
+
+
 def _client_is_flatpak() -> bool:
     """Is the client this plugin actually drives the FLATPAK one?
 
@@ -511,6 +537,63 @@ async def _run_client(client_args: list[str], timeout: float = 20.0) -> tuple[in
         return -1, "", ""
 
 
+def _parse_audio_endpoints(out: str) -> tuple[list[dict], list[dict]]:
+    """Split `punktfunk-session --list-audio` into ``(sinks, sources)``.
+
+    Its format is one endpoint per line, ``sink|source<TAB>node.name<TAB>description``. The
+    node.name is what gets STORED (it is the stable id the client resolves against), so a line
+    without one is unusable and dropped; a missing description falls back to the name rather than
+    rendering a picker entry with no label. Anything else on the line is ignored, so an extra
+    trailing column in a future client can't break this.
+    """
+    sinks: list[dict] = []
+    sources: list[dict] = []
+    for line in out.splitlines():
+        parts = line.split("\t")
+        if len(parts) < 3 or not parts[1].strip():
+            continue
+        kind, name, description = parts[0].strip(), parts[1].strip(), parts[2].strip()
+        entry = {"name": name, "description": description or name}
+        if kind == "sink":
+            sinks.append(entry)
+        elif kind == "source":
+            sources.append(entry)
+    return sinks, sources
+
+
+async def _run_session(session_args: list[str], timeout: float = 25.0) -> tuple[int, str]:
+    """Run the SESSION binary headlessly, returning ``(returncode, stdout)``; ``(-1, "")`` when
+    it isn't installed or the call errors/times out.
+
+    Only ever used for the two read-only device enumerations — the launch path goes through the
+    Steam shortcut and the wrapper script, never through here. The timeout is generous because
+    `--list-adapters` initialises Vulkan on a cold flatpak."""
+    prefix = _session_argv()
+    if not prefix:
+        return -1, ""
+    proc = None
+    try:
+        proc = await asyncio.create_subprocess_exec(
+            *prefix, *session_args,
+            stdout=asyncio.subprocess.PIPE, stderr=asyncio.subprocess.DEVNULL,
+            env=_flatpak_env(),
+        )
+        out, _ = await asyncio.wait_for(proc.communicate(), timeout=timeout)
+        rc = proc.returncode if proc.returncode is not None else -1
+        return rc, (out or b"").decode("utf-8", "replace")
+    except asyncio.TimeoutError:
+        decky.logger.warning("session %s timed out", " ".join(session_args))
+        if proc:
+            try:
+                proc.kill()
+            except ProcessLookupError:
+                pass
+        return -1, ""
+    except Exception:  # noqa: BLE001
+        decky.logger.exception("session %s failed", " ".join(session_args))
+        return -1, ""
+
+
 # The QAM panel and the full page each mount their own hosts view, and Gaming Mode remounts the
 # QAM often — every mount calls list_hosts, which spawns a flatpak cold-start plus a reachability
 # probe. Cache the last result briefly so back-to-back opens reuse it instead of re-probing; any
@@ -518,6 +601,11 @@ async def _run_client(client_args: list[str], timeout: float = 20.0) -> tuple[in
 _HOSTS_TTL_S = 12.0
 _hosts_cache: dict = {"at": 0.0, "probed": None, "data": None}
 
+# The settings tab's device lists (GPUs / audio endpoints). No TTL: this is hardware, and reading
+# it costs a Vulkan + PipeWire init. Held for the life of the plugin backend; `refresh_devices`
+# clears it for the user who just plugged a headset in.
+_devices_cache: dict = {"data": None}
+
 
 def _invalidate_hosts_cache() -> None:
     _hosts_cache["data"] = None
@@ -1044,24 +1132,84 @@ class Plugin:
         try:
             return json.loads(_settings_path().read_text())
         except (OSError, json.JSONDecodeError):
-            # The client's own defaults (native display, host-default bitrate, auto pad).
+            # The client's own defaults (native display, host-default bitrate, auto pad,
+            # stats overlay at Normal — `Settings::default` is `show_stats: true`).
             return {
                 "width": 0, "height": 0, "refresh_hz": 0, "render_scale": 1.0,
-                "bitrate_kbps": 0, "codec": "auto", "gamepad": "auto", "compositor": "auto",
+                "bitrate_kbps": 0, "codec": "auto", "gamepad": "auto",
+                "gamepad_forwarding": True, "compositor": "auto",
                 "inhibit_shortcuts": True, "mic_enabled": False,
+                "stats_verbosity": "normal", "show_stats": True,
             }
 
     async def set_settings(self, settings: dict) -> dict:
-        """Write the stream settings JSON the (sandboxed) client reads on launch."""
+        """Write the stream settings JSON the (sandboxed) client reads on launch.
+
+        MERGED onto whatever is on disk, never a wholesale replace: this file is shared with
+        the desktop client and the console's settings screen, and it holds far more keys than
+        this panel models (decoder, GPU, profiles, touch/mouse model…). The panel reads it once
+        when it mounts, so a straight write would post a snapshot that predates anything those
+        other editors stored in the meantime — silently reverting it.
+        """
         try:
             d = _client_config_dir()
             d.mkdir(parents=True, exist_ok=True)
-            _settings_path().write_text(json.dumps(settings, indent=2))
+            try:
+                on_disk = json.loads(_settings_path().read_text())
+                if not isinstance(on_disk, dict):
+                    on_disk = {}
+            except (OSError, json.JSONDecodeError):
+                on_disk = {}  # no file yet (or an unreadable one): this write creates it
+            on_disk.update(settings)
+            _settings_path().write_text(json.dumps(on_disk, indent=2))
             return {"ok": True}
         except OSError as exc:
             decky.logger.exception("could not write settings")
             return {"ok": False, "error": str(exc)}
 
+    async def list_devices(self) -> dict:
+        """GPUs + audio endpoints for the settings tab's device pickers.
+
+        Two subprocesses that initialise Vulkan and PipeWire, so the result is cached for the
+        Decky session: hardware doesn't come and go often enough to justify paying that on every
+        remount of the page, and a stale entry is harmless — a picked device that has since
+        vanished falls back to the OS default in the client anyway. `refresh_devices` clears it.
+
+        Best-effort in the same way every other client call here is: no session binary (an old
+        flatpak that predates the two-binary split, or a native install missing its sibling) just
+        means empty lists and `ok: false`, which the UI shows as "couldn't read" rather than as
+        "you have no devices".
+        """
+        if _devices_cache["data"] is not None:
+            return _devices_cache["data"]
+
+        adapters: list[str] = []
+        sinks: list[dict] = []
+        sources: list[dict] = []
+        rc_a, out_a = await _run_session(["--list-adapters"])
+        if rc_a == 0:
+            adapters = [ln.strip() for ln in out_a.splitlines() if ln.strip()]
+        rc_d, out_d = await _run_session(["--list-audio"])
+        if rc_d == 0:
+            sinks, sources = _parse_audio_endpoints(out_d)
+
+        result = {
+            "ok": rc_a == 0 or rc_d == 0,
+            "adapters": adapters,
+            "sinks": sinks,
+            "sources": sources,
+        }
+        # Only a run that actually answered is worth remembering — caching a failure would make
+        # a client installed after the page was first opened stay invisible until a Decky restart.
+        if result["ok"]:
+            _devices_cache["data"] = result
+        return result
+
+    async def refresh_devices(self) -> dict:
+        """Drop the cached enumeration and read it again (a headset was just plugged in)."""
+        _devices_cache["data"] = None
+        return await self.list_devices()
+
     # ---- Shared known-hosts store (the SAME file the desktop client reads/writes) ----
 
     async def list_hosts(self, probe: bool = True) -> dict:

clients/decky/scripts/test-backend.py

@@ -144,6 +144,33 @@ got = asyncio.run(plugin.get_pins())["pins"]
 check("pins: paired via known-hosts fp (case-insensitive)", got[0]["paired"] is True)
 shutil.rmtree(decky.DECKY_USER_HOME, ignore_errors=True)
 
+# ---- `--list-audio` parsing (the settings tab's device pickers) --------------------------
+sinks, sources = main._parse_audio_endpoints(
+    "sink\talsa_output.pci-0000_04_00.6.analog-stereo\tSteam Deck Speakers\n"
+    "sink\tbluez_output.AC_12_2F.1\tWH-1000XM4\n"
+    "source\talsa_input.pci-0000_04_00.6.analog-stereo\tSteam Deck Microphone\n"
+)
+check("audio: sinks parsed", [d["name"] for d in sinks] == [
+    "alsa_output.pci-0000_04_00.6.analog-stereo", "bluez_output.AC_12_2F.1"
+])
+check("audio: sources parsed", len(sources) == 1)
+check("audio: description kept", sinks[1]["description"] == "WH-1000XM4")
+
+# Junk the picker must not offer: no node.name is unusable (it is the id that gets stored), a
+# short line is malformed, and an unknown kind belongs to neither list. A blank description
+# falls back to the name so no entry renders unlabelled.
+sinks, sources = main._parse_audio_endpoints(
+    "sink\t\tNo node name\n"
+    "sink\tonly-two-columns\n"
+    "monitor\tsome.monitor\tNot a sink or source\n"
+    "source\tbare.node\t\n"
+    "\n"
+)
+check("audio: junk lines dropped", sinks == [])
+check("audio: blank description falls back to the node name", sources == [
+    {"name": "bare.node", "description": "bare.node"}
+])
+
 print()
 if failures:
     print(f"{failures} check(s) FAILED")

clients/decky/src/backend.ts

@@ -101,24 +101,97 @@ export interface RunnerInfo {
   client_bin?: string;
 }
 
-// The slice of the flatpak client's settings JSON this UI surfaces. The file can hold more
-// keys (decoder, … set from the desktop client's own UI) — they round-trip untouched
-// because get_settings returns the whole parsed file and patches are object spreads.
+// The flatpak client's settings JSON — the SAME `client-gtk-settings.json` the desktop client
+// and the console's settings screen own, so a value changed in any of them shows in the others.
+//
+// Every field the client's `Settings` struct persists is modelled here EXCEPT the ones that
+// cannot be answered from a plugin backend or aren't settings at all:
+//   • `forward_pad`   — which physical pad is player 1. Needs SDL's live device list, which only
+//                       the client process has; there is no CLI that enumerates pads.
+//   • `last_window_w/h` — the session's remembered window size, written BY the client, not a
+//                       preference anyone sets.
+// Both round-trip untouched: get_settings returns the whole parsed file, patches are object
+// spreads, and set_settings merges onto what's on disk.
+//
+// Optional (`?`) marks a key the client writes with a serde `default`, so a store written before
+// that key existed simply lacks it. Read those through the same fallback the client uses —
+// `?? true` for the default-on ones, never `!!` — or a pre-existing file reads as "off" here
+// while the stream runs with it on.
 export interface StreamSettings {
+  // ---- Stream mode ----
   width: number; // 0 = native
   height: number; // 0 = native
   refresh_hz: number; // 0 = native
   render_scale?: number; // render-resolution multiplier; 1.0 = native (absent in pre-scale files)
   bitrate_kbps: number; // 0 = host default
-  codec?: string; // "auto" | "hevc" | "h264" | "av1" — soft preference (absent in pre-codec files)
-  gamepad: string; // "auto" | "xbox360" | "xboxone" | "dualsense" | "dualshock4" | "steamdeck"
   compositor: string; // "auto" | "kwin" | "wlroots" | "mutter" | "gamescope"
-  // Round-trips only — deliberately NOT offered as a row here. It decides whether the session
-  // grabs the keyboard so Alt+Tab/Super reach the host, and Game Mode is gamescope: it has no
-  // compositor shortcuts to inhibit and hands the focused window every key already. A toggle
-  // here would be a dead one. The desktop client's row still edits this same file.
-  inhibit_shortcuts: boolean;
+  // Stream mode follows the session window instead of width/height, renegotiating on resize.
+  // Overrides width/height while on; degenerates to the display's native mode on fullscreen.
+  match_window?: boolean;
+
+  // ---- Video ----
+  codec?: string; // "auto" | "hevc" | "h264" | "av1" | "pyrowave" (absent in pre-codec files)
+  decoder?: string; // "auto" | "vulkan" | "vaapi" | "software"
+  hdr_enabled?: boolean; // default ON — advertise 10-bit/HDR10
+  enable_444?: boolean; // default off — ask for full chroma
+  adapter?: string; // decode/present GPU by marketing name; "" = automatic
+
+  // ---- Presentation ----
+  // What the client optimises for when a decoded frame is ready: "latency" | "smooth". Shared
+  // with the Apple and Android clients under this name, so one profile reads the same everywhere.
+  present_priority?: string;
+  smooth_buffer?: number; // frames held back under "smooth"; 0 = Automatic (resolves to 2), else 1–3
+  vsync?: boolean; // default ON — tear-free; off asks for a tearing present mode (best-effort)
+  allow_vrr?: boolean; // default ON — let a VRR panel refresh in step with the stream
+
+  // ---- Audio ----
+  audio_channels?: number; // 2 (stereo) | 6 (5.1) | 8 (7.1)
+  speaker_device?: string; // PipeWire node.name for playback; "" = system default
   mic_enabled: boolean;
+  mic_device?: string; // PipeWire node.name for capture; "" = system default
+  echo_cancel?: boolean; // default ON; only meaningful while mic_enabled
+
+  // ---- Controllers ----
+  gamepad: string; // "auto" | "xbox360" | "xboxone" | "dualsense" | "dualshock4" | "steamdeck"
+  // Forward this device's controllers at all. Absent in pre-forwarding files, where the
+  // client's own serde default (true) applies — so `?? true` at every read, never `!!`.
+  gamepad_forwarding?: boolean;
+
+  // ---- Touchscreen, mouse & keyboard ----
+  touch_mode?: string; // "trackpad" | "pointer" | "touch"
+  mouse_mode?: string; // "capture" | "desktop"
+  invert_scroll?: boolean;
+  // Whether the session grabs the keyboard so Alt+Tab/Super reach the host.
+  inhibit_shortcuts: boolean;
+
+  // ---- Interface & behaviour ----
+  // Stats-overlay tier: "off" | "compact" | "normal" | "detailed". Absent in a pre-tier file,
+  // which resolves through `show_stats` — read both the way the client's
+  // `Settings::stats_verbosity` does, and write both the way `set_stats_verbosity` does.
+  stats_verbosity?: string;
+  // The legacy on/off the tier supersedes; kept written in sync so a client that predates the
+  // tiers still honours an Off chosen here.
+  show_stats?: boolean;
+  fullscreen_on_stream?: boolean;
+  auto_wake?: boolean; // default ON — Wake-on-LAN a sleeping host before connecting
+  library_enabled?: boolean; // the CLIENT's own library browser (this plugin has its own)
+}
+
+// One audio endpoint from the client's enumeration: the stable id that gets stored, plus the
+// human name to show.
+export interface AudioDevice {
+  name: string; // PipeWire node.name — what `speaker_device` / `mic_device` store
+  description: string; // human label ("Steam Deck Speakers")
+}
+
+// What the device pickers need, read from the session binary (`--list-adapters` / `--list-audio`).
+// `ok: false` = the session binary couldn't be run or failed; every list is then empty and the
+// pickers stay on their stored value rather than pretending the device is gone.
+export interface DeviceLists {
+  ok: boolean;
+  adapters: string[]; // Vulkan physical devices, discrete first
+  sinks: AudioDevice[]; // playback endpoints
+  sources: AudioDevice[]; // capture endpoints
 }
 
 export interface UpdateInfo {
@@ -185,6 +258,11 @@ export const getSettings = callable<[], StreamSettings>("get_settings");
 export const setSettings = callable<[settings: StreamSettings], { ok: boolean }>(
   "set_settings",
 );
+// GPUs + audio endpoints for the device pickers. Costs a subprocess that initialises Vulkan and
+// PipeWire, so it is called ONCE when the settings tab mounts and never on the launch path.
+export const listDevices = callable<[], DeviceLists>("list_devices");
+// The same, bypassing the backend's cache — for the user who just plugged in a headset.
+export const refreshDevices = callable<[], DeviceLists>("refresh_devices");
 export const killStream = callable<[], { ok: boolean }>("kill_stream");
 // Send a Wake-on-LAN magic packet to a saved host (headless flatpak --wake) so a sleeping host is
 // up by the time the stream connects. The MAC is looked up from the flatpak client's own

clients/decky/src/page.tsx

@@ -334,8 +334,14 @@ const HostsTab: FC<{
   </div>
 );
 
+// NOT `tabScroll`: the settings screen is a SidebarNavigation, which lays out its own rail +
+// content pane and scrolls the pane itself. Wrapping it in an outer scroll area would give it an
+// indefinite height to fill, collapsing the rail — so this pane only hands it the full height and
+// keeps its hands off the overflow. The footer inset lives inside the pages instead.
+const settingsPane: CSSProperties = { height: "100%", overflow: "hidden" };
+
 const SettingsTab: FC = () => (
-  <div style={tabScroll}>
+  <div style={settingsPane}>
     <SettingsSection />
   </div>
 );

clients/decky/src/settings.tsx

@@ -1,10 +1,59 @@
-// Stream settings — resolution / refresh / bitrate / gamepad / compositor / mic, written to
-// the flatpak client's JSON (main.py set_settings), which the client reads on launch. The
-// accepted gamepad/compositor names mirror punktfunk-core's `*Pref::from_name`.
-import { Dropdown, Field, SliderField, Spinner, ToggleField } from "@decky/ui";
-import { CSSProperties, FC, useEffect, useState } from "react";
-import { getSettings, setSettings, StreamSettings } from "./backend";
-import { RowActions } from "./ui";
+// Stream settings — the client's WHOLE settings store, written to the JSON the client reads on
+// launch (main.py set_settings, merged onto what's on disk). This is the same
+// `client-gtk-settings.json` the desktop client and the console's settings screen own, so a value
+// changed in any of the three shows in the other two.
+//
+// SHAPE OF THIS SCREEN. Thirty rows is too many to scroll past on a thumbstick, so they are split
+// across a `SidebarNavigation` — the same left-rail-of-categories layout SteamOS's own Settings
+// uses, and the one Deck users already know. Every page fits on screen without scrolling, which is
+// the whole point of the split: the rail is the index, so nothing is more than one hop away.
+//
+// The categories, their order, and the wording of the rows are the console's settings screen
+// (pf-console-ui/src/screens/settings.rs) — that screen is the other settings editor a user
+// reaches without leaving Gaming Mode, and two different orders for one store is how people stop
+// trusting either. It shows them as one steppable list because it has no pointer and no room for
+// a rail; here they become the rail's pages, same groups, same sequence. Three more rules:
+//
+//   • A setting that depends on another is INDENTED under it and DISABLED, never hidden — the
+//     console dims those rows rather than dropping them, and a row that vanishes as you toggle
+//     the one above it is a moving target for a thumbstick.
+//   • A picker whose options this device doesn't have doesn't appear at all (the GPU row on a
+//     one-GPU Deck). A dead control is worse than an absent one.
+//   • Anything that behaves differently *here* than it does on a desktop says so in its own
+//     description, rather than being silently dropped from the screen.
+//
+// The accepted gamepad/compositor/codec/decoder names mirror punktfunk-core's `*Pref::from_name`
+// and the console's tables; the tier/mode names mirror the `StatsVerbosity` / `TouchMode` /
+// `MouseMode` enums, which serialize lowercase.
+import {
+  DialogButton,
+  Dropdown,
+  Field,
+  SidebarNavigation,
+  SliderField,
+  Spinner,
+  ToggleField,
+} from "@decky/ui";
+import { CSSProperties, FC, ReactElement, ReactNode, useEffect, useState } from "react";
+import {
+  FaDesktop,
+  FaGamepad,
+  FaHandPointer,
+  FaSlidersH,
+  FaTv,
+  FaVideo,
+  FaVolumeUp,
+} from "react-icons/fa";
+import {
+  AudioDevice,
+  DeviceLists,
+  getSettings,
+  listDevices,
+  refreshDevices,
+  setSettings,
+  StreamSettings,
+} from "./backend";
+import { actionButton, RowActions } from "./ui";
 
 // Decky's Dropdown has no width prop — it fills whatever container it's in, and a
 // `childrenContainerWidth="max"` Field is the whole row. Wrapping it in this fit-content shell
@@ -17,50 +66,543 @@ const selectShell: CSSProperties = {
   maxWidth: "24em",
 };
 
+// ----------------------------------------------------------------------------------------
+// Option tables — the console's, so the two Gaming-Mode editors offer the same choices.
+// ----------------------------------------------------------------------------------------
+
+// "native" and "match" are virtual: they store `width`/`height` of 0 with `match_window` off/on.
+// Match window is offered even though this plugin's launches are always fullscreen (where it
+// degenerates to the display's native mode) — leaving it out would make the row lie about a
+// store the desktop client can set it in.
+const MATCH_WINDOW = "match";
 const RESOLUTIONS: [number, number, string][] = [
   [0, 0, "Native display"],
   [1280, 720, "1280 × 720"],
   [1280, 800, "1280 × 800 (Deck)"],
   [1920, 1080, "1920 × 1080"],
   [2560, 1440, "2560 × 1440"],
+  [3840, 2160, "3840 × 2160"],
 ];
+const resolutionKey = (w: number, h: number): string => (w === 0 && h === 0 ? "native" : `${w}x${h}`);
+
 const REFRESH = [0, 30, 60, 90, 120];
 // Render-resolution multipliers (mirrors punktfunk_core::render_scale::PRESETS). 1.0 = native.
 const RENDER_SCALES = [0.5, 0.67, 0.75, 1.0, 1.25, 1.5, 2.0, 3.0, 4.0];
 const renderScaleLabel = (x: number): string =>
   x === 1 ? "Native (1×)" : x > 1 ? `${x}× · supersample` : `${x}×`;
-const GAMEPADS = ["auto", "xbox360", "xboxone", "dualsense", "dualshock4", "steamdeck"];
-const GAMEPAD_LABELS: Record<string, string> = {
-  auto: "Automatic",
-  xbox360: "Xbox 360",
-  xboxone: "Xbox One",
-  dualsense: "DualSense",
-  dualshock4: "DualShock 4",
-  steamdeck: "Steam Deck",
+
+const COMPOSITORS: [string, string][] = [
+  ["auto", "Automatic"],
+  ["kwin", "KDE Plasma (KWin)"],
+  ["wlroots", "Sway (wlroots)"],
+  ["mutter", "GNOME (Mutter)"],
+  ["gamescope", "gamescope"],
+];
+const CODECS: [string, string][] = [
+  ["auto", "Automatic"],
+  ["hevc", "HEVC (H.265)"],
+  ["h264", "H.264 (AVC)"],
+  ["av1", "AV1"],
+  // Opt-in wired-LAN low-latency codec (100–400 Mbit/s class, 8-bit SDR). Only ever selected
+  // when the host advertises it too; anything else falls back to HEVC.
+  ["pyrowave", "PyroWave (wired LAN)"],
+];
+const DECODERS: [string, string][] = [
+  ["auto", "Automatic"],
+  ["vulkan", "Vulkan Video"],
+  ["vaapi", "VAAPI"],
+  ["software", "Software"],
+];
+// Presentation intent — the `present_priority` key shared with the Apple and Android clients, so
+// one profile reads the same on every device.
+const PRESENT_PRIORITIES: [string, string][] = [
+  ["latency", "Lowest latency"],
+  ["smooth", "Smoothness"],
+];
+// Smoothness buffer depth in frames; 0 = Automatic (resolves to 2).
+const SMOOTH_BUFFERS: [number, string][] = [
+  [0, "Automatic"],
+  [1, "1 frame"],
+  [2, "2 frames"],
+  [3, "3 frames"],
+];
+const AUDIO_CHANNELS: [number, string][] = [
+  [2, "Stereo"],
+  [6, "5.1 surround"],
+  [8, "7.1 surround"],
+];
+const GAMEPADS: [string, string][] = [
+  ["auto", "Automatic"],
+  ["xbox360", "Xbox 360"],
+  ["xboxone", "Xbox One"],
+  ["dualsense", "DualSense"],
+  ["dualshock4", "DualShock 4"],
+  ["steamdeck", "Steam Deck"],
+];
+const TOUCH_MODES: [string, string][] = [
+  ["trackpad", "Trackpad"],
+  ["pointer", "Direct pointer"],
+  ["touch", "Touch passthrough"],
+];
+const MOUSE_MODES: [string, string][] = [
+  ["capture", "Capture (games)"],
+  ["desktop", "Desktop (absolute)"],
+];
+const STATS_TIERS: [string, string][] = [
+  ["off", "Off"],
+  ["compact", "Compact"],
+  ["normal", "Normal"],
+  ["detailed", "Detailed"],
+];
+
+// ----------------------------------------------------------------------------------------
+// Row primitives — every picker row is Field + right-aligned, content-sized Dropdown, so the
+// twelve of them below stay one line each and can't drift apart.
+// ----------------------------------------------------------------------------------------
+
+const SelectRow = <T extends string | number>({
+  label,
+  description,
+  options,
+  value,
+  onChange,
+  formatUnknown,
+  disabled,
+  indent,
+}: {
+  label: string;
+  description?: ReactNode;
+  options: [T, string][];
+  value: T;
+  onChange: (v: T) => void;
+  // How to name a stored value this table doesn't list (see below); defaults to the raw value.
+  formatUnknown?: (v: T) => string;
+  disabled?: boolean;
+  indent?: boolean;
+}): ReactElement => {
+  // A Dropdown can only display a value that is one of its options, and this store has four other
+  // writers — the desktop client, the console, a settings profile, a newer client with presets
+  // this build doesn't know. Rather than render a blank control (or, worse, silently show a
+  // different value than the stream will actually use), carry the stored one as its own entry.
+  const shown: [T, string][] = options.some(([v]) => v === value)
+    ? options
+    : [...options, [value, formatUnknown ? formatUnknown(value) : String(value)]];
+  return (
+    <Field
+      label={label}
+      description={description}
+      disabled={disabled}
+      indentLevel={indent ? 1 : undefined}
+      childrenContainerWidth="max"
+    >
+      <RowActions>
+        <div style={selectShell}>
+          <Dropdown
+            disabled={disabled}
+            rgOptions={shown.map(([data, l]) => ({ data, label: l }))}
+            selectedOption={value}
+            onChange={(o) => onChange(o.data as T)}
+          />
+        </div>
+      </RowActions>
+    </Field>
+  );
 };
-// Mirrors the desktop client's picker (ui_settings.rs CODECS) — a soft preference the host
-// falls back from when its GPU can't encode it.
-const CODECS = ["auto", "hevc", "h264", "av1"];
-const CODEC_LABELS: Record<string, string> = {
-  auto: "Automatic",
-  hevc: "HEVC (H.265)",
-  h264: "H.264 (AVC)",
-  av1: "AV1",
+
+// An audio-endpoint picker. The stored value is a PipeWire `node.name`; "" means "whatever the OS
+// is using". A stored endpoint that isn't in the current enumeration still gets an entry — it is
+// a real preference that simply isn't plugged in right now, and dropping it would silently
+// re-point the next stream at the default without ever showing the user why.
+const DeviceRow: FC<{
+  label: string;
+  description: string;
+  devices: AudioDevice[] | null;
+  value: string;
+  onChange: (v: string) => void;
+  disabled?: boolean;
+  indent?: boolean;
+}> = ({ label, description, devices, value, onChange, disabled, indent }) => {
+  const options: [string, string][] = [["", "System default"]];
+  for (const d of devices ?? []) options.push([d.name, d.description]);
+  if (value && !options.some(([name]) => name === value)) {
+    options.push([value, `${value} (not connected)`]);
+  }
+  return (
+    <SelectRow
+      label={label}
+      description={devices === null ? "Reading this device's audio endpoints…" : description}
+      options={options}
+      value={value}
+      onChange={onChange}
+      disabled={disabled || devices === null}
+      indent={indent}
+    />
+  );
 };
-const COMPOSITORS = ["auto", "kwin", "wlroots", "mutter", "gamescope"];
-const COMPOSITOR_LABELS: Record<string, string> = {
-  auto: "Automatic",
-  kwin: "KDE Plasma (KWin)",
-  wlroots: "Sway (wlroots)",
-  mutter: "GNOME (Mutter)",
-  gamescope: "gamescope",
+
+// ----------------------------------------------------------------------------------------
+// The pages. One settings object, seven views on it — every page takes the same context rather
+// than fetching or holding state of its own, so a change on one page is visible on the others
+// the moment you switch.
+// ----------------------------------------------------------------------------------------
+
+interface PageCtx {
+  s: StreamSettings;
+  patch: (p: Partial<StreamSettings>) => void;
+  devices: DeviceLists | null;
+  reading: boolean;
+  readDevices: (again: boolean) => void;
+}
+
+// SidebarNavigation gives each page Steam's own padding, but the routed page still renders
+// UNDER Gaming Mode's footer hint bar, so the last row of a page needs to clear it (the same
+// inset the tabs use).
+const pageBody: CSSProperties = { paddingBottom: "80px" };
+
+const StreamPage: FC<PageCtx> = ({ s, patch }) => {
+  const renderScale = s.render_scale ?? 1;
+  const resolution = s.match_window ? MATCH_WINDOW : resolutionKey(s.width, s.height);
+  return (
+    <div style={pageBody}>
+      <SelectRow
+        label="Resolution"
+        description="The host creates a virtual display at exactly this size — no scaling. Match window follows the stream window instead, which in Gaming Mode means the Deck's native size."
+        options={[
+          ...RESOLUTIONS.map(([w, h, label]) => [resolutionKey(w, h), label] as [string, string]),
+          [MATCH_WINDOW, "Match window"] as [string, string],
+        ]}
+        value={resolution}
+        // A size set from a desktop profile that isn't one of these presets, spelled the way the
+        // presets are rather than left as the raw "1600x900" key.
+        formatUnknown={(v) => v.replace("x", " × ")}
+        onChange={(v) => {
+          if (v === MATCH_WINDOW) {
+            // The tri-state the console stores: the flag on, the explicit size cleared.
+            patch({ match_window: true, width: 0, height: 0 });
+            return;
+          }
+          const found = RESOLUTIONS.find(([w, h]) => resolutionKey(w, h) === v);
+          patch({ match_window: false, width: found?.[0] ?? 0, height: found?.[1] ?? 0 });
+        }}
+      />
+      <SelectRow
+        label="Refresh rate"
+        description="Native follows the display the stream is on."
+        options={REFRESH.map((r) => [r, r === 0 ? "Native" : `${r} Hz`] as [number, string])}
+        value={s.refresh_hz}
+        formatUnknown={(v) => `${v} Hz`}
+        onChange={(v) => patch({ refresh_hz: v })}
+      />
+      <SelectRow
+        label="Render scale"
+        description="The host renders larger or smaller than the stream mode and the Deck resamples — above 1× supersamples for sharpness, below 1× saves bandwidth."
+        options={RENDER_SCALES.map((x) => [x, renderScaleLabel(x)] as [number, string])}
+        // Snap the stored value to the nearest preset so the dropdown always shows a match.
+        value={RENDER_SCALES.reduce((best, x) =>
+          Math.abs(x - renderScale) < Math.abs(best - renderScale) ? x : best,
+        )}
+        onChange={(v) => patch({ render_scale: v })}
+      />
+      <SliderField
+        label="Bitrate"
+        description="0 = the host's own default (20 Mbit/s)."
+        value={Math.round(s.bitrate_kbps / 1000)}
+        min={0}
+        max={150}
+        step={5}
+        showValue
+        valueSuffix=" Mbit/s"
+        onChange={(v) => patch({ bitrate_kbps: v * 1000 })}
+      />
+      <SelectRow
+        label="Host compositor"
+        description="Which compositor drives the virtual display — honoured only if it's available on the host. Automatic suits almost every host."
+        options={COMPOSITORS}
+        value={s.compositor}
+        onChange={(v) => patch({ compositor: v })}
+      />
+    </div>
+  );
 };
 
+const VideoPage: FC<PageCtx> = ({ s, patch, devices }) => {
+  // Only worth a row on a box that actually has a choice to make. A Deck has one adapter, and a
+  // picker with a single option is a control that can't do anything.
+  const showGpuRow = (devices?.adapters.length ?? 0) > 1;
+  return (
+    <div style={pageBody}>
+      <SelectRow
+        label="Video codec"
+        description="A preference — the host falls back when its GPU can't encode this one."
+        options={CODECS}
+        value={s.codec ?? "auto"}
+        onChange={(v) => patch({ codec: v })}
+      />
+      <SelectRow
+        label="Video decoder"
+        description="How the Deck decodes the stream. Automatic prefers Vulkan Video, then VAAPI, then software."
+        options={DECODERS}
+        value={s.decoder ?? "auto"}
+        onChange={(v) => patch({ decoder: v })}
+      />
+      {showGpuRow && (
+        <SelectRow
+          label="Decode GPU"
+          description="Which adapter decodes and presents the stream. Automatic picks the discrete GPU where there is one."
+          options={[
+            ["", "Automatic"],
+            ...(devices?.adapters ?? []).map((a) => [a, a] as [string, string]),
+          ]}
+          value={s.adapter ?? ""}
+          onChange={(v) => patch({ adapter: v })}
+        />
+      )}
+      <ToggleField
+        label="10-bit HDR"
+        description="Advertise HDR10 so the host sends 10-bit when the content is HDR. Off means never ask for 10-bit."
+        checked={s.hdr_enabled ?? true}
+        onChange={(v) => patch({ hdr_enabled: v })}
+      />
+      <ToggleField
+        label="Full chroma (4:4:4)"
+        description="Full-colour video: crisp small text and thin lines, at more bandwidth. Needs an NVIDIA host (NVENC) or the PyroWave codec — other encoders stream 4:2:0 and the session falls back silently."
+        checked={s.enable_444 ?? false}
+        onChange={(v) => patch({ enable_444: v })}
+      />
+    </div>
+  );
+};
+
+const PresentationPage: FC<PageCtx> = ({ s, patch }) => {
+  const smooth = (s.present_priority ?? "latency") === "smooth";
+  return (
+    <div style={pageBody}>
+      <SelectRow
+        label="Prioritize"
+        description="What to optimise for when a decoded frame is ready. Lowest latency shows each frame the moment the display can take it — a network hiccup becomes an occasional repeated or skipped frame. Smoothness buffers a little to even those out."
+        options={PRESENT_PRIORITIES}
+        value={s.present_priority ?? "latency"}
+        onChange={(v) => patch({ present_priority: v })}
+      />
+      <SelectRow
+        label="Smoothness buffer"
+        description="Frames held back before showing. Each one absorbs about a refresh of network hiccup and adds a refresh of delay. Automatic holds two."
+        options={SMOOTH_BUFFERS}
+        value={s.smooth_buffer ?? 0}
+        formatUnknown={(v) => `${v} frames`}
+        onChange={(v) => patch({ smooth_buffer: v })}
+        disabled={!smooth}
+        indent
+      />
+      <ToggleField
+        label="V-Sync"
+        description="Tear-free. Off removes the wait for the screen's refresh — the lowest possible delay, at the cost of visible tearing. Best-effort: not every driver offers it, and the Detailed stats overlay names the mode actually in use."
+        checked={s.vsync ?? true}
+        onChange={(v) => patch({ vsync: v })}
+      />
+      <ToggleField
+        label="Follow variable refresh"
+        description="On a VRR screen, let the panel refresh in step with the stream instead of on a fixed cadence. Applies to fullscreen sessions — which a Gaming-Mode stream always is — and is harmless on a fixed-refresh screen."
+        checked={s.allow_vrr ?? true}
+        onChange={(v) => patch({ allow_vrr: v })}
+      />
+    </div>
+  );
+};
+
+const AudioPage: FC<PageCtx> = ({ s, patch, devices, reading, readDevices }) => {
+  const micOn = s.mic_enabled;
+  // What the pickers get: null while the enumeration is in flight (they show a loading state),
+  // [] when it answered but couldn't read the endpoints (System default plus whatever is
+  // stored), and the real list otherwise.
+  const endpoints = (list: AudioDevice[] | undefined): AudioDevice[] | null =>
+    reading || !devices ? null : devices.ok ? (list ?? []) : [];
+  return (
+    <div style={pageBody}>
+      <SelectRow
+        label="Audio channels"
+        description="The speaker layout requested from the host, which clamps it to what it can capture."
+        options={AUDIO_CHANNELS}
+        value={s.audio_channels ?? 2}
+        formatUnknown={(v) => `${v} channels`}
+        onChange={(v) => patch({ audio_channels: v })}
+      />
+      <DeviceRow
+        label="Output device"
+        description="Where stream audio plays. System default follows whatever the Deck is using, including a headset you plug in mid-stream."
+        devices={endpoints(devices?.sinks)}
+        value={s.speaker_device ?? ""}
+        onChange={(v) => patch({ speaker_device: v })}
+      />
+      <ToggleField
+        label="Stream microphone"
+        description="Send the Deck's microphone to the host's virtual mic. Ctrl+Alt+Shift+V mutes and unmutes it mid-stream."
+        checked={micOn}
+        onChange={(v) => patch({ mic_enabled: v })}
+      />
+      <DeviceRow
+        label="Microphone device"
+        description="Which input the mic uplink captures from."
+        devices={endpoints(devices?.sources)}
+        value={s.mic_device ?? ""}
+        onChange={(v) => patch({ mic_device: v })}
+        disabled={!micOn}
+        indent
+      />
+      <ToggleField
+        label="Echo cancellation"
+        description="Stops the host's audio, playing from the Deck's speakers, being picked up and sent back. Turn it off if your microphone already runs its own processing."
+        checked={s.echo_cancel ?? true}
+        onChange={(v) => patch({ echo_cancel: v })}
+        disabled={!micOn}
+        indentLevel={1}
+      />
+      {/* The escape hatch for a headset plugged in after this page was opened, and the honest
+          answer when the enumeration failed outright (a client too old to ship the session
+          binary). Rendered unconditionally, including while it is reading: a row that comes and
+          goes under a thumbstick is a moving target, so only its wording changes. */}
+      <Field
+        label={
+          !reading && devices && !devices.ok ? "Couldn't read this device's hardware" : "Devices"
+        }
+        description={
+          reading
+            ? "Reading this device's audio endpoints and GPUs…"
+            : devices && !devices.ok
+              ? "The output, microphone and GPU pickers fall back to Automatic. Reading them needs the client's session binary, which a client older than the two-binary split doesn't ship — update it from the About tab."
+              : "Plugged something in just now? Read the audio endpoints and GPUs again."
+        }
+        childrenContainerWidth="max"
+      >
+        <RowActions>
+          <DialogButton style={actionButton} disabled={reading} onClick={() => readDevices(true)}>
+            {reading ? <Spinner style={{ height: "1em" }} /> : "Refresh"}
+          </DialogButton>
+        </RowActions>
+      </Field>
+    </div>
+  );
+};
+
+const ControllersPage: FC<PageCtx> = ({ s, patch }) => {
+  const forwarding = s.gamepad_forwarding ?? true;
+  return (
+    <div style={pageBody}>
+      <ToggleField
+        label="Forward controllers"
+        description="Send controllers connected to the Deck to the host. Turn it off when your controller already reaches the host another way — USB passthrough such as VirtualHere, or a pad plugged into the host — so games don't see two of them."
+        checked={forwarding}
+        onChange={(v) => patch({ gamepad_forwarding: v })}
+      />
+      <SelectRow
+        label="Controller type"
+        description="The virtual pad the host creates. Automatic matches the controller you're holding."
+        options={GAMEPADS}
+        value={s.gamepad}
+        onChange={(v) => patch({ gamepad: v })}
+        disabled={!forwarding}
+        indent
+      />
+      {forwarding && (s.gamepad === "steamdeck" || s.gamepad === "auto") && (
+        <Field
+          label="⚠ Disable Steam Input"
+          description="On a Deck, Automatic forwards the built-in controller as a Steam Deck pad — paddles, both trackpads, and gyro included. For that, Steam Input must be OFF for Punktfunk: on the game page tap ⚙ → Controller Settings → set Steam Input to Off. Otherwise Steam keeps the Deck's controls and only the sticks + buttons reach the host."
+          indentLevel={1}
+        />
+      )}
+    </div>
+  );
+};
+
+const PointerPage: FC<PageCtx> = ({ s, patch }) => (
+  <div style={pageBody}>
+    <SelectRow
+      label="Touch mode"
+      description="How the touchscreen drives the host: Trackpad (relative cursor, tap to click), Direct pointer (the cursor jumps to your finger), or Touch passthrough (every finger is a host contact — only helps apps that understand touch)."
+      options={TOUCH_MODES}
+      value={s.touch_mode ?? "trackpad"}
+      onChange={(v) => patch({ touch_mode: v })}
+    />
+    <SelectRow
+      label="Mouse mode"
+      description="How a physical mouse drives the host: Capture locks the pointer for games, Desktop leaves it free and sends absolute positions. Ctrl+Alt+Shift+M switches it live mid-stream."
+      options={MOUSE_MODES}
+      value={s.mouse_mode ?? "capture"}
+      onChange={(v) => patch({ mouse_mode: v })}
+    />
+    <ToggleField
+      label="Invert scroll direction"
+      description="Reverses the wheel and trackpad scroll direction sent to the host."
+      checked={s.invert_scroll ?? false}
+      onChange={(v) => patch({ invert_scroll: v })}
+    />
+    <ToggleField
+      label="Capture system shortcuts"
+      description="Sends Alt+Tab, Super and friends to the host while input is captured, instead of leaving them to the local desktop. Gaming Mode is gamescope, which has no shortcuts to hold back — this is for a keyboard attached to the Deck in Desktop Mode, and for the desktop client sharing these settings."
+      checked={s.inhibit_shortcuts}
+      onChange={(v) => patch({ inhibit_shortcuts: v })}
+    />
+  </div>
+);
+
+const InterfacePage: FC<PageCtx> = ({ s, patch }) => {
+  // `Settings::stats_verbosity`: no tier = a pre-tier store, resolved through the legacy bool,
+  // which itself defaults to true.
+  const statsTier = s.stats_verbosity ?? ((s.show_stats ?? true) ? "normal" : "off");
+  return (
+    <div style={pageBody}>
+      <SelectRow
+        label="Statistics overlay"
+        description="How much the in-stream overlay shows: Compact (fps · latency · bitrate on one line) → Normal → Detailed. A three-finger tap on the touchscreen cycles it mid-stream."
+        options={STATS_TIERS}
+        value={statsTier}
+        // Both keys, in sync — the same pairing `Settings::set_stats_verbosity` keeps, so a
+        // client too old for the tiers still honours an Off chosen here.
+        onChange={(v) => patch({ stats_verbosity: v, show_stats: v !== "off" })}
+      />
+      <ToggleField
+        label="Wake hosts automatically"
+        description="Send Wake-on-LAN to a sleeping host before connecting and wait for it to boot. Turn it off for hosts reached over a VPN, where an offline-looking host is really just unreachable by broadcast and the wait only adds delay."
+        checked={s.auto_wake ?? true}
+        onChange={(v) => patch({ auto_wake: v })}
+      />
+      <ToggleField
+        label="Show game library in the client"
+        description="Lets the client's own host cards browse a paired host's games. This plugin's library browser works either way — this is for the client's screens."
+        checked={s.library_enabled ?? false}
+        onChange={(v) => patch({ library_enabled: v })}
+      />
+      <ToggleField
+        label="Start streams fullscreen"
+        description="Streams open fullscreen instead of windowed. Launches from this plugin are always fullscreen whatever this says — it's here because the desktop client reads the same settings."
+        checked={s.fullscreen_on_stream ?? true}
+        onChange={(v) => patch({ fullscreen_on_stream: v })}
+      />
+    </div>
+  );
+};
+
+// ----------------------------------------------------------------------------------------
+
 export const SettingsSection: FC = () => {
   const [s, setS] = useState<StreamSettings | null>(null);
+  // null until the enumeration answers — the pickers show a loading state rather than briefly
+  // claiming this device has no endpoints.
+  const [devices, setDevices] = useState<DeviceLists | null>(null);
+  const [reading, setReading] = useState(true);
+
+  const readDevices = (again: boolean) => {
+    setReading(true);
+    void (again ? refreshDevices() : listDevices())
+      .then(setDevices)
+      .finally(() => setReading(false));
+  };
 
   useEffect(() => {
     void getSettings().then(setS);
+    // Deliberately not awaited together with the settings: a cold flatpak initialising Vulkan
+    // takes seconds, and the rest of the screen must not wait for it.
+    readDevices(false);
   }, []);
 
   const patch = (p: Partial<StreamSettings>) => {
@@ -74,128 +616,42 @@ export const SettingsSection: FC = () => {
 
   if (!s) return <Spinner style={{ height: "1.5em" }} />;
 
-  const resIdx = Math.max(
-    0,
-    RESOLUTIONS.findIndex(([w, h]) => w === s.width && h === s.height),
-  );
-
+  const ctx: PageCtx = { s, patch, devices, reading, readDevices };
   return (
-    <>
-      <Field
-        label="Resolution"
-        description="The host creates a virtual output at exactly this size"
-        childrenContainerWidth="max"
-      >
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={RESOLUTIONS.map(([, , label], i) => ({ data: i, label }))}
-              selectedOption={resIdx}
-              onChange={(o) => {
-                const [w, h] = RESOLUTIONS[o.data as number];
-                patch({ width: w, height: h });
-              }}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      <Field label="Refresh rate" childrenContainerWidth="max">
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={REFRESH.map((r) => ({ data: r, label: r === 0 ? "Native" : `${r} Hz` }))}
-              selectedOption={s.refresh_hz}
-              onChange={(o) => patch({ refresh_hz: o.data as number })}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      <Field
-        label="Render scale"
-        description="Supersample for sharpness (> 1×, more bandwidth) or render below native (< 1×) — the Deck resamples to its screen"
-        childrenContainerWidth="max"
-      >
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={RENDER_SCALES.map((x) => ({ data: x, label: renderScaleLabel(x) }))}
-              // Snap the stored value to the nearest preset so the dropdown always shows a match.
-              selectedOption={RENDER_SCALES.reduce((best, x) =>
-                Math.abs(x - (s.render_scale ?? 1)) < Math.abs(best - (s.render_scale ?? 1)) ? x : best,
-              )}
-              onChange={(o) => patch({ render_scale: o.data as number })}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      <SliderField
-        label="Bitrate"
-        description="Mbit/s · 0 = host default"
-        value={Math.round(s.bitrate_kbps / 1000)}
-        min={0}
-        max={150}
-        step={5}
-        showValue
-        valueSuffix=" Mbit/s"
-        onChange={(v) => patch({ bitrate_kbps: v * 1000 })}
-      />
-      <Field
-        label="Video codec"
-        description="Preferred stream codec — the host falls back when its GPU can't encode it"
-        childrenContainerWidth="max"
-      >
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={CODECS.map((c) => ({ data: c, label: CODEC_LABELS[c] ?? c }))}
-              selectedOption={s.codec ?? "auto"}
-              onChange={(o) => patch({ codec: o.data as string })}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      <Field
-        label="Gamepad type"
-        description="Which virtual controller the host creates for your inputs"
-        childrenContainerWidth="max"
-      >
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={GAMEPADS.map((g) => ({ data: g, label: GAMEPAD_LABELS[g] ?? g }))}
-              selectedOption={s.gamepad}
-              onChange={(o) => patch({ gamepad: o.data as string })}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      {(s.gamepad === "steamdeck" || s.gamepad === "auto") && (
-        <Field
-          label="⚠ Disable Steam Input"
-          description="On a Deck, Automatic forwards the built-in controller as a Steam Deck pad — paddles, both trackpads, and gyro included. For that, Steam Input must be OFF for Punktfunk: on the game page tap ⚙ → Controller Settings → set Steam Input to Off. Otherwise Steam keeps the Deck's controls and only the sticks + buttons reach the host."
-        />
-      )}
-      <Field
-        label="Host compositor"
-        description="Which compositor backend the host uses for the virtual display — Automatic suits almost every host"
-        childrenContainerWidth="max"
-      >
-        <RowActions>
-          <div style={selectShell}>
-            <Dropdown
-              rgOptions={COMPOSITORS.map((c) => ({ data: c, label: COMPOSITOR_LABELS[c] ?? c }))}
-              selectedOption={s.compositor}
-              onChange={(o) => patch({ compositor: o.data as string })}
-            />
-          </div>
-        </RowActions>
-      </Field>
-      <ToggleField
-        label="Stream microphone"
-        description="Send the Deck's microphone to the host's virtual mic"
-        checked={s.mic_enabled}
-        onChange={(v) => patch({ mic_enabled: v })}
-      />
-    </>
+    <SidebarNavigation
+      // We are already inside the plugin's own `/punktfunk` route, rendered in a tab. Route
+      // reporting would have this nav push entries of its own onto the router and fight the
+      // page for the back gesture; the pages are addressed by `identifier` instead.
+      disableRouteReporting
+      pages={[
+        { title: "Stream", identifier: "stream", icon: <FaDesktop />, content: <StreamPage {...ctx} /> },
+        { title: "Video", identifier: "video", icon: <FaVideo />, content: <VideoPage {...ctx} /> },
+        {
+          title: "Presentation",
+          identifier: "presentation",
+          icon: <FaTv />,
+          content: <PresentationPage {...ctx} />,
+        },
+        { title: "Audio", identifier: "audio", icon: <FaVolumeUp />, content: <AudioPage {...ctx} /> },
+        {
+          title: "Controllers",
+          identifier: "controllers",
+          icon: <FaGamepad />,
+          content: <ControllersPage {...ctx} />,
+        },
+        {
+          title: "Touch & mouse",
+          identifier: "pointer",
+          icon: <FaHandPointer />,
+          content: <PointerPage {...ctx} />,
+        },
+        {
+          title: "Interface",
+          identifier: "interface",
+          icon: <FaSlidersH />,
+          content: <InterfacePage {...ctx} />,
+        },
+      ]}
+    />
   );
 };

clients/linux/src/ui_settings.rs

@@ -156,6 +156,20 @@ mod index {
     pub fn gamepad(s: &Settings) -> u32 {
         GAMEPADS.iter().position(|&g| g == s.gamepad).unwrap_or(0) as u32
     }
+
+    pub fn present_priority(s: &Settings) -> u32 {
+        // Unknown values (a newer client's intent) read as the default, exactly as
+        // `PresentPriority::resolve` treats them.
+        PRESENT_PRIORITIES
+            .iter()
+            .position(|&p| p == s.present_priority)
+            .unwrap_or(0) as u32
+    }
+
+    pub fn smooth_buffer(s: &Settings) -> u32 {
+        // The index IS the stored value: 0 = Automatic, 1..3 = frames.
+        u32::from(s.smooth_buffer).min(SMOOTH_BUFFER_LABELS.len() as u32 - 1)
+    }
 }
 
 /// The chip palette a profile can carry (`StreamProfile.accent`). Eight entries rather than a
@@ -625,12 +639,27 @@ fn commit_profile(active: &StreamProfile, touched: &Touched, values: &Settings)
     if touched.has("gamepad") {
         o.gamepad = Some(values.gamepad.clone());
     }
+    if touched.has("gamepad_forwarding") {
+        o.gamepad_forwarding = Some(values.gamepad_forwarding);
+    }
     if touched.has("stats_verbosity") {
         o.stats_verbosity = Some(values.stats_verbosity());
     }
     if touched.has("fullscreen_on_stream") {
         o.fullscreen_on_stream = Some(values.fullscreen_on_stream);
     }
+    if touched.has("present_priority") {
+        o.present_priority = Some(values.present_priority.clone());
+    }
+    if touched.has("smooth_buffer") {
+        o.smooth_buffer = Some(values.smooth_buffer);
+    }
+    if touched.has("vsync") {
+        o.vsync = Some(values.vsync);
+    }
+    if touched.has("allow_vrr") {
+        o.allow_vrr = Some(values.allow_vrr);
+    }
     // Resets are not handled here: they clear the field and re-seed their row the moment the
     // user asks, so by the time this runs the catalog already reflects them and the row is no
     // longer marked touched.
@@ -684,6 +713,20 @@ const TOUCH_MODE_CAPTIONS: &[&str] = &[
     "The cursor jumps to your finger — a tap clicks there",
     "Real multi-touch reaches the host — for touch-native apps",
 ];
+/// Presentation-intent values (persisted under the `present_priority` key the Apple and
+/// Android clients share) + labels + dynamic captions. Captions stay ONE line, like the
+/// touch/mouse rows.
+const PRESENT_PRIORITIES: &[&str] = &["latency", "smooth"];
+const PRESENT_PRIORITY_LABELS: &[&str] = &["Lowest latency", "Smoothness"];
+const PRESENT_PRIORITY_CAPTIONS: &[&str] = &[
+    "Each frame shows the moment the display can take it",
+    "Buffers a little to even out network hiccups",
+];
+/// Smoothness buffer depth, in frames — the index IS the stored `smooth_buffer` value
+/// (0 = Automatic, which resolves to 2). No millisecond hints: the cost is one refresh
+/// per frame, and the session's refresh isn't known here when the mode is Native.
+const SMOOTH_BUFFER_LABELS: &[&str] = &["Automatic", "1 frame", "2 frames", "3 frames"];
+
 /// Physical-mouse model values (persisted) + labels + dynamic captions — same idiom as
 /// the touch rows. Ctrl+Alt+Shift+M flips the model live in-stream.
 const MOUSE_MODES: &[&str] = &["capture", "desktop"];
@@ -1213,6 +1256,50 @@ pub fn show_scoped(
         row
     });
 
+    // ---- Display: Presentation ----
+    // The intent pair the Apple and Android clients already carry. The buffer row only
+    // means anything under Smoothness, so it hides itself the rest of the time rather
+    // than sitting there inert.
+    let present_row = ChoiceRow::new(
+        &dialog,
+        inline,
+        "Prioritize",
+        PRESENT_PRIORITY_CAPTIONS[0],
+        PRESENT_PRIORITY_LABELS,
+    );
+    let buffer_row = ChoiceRow::new(
+        &dialog,
+        inline,
+        "Smoothness buffer",
+        "Each frame held absorbs one refresh of hiccup and adds one of delay",
+        SMOOTH_BUFFER_LABELS,
+    );
+    {
+        let w = present_row.widget().clone();
+        let buffer = buffer_row.widget().clone();
+        present_row.connect_changed(move |i| {
+            let i = (i as usize).min(PRESENT_PRIORITY_CAPTIONS.len() - 1);
+            set_row_subtitle(&w, PRESENT_PRIORITY_CAPTIONS[i]);
+            buffer.set_visible(PRESENT_PRIORITIES[i] == "smooth");
+        });
+    }
+    let vsync_row = adw::SwitchRow::builder()
+        .title("V-Sync")
+        .subtitle(
+            "Tear-free. Turning it off removes the wait for the screen's refresh — the \
+             lowest possible delay, at the cost of visible tearing. Not every driver \
+             offers it; the stats overlay names the mode actually in use",
+        )
+        .build();
+    let vrr_row = adw::SwitchRow::builder()
+        .title("Follow variable refresh rate")
+        .subtitle(
+            "On a VRR/FreeSync/G-Sync screen, let the panel refresh in step with the \
+             stream instead of on a fixed cadence. Applies to fullscreen sessions; \
+             harmless on a fixed-refresh screen",
+        )
+        .build();
+
     // ---- Display: Host output ----
     let compositor_row = ChoiceRow::new(
         &dialog,
@@ -1376,6 +1463,17 @@ pub fn show_scoped(
     // controller (single-player). The pin is persisted by stable key (`Settings::forward_pad`),
     // so it survives restarts — and disconnects: an offline pinned pad keeps its entry here
     // instead of silently snapping back to Automatic.
+    // Off = this device's controllers are not sent at all, because they reach the host
+    // another way (USB passthrough such as VirtualHere, or a pad plugged into the host).
+    // It also stops the session OPENING the pad, which is what frees the device for a
+    // passthrough tool to bind — so the two rows below have nothing to act on while it is
+    // off, and are desensitised to say so.
+    let pad_forward_row = adw::SwitchRow::builder()
+        .title("Forward controllers")
+        .subtitle(
+            "Send this device's controllers to the host — off if it already has them another way",
+        )
+        .build();
     let pads = gamepads.pads();
     let saved_pin = settings.borrow().forward_pad.clone();
     let mut pad_names = vec!["Automatic (all controllers)".to_string()];
@@ -1444,6 +1542,18 @@ pub fn show_scoped(
             "Steam Deck",
         ],
     );
+    // Both pad rows only mean something while something is being forwarded (the same
+    // relationship mic → echo cancellation draws just above, initial state included: the
+    // seed's `set_active` fires this only when it CHANGES the switch).
+    {
+        let (f, t) = (forward_row.widget().clone(), pad_row.widget().clone());
+        f.set_sensitive(seed.gamepad_forwarding);
+        t.set_sensitive(seed.gamepad_forwarding);
+        pad_forward_row.connect_active_notify(move |r| {
+            f.set_sensitive(r.is_active());
+            t.set_sensitive(r.is_active());
+        });
+    }
 
     // ---- Seed from the effective settings for this scope ----
     {
@@ -1454,6 +1564,7 @@ pub fn show_scoped(
         hz_row.set_selected(index::refresh(s));
         scale_row.set_selected(index::render_scale(s));
         bitrate_row.set_value(f64::from(s.bitrate_kbps) / 1000.0);
+        pad_forward_row.set_active(s.gamepad_forwarding);
         pad_row.set_selected(index::gamepad(s));
         let touch_i = index::touch(s);
         touch_row.set_selected(touch_i);
@@ -1479,6 +1590,19 @@ pub fn show_scoped(
         let codec_i = index::codec(s);
         codec_row.set_selected(codec_i);
         set_row_subtitle(codec_row.widget(), codec_caption(codec_i));
+        let present_i = index::present_priority(s);
+        present_row.set_selected(present_i);
+        set_row_subtitle(
+            present_row.widget(),
+            PRESENT_PRIORITY_CAPTIONS[present_i as usize],
+        );
+        buffer_row.set_selected(index::smooth_buffer(s));
+        // `set_selected` never fires the changed hook, so mirror its visibility rule here.
+        buffer_row
+            .widget()
+            .set_visible(PRESENT_PRIORITIES[present_i as usize] == "smooth");
+        vsync_row.set_active(s.vsync);
+        vrr_row.set_active(s.allow_vrr);
     }
 
     // ---- Override markers, per-row reset, and the touch that creates an override ----
@@ -1671,6 +1795,26 @@ pub fn show_scoped(
             index::surround
         );
         choice!(pad_row, "gamepad", o.gamepad.is_some(), index::gamepad);
+        toggle!(
+            pad_forward_row,
+            "gamepad_forwarding",
+            o.gamepad_forwarding.is_some(),
+            gamepad_forwarding
+        );
+        choice!(
+            present_row,
+            "present_priority",
+            o.present_priority.is_some(),
+            index::present_priority
+        );
+        choice!(
+            buffer_row,
+            "smooth_buffer",
+            o.smooth_buffer.is_some(),
+            index::smooth_buffer
+        );
+        toggle!(vsync_row, "vsync", o.vsync.is_some(), vsync);
+        toggle!(vrr_row, "allow_vrr", o.allow_vrr.is_some(), allow_vrr);
         toggle!(hdr_row, "hdr_enabled", o.hdr_enabled.is_some(), hdr_enabled);
         toggle!(chroma_row, "enable_444", o.enable_444.is_some(), enable_444);
         toggle!(
@@ -1775,6 +1919,11 @@ pub fn show_scoped(
     if let (Some(r), false) = (&gpu_row, profile_mode) {
         quality_group.add(r.widget());
     }
+    let presentation_group = group("Presentation", "");
+    presentation_group.add(present_row.widget());
+    presentation_group.add(buffer_row.widget());
+    presentation_group.add(&vsync_row);
+    presentation_group.add(&vrr_row);
     // The one form-level note (deliberately not repeated on every row).
     let output_group = group(
         "Host output",
@@ -1783,6 +1932,7 @@ pub fn show_scoped(
     output_group.add(compositor_row.widget());
     display.add(&resolution_group);
     display.add(&quality_group);
+    display.add(&presentation_group);
     display.add(&output_group);
 
     let input = page("Input", "input-keyboard-symbolic");
@@ -1843,6 +1993,10 @@ pub fn show_scoped(
             controllers_group.add(&row);
         }
     }
+    // Profileable, so it shows in both scopes — unlike the pin below it, which is about
+    // which of THIS device's pads goes first: a "Work" profile can decline to forward
+    // controllers to a host that a "Game" profile forwards them to.
+    controllers_group.add(&pad_forward_row);
     if !profile_mode {
         controllers_group.add(forward_row.widget());
     }
@@ -1915,6 +2069,7 @@ pub fn show_scoped(
             s.auto_wake = wake_row.is_active();
             s.inhibit_shortcuts = inhibit_row.is_active();
             s.invert_scroll = invert_row.is_active();
+            s.gamepad_forwarding = pad_forward_row.is_active();
             s.mic_enabled = mic_row.is_active();
             s.echo_cancel = echo_row.is_active();
             s.hdr_enabled = hdr_row.is_active();
@@ -1925,6 +2080,14 @@ pub fn show_scoped(
                 _ => 2,
             };
             s.codec = CODECS[(codec_row.selected() as usize).min(CODECS.len() - 1)].to_string();
+            s.present_priority = PRESENT_PRIORITIES
+                [(present_row.selected() as usize).min(PRESENT_PRIORITIES.len() - 1)]
+            .to_string();
+            // The index IS the value (0 = Automatic).
+            s.smooth_buffer =
+                (buffer_row.selected() as u8).min(SMOOTH_BUFFER_LABELS.len() as u8 - 1);
+            s.vsync = vsync_row.is_active();
+            s.allow_vrr = vrr_row.is_active();
             s.library_enabled = library_row.is_active();
         };
 

clients/session/src/console.rs

@@ -169,6 +169,11 @@ pub fn run(target: Option<&str>) -> u8 {
         mouse_mode: settings_at_start.mouse_mode(),
         invert_scroll: settings_at_start.invert_scroll,
         inhibit_shortcuts: settings_at_start.inhibit_shortcuts,
+        // Presentation-tier like the rows above: latched at console start, a per-host
+        // profile cannot move it in this mode (the documented P4 gap).
+        present_priority: settings_at_start.present_priority(),
+        vsync: settings_at_start.vsync,
+        allow_vrr: settings_at_start.allow_vrr,
         json_status,
         on_connected: Some(Box::new(move |fingerprint: [u8; 32]| {
             let fp_hex = trust::hex(&fingerprint);

clients/session/src/main.rs

@@ -188,6 +188,12 @@ mod session_main {
         if !settings.forward_pad.is_empty() {
             gamepad.set_pinned(Some(settings.forward_pad.clone()));
         }
+        // Whether to forward controllers AT ALL (off = the pad reaches the host by some other
+        // route — VirtualHere and friends). Set unconditionally, not only when off: browse mode
+        // reuses one service across launches, so a stream that follows one with it off must put
+        // it back. It goes on before the attach below, so a non-forwarding session never opens
+        // — never grabs — the device.
+        gamepad.set_forwarding(settings.gamepad_forwarding);
         let mode = Mode {
             width: if settings.width == 0 {
                 native.width
@@ -617,6 +623,9 @@ mod session_main {
             mouse_mode: settings.mouse_mode(),
             invert_scroll: settings.invert_scroll,
             inhibit_shortcuts: settings.inhibit_shortcuts,
+            present_priority: settings.present_priority(),
+            vsync: settings.vsync,
+            allow_vrr: settings.allow_vrr,
             json_status: true,
             on_connected: Some(Box::new(|fingerprint: [u8; 32]| {
                 // This host's card carries the accent bar in the desktop client now.

clients/windows/src/app/hosts.rs

@@ -623,8 +623,14 @@ pub(crate) fn hosts_page(props: &HostsProps, cx: &mut RenderCx) -> Element {
                 actions.push(
                     icon_btn("Settings", Symbol::Setting)
                         .on_click({
-                            let ss = set_screen.clone();
-                            move || ss.call(Screen::Settings)
+                            let (c, ss) = (ctx.clone(), set_screen.clone());
+                            move || {
+                                // Re-base the settings snapshot on the file before the page
+                                // renders — this process is not its only writer (see
+                                // settings::refresh_snapshot).
+                                super::settings::refresh_snapshot(&c);
+                                ss.call(Screen::Settings)
+                            }
                         })
                         .into(),
                 );

clients/windows/src/app/licenses.rs

@@ -2,7 +2,8 @@
 //! Settings).
 
 use super::style::*;
-use super::Screen;
+use super::{AppCtx, Screen};
+use std::sync::Arc;
 use windows_reactor::*;
 
 /// punktfunk's own license (MIT OR Apache-2.0).
@@ -15,10 +16,15 @@ const APP_LICENSE: &str = concat!(
 /// scripts/gen-third-party-notices.sh; the MSIX also ships this under licenses/).
 const THIRD_PARTY_NOTICES: &str = include_str!("../../../../THIRD-PARTY-NOTICES.txt");
 
-pub(crate) fn licenses_page(set_screen: &AsyncSetState<Screen>) -> Element {
+pub(crate) fn licenses_page(ctx: &Arc<AppCtx>, set_screen: &AsyncSetState<Screen>) -> Element {
     let back_btn = button("Back").accent().icon(Symbol::Back).on_click({
-        let ss = set_screen.clone();
-        move || ss.call(Screen::Settings)
+        let (c, ss) = (ctx.clone(), set_screen.clone());
+        move || {
+            // Back RE-ENTERS the settings page — re-base its snapshot on the file, same
+            // as the hosts page's Settings button (see settings::refresh_snapshot).
+            super::settings::refresh_snapshot(&c);
+            ss.call(Screen::Settings)
+        }
     });
 
     let app_card = card(

clients/windows/src/app/mod.rs

@@ -172,6 +172,10 @@ pub(crate) struct Shared {
 
 pub struct AppCtx {
     pub(crate) identity: (String, String),
+    /// The settings snapshot the UI renders from. Loaded once at startup, and RE-BASED on
+    /// the file when the settings page is (re)entered (`settings::refresh_snapshot`) and
+    /// inside every `commit` — this process is not the file's only writer (session resize,
+    /// console UI, Decky), so a plain process-lifetime snapshot goes stale on screen.
     pub(crate) settings: Mutex<Settings>,
     pub(crate) gamepad: GamepadService,
     pub(crate) shared: Arc<Shared>,
@@ -688,7 +692,7 @@ fn root(cx: &mut RenderCx, ctx: &Arc<AppCtx>) -> Element {
             &set_settings_rev,
             nav_progress,
         ),
-        Screen::Licenses => licenses::licenses_page(&set_screen),
+        Screen::Licenses => licenses::licenses_page(ctx, &set_screen),
         Screen::Help => help::help_page(&set_screen),
         Screen::Pair => component(pair::pair_page, svc),
         Screen::SpeedTest => component(speed::speed_page, SpeedProps { svc, state: speed }),

clients/windows/src/app/settings.rs

@@ -101,6 +101,19 @@ const MOUSE_MODES: &[(&str, &str)] = &[
     ("capture", "Capture (games)"),
     ("desktop", "Desktop (absolute)"),
 ];
+/// Presentation intent: `(stored value, display label)` — the `present_priority` key the
+/// Apple and Android clients share, so one profile means the same thing everywhere.
+const PRESENT_PRIORITIES: &[(&str, &str)] =
+    &[("latency", "Lowest latency"), ("smooth", "Smoothness")];
+/// Smoothness buffer depth in frames: `(stored value, display label)`. `0` = Automatic,
+/// which resolves to 2 (`PresentPriority::resolve`). No millisecond hints — the cost is
+/// one refresh per frame, and the refresh isn't known here when the mode is Native.
+const SMOOTH_BUFFERS: &[(u8, &str)] = &[
+    (0, "Automatic"),
+    (1, "1 frame"),
+    (2, "2 frames"),
+    (3, "3 frames"),
+];
 /// Host compositor presets: `(stored value, display label)`. Advisory — the host falls back to
 /// auto-detect when the choice is unavailable. Only meaningful against a Linux host.
 const COMPOSITORS: &[(&str, &str)] = &[
@@ -411,7 +424,16 @@ fn commit(
         return;
     }
     let mut catalog = ProfilesFile::load();
-    let base = ctx.settings.lock().unwrap().clone();
+    // The same rebase as the global arm above: `base` is what `absorb`'s before/after
+    // effective settings derive from, and the snapshot is not the file — another process
+    // (session resize, console UI, Decky) may have moved a global under us. The historical
+    // rebase fix ("settings saves stop reverting each other") covered the whole-file
+    // writers but missed this arm.
+    let base = {
+        let mut s = ctx.settings.lock().unwrap();
+        *s = Settings::load();
+        s.clone()
+    };
     let Some(p) = catalog.profiles.iter_mut().find(|p| p.id == scope) else {
         return; // deleted from under us; the next render falls back to the defaults scope
     };
@@ -425,6 +447,17 @@ fn commit(
     rev.1.call(rev.0 + 1);
 }
 
+/// Re-base the process-lifetime settings snapshot on the file — called from the navigation
+/// handlers that (re)enter this page, NOT per render pass. `ctx.settings` is loaded once at
+/// process start and this process is not the file's only writer (a spawned session persists
+/// its match-window size, the console UI and Decky save too — profiles.rs documents the
+/// family), so without this the page opens showing values another process already replaced,
+/// which then visibly "jump" the moment a row is touched and `commit`'s rebase pulls the
+/// file in. The field report this fixes: a codec setting that "changed by itself".
+pub(crate) fn refresh_snapshot(ctx: &Arc<AppCtx>) {
+    *ctx.settings.lock().unwrap() = Settings::load();
+}
+
 /// Which tier-P rows the profile in scope overrides. Plain bools rather than a lookup so the
 /// call sites read as `over.codec` — the row and its flag stay visibly paired.
 #[derive(Default)]
@@ -445,8 +478,13 @@ struct OverrideFlags {
     invert_scroll: bool,
     inhibit_shortcuts: bool,
     gamepad: bool,
+    gamepad_forwarding: bool,
     stats_verbosity: bool,
     fullscreen_on_stream: bool,
+    present_priority: bool,
+    smooth_buffer: bool,
+    vsync: bool,
+    allow_vrr: bool,
 }
 
 impl OverrideFlags {
@@ -473,8 +511,13 @@ impl OverrideFlags {
             invert_scroll: o.invert_scroll.is_some(),
             inhibit_shortcuts: o.inhibit_shortcuts.is_some(),
             gamepad: o.gamepad.is_some(),
+            gamepad_forwarding: o.gamepad_forwarding.is_some(),
             stats_verbosity: o.stats_verbosity.is_some(),
             fullscreen_on_stream: o.fullscreen_on_stream.is_some(),
+            present_priority: o.present_priority.is_some(),
+            smooth_buffer: o.smooth_buffer.is_some(),
+            vsync: o.vsync.is_some(),
+            allow_vrr: o.allow_vrr.is_some(),
         }
     }
 }
@@ -851,6 +894,32 @@ pub(crate) fn settings_page(
     let chroma_toggle = setting_toggle(ctx, scope, (rev, set_rev), s.enable_444, |s, on| {
         s.enable_444 = on
     });
+    // Presentation intent (design/desktop-presentation-rebuild.md). The buffer row is
+    // rendered only under Smoothness — `commit` bumps the revision, so flipping the
+    // intent re-renders the section and the row appears/disappears with it.
+    let (present_names, present_i) = presets(PRESENT_PRIORITIES, |v| *v == s.present_priority);
+    let present_combo = setting_combo(
+        ctx,
+        scope,
+        (rev, set_rev),
+        present_names,
+        present_i,
+        |s, i| s.present_priority = PRESENT_PRIORITIES[i].0.to_string(),
+    );
+    let smoothing = s.present_priority == "smooth";
+    let (buffer_names, buffer_i) = presets(SMOOTH_BUFFERS, |v| *v == s.smooth_buffer);
+    let buffer_combo = setting_combo(
+        ctx,
+        scope,
+        (rev, set_rev),
+        buffer_names,
+        buffer_i,
+        |s, i| s.smooth_buffer = SMOOTH_BUFFERS[i].0,
+    );
+    let vsync_toggle = setting_toggle(ctx, scope, (rev, set_rev), s.vsync, |s, on| s.vsync = on);
+    let vrr_toggle = setting_toggle(ctx, scope, (rev, set_rev), s.allow_vrr, |s, on| {
+        s.allow_vrr = on
+    });
 
     // --- Input -----------------------------------------------------------------------------
     // Controller forwarding: Automatic forwards EVERY real controller, each as its own pad;
@@ -898,6 +967,10 @@ pub(crate) fn settings_page(
                 s.save();
             })
     };
+    let pad_forward_toggle =
+        setting_toggle(ctx, scope, (rev, set_rev), s.gamepad_forwarding, |s, on| {
+            s.gamepad_forwarding = on
+        });
     let (pad_names, pad_i) = presets(GAMEPADS, |v| {
         GamepadPref::from_name(v) == GamepadPref::from_name(&s.gamepad)
     });
@@ -972,6 +1045,16 @@ pub(crate) fn settings_page(
         let ss = set_screen.clone();
         button("Third-party licenses").on_click(move || ss.call(Screen::Licenses))
     };
+    // The client log's home (%LOCALAPPDATA%\punktfunk\logs) — the file every "check the
+    // client log" message means, which until this row had no way in from the UI at all.
+    // The folder rather than the file so the rotated `.old` generation is in reach too.
+    // Best-effort, like the log itself: a missing dir or a failed spawn stays silent.
+    let logs_button = button("Open log folder").on_click(|| {
+        if let Some(dir) = crate::logfile::log_dir() {
+            let _ = std::fs::create_dir_all(&dir);
+            let _ = std::process::Command::new("explorer.exe").arg(&dir).spawn();
+        }
+    });
     let library_toggle = setting_toggle(ctx, scope, (rev, set_rev), s.library_enabled, |s, on| {
         s.library_enabled = on
     });
@@ -1065,8 +1148,9 @@ pub(crate) fn settings_page(
                         "HDR10, when the host has HDR content and this display supports it. \
                          HEVC only; otherwise the stream stays SDR.",
                     ),
-                    // Wording shared with the GTK client (its chroma_row) — same setting,
-                    // same constraints.
+                    // First sentence shared with the GTK client (its chroma_row); the
+                    // constraint sentence names the real gate (host: PyroWave || NVENC) —
+                    // "where the host can encode it" cost field users the discovery time.
                     described_overridable(
                         (rev, set_rev),
                         scope,
@@ -1075,7 +1159,8 @@ pub(crate) fn settings_page(
                         over.enable_444,
                         chroma_toggle,
                         "Full-colour video: crisp small text and thin lines, at more \
-                         bandwidth. HEVC only, and only where the host can encode it.",
+                         bandwidth. Requires an NVIDIA host (NVENC) or the PyroWave \
+                         codec \u{2014} other encoders stream 4:2:0.",
                     ),
                 ],
                 None,
@@ -1105,6 +1190,60 @@ pub(crate) fn settings_page(
                 },
                 None,
             ));
+            out.extend(group(
+                Some("Presentation"),
+                {
+                    let mut fields = vec![described_overridable(
+                        (rev, set_rev),
+                        scope,
+                        "present_priority",
+                        "Prioritize",
+                        over.present_priority,
+                        present_combo,
+                        "Lowest latency shows each frame the moment the display can take \
+                         it \u{2014} a network hiccup becomes an occasional repeated or \
+                         skipped frame. Smoothness buffers a little to even those out.",
+                    )];
+                    if smoothing {
+                        fields.push(described_overridable(
+                            (rev, set_rev),
+                            scope,
+                            "smooth_buffer",
+                            "Smoothness buffer",
+                            over.smooth_buffer,
+                            buffer_combo,
+                            "Frames held back before showing. Each one absorbs about a \
+                             refresh of network hiccup and adds a refresh of delay. \
+                             Automatic holds two.",
+                        ));
+                    }
+                    fields.push(described_overridable(
+                        (rev, set_rev),
+                        scope,
+                        "vsync",
+                        "V-Sync",
+                        over.vsync,
+                        vsync_toggle,
+                        "Tear-free. Turning it off removes the wait for the screen\u{2019}s \
+                         refresh \u{2014} the lowest possible delay, at the cost of visible \
+                         tearing. Not every driver offers it; the stats overlay names the \
+                         mode actually in use.",
+                    ));
+                    fields.push(described_overridable(
+                        (rev, set_rev),
+                        scope,
+                        "allow_vrr",
+                        "Follow variable refresh rate",
+                        over.allow_vrr,
+                        vrr_toggle,
+                        "On a VRR/FreeSync/G-Sync screen, let the panel refresh in step with \
+                         the stream instead of on a fixed cadence. Applies to fullscreen \
+                         sessions; harmless on a fixed-refresh screen.",
+                    ));
+                    fields
+                },
+                None,
+            ));
             out.extend(group(
                 Some("Host output"),
                 vec![described_overridable(
@@ -1223,6 +1362,23 @@ pub(crate) fn settings_page(
                             "Plug in or pair a controller and it appears here.",
                         )
                     }),
+                    // Whether ANY controller is forwarded — profileable, so it renders in
+                    // both scopes (a "Work" profile can decline what "Game" forwards),
+                    // unlike the device-fact picker below it.
+                    Some(described_overridable(
+                        (rev, set_rev),
+                        scope,
+                        "gamepad_forwarding",
+                        "Forward controllers",
+                        over.gamepad_forwarding,
+                        pad_forward_toggle,
+                        "Sends controllers connected to this PC to the host. Turn it off when \
+                         your controller already reaches the host another way \u{2014} USB \
+                         passthrough such as VirtualHere, or a pad plugged into the host \
+                         itself \u{2014} so games don't see two of them. Off, this PC never \
+                         opens the controller at all, which is what leaves it free for a \
+                         passthrough tool to claim.",
+                    )),
                     // NOT Apple's wording: Apple forwards ONE pad as player 1, this client
                     // forwards every controller as its own player. Same picker, different rule.
                     // Which physical pad this device forwards is a device fact (tier G), so it
@@ -1325,7 +1481,16 @@ pub(crate) fn settings_page(
             "About",
             group(
                 None,
-                vec![about_identity.into(), licenses_button.into()],
+                vec![
+                    about_identity.into(),
+                    described_labeled(
+                        "Diagnostics",
+                        logs_button,
+                        "The client log (client.log, plus the session\u{2019}s whole \
+                         receive/decode/present trail) \u{2014} attach it to a bug report.",
+                    ),
+                    licenses_button.into(),
+                ],
                 None,
             ),
         ),
@@ -1727,5 +1892,26 @@ mod tests {
         let f3 = OverrideFlags::of(Some(&p3));
         assert!(f3.echo_cancel);
         assert!(!f3.mic_enabled);
+
+        // The presentation pair, likewise independent: pinning the intent doesn't claim
+        // the buffer (a "Smoothness, whatever the global buffer is" profile is valid).
+        let mut p4 = StreamProfile::new("t4".to_string());
+        p4.overrides = SettingsOverlay {
+            present_priority: Some("smooth".into()),
+            ..Default::default()
+        };
+        let f4 = OverrideFlags::of(Some(&p4));
+        assert!(f4.present_priority);
+        assert!(!f4.smooth_buffer);
+
+        // V-Sync and VRR are independent of each other and of the intent pair.
+        let mut p5 = StreamProfile::new("t5".to_string());
+        p5.overrides = SettingsOverlay {
+            vsync: Some(false),
+            ..Default::default()
+        };
+        let f5 = OverrideFlags::of(Some(&p5));
+        assert!(f5.vsync);
+        assert!(!f5.allow_vrr && !f5.present_priority);
     }
 }

clients/windows/src/logfile.rs

@@ -21,11 +21,12 @@ const ROTATE_BYTES: u64 = 10 * 1024 * 1024;
 
 static SINK: OnceLock<Option<Arc<Mutex<File>>>> = OnceLock::new();
 
-fn log_dir() -> Option<PathBuf> {
+/// The log directory — Settings ▸ About's "Open log folder" opens it in Explorer.
+pub(crate) fn log_dir() -> Option<PathBuf> {
     Some(PathBuf::from(std::env::var_os("LOCALAPPDATA")?).join(r"punktfunk\logs"))
 }
 
-/// The log file's path, for the "logs land here" startup line (and any future UI affordance).
+/// The log file's path, for the "logs land here" startup line and the failed-spawn banner.
 pub(crate) fn path() -> Option<PathBuf> {
     Some(log_dir()?.join("client.log"))
 }

clients/windows/src/spawn.rs

@@ -105,7 +105,14 @@ fn parse_line(line: &str) -> Option<ChildLine> {
 /// connect that silently drops back to the host list.
 pub(crate) fn silent_exit_banner(code: i32) -> Option<String> {
     (code != 0 && code != -1).then(|| {
-        format!("The session didn't start (punktfunk-session exited with code {code}). Check the client log.")
+        // Name the log's actual location — "check the client log" without a path is a
+        // scavenger hunt (Settings ▸ About's "Open log folder" reaches it too).
+        let log = crate::logfile::path()
+            .map(|p| p.display().to_string())
+            .unwrap_or_else(|| "the client log".into());
+        format!(
+            "The session didn't start (punktfunk-session exited with code {code}). Check {log}."
+        )
     })
 }
 

crates/pf-capture/src/lib.rs

@@ -612,7 +612,10 @@ pub fn open_portal_monitor(
 /// 10-bit PQ/BT.2020 formats instead of the SDR set — pass it only when the output was actually
 /// brought up HDR (a gamescope spawned with `--hdr-enabled` off our `pipewire-hdr` build); the
 /// host resolves that in `capture::capturer_supports_hdr_for` **before** the Welcome, because a
-/// session that negotiated PQ cannot fall back to SDR afterwards.
+/// session that negotiated PQ cannot fall back to SDR afterwards. `cursor_id0_hides` declares the
+/// producer's cursor-meta contract — pass it for outputs whose compositor rewrites
+/// `SPA_META_Cursor` on every buffer (KWin), where an `id == 0` meta is an authoritative
+/// "pointer hidden" the composited/forwarded cursor must honor.
 #[cfg(target_os = "linux")]
 #[allow(clippy::too_many_arguments)]
 pub fn open_virtual_output(
@@ -625,6 +628,7 @@ pub fn open_virtual_output(
     want_hdr: bool,
     policy: ZeroCopyPolicy,
     expect_exact_dims: bool,
+    cursor_id0_hides: bool,
 ) -> Result<Box<dyn Capturer>> {
     linux::PortalCapturer::from_virtual_output(
         remote_fd,
@@ -636,6 +640,7 @@ pub fn open_virtual_output(
         want_hdr && !hdr_capture_failed(HdrSource::VirtualOutput),
         policy,
         expect_exact_dims,
+        cursor_id0_hides,
     )
     .map(|c| Box::new(c) as Box<dyn Capturer>)
 }

crates/pf-capture/src/linux/mod.rs

@@ -72,6 +72,11 @@ struct CaptureOpts {
     /// the doomed birth mode. `false` everywhere else (Mutter SIZES the monitor from negotiation and
     /// gamescope fixates its own — gating those would starve legitimate first frames).
     expect_exact_dims: bool,
+    /// The producer rewrites `SPA_META_Cursor` on EVERY buffer, so an `id == 0` meta is an
+    /// authoritative "pointer hidden / off this output" the blend must honor (KWin). `false` for
+    /// the stale-meta producers (Mutter recycles buffers without rewriting the region) — see
+    /// [`pw_cursor::CursorState::id0_hides`](pw_cursor) for the full contract.
+    cursor_id0_hides: bool,
 }
 
 /// The shared state the PipeWire thread PUBLISHES and the capturer READS — one struct instead of
@@ -301,6 +306,10 @@ impl PortalCapturer {
                 want_444: false,
                 want_hdr,
                 expect_exact_dims: false,
+                // The portal-monitor path today is Mutter (the GNOME HDR mirror) — the stale-meta
+                // id-0 contract. A KDE portal capture would rewrite per buffer, but nothing routes
+                // one through here yet; the virtual-output path below carries the real flag.
+                cursor_id0_hides: false,
             },
             policy,
         )?
@@ -316,7 +325,8 @@ impl PortalCapturer {
     /// the GPU zero-copy path subject to `PUNKTFUNK_ZEROCOPY`. `want_444` (a 4:4:4 session) makes the
     /// zero-copy worker convert tiled dmabufs to planar YUV444 on the GPU instead of NV12/RGB.
     /// `want_hdr` runs the 10-bit PQ/BT.2020 offer instead of the SDR set — see
-    /// [`crate::open_virtual_output`] for who is allowed to pass it.
+    /// [`crate::open_virtual_output`] for who is allowed to pass it. `cursor_id0_hides` declares
+    /// the producer's cursor-meta contract ([`CaptureOpts::cursor_id0_hides`]).
     #[allow(clippy::too_many_arguments)]
     pub fn from_virtual_output(
         remote_fd: Option<OwnedFd>,
@@ -328,6 +338,7 @@ impl PortalCapturer {
         want_hdr: bool,
         policy: ZeroCopyPolicy,
         expect_exact_dims: bool,
+        cursor_id0_hides: bool,
     ) -> Result<PortalCapturer> {
         tracing::info!(
             node_id,
@@ -335,6 +346,7 @@ impl PortalCapturer {
             want_444,
             want_hdr,
             expect_exact_dims,
+            cursor_id0_hides,
             "connecting PipeWire to virtual output"
         );
         // Most virtual outputs are SDR-only upstream (Mutter's RecordVirtual streams advertise
@@ -350,6 +362,7 @@ impl PortalCapturer {
                 want_444,
                 want_hdr,
                 expect_exact_dims,
+                cursor_id0_hides,
             },
             policy,
         )?

crates/pf-capture/src/linux/pipewire.rs

@@ -811,6 +811,7 @@ pub fn pipewire_thread(
         want_444,
         want_hdr,
         expect_exact_dims,
+        cursor_id0_hides,
         ..
     } = opts;
     crate::pwinit::ensure_init();
@@ -985,7 +986,7 @@ pub fn pipewire_thread(
         yuv444: want_444,
         linear_nv12_failed: false,
         dbg_log_n: 0,
-        cursor: CursorState::default(),
+        cursor: CursorState::new(cursor_id0_hides),
         expect_dims: if expect_exact_dims {
             preferred.map(|(w, h, _)| (w, h))
         } else {

crates/pf-capture/src/linux/pw_cursor.rs

@@ -39,9 +39,23 @@ pub(super) struct CursorState {
     /// negotiated). Per-stream deliberately — a host serves many sessions per process, and a
     /// process-wide latch made the second session's triage read as "no meta".
     seen_meta: bool,
+    /// This stream's producer rewrites the cursor meta on EVERY buffer, so an `id == 0` meta is
+    /// an authoritative "pointer hidden / off this output" rather than a stale recycled region.
+    /// True for KWin virtual outputs; false for the stale-meta producers (Mutter) — see
+    /// [`note_cursor_id`].
+    id0_hides: bool,
 }
 
 impl CursorState {
+    /// The per-stream state, declaring which `id == 0` contract the producer follows
+    /// ([`Self::id0_hides`]).
+    pub(super) fn new(id0_hides: bool) -> CursorState {
+        CursorState {
+            id0_hides,
+            ..CursorState::default()
+        }
+    }
+
     /// A shareable overlay for the encode/forward paths, or `None` before the first bitmap
     /// arrived. A HIDDEN pointer still yields `Some` (with `visible: false`): the
     /// cursor-forward channel needs "known but hidden" — an app grabbed the pointer, the
@@ -79,6 +93,31 @@ pub(super) fn decode_bitmap_pixel(vfmt: u32, s: &[u8]) -> (u8, u8, u8, u8) {
     }
 }
 
+/// Apply one parsed `spa_meta_cursor.id` to the visibility state; returns whether the rest of the
+/// meta region (position, bitmap) is worth parsing.
+///
+/// Two producer contracts meet on `id == 0`. **KWin** rewrites the cursor meta on EVERY enqueued
+/// buffer, and writes id 0 whenever `Cursor::isOnOutput` says the pointer is not in this stream —
+/// which covers a globally hidden cursor AND a client null-cursor surface (empty cursor geometry
+/// intersects nothing). There id 0 is the authoritative hide, and honoring it is what lets a game
+/// or Big Picture hide the pointer mid-stream ([`CursorState::id0_hides`], set for KWin virtual
+/// outputs; without it the composited arrow outlived every hide — the 0.22.0 field report).
+/// **Mutter** only rewrites a buffer's meta region when the cursor changed, so recycled buffers
+/// between damage frames carry a stale id-0 meta — treating that as hidden flickered the cursor
+/// off between hovers (on-glass round 5). There the last-known state holds, and a pointer that
+/// really left/hid simply stops producing updates (the M3 hidden hint has no Mutter signal —
+/// Windows has its own CURSOR_SUPPRESSED source).
+fn note_cursor_id(cursor: &mut CursorState, id: u32) -> bool {
+    if id == 0 {
+        if cursor.id0_hides {
+            cursor.visible = false;
+        }
+        return false;
+    }
+    cursor.visible = true;
+    true
+}
+
 /// Update `cursor` from the newest buffer's `SPA_META_Cursor` (no-op when the buffer carries no
 /// cursor meta — producer doesn't support it, or the portal isn't in Metadata cursor mode).
 /// Called for EVERY dequeued buffer, before the stale-frame skip, so pointer-only movements
@@ -121,16 +160,9 @@ pub(super) fn update_cursor_meta(cursor: &mut CursorState, spa_buf: *mut spa::sy
             (*cur).bitmap_offset,
         )
     };
-    if id == 0 {
-        // SPA contract: id 0 = "no cursor information", NOT "cursor hidden". Mutter only
-        // REWRITES a buffer's meta region when the cursor changed, so recycled buffers
-        // between damage frames carry a stale id-0 meta — treating that as hidden flickered
-        // the cursor off between hovers (on-glass round 5). Keep the last-known state; a
-        // pointer that really left/hid simply stops producing updates. (The M3 hidden hint
-        // loses its Mutter signal — Windows has its own CURSOR_SUPPRESSED source.)
+    if !note_cursor_id(cursor, id) {
         return;
     }
-    cursor.visible = true;
     cursor.x = pos_x - hot_x;
     cursor.y = pos_y - hot_y;
     cursor.hot_x = hot_x;
@@ -367,9 +399,44 @@ mod tests {
             hot_x: 0,
             hot_y: 0,
             seen_meta: true,
+            id0_hides: false,
         }
     }
 
+    // ---- note_cursor_id: the two producer id-0 contracts --------------------------------------
+
+    #[test]
+    fn id_zero_hides_only_on_a_rewriting_producer() {
+        // KWin contract (`id0_hides`): id 0 is written fresh on every buffer, so it IS the hide —
+        // a game or Big Picture hiding the pointer must reach the stream.
+        let mut kwin = cursor(10, 10, 8, 8, (255, 255, 255), 255);
+        kwin.id0_hides = true;
+        assert!(!note_cursor_id(&mut kwin, 0), "id 0 parses no further");
+        let o = kwin.overlay().expect("bitmap stays cached across a hide");
+        assert!(!o.visible, "KWin id 0 must hide the overlay");
+        // The pointer coming back re-shows the SAME cached bitmap.
+        assert!(note_cursor_id(&mut kwin, 1));
+        assert!(kwin.overlay().expect("still cached").visible);
+
+        // Mutter contract: recycled buffers carry stale id-0 metas — the last-known state holds
+        // (honoring them flickered the cursor off between hovers, on-glass round 5).
+        let mut mutter = cursor(10, 10, 8, 8, (255, 255, 255), 255);
+        assert!(!note_cursor_id(&mut mutter, 0));
+        assert!(
+            mutter.overlay().expect("cached").visible,
+            "a stale-meta producer's id 0 must NOT hide"
+        );
+    }
+
+    #[test]
+    fn id_zero_before_any_bitmap_yields_no_overlay() {
+        // A KWin stream whose pointer was never on the output: hides arrive before any bitmap —
+        // `overlay()` must stay `None` (nothing to blend), not a phantom empty cursor.
+        let mut c = CursorState::new(true);
+        assert!(!note_cursor_id(&mut c, 0));
+        assert!(c.overlay().is_none());
+    }
+
     // ---- bitmap_extent: the guard whose absence SIGSEGVs uncatchably -------------------------
 
     #[test]

crates/pf-client-core/src/gamepad.rs

@@ -336,6 +336,7 @@ enum Ctl {
     Detach,
     Pin(Option<String>),
     KindOverride(GamepadPref),
+    Forwarding(bool),
     MenuMode(bool),
     MenuRumble(MenuPulse),
 }
@@ -482,6 +483,26 @@ impl GamepadService {
         let _ = self.ctl.send(Ctl::KindOverride(pref));
     }
 
+    /// Forward this device's controllers to the host at all ([`Settings::gamepad_forwarding`],
+    /// default on). Off is for a couch whose pad reaches the host another way — a USB
+    /// passthrough tool like VirtualHere, or a controller plugged into the host itself —
+    /// where forwarding as well would give the host two pads for one pair of hands.
+    ///
+    /// Off holds no slot open, so nothing is sent AND nothing is *grabbed*: no arrival, no
+    /// virtual pad host-side, and the hidraw node stays free for the passthrough tool to
+    /// bind (SDL's HIDAPI drivers take it at open — a held device cannot be bound away).
+    /// It follows that the escape chord, which only listens on forwarded pads, is not
+    /// available while off; the keyboard chord and the client's own UI still end a session.
+    ///
+    /// Menu navigation is untouched: the launcher still opens the active pad to drive its
+    /// UI, and a session — which supersedes menu mode whether it forwards or not — releases
+    /// it again, so the pad is free for the whole time a stream is up.
+    ///
+    /// [`Settings::gamepad_forwarding`]: crate::trust::Settings::gamepad_forwarding
+    pub fn set_forwarding(&self, on: bool) {
+        let _ = self.ctl.send(Ctl::Forwarding(on));
+    }
+
     pub fn attach(&self, connector: Arc<NativeClient>) {
         let _ = self.ctl.send(Ctl::Attach(connector));
     }
@@ -721,6 +742,10 @@ struct Worker {
     /// connected pads, so it survives restarts and disconnects. A pin forwards ONLY that pad
     /// (an explicit single-player choice); Automatic forwards every real controller.
     pinned: Option<String>,
+    /// Forward controllers to an attached session at all ([`GamepadService::set_forwarding`]).
+    /// Off makes [`Self::forwarded_ids`] empty, so a session opens no slot — the whole point
+    /// being that the hardware stays ungrabbed for a USB passthrough tool.
+    forwarding: bool,
     /// The user's explicit "controller type" setting ([`GamepadService::set_kind_override`]);
     /// `Auto` = per-pad detection. Applied at slot open to the kind DECLARED to the host, never
     /// to [`Slot::pref`] — the local feedback paths must keep reading the physical pad.
@@ -815,6 +840,11 @@ impl Worker {
     /// back to the single most-recent pad when only a Steam-virtual pad is present (the Deck
     /// game-mode case — otherwise its gyro/paddles/input would have nowhere to land).
     fn forwarded_ids(&self) -> Vec<u32> {
+        // Forwarding off: nothing is forwarded, so nothing is opened either — the device stays
+        // free for whatever route the user's controller actually takes to the host.
+        if !self.forwarding {
+            return Vec::new();
+        }
         if let Some(key) = &self.pinned {
             if let Some(id) = self
                 .order
@@ -1243,10 +1273,16 @@ impl Worker {
                 Ok(Ctl::Attach(c)) => {
                     self.attached = Some(c);
                     self.reset_chord(); // every session starts un-latched (Attach doesn't flush)
-                                        // The Valve HIDAPI drivers run only in-session (see set_valve_hidapi);
-                                        // enabling them re-enumerates a Deck's built-in pad with paddles/
-                                        // trackpads/gyro first-class — sync_open opens a slot per forwarded pad.
-                    set_valve_hidapi(true);
+
+                    // The Valve HIDAPI drivers run only in-session (see set_valve_hidapi);
+                    // enabling them re-enumerates a Deck's built-in pad with paddles/
+                    // trackpads/gyro first-class — sync_open opens a slot per forwarded pad.
+                    // Not with forwarding off: this session opens no slot, and the drivers'
+                    // mere enumeration both kills the Deck's trackpad-mouse and is the
+                    // opposite of leaving the hardware alone for a passthrough tool.
+                    if self.forwarding {
+                        set_valve_hidapi(true);
+                    }
                     self.sync_open();
                 }
                 Ok(Ctl::Detach) => {
@@ -1269,6 +1305,31 @@ impl Worker {
                     self.refresh_active();
                 }
                 Ok(Ctl::KindOverride(pref)) => self.kind_override = pref,
+                Ok(Ctl::Forwarding(on)) => {
+                    if self.forwarding == on {
+                        continue;
+                    }
+                    self.forwarding = on;
+                    self.reset_chord(); // no forwarded pad can be mid-chord across the flip
+
+                    // Applied live rather than at attach only, so a mid-session flip (an
+                    // in-stream settings screen) takes effect on the pad in your hands.
+                    //
+                    // The Valve HIDAPI drivers are an in-session-only thing (see
+                    // set_valve_hidapi), and forwarding off is — for their purpose — not in
+                    // session. Order matters and differs by direction: ON must enable them
+                    // BEFORE `sync_open`, or a Deck's built-in pad opens under its old
+                    // identity; OFF must disable them AFTER, so no slot outlives the driver
+                    // that opened it.
+                    let attached = self.attached.is_some();
+                    if on && attached {
+                        set_valve_hidapi(true);
+                    }
+                    self.sync_open();
+                    if !on && attached {
+                        set_valve_hidapi(false);
+                    }
+                }
                 Ok(Ctl::MenuMode(on)) => {
                     self.menu_mode = on;
                     if on {
@@ -1608,6 +1669,7 @@ impl Worker {
             menu_open: None,
             order: Vec::new(),
             pinned: None,
+            forwarding: true,
             kind_override: GamepadPref::Auto,
             attached: None,
             escape_tx,

crates/pf-client-core/src/orchestrate.rs

@@ -982,6 +982,10 @@ mod tests {
                 height: 1440,
                 bitrate_kbps: 55000,
                 codec: "av1".into(),
+                present_priority: "smooth".into(),
+                smooth_buffer: 2,
+                vsync: false,
+                allow_vrr: false,
                 ..Default::default()
             },
             clipboard: true,

crates/pf-client-core/src/profiles.rs

@@ -74,9 +74,23 @@ pub struct SettingsOverlay {
     #[serde(skip_serializing_if = "Option::is_none")]
     pub gamepad: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
+    pub gamepad_forwarding: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
     pub stats_verbosity: Option<StatsVerbosity>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub fullscreen_on_stream: Option<bool>,
+    /// The presentation cluster — the keys the Apple client already writes into this
+    /// same catalog shape (`present_priority`/`smooth_buffer`/`vsync`/`allow_vrr`;
+    /// Android carries the first two). First-class here so a profile authored on any
+    /// client applies on all of them instead of riding `extra` unapplied.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub present_priority: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub smooth_buffer: Option<u8>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub vsync: Option<bool>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub allow_vrr: Option<bool>,
     /// Overlay keys a newer client wrote and this one doesn't model — carried through a
     /// load→save round-trip untouched.
     #[serde(flatten)]
@@ -142,6 +156,9 @@ impl SettingsOverlay {
         if let Some(v) = &self.gamepad {
             s.gamepad = v.clone();
         }
+        if let Some(v) = self.gamepad_forwarding {
+            s.gamepad_forwarding = v;
+        }
         if let Some(v) = self.stats_verbosity {
             // Through the setter so the legacy `show_stats` bool stays coherent for
             // pre-tier binaries reading the same settings file.
@@ -150,6 +167,18 @@ impl SettingsOverlay {
         if let Some(v) = self.fullscreen_on_stream {
             s.fullscreen_on_stream = v;
         }
+        if let Some(v) = &self.present_priority {
+            s.present_priority = v.clone();
+        }
+        if let Some(v) = self.smooth_buffer {
+            s.smooth_buffer = v;
+        }
+        if let Some(v) = self.vsync {
+            s.vsync = v;
+        }
+        if let Some(v) = self.allow_vrr {
+            s.allow_vrr = v;
+        }
         s
     }
 
@@ -220,12 +249,27 @@ impl SettingsOverlay {
         if after.gamepad != before.gamepad {
             self.gamepad = Some(after.gamepad.clone());
         }
+        if after.gamepad_forwarding != before.gamepad_forwarding {
+            self.gamepad_forwarding = Some(after.gamepad_forwarding);
+        }
         if after.stats_verbosity() != before.stats_verbosity() {
             self.stats_verbosity = Some(after.stats_verbosity());
         }
         if after.fullscreen_on_stream != before.fullscreen_on_stream {
             self.fullscreen_on_stream = Some(after.fullscreen_on_stream);
         }
+        if after.present_priority != before.present_priority {
+            self.present_priority = Some(after.present_priority.clone());
+        }
+        if after.smooth_buffer != before.smooth_buffer {
+            self.smooth_buffer = Some(after.smooth_buffer);
+        }
+        if after.vsync != before.vsync {
+            self.vsync = Some(after.vsync);
+        }
+        if after.allow_vrr != before.allow_vrr {
+            self.allow_vrr = Some(after.allow_vrr);
+        }
     }
 
     /// Drop one override by its overlay field name, putting the row back to inheriting. The
@@ -257,8 +301,13 @@ impl SettingsOverlay {
             "invert_scroll" => self.invert_scroll = None,
             "inhibit_shortcuts" => self.inhibit_shortcuts = None,
             "gamepad" => self.gamepad = None,
+            "gamepad_forwarding" => self.gamepad_forwarding = None,
             "stats_verbosity" => self.stats_verbosity = None,
             "fullscreen_on_stream" => self.fullscreen_on_stream = None,
+            "present_priority" => self.present_priority = None,
+            "smooth_buffer" => self.smooth_buffer = None,
+            "vsync" => self.vsync = None,
+            "allow_vrr" => self.allow_vrr = None,
             _ => return false,
         }
         true
@@ -433,6 +482,10 @@ mod tests {
         assert_eq!((out.width, out.height), (1920, 1080));
         assert_eq!(out.bitrate_kbps, 20000);
         assert_eq!(out.codec, "hevc");
+        assert!(
+            out.gamepad_forwarding,
+            "default on, and an empty overlay leaves it alone"
+        );
         assert!(empty.is_empty());
 
         let overlay = SettingsOverlay {
@@ -452,9 +505,14 @@ mod tests {
             invert_scroll: Some(true),
             inhibit_shortcuts: Some(false),
             gamepad: Some("dualsense".into()),
+            gamepad_forwarding: Some(false),
             match_window: Some(true),
             fullscreen_on_stream: Some(false),
             stats_verbosity: Some(StatsVerbosity::Detailed),
+            present_priority: Some("smooth".into()),
+            smooth_buffer: Some(3),
+            vsync: Some(false),
+            allow_vrr: Some(false),
             ..Default::default()
         };
         assert!(!overlay.is_empty());
@@ -473,9 +531,14 @@ mod tests {
         assert!(out.invert_scroll);
         assert!(!out.inhibit_shortcuts);
         assert_eq!(out.gamepad, "dualsense");
+        assert!(!out.gamepad_forwarding);
         assert!(out.match_window);
         assert!(!out.fullscreen_on_stream);
         assert_eq!(out.stats_verbosity(), StatsVerbosity::Detailed);
+        assert_eq!(out.present_priority, "smooth");
+        assert_eq!(out.smooth_buffer, 3);
+        assert!(!out.vsync);
+        assert!(!out.allow_vrr);
         // The tier goes through the setter, so the legacy bool a pre-tier binary reads
         // stays coherent with it.
         assert!(out.show_stats);
@@ -573,6 +636,59 @@ mod tests {
         assert!(o.is_empty());
     }
 
+    /// The presentation cluster is first-class, not `extra` passengers: it applies,
+    /// absorbs, clears, and serialises under the exact keys the Apple client already
+    /// writes (`present_priority`/`smooth_buffer`/`vsync`/`allow_vrr`) — one catalog
+    /// has to round-trip through every platform, and a mismatched key would be carried
+    /// but never applied.
+    #[test]
+    fn presentation_cluster_is_first_class() {
+        let base = Settings::default();
+        let mut o = SettingsOverlay::default();
+        let before = o.apply(&base);
+        let mut after = before.clone();
+        after.present_priority = "smooth".into();
+        o.absorb(&before, &after);
+        let before = o.apply(&base);
+        let mut after = before.clone();
+        after.smooth_buffer = 1;
+        o.absorb(&before, &after);
+        assert_eq!(o.present_priority.as_deref(), Some("smooth"));
+        assert_eq!(o.smooth_buffer, Some(1));
+        assert!(
+            o.extra.is_empty(),
+            "modelled fields must never land in the passthrough"
+        );
+        let out = o.apply(&base);
+        assert_eq!(
+            out.present_priority(),
+            crate::trust::PresentPriority::Smooth { buffer: 1 }
+        );
+
+        // Serialised under the shared keys, and read back from a foreign client's file.
+        let text = serde_json::to_string(&o).unwrap();
+        assert!(text.contains("\"present_priority\":\"smooth\""), "{text}");
+        assert!(text.contains("\"smooth_buffer\":1"), "{text}");
+        let from_apple: SettingsOverlay = serde_json::from_str(
+            r#"{"present_priority":"latency","smooth_buffer":2,"vsync":true,"allow_vrr":false}"#,
+        )
+        .unwrap();
+        assert_eq!(from_apple.present_priority.as_deref(), Some("latency"));
+        assert_eq!(from_apple.smooth_buffer, Some(2));
+        assert_eq!(from_apple.vsync, Some(true));
+        assert_eq!(from_apple.allow_vrr, Some(false));
+        assert!(from_apple.extra.is_empty());
+
+        assert!(o.clear("present_priority"));
+        assert!(o.clear("smooth_buffer"));
+        assert_eq!(o.present_priority, None);
+        assert!(o.is_empty());
+        let mut vrr = from_apple;
+        assert!(vrr.clear("vsync"));
+        assert!(vrr.clear("allow_vrr"));
+        assert_eq!((vrr.vsync, vrr.allow_vrr), (None, None));
+    }
+
     /// `clear` is the explicit way back to inheriting, including the resolution tri-state.
     #[test]
     fn clear_drops_one_override() {
@@ -591,6 +707,29 @@ mod tests {
         assert!(!o.clear("no_such_field"));
     }
 
+    /// Controller forwarding defaults ON, so its interesting override is the FALSE one — and a
+    /// `false` that `apply` dropped would silently forward a pad the profile said not to.
+    /// `absorb` must record it, `clear` must undo it, and the serialized name both carry is the
+    /// one every client's reset button sends.
+    #[test]
+    fn gamepad_forwarding_overrides_off_and_resets_back() {
+        let base = Settings::default();
+        assert!(base.gamepad_forwarding, "the shipped default");
+
+        let mut o = SettingsOverlay::default();
+        let mut after = base.clone();
+        after.gamepad_forwarding = false;
+        o.absorb(&base, &after);
+        assert_eq!(o.gamepad_forwarding, Some(false));
+        assert!(!o.apply(&base).gamepad_forwarding);
+
+        assert!(o.clear("gamepad_forwarding"));
+        assert_eq!(o.gamepad_forwarding, None);
+        assert!(o.is_empty());
+        // Back to inheriting: the global's live value, not a remembered false.
+        assert!(o.apply(&base).gamepad_forwarding);
+    }
+
     /// Stats verbosity Off must survive `apply` — it is a legitimate override, and going
     /// through `set_stats_verbosity` keeps `show_stats` in sync in that direction too.
     #[test]

crates/pf-client-core/src/trust.rs

@@ -14,6 +14,7 @@ use anyhow::{anyhow, Context, Result};
 use punktfunk_core::client::NativeClient;
 use punktfunk_core::quic::endpoint;
 use serde::{Deserialize, Serialize};
+use std::collections::BTreeMap;
 use std::path::{Path, PathBuf};
 
 pub fn config_dir() -> Result<PathBuf> {
@@ -787,6 +788,45 @@ impl MouseMode {
     }
 }
 
+/// Presentation intent — what the presenter optimizes for
+/// (design/desktop-presentation-rebuild.md; the Apple/Android clients' shared
+/// `present_priority`/`smooth_buffer` pair). Stored stringly in
+/// [`Settings::present_priority`] + [`Settings::smooth_buffer`]; resolved with
+/// [`PresentPriority::resolve`], whose rules match the Android reference
+/// (`decode/presenter.rs`): anything but an explicit `"smooth"` is latency, and a
+/// smooth buffer outside 1..=3 (including 0 = Automatic) becomes 2.
+#[derive(Clone, Copy, PartialEq, Eq, Debug)]
+pub enum PresentPriority {
+    /// Every frame presents the moment the display can take it; a network hiccup is an
+    /// occasional repeated or skipped frame. The default.
+    Latency,
+    /// A small frame buffer (1–3 frames) evens out network/decode jitter, at the
+    /// buffer's worth of added display latency.
+    Smooth { buffer: u8 },
+}
+
+impl PresentPriority {
+    /// The shared cross-client resolution rule — pure, so every embedder agrees on what
+    /// a foreign profile's values mean.
+    pub fn resolve(name: &str, buffer: u8) -> PresentPriority {
+        if name == "smooth" {
+            PresentPriority::Smooth {
+                buffer: if (1..=3).contains(&buffer) { buffer } else { 2 },
+            }
+        } else {
+            PresentPriority::Latency
+        }
+    }
+
+    /// Frames the smoothing store holds; `0` = newest-wins (the latency intent).
+    pub fn fifo_capacity(self) -> u8 {
+        match self {
+            PresentPriority::Latency => 0,
+            PresentPriority::Smooth { buffer } => buffer,
+        }
+    }
+}
+
 /// App settings, persisted as JSON. Stringly-typed gamepad/compositor prefs so the file
 /// stays readable; parsed with `*Pref::from_name` at connect time.
 #[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
@@ -808,6 +848,21 @@ pub struct Settings {
     /// container `#[serde(default)]`.
     pub render_scale: f64,
     pub gamepad: String,
+    /// Forward this device's controllers to the host at all. Default ON — that was the
+    /// unconditional behaviour before this became a setting.
+    ///
+    /// Off is for the couch whose controller reaches the host by some *other* route: a USB
+    /// passthrough tool (VirtualHere and friends), or a pad simply plugged into the host
+    /// itself. Leaving forwarding on there gives the host two controllers for one pair of
+    /// hands, and games read both.
+    ///
+    /// It is deliberately stronger than "send no input": with it off the client never
+    /// *opens* the controller, and opening is what grabs the hardware (SDL's HIDAPI drivers
+    /// take the hidraw node) — a held device is one a passthrough tool cannot bind. Menu
+    /// navigation in the launcher still opens the active pad, and the session releases it;
+    /// see [`crate::gamepad::GamepadService::set_forwarding`].
+    #[serde(default = "default_true")]
+    pub gamepad_forwarding: bool,
     /// Stable identity (`vid:pid:name`, see `PadInfo::key`) of the physical controller
     /// forwarded as pad 0; empty = automatic (most recently connected). Applied to the
     /// gamepad service at startup so the choice survives restarts.
@@ -874,6 +929,32 @@ pub struct Settings {
     /// `default = true`: the Linux stores never carried this and always advertised.
     #[serde(default = "default_true")]
     pub hdr_enabled: bool,
+    /// Presentation intent: `"latency"` (default) or `"smooth"` — the Apple/Android
+    /// clients' shared `present_priority` profile key, resolved with
+    /// [`PresentPriority::resolve`] (via [`Settings::present_priority`]). Anything
+    /// unknown reads as latency, so a newer client's future value degrades safely.
+    #[serde(default = "default_present_priority")]
+    pub present_priority: String,
+    /// Smoothness buffer size in frames: `0` = Automatic (resolves to 2), else 1–3.
+    /// Only meaningful under `present_priority = "smooth"` (the shared `smooth_buffer`
+    /// key). Each buffered frame absorbs about one refresh of jitter and adds one
+    /// refresh of display latency.
+    #[serde(default)]
+    pub smooth_buffer: u8,
+    /// Tear-free presentation (default ON = today's behavior: MAILBOX, FIFO fallback).
+    /// Off asks for a tearing present mode (IMMEDIATE) for the lowest possible latch
+    /// latency — best-effort: platforms/drivers without tearing silently stay tear-free
+    /// and the active mode is visible in the detailed stats. The shared `vsync` profile
+    /// key; the desktop default differs from macOS's (`false` there) deliberately —
+    /// sync-off means something different on each platform, the key is the contract.
+    #[serde(default = "default_true")]
+    pub vsync: bool,
+    /// Let a variable-refresh display follow the stream cadence: prefers the present
+    /// mode that drives VRR panels directly when fullscreen. Inert on fixed-refresh
+    /// displays (detection is measured from on-glass timestamps, not queried). The
+    /// shared `allow_vrr` profile key. Default ON, like the Apple client.
+    #[serde(default = "default_true")]
+    pub allow_vrr: bool,
     /// Legacy on/off for the stats overlay — superseded by `stats_verbosity` but kept
     /// written in sync (`set_stats_verbosity`) so pre-tier binaries reading the same
     /// file keep working. `alias`: the pre-unification WinUI shell (≤ 0.8.4) persisted
@@ -925,6 +1006,14 @@ pub struct Settings {
     /// the user will be looking at. `0` = never stored → the 1280×720 default.
     pub last_window_w: u32,
     pub last_window_h: u32,
+    /// Settings keys this build doesn't model (a newer client's field), carried through a
+    /// load→save round-trip untouched — [`crate::profiles::SettingsOverlay`]'s `extra`
+    /// pattern extended to the globals. Without it, every whole-file writer of this store
+    /// (two shells, the console settings screen, the session's resize callback, Decky)
+    /// running as an OLDER binary silently drops what a newer one persisted. Empty on
+    /// every existing store, and an empty map serializes to nothing, so files don't churn.
+    #[serde(flatten)]
+    pub extra: BTreeMap<String, serde_json::Value>,
 }
 
 fn default_codec() -> String {
@@ -939,6 +1028,10 @@ fn default_mouse_mode() -> String {
     "capture".into()
 }
 
+fn default_present_priority() -> String {
+    "latency".into()
+}
+
 fn default_true() -> bool {
     true
 }
@@ -970,6 +1063,12 @@ impl Settings {
         MouseMode::from_name(&self.mouse_mode)
     }
 
+    /// The presentation intent for this session (the resolved
+    /// `present_priority` × `smooth_buffer` pair).
+    pub fn present_priority(&self) -> PresentPriority {
+        PresentPriority::resolve(&self.present_priority, self.smooth_buffer)
+    }
+
     /// The `codec` setting as a `quic::CODEC_*` preference bit (`0` = auto).
     pub fn preferred_codec(&self) -> u8 {
         match self.codec.as_str() {
@@ -994,6 +1093,7 @@ impl Default for Settings {
             bitrate_kbps: 0,
             render_scale: 1.0,
             gamepad: "auto".into(),
+            gamepad_forwarding: true,
             forward_pad: String::new(),
             compositor: "auto".into(),
             touch_mode: "trackpad".into(),
@@ -1007,6 +1107,10 @@ impl Default for Settings {
             adapter: String::new(),
             enable_444: false,
             hdr_enabled: true,
+            present_priority: "latency".into(),
+            smooth_buffer: 0,
+            vsync: true,
+            allow_vrr: true,
             show_stats: true,
             stats_verbosity: None,
             fullscreen_on_stream: true,
@@ -1018,6 +1122,7 @@ impl Default for Settings {
             match_window: false,
             last_window_w: 0,
             last_window_h: 0,
+            extra: BTreeMap::new(),
         }
     }
 }
@@ -1144,6 +1249,43 @@ mod tests {
         }
     }
 
+    /// A settings file predating the presentation cluster loads with the shipped
+    /// defaults (latency intent, Automatic buffer, tear-free, VRR allowed), and the
+    /// resolution rules match the Apple/Android reference: anything but an explicit
+    /// `"smooth"` is latency, and a smooth buffer outside 1..=3 becomes 2.
+    #[test]
+    fn settings_presentation_defaults_and_resolution() {
+        let old = r#"{"width":1280,"height":720,"gamepad":"auto","compositor":"auto"}"#;
+        let s: Settings = serde_json::from_str(old).unwrap();
+        assert_eq!(s.present_priority, "latency");
+        assert_eq!(s.smooth_buffer, 0);
+        assert!(s.vsync);
+        assert!(s.allow_vrr);
+        assert_eq!(s.present_priority(), PresentPriority::Latency);
+
+        assert_eq!(
+            PresentPriority::resolve("smooth", 0),
+            PresentPriority::Smooth { buffer: 2 },
+            "Automatic resolves to 2"
+        );
+        assert_eq!(
+            PresentPriority::resolve("smooth", 3),
+            PresentPriority::Smooth { buffer: 3 }
+        );
+        assert_eq!(
+            PresentPriority::resolve("smooth", 9),
+            PresentPriority::Smooth { buffer: 2 },
+            "out-of-range pins to the Automatic resolution"
+        );
+        assert_eq!(
+            PresentPriority::resolve("balanced-from-the-future", 2),
+            PresentPriority::Latency,
+            "unknown intents degrade to latency"
+        );
+        assert_eq!(PresentPriority::Latency.fifo_capacity(), 0);
+        assert_eq!(PresentPriority::Smooth { buffer: 3 }.fifo_capacity(), 3);
+    }
+
     /// A pre-`forward_pad` settings file (≤ 0.5.0) loads with the pin on automatic.
     #[test]
     fn settings_forward_pad_defaults_empty() {
@@ -1192,6 +1334,28 @@ mod tests {
         assert!(s.echo_cancel);
     }
 
+    /// A key this build doesn't model (a newer client's setting) survives a load→save
+    /// round trip instead of being dropped by the next whole-file write — the same
+    /// contract `SettingsOverlay.extra` gives profiles. And when there are no unknown
+    /// keys, the flatten map adds nothing, so existing files don't churn.
+    #[test]
+    fn settings_unknown_keys_survive_round_trip() {
+        let newer = r#"{"width":1920,"height":1080,"frob_mode":"fancy","frob_level":3}"#;
+        let s: Settings = serde_json::from_str(newer).unwrap();
+        assert_eq!((s.width, s.height), (1920, 1080));
+        assert_eq!(
+            s.extra.get("frob_mode").and_then(|v| v.as_str()),
+            Some("fancy")
+        );
+        let out = serde_json::to_string(&s).unwrap();
+        assert!(out.contains(r#""frob_mode":"fancy""#), "{out}");
+        assert!(out.contains(r#""frob_level":3"#), "{out}");
+        // No unknown keys → no artifact of the passthrough field in the file.
+        let plain = serde_json::to_string(&Settings::default()).unwrap();
+        assert!(!plain.contains("extra"), "{plain}");
+        assert!(!plain.contains("frob"), "{plain}");
+    }
+
     /// Stats-tier resolution: a pre-tier store falls back to `show_stats` (off → Off,
     /// on/absent → Normal), an explicit tier wins, and setting a tier keeps the legacy
     /// bool in sync so pre-tier binaries reading the same file agree on off vs on.

crates/pf-console-ui/src/screens/settings.rs

@@ -26,9 +26,14 @@ enum RowId {
     Decoder,
     Hdr,
     Chroma444,
+    PresentPriority,
+    SmoothBuffer,
+    Vsync,
+    AllowVrr,
     Audio,
     Mic,
     EchoCancel,
+    PadForward,
     Pad,
     PadType,
     Touch,
@@ -46,7 +51,7 @@ enum RowId {
 // scroll/shortcut behavior, fullscreen-on-stream, auto-wake, the library toggle and echo
 // cancellation all were). Still deliberately smaller than the desktop dialogs — device
 // pickers (GPU/speaker/mic) and the profile catalog stay desktop-only.
-const ROWS: [RowId; 22] = [
+const ROWS: [RowId; 27] = [
     RowId::Resolution,
     RowId::Refresh,
     RowId::RenderScale,
@@ -56,9 +61,14 @@ const ROWS: [RowId; 22] = [
     RowId::Decoder,
     RowId::Hdr,
     RowId::Chroma444,
+    RowId::PresentPriority,
+    RowId::SmoothBuffer,
+    RowId::Vsync,
+    RowId::AllowVrr,
     RowId::Audio,
     RowId::Mic,
     RowId::EchoCancel,
+    RowId::PadForward,
     RowId::Pad,
     RowId::PadType,
     RowId::Touch,
@@ -117,6 +127,17 @@ const DECODERS: [(&str, &str); 4] = [
     ("software", "Software"),
 ];
 const AUDIO: [(u8, &str); 3] = [(2, "Stereo"), (6, "5.1"), (8, "7.1")];
+/// Presentation intent — the `present_priority` key shared with the Apple and Android
+/// clients, so one profile reads the same on every device.
+const PRESENT_PRIORITIES: [(&str, &str); 2] =
+    [("latency", "Lowest latency"), ("smooth", "Smoothness")];
+/// Smoothness buffer depth in frames; `0` = Automatic (resolves to 2).
+const SMOOTH_BUFFERS: [(u8, &str); 4] = [
+    (0, "Automatic"),
+    (1, "1 frame"),
+    (2, "2 frames"),
+    (3, "3 frames"),
+];
 const PAD_TYPES: [(&str, &str); 6] = [
     ("auto", "Automatic"),
     ("xbox360", "Xbox 360"),
@@ -222,9 +243,18 @@ impl SettingsScreen {
 
 fn row_spec(id: RowId, ctx: &Ctx) -> RowSpec {
     let s = &ctx.settings;
-    // Echo cancellation only means anything while the mic streams — dimmed and inert while it
-    // doesn't, the same relationship the desktop shells draw with a greyed-out row.
-    let enabled = !matches!(id, RowId::EchoCancel) || s.mic_enabled;
+    // Several rows follow another: echo cancellation only means anything while the mic
+    // streams, the pad rows only while any controller is forwarded at all, and the
+    // smoothness buffer only while that intent is chosen. All go dim and inert otherwise
+    // — the same relationship the desktop shells draw by greying a row out (they hide the
+    // buffer row entirely; a fixed row list can't, and a row that vanished mid-list would
+    // move everything under the cursor).
+    let enabled = match id {
+        RowId::EchoCancel => s.mic_enabled,
+        RowId::Pad | RowId::PadType => s.gamepad_forwarding,
+        RowId::SmoothBuffer => s.present_priority == "smooth",
+        _ => true,
+    };
     let (header, label, value): (Option<&'static str>, &str, String) = match id {
         RowId::Resolution => (
             Some("Stream"),
@@ -279,6 +309,22 @@ fn row_spec(id: RowId, ctx: &Ctx) -> RowSpec {
         RowId::Decoder => (None, "Decoder", label_for(&DECODERS, &s.decoder).into()),
         RowId::Hdr => (None, "10-bit HDR", on_off(s.hdr_enabled).into()),
         RowId::Chroma444 => (None, "Full chroma (4:4:4)", on_off(s.enable_444).into()),
+        RowId::PresentPriority => (
+            Some("Presentation"),
+            "Prioritize",
+            label_for(&PRESENT_PRIORITIES, &s.present_priority).into(),
+        ),
+        RowId::SmoothBuffer => (
+            None,
+            "Smoothness buffer",
+            SMOOTH_BUFFERS
+                .iter()
+                .find(|(v, _)| *v == s.smooth_buffer)
+                .map_or("Automatic", |(_, l)| l)
+                .into(),
+        ),
+        RowId::Vsync => (None, "V-Sync", on_off(s.vsync).into()),
+        RowId::AllowVrr => (None, "Follow variable refresh", on_off(s.allow_vrr).into()),
         RowId::Audio => (
             Some("Audio"),
             "Audio channels",
@@ -290,8 +336,13 @@ fn row_spec(id: RowId, ctx: &Ctx) -> RowSpec {
         ),
         RowId::Mic => (None, "Microphone", on_off(s.mic_enabled).into()),
         RowId::EchoCancel => (None, "Echo cancellation", on_off(s.echo_cancel).into()),
-        RowId::Pad => (
+        RowId::PadForward => (
             Some("Controller"),
+            "Forward controllers",
+            on_off(s.gamepad_forwarding).into(),
+        ),
+        RowId::Pad => (
+            None,
             "Use controller",
             if s.forward_pad.is_empty() {
                 "Automatic".into()
@@ -368,6 +419,24 @@ fn detail(id: RowId) -> &'static str {
              Needs an NVIDIA host (NVENC) or the PyroWave codec — other encoders \
              stream 4:2:0 and the session falls back silently."
         }
+        RowId::PresentPriority => {
+            "Lowest latency shows each frame the moment the display can take it — a \
+             network hiccup becomes an occasional repeated or skipped frame. Smoothness \
+             buffers a little to even those out."
+        }
+        RowId::SmoothBuffer => {
+            "Frames held back before showing. Each one absorbs about a refresh of network \
+             hiccup and adds a refresh of delay. Automatic holds two."
+        }
+        RowId::Vsync => {
+            "Tear-free. Off removes the wait for the screen's refresh — the lowest \
+             possible delay, at the cost of visible tearing. Not every driver offers it; \
+             the stats overlay names the mode actually in use."
+        }
+        RowId::AllowVrr => {
+            "On a VRR screen, let the panel refresh in step with the stream instead of on \
+             a fixed cadence. Applies to fullscreen sessions; harmless on a fixed screen."
+        }
         RowId::Audio => "The speaker layout requested from the host.",
         RowId::Mic => {
             "Send this device's microphone to the host's virtual mic. \
@@ -377,6 +446,11 @@ fn detail(id: RowId) -> &'static str {
             "Stops the host's audio, playing from this device's speakers, being picked up \
              and sent back. Turn it off if your microphone already runs its own processing."
         }
+        RowId::PadForward => {
+            "Send controllers connected to this device to the host. Turn it off when your \
+             controller already reaches the host another way — USB passthrough such as \
+             VirtualHere, or a pad plugged into the host — so games don't see two of them."
+        }
         RowId::Pad => "Which pad is forwarded to the host, as player 1.",
         RowId::PadType => "The virtual pad the host creates — Automatic matches this controller.",
         RowId::Touch => {
@@ -463,6 +537,27 @@ fn adjust(id: RowId, delta: i32, wrap: bool, ctx: &mut Ctx) -> bool {
         RowId::Decoder => step_str(&DECODERS, &mut s.decoder, delta, wrap),
         RowId::Hdr => toggle(&mut s.hdr_enabled, delta, wrap),
         RowId::Chroma444 => toggle(&mut s.enable_444, delta, wrap),
+        RowId::PresentPriority => {
+            let cur = PRESENT_PRIORITIES
+                .iter()
+                .position(|(v, _)| *v == s.present_priority);
+            step_option(cur, PRESENT_PRIORITIES.len(), delta, wrap)
+                .map(|i| s.present_priority = PRESENT_PRIORITIES[i].0.to_string())
+        }
+        // Inert unless smoothness is chosen — a boundary thud, matching the dimmed row.
+        RowId::SmoothBuffer => {
+            if s.present_priority == "smooth" {
+                let cur = SMOOTH_BUFFERS
+                    .iter()
+                    .position(|(v, _)| *v == s.smooth_buffer);
+                step_option(cur, SMOOTH_BUFFERS.len(), delta, wrap)
+                    .map(|i| s.smooth_buffer = SMOOTH_BUFFERS[i].0)
+            } else {
+                None
+            }
+        }
+        RowId::Vsync => toggle(&mut s.vsync, delta, wrap),
+        RowId::AllowVrr => toggle(&mut s.allow_vrr, delta, wrap),
         RowId::Audio => {
             let cur = AUDIO.iter().position(|(v, _)| *v == s.audio_channels);
             step_option(cur, AUDIO.len(), delta, wrap).map(|i| s.audio_channels = AUDIO[i].0)
@@ -476,7 +571,11 @@ fn adjust(id: RowId, delta: i32, wrap: bool, ctx: &mut Ctx) -> bool {
                 None
             }
         }
+        RowId::PadForward => toggle(&mut s.gamepad_forwarding, delta, wrap),
         RowId::Pad => {
+            if !s.gamepad_forwarding {
+                return false;
+            }
             // Automatic first, then every connected pad by stable key.
             let keys: Vec<String> = std::iter::once(String::new())
                 .chain(ctx.pads.iter().map(|p| p.key.clone()))
@@ -484,7 +583,12 @@ fn adjust(id: RowId, delta: i32, wrap: bool, ctx: &mut Ctx) -> bool {
             let cur = keys.iter().position(|c| *c == s.forward_pad);
             step_option(cur, keys.len(), delta, wrap).map(|i| s.forward_pad = keys[i].clone())
         }
-        RowId::PadType => step_str(&PAD_TYPES, &mut s.gamepad, delta, wrap),
+        RowId::PadType => {
+            if !s.gamepad_forwarding {
+                return false;
+            }
+            step_str(&PAD_TYPES, &mut s.gamepad, delta, wrap)
+        }
         RowId::Touch => {
             let cur = TouchMode::ALL.iter().position(|m| *m == s.touch_mode());
             step_option(cur, TouchMode::ALL.len(), delta, wrap)
@@ -648,6 +752,45 @@ mod tests {
         assert!(ctx.settings.echo_cancel);
     }
 
+    /// The smoothness buffer follows the presentation intent, exactly as echo cancellation
+    /// follows the mic: dimmed and inert under Lowest latency (where holding frames means
+    /// nothing), live under Smoothness. The desktop shells hide the row instead; a fixed
+    /// row list dims it, because a row vanishing mid-list would shift everything under the
+    /// cursor.
+    #[test]
+    fn smoothness_buffer_follows_the_intent() {
+        let (mut settings, pads) = ctx_parts();
+        assert_eq!(settings.present_priority, "latency", "the shipped default");
+        let library = crate::library::LibraryShared::default();
+        let mut ctx = Ctx {
+            hosts: &[],
+            library: &library,
+            settings: &mut settings,
+            pads: &pads,
+            deck: false,
+            device_name: "t",
+            t: 0.0,
+        };
+        assert!(!row_spec(RowId::SmoothBuffer, &ctx).enabled);
+        assert!(
+            !adjust(RowId::SmoothBuffer, 1, false, &mut ctx),
+            "latency intent = thud"
+        );
+        assert_eq!(ctx.settings.smooth_buffer, 0, "and nothing was written");
+
+        // Stepping the intent to Smoothness brings the buffer row to life.
+        assert!(adjust(RowId::PresentPriority, 1, false, &mut ctx));
+        assert_eq!(ctx.settings.present_priority, "smooth");
+        assert!(row_spec(RowId::SmoothBuffer, &ctx).enabled);
+        assert!(adjust(RowId::SmoothBuffer, 1, false, &mut ctx));
+        assert_eq!(ctx.settings.smooth_buffer, 1);
+
+        // The intent wraps back and the row goes inert again.
+        assert!(adjust(RowId::PresentPriority, -1, false, &mut ctx));
+        assert_eq!(ctx.settings.present_priority, "latency");
+        assert!(!row_spec(RowId::SmoothBuffer, &ctx).enabled);
+    }
+
     #[test]
     fn touch_mode_steps_and_wraps() {
         let (mut settings, pads) = ctx_parts();

crates/pf-presenter/src/lib.rs

@@ -52,6 +52,8 @@ pub mod keymap_sdl;
 #[cfg(any(target_os = "linux", windows))]
 pub mod overlay;
 #[cfg(any(target_os = "linux", windows))]
+mod present_pace;
+#[cfg(any(target_os = "linux", windows))]
 mod run;
 #[cfg(any(target_os = "linux", windows))]
 pub mod touch;

crates/pf-presenter/src/present_pace.rs

@@ -0,0 +1,751 @@
+//! The presentation intent engine (design/desktop-presentation-rebuild.md WP2): the
+//! store, clock, and gate the run loop composes into the two intents.
+//!
+//! * [`FrameStore`] — newest-wins slot (latency) or smoothing FIFO with preroll
+//!   (smoothness), ported from the Apple `FrameStore` / Android `presenter.rs` so all
+//!   three clients agree on what the intents mean.
+//! * [`LatchClock`] — the panel latch grid, learned from `VK_KHR_present_wait` on-glass
+//!   stamps (measured, never queried — the Android refresh-rate lie and VRR both punish
+//!   trusting a reported rate). Without present-wait it degrades to a grid rooted at the
+//!   last submit on the mode's refresh period.
+//! * [`PresentGate`] — the FIFO glass budget: one undisplayed present in flight, so the
+//!   swapchain's own queue can never become a standing queue (+1 refresh per slot,
+//!   forever — the law every bounded-FIFO pacing rediscovered on Apple). MAILBOX cannot
+//!   queue and never needs it.
+//!
+//! Everything here is pure state + arithmetic on `CLOCK_REALTIME` ns (the
+//! `pf_client_core::session::now_ns` domain the on-glass stamps live in); the run loop
+//! owns all clocks and Vulkan calls, which is what keeps this testable.
+
+use std::collections::VecDeque;
+
+/// Stale-present force-open: an undisplayed present older than this is presumed lost
+/// (occluded window, wedged compositor) and the gate opens anyway, counted as `forced`
+/// — reads 0 on healthy systems. The Apple/Android presenters use the same 100 ms.
+const STALE_REOPEN_NS: u64 = 100_000_000;
+
+/// The adaptive slot-pick margin's ceiling and step (Android's measured values: start
+/// at 0 — a fixed lead was pure display tax on the reference device — and widen only
+/// when measured misses demand it).
+pub(crate) const MARGIN_STEP_NS: u64 = 500_000;
+pub(crate) const MARGIN_MAX_NS: u64 = 2_500_000;
+
+/// The decoded-frame store between the wake channel and the present call.
+///
+/// `capacity == 0` = newest-wins (latency intent): `submit` replaces, `take` clears.
+/// `capacity 1..=3` = smoothing FIFO: preroll-to-capacity, drop-oldest on overflow,
+/// an underflow after preroll re-arms the preroll (the previous frame persists on
+/// glass — a repeat by omission) while headroom rebuilds.
+pub(crate) struct FrameStore<T> {
+    capacity: usize,
+    frames: VecDeque<T>,
+    prerolled: bool,
+    /// Newest-wins displacements (normal operation under latency, not a fault signal).
+    replaced: u32,
+    /// FIFO drop-oldest evictions — the Apple debug line's `qDrop`.
+    overflow_drops: u32,
+    /// FIFO dry-after-preroll events — `qDry`.
+    underflows: u32,
+}
+
+impl<T> FrameStore<T> {
+    pub(crate) fn new(capacity: usize) -> FrameStore<T> {
+        FrameStore {
+            capacity,
+            frames: VecDeque::with_capacity(capacity.max(1) + 1),
+            prerolled: false,
+            replaced: 0,
+            overflow_drops: 0,
+            underflows: 0,
+        }
+    }
+
+    pub(crate) fn is_smoothing(&self) -> bool {
+        self.capacity > 0
+    }
+
+    pub(crate) fn is_empty(&self) -> bool {
+        self.frames.is_empty()
+    }
+
+    pub(crate) fn submit(&mut self, f: T) {
+        if self.capacity == 0 {
+            if self.frames.pop_front().is_some() {
+                self.replaced += 1;
+            }
+            self.frames.push_back(f);
+        } else {
+            self.frames.push_back(f);
+            // Drop the OLDEST past capacity: bounded added latency, the newest keeps
+            // flowing. Also trims a transient capacity+1 a put_back left behind.
+            while self.frames.len() > self.capacity {
+                self.frames.pop_front();
+                self.overflow_drops += 1;
+            }
+        }
+    }
+
+    pub(crate) fn take(&mut self) -> Option<T> {
+        if self.capacity == 0 {
+            return self.frames.pop_front();
+        }
+        if !self.prerolled {
+            // Preroll gate: without it a steady stream drains every frame on arrival
+            // and jitter headroom never builds (the Apple store's lesson).
+            if self.frames.len() < self.capacity {
+                return None;
+            }
+            self.prerolled = true;
+        }
+        match self.frames.pop_front() {
+            Some(f) => Some(f),
+            None => {
+                self.underflows += 1;
+                self.prerolled = false;
+                None
+            }
+        }
+    }
+
+    /// A frame taken but not presented (gate closed, present failed before consuming
+    /// it). Newest-wins reinserts only into an empty slot — a fresher decode wins;
+    /// FIFO puts it back at the front (it is the oldest).
+    pub(crate) fn put_back(&mut self, f: T) {
+        if self.capacity == 0 {
+            if self.frames.is_empty() {
+                self.frames.push_back(f);
+            }
+        } else {
+            self.frames.push_front(f);
+        }
+    }
+
+    /// Collapse to newest-wins for the rest of the stream (PyroWave: its plane-ring
+    /// retirement accounting assumes the depth-2 newest-wins hand-off, and its all-intra
+    /// frames make buffering pointless anyway).
+    ///
+    /// Gated with its only caller: the power-user build (`--no-default-features`, which
+    /// the Windows ARM64 leg ships) has no PyroWave decode path, and an ungated helper
+    /// is dead code there.
+    #[cfg(feature = "pyrowave")]
+    pub(crate) fn force_latency(&mut self) {
+        if self.capacity == 0 {
+            return;
+        }
+        self.capacity = 0;
+        self.prerolled = false;
+        while self.frames.len() > 1 {
+            self.frames.pop_front();
+        }
+    }
+
+    /// Drain the window's counters: `(replaced, overflow_drops, underflows)`.
+    pub(crate) fn take_counters(&mut self) -> (u32, u32, u32) {
+        let c = (self.replaced, self.overflow_drops, self.underflows);
+        self.replaced = 0;
+        self.overflow_drops = 0;
+        self.underflows = 0;
+        c
+    }
+}
+
+/// The panel latch grid: a recent on-glass instant + the latch period, extrapolated
+/// forward for slot targeting.
+///
+/// The period learner is the SHARED [`punktfunk_core::phase::PanelGrid`], not a local
+/// rule. An earlier version of this clock capped the learned period at the display
+/// mode's refresh, on the reasoning that a stream running below panel rate spaces its
+/// presents at k×period and the cap stops a 30 fps stream claiming a 30 Hz panel. That
+/// cap is the same defect the Android presenter shipped in 0.23.0: the seed is only what
+/// the *mode* claims, and when the real panel is slower (a refused mode switch, a
+/// compositor running its own rate) a downward-only learner pins a grid that never
+/// arrives, for the whole session, with no way back. `PanelGrid` moves both ways —
+/// narrowing at once, widening only after eight consecutive agreeing observations and
+/// then to the narrowest of them.
+///
+/// What is fed to it is still the window's MIN spacing: within one window that resists
+/// the k×period inflation the old cap was aimed at, while the streak requirement means a
+/// genuinely slower panel is still discovered. Same grid the host-facing `LatchGrid`
+/// publish reads, so the phase-lock report and the local scheduler cannot disagree.
+pub(crate) struct LatchClock {
+    anchor_ns: u64,
+    /// The previous stamp, kept ACROSS calls. The run loop drains present-wait samples
+    /// every pass, so a "batch" is very often a single stamp — computing spacings only
+    /// within a batch (`windows(2)`) observed nothing at all on glass, and the learner
+    /// silently ran on its seed forever.
+    last_ns: u64,
+    /// Narrowest spacing seen since the last handoff to the grid, and how many have
+    /// accumulated. The grid is fed the MIN of a run rather than every spacing: our
+    /// observations are the spacing of OUR presents, which is k×period whenever the
+    /// stream runs below panel rate, and the min over a run is the best available
+    /// estimate of the true grid step.
+    pending_min_ns: u64,
+    pending_count: u32,
+    grid: punktfunk_core::phase::PanelGrid,
+    fallback_period_ns: u64,
+}
+
+/// Spacings per handoff to [`punktfunk_core::phase::PanelGrid`]. Small enough that a real
+/// mode change is picked up in well under a second at any sane frame rate.
+const GRID_OBSERVE_EVERY: u32 = 16;
+
+impl LatchClock {
+    pub(crate) fn new(refresh_hz: u32) -> LatchClock {
+        LatchClock {
+            anchor_ns: 0,
+            last_ns: 0,
+            pending_min_ns: 0,
+            pending_count: 0,
+            grid: punktfunk_core::phase::PanelGrid::seeded(refresh_hz as i32),
+            fallback_period_ns: 1_000_000_000 / u64::from(refresh_hz.max(1)),
+        }
+    }
+
+    /// Fold on-glass stamps (ascending). Spacings are measured against the previous
+    /// stamp whatever the batching, so the loop's one-sample-per-pass drain still feeds
+    /// the learner.
+    pub(crate) fn note_batch(&mut self, stamps: &[u64]) {
+        for &s in stamps {
+            if self.last_ns != 0 && s > self.last_ns {
+                let d = s - self.last_ns;
+                // < 1 ms apart = a queued pair, not a grid step.
+                if d > 1_000_000 {
+                    self.pending_min_ns = if self.pending_min_ns == 0 {
+                        d
+                    } else {
+                        self.pending_min_ns.min(d)
+                    };
+                    self.pending_count += 1;
+                    if self.pending_count >= GRID_OBSERVE_EVERY {
+                        self.grid.observe(self.pending_min_ns as i64);
+                        self.pending_min_ns = 0;
+                        self.pending_count = 0;
+                    }
+                }
+            }
+            self.last_ns = s;
+        }
+        if let Some(&last) = stamps.last() {
+            self.anchor_ns = last;
+        }
+    }
+
+    pub(crate) fn period_ns(&self) -> u64 {
+        let learned = self.grid.period_ns();
+        if learned > 0 {
+            learned as u64
+        } else {
+            self.fallback_period_ns
+        }
+    }
+
+    pub(crate) fn anchor_ns(&self) -> u64 {
+        self.anchor_ns
+    }
+
+    /// The first predicted latch strictly after `after_ns` (`anchor + k·period`). With
+    /// no anchor yet: one period out — callers get a usable, if unanchored, deadline.
+    pub(crate) fn next_slot_after(&self, after_ns: u64) -> u64 {
+        let p = self.period_ns();
+        if self.anchor_ns == 0 || after_ns < self.anchor_ns {
+            return after_ns.saturating_add(p);
+        }
+        let k = (after_ns - self.anchor_ns) / p + 1;
+        self.anchor_ns + k * p
+    }
+}
+
+/// Whether the panel is refreshing on a fixed grid or following our cadence.
+#[derive(Clone, Copy, PartialEq, Eq, Debug, Default)]
+pub(crate) enum Cadence {
+    /// Not enough evidence yet — say nothing rather than guess.
+    #[default]
+    Unknown,
+    /// On-glass instants land on multiples of the panel period: a fixed-refresh panel.
+    Fixed,
+    /// On-glass instants track our present spacing instead: variable refresh is live.
+    Variable,
+}
+
+impl Cadence {
+    pub(crate) fn label(self) -> &'static str {
+        match self {
+            Cadence::Unknown => "",
+            Cadence::Fixed => "no",
+            Cadence::Variable => "yes",
+        }
+    }
+}
+
+/// Is variable refresh actually live? **Measured, never queried** — no portable query
+/// exists (SDL exposes none, Wayland does not report adaptive-sync state, and Windows
+/// surfaces nothing through Vulkan), and the platforms that *do* answer have been caught
+/// lying before (Android reports a game-uid's down-rated refresh as the panel's).
+///
+/// The discriminator is quantization. On a fixed-refresh panel every on-glass instant
+/// lands on the vblank grid, so the spacing between consecutive presents is always
+/// ~k×period for whole k — even when the stream runs slower than the panel, where it just
+/// picks a larger k. Under real VRR the panel refreshes *when we present*, so the spacing
+/// follows our own cadence and sits wherever it likes relative to the grid.
+///
+/// So: fold each delta to its distance from the nearest multiple of the period. Tight
+/// against the grid ⇒ Fixed; consistently off it ⇒ Variable. A stream running exactly at
+/// panel rate is indistinguishable either way (both give delta ≈ period), which is
+/// harmless — at that rate VRR has nothing to do.
+pub(crate) struct CadenceProbe {
+    /// Off-grid distances as a fraction of the period, in thousandths.
+    off_grid_milli: Vec<u32>,
+    /// Previous stamp, kept across calls for the same reason [`LatchClock`] does: the
+    /// live drain hands over one sample at a time.
+    last_ns: u64,
+    /// The last round's raw reading and how many rounds have agreed — a verdict is only
+    /// published once [`CADENCE_STABLE_ROUNDS`] agree.
+    candidate: Cadence,
+    agree_rounds: u8,
+    verdict: Cadence,
+}
+
+/// Enough deltas to distinguish jitter from a real off-grid cadence.
+const CADENCE_MIN_SAMPLES: usize = 24;
+/// Consecutive agreeing rounds before a verdict is published.
+///
+/// ⭐ On glass (GNOME/Wayland, .21, 2026-08-02) the raw per-round verdict FLAPPED between
+/// runs with VRR provably disabled. The cause is structural, not a tuning miss: under a
+/// compositor our on-glass stamp is the compositor's release, so anything that perturbs
+/// delivery — an occluded or unfocused surface being throttled, a distressed pipeline
+/// missing vblanks — smears the spacings exactly the way real VRR does. This probe can
+/// therefore only ever say "presents are not landing on the grid", so it demands
+/// agreement across rounds and refuses evidence from a distressed window (see
+/// [`CadenceProbe::note`]'s `healthy` flag) before claiming anything.
+const CADENCE_STABLE_ROUNDS: u8 = 2;
+/// Median off-grid distance under this fraction of a period reads as grid-locked. Present
+/// stamps carry real measurement jitter (the wait returns, then we read the clock), so
+/// this is deliberately loose — the two regimes differ by far more than this in practice.
+const CADENCE_FIXED_MILLI: u32 = 150;
+
+impl CadenceProbe {
+    pub(crate) fn new() -> CadenceProbe {
+        CadenceProbe {
+            off_grid_milli: Vec::with_capacity(64),
+            last_ns: 0,
+            candidate: Cadence::Unknown,
+            agree_rounds: 0,
+            verdict: Cadence::Unknown,
+        }
+    }
+
+    /// Fold on-glass stamps against the learned panel period. Spacings are measured
+    /// against the previous stamp whatever the batching.
+    ///
+    /// `healthy` is the caller's statement that this window's presents were flowing
+    /// normally (no stale force-opens). A distressed pipeline smears spacings for reasons
+    /// that have nothing to do with the panel, so its evidence is dropped — the timeline
+    /// continuity is still advanced, it simply does not count as a sample.
+    pub(crate) fn note(&mut self, stamps: &[u64], period_ns: u64, healthy: bool) {
+        if period_ns == 0 || !healthy {
+            self.last_ns = stamps.last().copied().unwrap_or(self.last_ns);
+            return;
+        }
+        for &s in stamps {
+            let prev = std::mem::replace(&mut self.last_ns, s);
+            if prev == 0 || s <= prev {
+                continue;
+            }
+            let delta = s - prev;
+            let rem = delta % period_ns;
+            // Distance to the NEAREST multiple, so a delta just under k×period reads as
+            // close to the grid rather than a whole period away from k-1.
+            let off = rem.min(period_ns - rem);
+            self.off_grid_milli
+                .push((off.saturating_mul(1000) / period_ns) as u32);
+            // A round closes on the SAMPLE count, inside the loop — not once per call.
+            // Evaluating per call would make the verdict depend on how the caller happens
+            // to batch its stamps (one big batch = one round, forever short of the
+            // agreement requirement), and the live drain and the tests batch differently.
+            self.close_round_if_ready();
+        }
+    }
+
+    /// Publish a verdict once a round's worth of spacings agree with the previous round.
+    fn close_round_if_ready(&mut self) {
+        if self.off_grid_milli.len() >= CADENCE_MIN_SAMPLES {
+            self.off_grid_milli.sort_unstable();
+            let median = self.off_grid_milli[self.off_grid_milli.len() / 2];
+            let round = if median <= CADENCE_FIXED_MILLI {
+                Cadence::Fixed
+            } else {
+                Cadence::Variable
+            };
+            if round == self.candidate {
+                self.agree_rounds = self.agree_rounds.saturating_add(1);
+            } else {
+                self.candidate = round;
+                self.agree_rounds = 1;
+            }
+            if self.agree_rounds >= CADENCE_STABLE_ROUNDS {
+                self.verdict = round;
+            }
+            self.off_grid_milli.clear();
+        }
+    }
+
+    pub(crate) fn verdict(&self) -> Cadence {
+        self.verdict
+    }
+
+    /// A mode switch / display change invalidates the evidence.
+    pub(crate) fn reset(&mut self) {
+        self.off_grid_milli.clear();
+        self.last_ns = 0;
+        self.candidate = Cadence::Unknown;
+        self.agree_rounds = 0;
+        self.verdict = Cadence::Unknown;
+    }
+}
+
+/// The FIFO glass budget: at most one undisplayed present in flight, measured by the
+/// present-wait waiter's outstanding count. Never consulted under MAILBOX/IMMEDIATE
+/// (they cannot queue) or without present-wait (nothing to count with — behavior is
+/// then exactly the shipped arrival pacing).
+#[derive(Default)]
+pub(crate) struct PresentGate {
+    /// Submit stamp of the newest tracked present; 0 = none yet.
+    last_present_ns: u64,
+    gated: u32,
+    forced: u32,
+}
+
+impl PresentGate {
+    /// May a new present go out? Open when nothing undisplayed is in flight; a stale
+    /// in-flight present (occlusion, wedged compositor) force-opens after 100 ms so the
+    /// stream survives, counted as `forced`.
+    pub(crate) fn open(&mut self, outstanding: usize, now_ns: u64) -> bool {
+        if outstanding == 0 {
+            return true;
+        }
+        if self.last_present_ns != 0
+            && now_ns.saturating_sub(self.last_present_ns) > STALE_REOPEN_NS
+        {
+            self.forced += 1;
+            return true;
+        }
+        self.gated += 1;
+        false
+    }
+
+    pub(crate) fn note_present(&mut self, now_ns: u64) {
+        self.last_present_ns = now_ns;
+    }
+
+    /// Drain the window's counters: `(gated, forced)`.
+    pub(crate) fn take_counters(&mut self) -> (u32, u32) {
+        let c = (self.gated, self.forced);
+        self.gated = 0;
+        self.forced = 0;
+        c
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    /// Newest-wins: submit replaces, take clears, put_back only fills an empty slot.
+    #[test]
+    fn newest_wins_replaces_and_putback_never_clobbers() {
+        let mut s: FrameStore<u32> = FrameStore::new(0);
+        assert!(!s.is_smoothing());
+        assert_eq!(s.take(), None);
+        s.submit(1);
+        s.submit(2);
+        s.submit(3);
+        assert_eq!(s.take(), Some(3), "only the newest survives");
+        assert_eq!(s.take(), None);
+        // A taken-but-unpresented frame returns — unless a fresher one arrived.
+        s.submit(4);
+        let f = s.take().unwrap();
+        s.put_back(f);
+        assert_eq!(s.take(), Some(4));
+        let f = s.take();
+        assert_eq!(f, None);
+        s.submit(5);
+        let f = s.take().unwrap();
+        s.submit(6);
+        s.put_back(f); // 6 arrived while 5 was out — 6 wins
+        assert_eq!(s.take(), Some(6));
+        assert_eq!(
+            s.take_counters(),
+            (2, 0, 0),
+            "two displacements, no fifo counters"
+        );
+    }
+
+    /// FIFO: preroll to capacity, drop-oldest overflow, underflow re-arms the preroll.
+    #[test]
+    fn fifo_prerolls_overflows_oldest_and_rearms_on_dry() {
+        let mut s: FrameStore<u32> = FrameStore::new(2);
+        assert!(s.is_smoothing());
+        s.submit(1);
+        assert_eq!(s.take(), None, "prerolling: below capacity, nothing vends");
+        s.submit(2);
+        assert_eq!(s.take(), Some(1), "preroll reached — FIFO order");
+        assert_eq!(
+            s.take(),
+            Some(2),
+            "once prerolled the buffer drains normally"
+        );
+        // Dry after preroll = one underflow, preroll re-arms.
+        assert_eq!(s.take(), None);
+        s.submit(3);
+        assert_eq!(s.take(), None, "re-armed preroll holds again");
+        s.submit(4);
+        assert_eq!(s.take(), Some(3));
+        // Overflow drops the OLDEST: [4] → [4,5] → 6 evicts 4 → 7 evicts 5.
+        s.submit(5);
+        s.submit(6);
+        s.submit(7);
+        assert_eq!(s.take(), Some(6));
+        assert_eq!(s.take(), Some(7));
+        let (replaced, drops, dry) = s.take_counters();
+        assert_eq!(replaced, 0);
+        assert_eq!(drops, 2, "6 evicted 4, 7 evicted 5");
+        assert_eq!(dry, 1);
+    }
+
+    /// put_back under FIFO goes to the FRONT (it is the oldest), and the transient
+    /// capacity+1 is trimmed by the next submit.
+    #[test]
+    fn fifo_putback_restores_order() {
+        let mut s: FrameStore<u32> = FrameStore::new(2);
+        s.submit(1);
+        s.submit(2);
+        let f = s.take().unwrap();
+        s.put_back(f);
+        assert_eq!(s.take(), Some(1), "the put-back frame is still first");
+    }
+
+    /// force_latency collapses a smoothing store to a newest-wins slot mid-stream.
+    #[cfg(feature = "pyrowave")]
+    #[test]
+    fn force_latency_collapses_to_one_slot() {
+        let mut s: FrameStore<u32> = FrameStore::new(3);
+        s.submit(1);
+        s.submit(2);
+        s.submit(3);
+        s.force_latency();
+        assert!(!s.is_smoothing());
+        assert_eq!(s.take(), Some(3), "only the newest survives the collapse");
+        s.submit(4);
+        s.submit(5);
+        assert_eq!(s.take(), Some(5));
+    }
+
+    /// The clock learns the min positive spacing (capped at the mode refresh), anchors
+    /// on the newest stamp, and extrapolates the next slot; sub-ms pairs (a queued
+    /// double-present) never become the period.
+    #[test]
+    fn latch_clock_learns_and_extrapolates() {
+        const P: u64 = 16_666_666; // 60 Hz
+        let mut c = LatchClock::new(60);
+        assert_eq!(c.period_ns(), P, "fallback = the mode refresh");
+        // No anchor: a usable deadline one period out.
+        assert_eq!(c.next_slot_after(1_000), 1_000 + P);
+
+        c.note_batch(&[1_000_000_000, 1_000_000_000 + P, 1_000_000_000 + 2 * P]);
+        assert_eq!(c.period_ns(), P);
+        assert_eq!(c.anchor_ns(), 1_000_000_000 + 2 * P);
+        let next = c.next_slot_after(c.anchor_ns());
+        assert_eq!(next, 1_000_000_000 + 3 * P);
+        // Mid-slot query lands on the same boundary; a later one steps whole periods.
+        assert_eq!(c.next_slot_after(next - 1), next);
+        assert_eq!(c.next_slot_after(next), next + P);
+
+        // A queued pair (< 1 ms apart) must not poison the period.
+        c.note_batch(&[2_000_000_000, 2_000_000_500]);
+        assert_eq!(c.period_ns(), P);
+        assert_eq!(c.anchor_ns(), 2_000_000_500, "the anchor still advances");
+
+        // A stream presenting every OTHER refresh spaces its glass stamps at 2×P. One
+        // such window must NOT move the grid — the shared learner needs a streak before
+        // it will widen, which is what keeps a briefly-slow stream from claiming a slow
+        // panel while still allowing a genuinely slower display to be discovered.
+        c.note_batch(&[3_000_000_000, 3_000_000_000 + 2 * P]);
+        assert_eq!(c.period_ns(), P, "one wide window is not a slower panel");
+
+        // A single stamp re-anchors without touching the period.
+        c.note_batch(&[5_000_000_000]);
+        assert_eq!(c.anchor_ns(), 5_000_000_000);
+        assert_eq!(c.period_ns(), P);
+
+        // A faster panel learns its own finer grid.
+        let mut fast = LatchClock::new(120);
+        fast.note_batch(&[1_000_000_000, 1_008_333_333]);
+        assert_eq!(fast.period_ns(), 8_333_333);
+    }
+
+    /// ⭐ The live loop drains present-wait samples EVERY pass, so stamps arrive one at a
+    /// time. Measuring spacings only within a batch meant the learner observed nothing on
+    /// glass and silently ran on its seed (found on .21, 2026-08-02: `period_us` read back
+    /// exactly the 60 Hz fallback while the panel really was 60 Hz — correct by luck, and
+    /// wrong the moment the mode lies).
+    #[test]
+    fn latch_clock_learns_from_one_sample_at_a_time() {
+        const REAL: u64 = 16_666_666;
+        let mut c = LatchClock::new(120); // seeded too fast, as a refused mode switch would
+        let mut t = 1_000_000_000u64;
+        for _ in 0..(GRID_OBSERVE_EVERY * 8 + 8) {
+            t += REAL;
+            c.note_batch(&[t]); // ONE stamp per call — the live shape
+        }
+        assert_eq!(
+            c.period_ns(),
+            REAL,
+            "single-stamp batches must still feed the grid learner"
+        );
+        assert_eq!(c.anchor_ns(), t);
+    }
+
+    /// The mode's refresh is a CLAIM, not a measurement — a refused mode switch or a
+    /// compositor running its own rate leaves the seed too fast. The old downward-only
+    /// cap pinned that wrong grid for the session (the Android 0.23.0 defect); the
+    /// shared learner climbs back out once the evidence is consistent.
+    #[test]
+    fn latch_clock_recovers_from_a_seed_faster_than_the_real_panel() {
+        const REAL: u64 = 16_666_666; // the panel is really 60 Hz…
+        let mut c = LatchClock::new(120); // …but the mode claimed 120
+        assert_eq!(c.period_ns(), 8_333_333, "seeded from the claim");
+
+        // Consistent 60 Hz evidence. The grid is fed the MIN of every
+        // GRID_OBSERVE_EVERY spacings, and PanelGrid widens only after 8 agreeing
+        // observations, so a real widen needs 8 × GRID_OBSERVE_EVERY spacings — the
+        // deliberate cost of not letting one slow patch redefine the panel.
+        let mut t = 1_000_000_000u64;
+        for _ in 0..(GRID_OBSERVE_EVERY * 8 + GRID_OBSERVE_EVERY) {
+            t += REAL;
+            c.note_batch(&[t]);
+        }
+        assert_eq!(
+            c.period_ns(),
+            REAL,
+            "a sustained slower grid is adopted instead of aimed past forever"
+        );
+    }
+
+    /// The VRR discriminator: presents landing on the vblank grid read Fixed, presents
+    /// landing wherever our own cadence puts them read Variable — including the case that
+    /// matters most, a stream SLOWER than the panel, where a fixed panel still quantizes
+    /// to a larger whole multiple.
+    #[test]
+    fn cadence_probe_separates_grid_locked_from_variable() {
+        const P: u64 = 8_333_333; // 120 Hz
+                                  // Enough spacings for CADENCE_STABLE_ROUNDS full rounds: a verdict is published
+                                  // only once consecutive rounds agree (on glass a single round FLAPPED).
+        const ROUNDS: u64 = (CADENCE_MIN_SAMPLES as u64) * (CADENCE_STABLE_ROUNDS as u64) + 4;
+
+        // Fixed panel, stream at panel rate: every delta is exactly one period.
+        let mut probe = CadenceProbe::new();
+        assert_eq!(probe.verdict(), Cadence::Unknown, "no evidence yet");
+        let stamps: Vec<u64> = (0..ROUNDS).map(|i| 1_000_000_000 + i * P).collect();
+        probe.note(&stamps, P, true);
+        assert_eq!(probe.verdict(), Cadence::Fixed);
+
+        // Fixed panel, stream at HALF panel rate: deltas are 2×P — still grid-locked.
+        let mut probe = CadenceProbe::new();
+        let stamps: Vec<u64> = (0..ROUNDS).map(|i| 1_000_000_000 + i * 2 * P).collect();
+        probe.note(&stamps, P, true);
+        assert_eq!(
+            probe.verdict(),
+            Cadence::Fixed,
+            "a slower stream on a fixed panel picks a larger k, it does not leave the grid"
+        );
+
+        // Fixed panel with realistic measurement jitter (±0.5 ms on an 8.3 ms period)
+        // must not read as variable.
+        let mut probe = CadenceProbe::new();
+        let jitter = [0i64, 300_000, -250_000, 120_000, -400_000, 80_000];
+        let stamps: Vec<u64> = (0..ROUNDS as usize)
+            .map(|i| (1_000_000_000 + i as i64 * P as i64 + jitter[i % jitter.len()]) as u64)
+            .collect();
+        probe.note(&stamps, P, true);
+        assert_eq!(probe.verdict(), Cadence::Fixed, "jitter is not VRR");
+
+        // VRR live: a 100 fps stream on a 120 Hz-max panel. 10 ms is not a multiple of
+        // 8.33 ms, so every present sits off the grid.
+        let mut probe = CadenceProbe::new();
+        let stamps: Vec<u64> = (0..ROUNDS)
+            .map(|i| 1_000_000_000 + i * 10_000_000)
+            .collect();
+        probe.note(&stamps, P, true);
+        assert_eq!(probe.verdict(), Cadence::Variable);
+
+        // A display change throws the evidence away rather than carrying a stale verdict.
+        probe.reset();
+        assert_eq!(probe.verdict(), Cadence::Unknown);
+
+        // Below the sample floor nothing is claimed.
+        let mut probe = CadenceProbe::new();
+        probe.note(&[1_000_000_000, 1_010_000_000, 1_020_000_000], P, true);
+        assert_eq!(probe.verdict(), Cadence::Unknown);
+
+        // ⭐ THE SHAPE THE LIVE LOOP ACTUALLY PRODUCES: the run loop drains present-wait
+        // samples every pass, so stamps arrive ONE AT A TIME. Measuring spacings only
+        // within a batch observed nothing at all on glass — `vrr` stayed Unknown and the
+        // latch clock ran on its seed forever. Found on .21, 2026-08-02.
+        let mut probe = CadenceProbe::new();
+        for i in 0..ROUNDS {
+            probe.note(&[1_000_000_000 + i * 10_000_000], P, true); // 100 fps, off a 120 Hz grid
+        }
+        assert_eq!(
+            probe.verdict(),
+            Cadence::Variable,
+            "one-sample batches must still yield spacings"
+        );
+
+        // A period we never learned can't discriminate anything.
+        let mut probe = CadenceProbe::new();
+        let stamps: Vec<u64> = (0..ROUNDS)
+            .map(|i| 1_000_000_000 + i * 10_000_000)
+            .collect();
+        probe.note(&stamps, 0, true);
+        assert_eq!(probe.verdict(), Cadence::Unknown);
+    }
+
+    /// ⭐ Batching must not change the verdict. The same spacings delivered as one big
+    /// batch, or one stamp at a time, must reach the same conclusion — the live loop
+    /// drains one at a time while tests hand over vectors, and an evaluation keyed to
+    /// call boundaries silently made the two disagree.
+    #[test]
+    fn cadence_verdict_is_independent_of_batching() {
+        const P: u64 = 8_333_333;
+        let n = (CADENCE_MIN_SAMPLES as u64) * (CADENCE_STABLE_ROUNDS as u64) + 4;
+
+        let stamps: Vec<u64> = (0..n).map(|i| 1_000_000_000 + i * P).collect();
+        let mut bulk = CadenceProbe::new();
+        bulk.note(&stamps, P, true);
+
+        let mut drip = CadenceProbe::new();
+        for s in &stamps {
+            drip.note(&[*s], P, true);
+        }
+
+        assert_eq!(bulk.verdict(), Cadence::Fixed);
+        assert_eq!(drip.verdict(), bulk.verdict(), "batching must not matter");
+    }
+
+    /// Gate: open at zero outstanding, closed at one, force-open past the stale bound.
+    #[test]
+    fn gate_budgets_one_undisplayed_present() {
+        let mut g = PresentGate::default();
+        let t0 = 1_000_000_000u64;
+        assert!(g.open(0, t0));
+        g.note_present(t0);
+        assert!(!g.open(1, t0 + 8_000_000), "one in flight — hold");
+        assert!(
+            g.open(1, t0 + STALE_REOPEN_NS + 1),
+            "stale in-flight present force-opens"
+        );
+        let (gated, forced) = g.take_counters();
+        assert_eq!((gated, forced), (1, 1));
+        assert_eq!(g.take_counters(), (0, 0), "counters drain");
+    }
+}

crates/pf-presenter/src/run.rs

@@ -18,12 +18,15 @@
 
 use crate::input::{Capture, FingerPhase};
 use crate::overlay::{FrameCtx, Overlay, OverlayAction, OverlayFrame, SessionPhase};
+use crate::present_pace::{
+    Cadence, CadenceProbe, FrameStore, LatchClock, PresentGate, MARGIN_MAX_NS, MARGIN_STEP_NS,
+};
 use crate::touch::Abs;
 use crate::vk::{FrameInput, Presenter};
 use anyhow::{Context as _, Result};
 use pf_client_core::gamepad::GamepadService;
 use pf_client_core::session::{self, SessionEvent, SessionHandle, SessionParams, Stats};
-use pf_client_core::trust::{MouseMode, StatsVerbosity, TouchMode};
+use pf_client_core::trust::{MouseMode, PresentPriority, StatsVerbosity, TouchMode};
 use pf_client_core::video::VulkanDecodeDevice;
 use pf_client_core::video::{DecodedFrame, DecodedImage};
 use punktfunk_core::client::NativeClient;
@@ -63,6 +66,20 @@ pub struct SessionOpts {
     /// work profile that streams on a second screen and still Alt-Tabs here. Never applies
     /// under the `desktop` mouse model, which is something you Alt-Tab *away* from.
     pub inhibit_shortcuts: bool,
+    /// Presentation intent ([`Settings::present_priority`] resolved): `Latency` keeps the
+    /// shipped arrival pacing (newest-wins, present the moment a frame can go out);
+    /// `Smooth { buffer }` runs the smoothing FIFO drained one frame per latch slot
+    /// (design/desktop-presentation-rebuild.md). `PUNKTFUNK_PRESENTER=arrival` overrides
+    /// the whole engine back to the legacy drain for field A/B without a rebuild.
+    pub present_priority: PresentPriority,
+    /// Tear-free presentation ([`Settings::vsync`], default on). Off asks for a tearing
+    /// present mode for the lowest possible latch — best-effort, and the mode that
+    /// actually took is named in the stats line.
+    pub vsync: bool,
+    /// Let a variable-refresh display follow the stream cadence ([`Settings::allow_vrr`],
+    /// default on) — prefers the present mode that drives VRR panels directly when the
+    /// session starts fullscreen.
+    pub allow_vrr: bool,
     /// Emit the `{"ready":true}` stdout line after the first presented frame.
     pub json_status: bool,
     /// Called once on `Connected` with the host's fingerprint (trust persistence is the
@@ -213,8 +230,47 @@ struct StreamState {
     // capture→displayed (host-clock corrected) p50+p95, display = decoded→displayed p50.
     win_e2e_us: Vec<u64>,
     win_disp_us: Vec<u64>,
+    /// The display stage's two halves (present-timing sessions only): decoded→submit and
+    /// submit→on-glass. See [`PresentedWindow::pace_ms`].
+    win_pace_us: Vec<u64>,
+    win_latch_us: Vec<u64>,
     win_start: Instant,
     presented: PresentedWindow,
+    /// The intent engine (design/desktop-presentation-rebuild.md WP2): the decoded-frame
+    /// store between the wake channel and the present call — a newest-wins slot under
+    /// the latency intent (behaviorally the shipped drain), the smoothing FIFO under
+    /// smoothness. NOTE: a smoothing store holds decoder-pool frames (Vulkan-Video
+    /// AVFrames) up to `buffer` deep on top of the depth-2 wake channels — within pool
+    /// headroom for 1..=3, but any deeper store must revisit pool sizing.
+    store: FrameStore<DecodedFrame>,
+    /// The panel latch grid (present-wait glass stamps; submit-anchored fallback) — the
+    /// smoothness slot clock, and the values published to the host-facing `latch_grid`.
+    clock: LatchClock,
+    /// The FIFO glass budget (one undisplayed present in flight) — inert off FIFO modes
+    /// or without present timing.
+    gate: PresentGate,
+    /// Is variable refresh actually live? Measured from the same on-glass stamps (no
+    /// portable query exists) — see [`CadenceProbe`].
+    cadence: CadenceProbe,
+    /// The DISPLAY MODE's refresh period — the vblank grid presents quantize to when
+    /// VRR is off, and so the cadence probe's reference. Deliberately not the learned
+    /// period (see the probe's call site).
+    mode_period_ns: u64,
+    /// The latch slot the last smoothness present served (one present per slot); 0 =
+    /// none yet.
+    last_target_ns: u64,
+    /// Smoothness slot-pick margin: starts 0 (a fixed lead is pure display tax —
+    /// measured on Android), widens +500 µs per >2-miss window toward 2.5 ms.
+    margin_ns: u64,
+    /// This window's latch misses (a present that reached glass > 1.5 latch periods
+    /// after submit) — the adaptive margin's error signal.
+    win_misses: u32,
+    /// This window's peak undisplayed-presents-in-flight (present timing only).
+    win_out_max: usize,
+    /// One-shot log latch: smoothness was requested but a PyroWave stream collapsed the
+    /// store to latency (its plane-ring retirement assumes the newest-wins hand-off).
+    #[cfg(all(any(target_os = "linux", windows), feature = "pyrowave"))]
+    pyro_latency_forced: bool,
     // Hardware-path health: a failure streak (or a device with no import support at
     // all) demotes the decoder to software via the shared flag — once per session.
     dmabuf_demoted: bool,
@@ -279,6 +335,8 @@ impl StreamState {
         params: SessionParams,
         force_software: Arc<AtomicBool>,
         wake: sdl3::event::EventSender,
+        priority: PresentPriority,
+        native_refresh_hz: u32,
     ) -> StreamState {
         let profile = params.profile.clone();
         // The presenter's half of phase-locked capture: it writes the latch grid the
@@ -316,8 +374,21 @@ impl StreamState {
             hdr_untonemapped: false,
             win_e2e_us: Vec::with_capacity(256),
             win_disp_us: Vec::with_capacity(256),
+            win_pace_us: Vec::with_capacity(256),
+            win_latch_us: Vec::with_capacity(256),
             win_start: Instant::now(),
             presented: PresentedWindow::default(),
+            store: FrameStore::new(usize::from(priority.fifo_capacity())),
+            clock: LatchClock::new(native_refresh_hz),
+            gate: PresentGate::default(),
+            cadence: CadenceProbe::new(),
+            mode_period_ns: 1_000_000_000 / u64::from(native_refresh_hz.max(1)),
+            last_target_ns: 0,
+            margin_ns: 0,
+            win_misses: 0,
+            win_out_max: 0,
+            #[cfg(all(any(target_os = "linux", windows), feature = "pyrowave"))]
+            pyro_latency_forced: false,
             dmabuf_demoted: false,
             #[cfg(all(any(target_os = "linux", windows), feature = "pyrowave"))]
             pyro_present_warned: false,
@@ -356,6 +427,25 @@ impl StreamState {
         }
         self.handle.stop.store(true, Ordering::SeqCst);
     }
+
+    /// The event-loop wait bound: a smoothness stream with buffered frames sleeps only
+    /// to its next latch-slot deadline; everything else keeps the 15 ms housekeeping
+    /// tick (frames, input, and present completions all wake the loop early anyway).
+    fn wake_timeout(&self) -> Duration {
+        const TICK: Duration = Duration::from_millis(15);
+        if !self.store.is_smoothing() || self.store.is_empty() {
+            return TICK;
+        }
+        let now = session::now_ns();
+        let mut target = self
+            .clock
+            .next_slot_after(now.saturating_add(self.margin_ns));
+        if target == self.last_target_ns {
+            // This slot is already served — the next boundary is the deadline.
+            target += self.clock.period_ns();
+        }
+        Duration::from_nanos(target.saturating_sub(now)).clamp(Duration::from_millis(1), TICK)
+    }
 }
 
 /// Whether a present error is `VK_ERROR_DEVICE_LOST` anywhere in its chain. A lost
@@ -438,9 +528,43 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
     let instance_exts = window
         .vulkan_instance_extensions()
         .map_err(|e| anyhow::anyhow!("vulkan instance extensions: {e}"))?;
-    let mut presenter = Presenter::new(&window, &instance_exts).context("vulkan presenter")?;
+    let mut presenter = Presenter::new(
+        &window,
+        &instance_exts,
+        crate::vk::PresentPref {
+            vsync: opts.vsync,
+            allow_vrr: opts.allow_vrr,
+            fullscreen: opts.fullscreen,
+            // `vrr_fifo_opt_in` (env) and `fifo_latest_ready` (device capability) are
+            // both resolved inside `Presenter::new` — the swapchain owns those, so every
+            // caller gets the same answer. `..Default` keeps this site from breaking each
+            // time the struct learns another one.
+            ..Default::default()
+        },
+    )
+    .context("vulkan presenter")?;
     // A valid black frame immediately — the window is honest while the connect runs.
     presenter.present(&window, FrameInput::Redraw, None)?;
+
+    // `PUNKTFUNK_PRESENTER=arrival` — the legacy drain, the intent engine's field-A/B
+    // kill switch (the Android sysprop pattern: no rebuild to bisect a pacing suspicion).
+    let arrival_override = std::env::var("PUNKTFUNK_PRESENTER").ok().as_deref() == Some("arrival");
+    let present_priority = if arrival_override {
+        tracing::info!("PUNKTFUNK_PRESENTER=arrival — presentation pacing disabled");
+        PresentPriority::Latency
+    } else {
+        opts.present_priority
+    };
+    let pacing_active = !arrival_override;
+    let present_debug = std::env::var_os("PUNKTFUNK_PRESENT_DEBUG").is_some();
+    // Present completions wake the loop exactly like decoded frames: a glass-gate
+    // reopen or a smoothness slot must not wait out the event timeout.
+    {
+        let sender = events.event_sender();
+        presenter.set_present_wake(Box::new(move || {
+            let _ = sender.push_custom_event(FrameWake);
+        }));
+    }
     // Browse mode is "ready" the moment the library window presents — there may never be
     // a stream. (Single mode announces on the first VIDEO frame instead, further down, so
     // a shell only yields to a window that actually shows the stream.)
@@ -517,6 +641,8 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                 params,
                 force_software,
                 events.event_sender(),
+                present_priority,
+                native.refresh_hz,
             ))
         }
         ModeCtl::Browse(_) => None,
@@ -544,8 +670,11 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
         // forwarder's FrameWake) all land in this one queue, so the loop wakes exactly
         // when there is work — a short-timeout poll here burned a full core (measured;
         // the timeout only bounds stop-flag/pump-tick latency now). In browse-idle the
-        // per-iteration FIFO present vsync-throttles the loop anyway.
-        let timeout = Duration::from_millis(15);
+        // per-iteration FIFO present vsync-throttles the loop anyway. A smoothness
+        // stream tightens the bound to its next latch-slot deadline.
+        let timeout = stream
+            .as_ref()
+            .map_or(Duration::from_millis(15), |st| st.wake_timeout());
         let first = event_pump.wait_event_timeout(timeout);
         let mut queued: Vec<Event> = Vec::new();
         if let Some(e) = first {
@@ -608,6 +737,29 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                             }
                         }
                     }
+                    // Dragged to another monitor (or the mode changed under us): the
+                    // latch grid and the VRR verdict both belong to the OLD panel. The
+                    // refresh rate used to be read once at startup and never revisited,
+                    // so a 60 Hz-seeded clock would keep pacing a 144 Hz panel.
+                    WindowEvent::DisplayChanged(..) => {
+                        let hz = window
+                            .get_display()
+                            .and_then(|d| d.get_mode())
+                            .map(|m| m.refresh_rate.round().max(0.0) as u32)
+                            .unwrap_or(0);
+                        if let Some(st) = stream.as_mut() {
+                            if hz > 0 {
+                                st.clock = LatchClock::new(hz);
+                                st.mode_period_ns = 1_000_000_000 / u64::from(hz);
+                            }
+                            st.cadence.reset();
+                            st.last_target_ns = 0;
+                            tracing::info!(
+                                refresh_hz = hz,
+                                "display changed — relearning the latch grid"
+                            );
+                        }
+                    }
                     WindowEvent::Exposed => {
                         presenter.present(&window, FrameInput::Redraw, overlay_frame.as_ref())?;
                     }
@@ -1032,6 +1184,8 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                                     *params,
                                     force_software,
                                     events.event_sender(),
+                                    present_priority,
+                                    native.refresh_hz,
                                 ));
                                 if let Some(o) = overlay.as_mut() {
                                     o.session_phase(SessionPhase::Connecting);
@@ -1279,11 +1433,148 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                     presenter.set_hdr_metadata(m);
                 }
             }
-            let mut newest: Option<DecodedFrame> = None;
-            while let Ok(f) = st.frames.try_recv() {
-                newest = Some(f);
+            // Present-wait completions drive the latch clock, the glass gate, and the
+            // host-facing grid — drained every pass (a 1 Hz batch would starve all
+            // three; the waiter's SDL wake pairs with this so completions never wait
+            // out the event timeout).
+            if presenter.present_timing_active() {
+                let samples = presenter.take_presented_samples();
+                if !samples.is_empty() {
+                    let clock_offset_ns = st
+                        .clock_offset
+                        .as_ref()
+                        .map_or(0, |o| o.load(Ordering::Relaxed));
+                    let period = st.clock.period_ns();
+                    let mut stamps = Vec::with_capacity(samples.len());
+                    for s in &samples {
+                        let e2e = (s.displayed_ns as i128 + clock_offset_ns as i128
+                            - s.pts_ns as i128)
+                            .max(0) as u64;
+                        if e2e > 0 && e2e < 10_000_000_000 {
+                            st.win_e2e_us.push(e2e / 1000);
+                        }
+                        st.win_disp_us
+                            .push(s.displayed_ns.saturating_sub(s.decoded_ns) / 1000);
+                        // The display split (WP4): our pipeline vs the vsync latch. Only
+                        // meaningful with true glass stamps, which is exactly when this
+                        // branch runs.
+                        st.win_pace_us
+                            .push(s.submitted_ns.saturating_sub(s.decoded_ns) / 1000);
+                        st.win_latch_us
+                            .push(s.displayed_ns.saturating_sub(s.submitted_ns) / 1000);
+                        // Latch miss (the adaptive margin's error signal): glass later
+                        // than one panel period past submit, PLUS the lead we already
+                        // applied — i.e. the slot we aimed at was missed. Measuring the
+                        // real latch rather than the store's own evictions is the
+                        // Android 0.23.0 correction: policy drops happen whenever the
+                        // stream out-runs the panel and say nothing about the latch, and
+                        // widening on them walked the margin to its ceiling on healthy
+                        // devices, re-imposing the very display latency it had removed.
+                        if st.store.is_smoothing()
+                            && s.displayed_ns.saturating_sub(s.submitted_ns) > period + st.margin_ns
+                        {
+                            st.win_misses += 1;
+                        }
+                        stamps.push(s.displayed_ns);
+                    }
+                    st.clock.note_batch(&stamps);
+                    // Same stamps answer "is VRR live" — the panel either quantizes them
+                    // to its grid or follows our cadence. Evidence only counts from a
+                    // window whose presents were flowing normally: a distressed pipeline
+                    // (stale force-opens) smears spacings for reasons that have nothing
+                    // to do with the panel, and on glass that flapped the verdict.
+                    //
+                    // ⚠ The reference is the DISPLAY MODE's period, NOT the learned one.
+                    // The learned grid comes from our own present spacings, and a stream
+                    // running below panel rate only ever produces multiples ≥ its frame
+                    // interval — so the learner adopts our cadence as "the grid" and every
+                    // delta then looks on-grid by construction. Measured on .21
+                    // (2026-08-02): a 40-50 fps stream on a 60 Hz panel learned 18-22 ms
+                    // and the probe reported VRR on a display with VRR provably disabled.
+                    // The vblank grid is the mode's refresh; that is what presents
+                    // quantize to when VRR is off.
+                    //
+                    // ⚠⚠ And it is only asked under a FIFO-family mode. The whole test
+                    // rests on "with VRR off, a present waits for vblank" — MAILBOX and
+                    // IMMEDIATE deliberately break that, so their stamps are never
+                    // grid-quantized and the probe would call every mailbox session VRR.
+                    // Measured on .21: same panel, same second — fifo read `no`
+                    // (correct, period 16.56 ms), mailbox read `yes` (wrong). Outside
+                    // FIFO the honest answer is "cannot tell", i.e. Unknown.
+                    let healthy = st.presented.forced == 0;
+                    if presenter.vblank_locked() {
+                        st.cadence.note(&stamps, st.mode_period_ns, healthy);
+                    }
+                    // Phase-locked capture, the presenter's half: publish the grid the
+                    // local clock just learned — a recent TRUE on-glass instant plus
+                    // the latch period — for the pump's ~1 Hz PhaseReport. One learner
+                    // feeds both, so the report and the scheduler cannot disagree.
+                    if let Some(grid) = &st.latch_grid {
+                        grid.period_ns
+                            .store(st.clock.period_ns(), Ordering::Relaxed);
+                        grid.anchor_ns
+                            .store(st.clock.anchor_ns(), Ordering::Relaxed);
+                    }
+                }
             }
-            if let Some(f) = newest {
+
+            // Intake into the intent store: a newest-wins slot under latency (the
+            // shipped drain, now with displacement counters), the smoothing FIFO under
+            // smoothness. PyroWave collapses smoothness to latency for the stream: its
+            // plane-ring retirement accounting assumes the newest-wins hand-off
+            // (`video_pyrowave::RETIRE_HANDOVERS`), and all-intra frames make
+            // buffering moot anyway.
+            while let Ok(f) = st.frames.try_recv() {
+                #[cfg(all(any(target_os = "linux", windows), feature = "pyrowave"))]
+                if st.store.is_smoothing() && matches!(f.image, DecodedImage::PyroWave(_)) {
+                    st.store.force_latency();
+                    if !st.pyro_latency_forced {
+                        st.pyro_latency_forced = true;
+                        tracing::info!(
+                            "PyroWave stream — smoothness buffering does not apply \
+                             (latency pacing)"
+                        );
+                    }
+                }
+                st.store.submit(f);
+            }
+
+            // One frame out, by intent: latency takes the newest whenever the glass
+            // gate allows; smoothness serves at most one frame per latch slot (the
+            // preroll/underflow behavior lives in the store).
+            let now_ns = session::now_ns();
+            let mut slot_target = 0u64;
+            let mut to_present = if st.store.is_smoothing() {
+                let target = st
+                    .clock
+                    .next_slot_after(now_ns.saturating_add(st.margin_ns));
+                if target != st.last_target_ns {
+                    slot_target = target;
+                    st.store.take()
+                } else {
+                    None
+                }
+            } else {
+                st.store.take()
+            };
+            // The FIFO glass budget: one undisplayed present in flight, so the
+            // swapchain's own FIFO can never become a standing queue (a measured
+            // 11-13 ms at 60 Hz on MAILBOX-less drivers). Only FIFO modes queue and
+            // only present timing can count, so everywhere else this stays inert and
+            // behavior is the shipped arrival pacing.
+            if pacing_active && presenter.needs_glass_gate() && presenter.present_timing_active() {
+                if let Some(f) = to_present.take() {
+                    if st.gate.open(presenter.presents_outstanding(), now_ns) {
+                        to_present = Some(f);
+                    } else {
+                        // Parked: a newest-wins store replaces it if a fresher frame
+                        // lands; the waiter's wake (or the 100 ms stale force-open)
+                        // retries.
+                        st.store.put_back(f);
+                    }
+                }
+            }
+            if let Some(f) = to_present {
                 // Resize END: a frame at the steered target size means the sharp new-mode
                 // picture is here — lift the scrim. A no-op unless a switch is in flight.
                 let (fw, fh) = f.image.dimensions();
@@ -1472,6 +1763,12 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                 };
                 if did_present {
                     presented_video = true;
+                    // Smoothness: this latch slot is served — one present per slot.
+                    // (Set only on success: a gated or failed present leaves the slot
+                    // open for the retry.)
+                    if slot_target != 0 {
+                        st.last_target_ns = slot_target;
+                    }
                     if opts.json_status && !st.ready_announced {
                         st.ready_announced = true;
                         println!("{{\"ready\":true}}");
@@ -1481,6 +1778,8 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                         // e2e/display samples arrive via `take_presented_samples` with a
                         // TRUE on-glass stamp instead of the submit-time one below.
                         presenter.note_presented(pts_ns, decoded_ns);
+                        st.gate.note_present(now_ns);
+                        st.win_out_max = st.win_out_max.max(presenter.presents_outstanding());
                     } else {
                         let displayed_ns = session::now_ns();
                         // The `displayed` stamp (same clamp rules as the pump's windows).
@@ -1495,59 +1794,81 @@ fn run_inner(mut opts: SessionOpts, mut mode: ModeCtl) -> Result<Option<Outcome>
                         }
                         st.win_disp_us
                             .push(displayed_ns.saturating_sub(decoded_ns) / 1000);
+                        // No glass stamps on this stack: the submit instant anchors an
+                        // approximate grid on the mode's refresh period, so smoothness
+                        // still drains one frame per (approximate) slot.
+                        st.clock.note_batch(&[displayed_ns]);
                     }
                 }
             }
 
             // Fold the presenter window into the shared stats line once per second.
+            // (The on-glass samples themselves are drained every pass above — they
+            // drive the latch clock and glass gate, not just this fold.)
             if st.win_start.elapsed() >= Duration::from_secs(1) {
-                // On-glass samples the present-wait waiter completed this window (empty
-                // when timing is inactive — the legacy submit-time pushes fill in then).
-                let clock_offset_ns = st
-                    .clock_offset
-                    .as_ref()
-                    .map_or(0, |o| o.load(Ordering::Relaxed));
-                let samples = presenter.take_presented_samples();
-                // Phase-locked capture, the presenter's half: publish this window's latch
-                // grid — a recent TRUE on-glass instant plus the panel period — for the
-                // pump's ~1 Hz PhaseReport. The period is the min positive spacing of
-                // consecutive on-glass stamps (Apple's method: honest under VRR), capped
-                // by the display mode's refresh — under arrival-paced MAILBOX a stream
-                // running below the panel rate spaces its presents at k×period, and the
-                // cap keeps a 30 fps stream from claiming a 30 Hz panel grid.
-                if let Some(grid) = &st.latch_grid {
-                    if let Some(last) = samples.last() {
-                        let refresh_period = 1_000_000_000u64 / u64::from(native.refresh_hz.max(1));
-                        let min_delta = samples
-                            .windows(2)
-                            .map(|w| w[1].displayed_ns.saturating_sub(w[0].displayed_ns))
-                            .filter(|&d| d > 1_000_000) // < 1 ms apart = queued pair, not a grid step
-                            .min()
-                            .unwrap_or(refresh_period);
-                        grid.period_ns
-                            .store(min_delta.min(refresh_period), Ordering::Relaxed);
-                        grid.anchor_ns.store(last.displayed_ns, Ordering::Relaxed);
-                    }
-                }
-                for s in samples {
-                    let e2e = (s.displayed_ns as i128 + clock_offset_ns as i128 - s.pts_ns as i128)
-                        .max(0) as u64;
-                    if e2e > 0 && e2e < 10_000_000_000 {
-                        st.win_e2e_us.push(e2e / 1000);
-                    }
-                    st.win_disp_us
-                        .push(s.displayed_ns.saturating_sub(s.decoded_ns) / 1000);
-                }
                 let (e2e_p50, e2e_p95) = session::window_percentiles(&mut st.win_e2e_us);
                 let (disp_p50, _) = session::window_percentiles(&mut st.win_disp_us);
+                let (pace_p50, _) = session::window_percentiles(&mut st.win_pace_us);
+                let (latch_p50, _) = session::window_percentiles(&mut st.win_latch_us);
+                // Drained ONCE per window and shared by the HUD and the log line below —
+                // a second `take_counters` would read zeros.
+                let (replaced, q_drop, q_dry) = st.store.take_counters();
+                let (gated, forced) = st.gate.take_counters();
                 st.presented = PresentedWindow {
                     e2e_p50_ms: e2e_p50 as f32 / 1000.0,
                     e2e_p95_ms: e2e_p95 as f32 / 1000.0,
                     display_ms: disp_p50 as f32 / 1000.0,
+                    pace_ms: pace_p50 as f32 / 1000.0,
+                    latch_ms: latch_p50 as f32 / 1000.0,
+                    mode: presenter.present_mode_name(),
+                    vrr: st.cadence.verdict(),
+                    smoothing: st.store.is_smoothing(),
+                    q_drop,
+                    q_dry,
+                    gated,
+                    forced,
                 };
                 st.win_e2e_us.clear();
                 st.win_disp_us.clear();
+                st.win_pace_us.clear();
+                st.win_latch_us.clear();
                 st.win_start = Instant::now();
+                // Adaptive slot margin (the Android presenter's measured recipe):
+                // start at 0 — a fixed lead is pure display tax — and widen one step
+                // per window whose measured latch misses demand it. One-way per
+                // stream; the next stream restarts at 0.
+                if st.store.is_smoothing() && st.win_misses > 2 && st.margin_ns < MARGIN_MAX_NS {
+                    st.margin_ns = (st.margin_ns + MARGIN_STEP_NS).min(MARGIN_MAX_NS);
+                    tracing::info!(
+                        margin_us = st.margin_ns / 1000,
+                        misses = st.win_misses,
+                        "smoothness slot margin widened (measured latch misses)"
+                    );
+                }
+                // The 1 Hz presenter line (the Apple `pf-present` analogue): emitted
+                // when anything moved, or always under PUNKTFUNK_PRESENT_DEBUG=1 —
+                // the field-triage instrument for the intent engine.
+                if pacing_active && (present_debug || q_drop + q_dry + gated + forced > 0) {
+                    tracing::info!(
+                        smoothing = st.presented.smoothing,
+                        mode = st.presented.mode,
+                        vrr = st.presented.vrr.label(),
+                        replaced,
+                        q_drop,
+                        q_dry,
+                        gated,
+                        forced,
+                        misses = st.win_misses,
+                        out_max = st.win_out_max,
+                        pace_ms = st.presented.pace_ms,
+                        latch_ms = st.presented.latch_ms,
+                        period_us = st.clock.period_ns() / 1000,
+                        margin_us = st.margin_ns / 1000,
+                        "presenter window"
+                    );
+                }
+                st.win_misses = 0;
+                st.win_out_max = 0;
             }
         }
 
@@ -2007,6 +2328,32 @@ struct PresentedWindow {
     e2e_p50_ms: f32,
     e2e_p95_ms: f32,
     display_ms: f32,
+    /// The display stage split (design/desktop-presentation-rebuild.md WP4):
+    /// `pace` = decoded → present-submit (our own pipeline), `latch` = submit → on-glass
+    /// (the presentation engine's queue + the vblank wait). Both `0` without
+    /// `VK_KHR_present_wait`, where the two are not separable — the HUD then shows the
+    /// unsplit figure rather than inventing a zero latch.
+    ///
+    /// This split is what makes a high `display` self-diagnosing: latch dominating means
+    /// the vsync/queue floor (or a standing queue), pace dominating means us.
+    /// `pace` is also the honest cross-platform twin of the Apple client's shaved
+    /// number — Apple subtracts its measured OS present floor, and the latch IS our
+    /// floor, so `pace` is what remains on both sides of that comparison.
+    pace_ms: f32,
+    latch_ms: f32,
+    /// The live swapchain present mode (`mailbox`/`fifo`/…). Shown because a mode is
+    /// chosen from what the surface offers, so "why is my latch a refresh long" is
+    /// usually answered by a MAILBOX request having landed on FIFO.
+    mode: &'static str,
+    /// Whether variable refresh is measurably live (never claimed without evidence).
+    vrr: Cadence,
+    /// Presenter-engine counters for the window: the smoothing FIFO's overflow drops and
+    /// post-preroll underflows, and the FIFO glass gate's holds/stale force-opens.
+    smoothing: bool,
+    q_drop: u32,
+    q_dry: u32,
+    gated: u32,
+    forced: u32,
 }
 
 /// The capture hints (`ui_stream` parity — the words the user reads while released).
@@ -2112,6 +2459,15 @@ fn stats_text(
             " · decode {:.1} · display {:.1} ms",
             s.decode_ms, p.display_ms
         ));
+        // The display split (WP4). Only with true on-glass stamps — without them the
+        // two halves are not separable and the unsplit figure stands alone rather than
+        // implying a zero latch.
+        if p.latch_ms > 0.0 || p.pace_ms > 0.0 {
+            text.push_str(&format!(
+                " (pace {:.1} + latch {:.1})",
+                p.pace_ms, p.latch_ms
+            ));
+        }
         // Extended 0xCF host-stage split (T0.1): its own line so the per-stage attribution
         // (queue → encode → seal/xfer → pace) reads as the host pipeline in order.
         if s.staged {
@@ -2120,6 +2476,32 @@ fn stats_text(
                 s.host_queue_ms, s.host_encode_ms, s.host_xfer_ms, s.host_pace_ms
             ));
         }
+        // The presenter line: the swapchain mode that is actually live, the chosen
+        // intent, and the engine's own counters. Present-mode alone answers most
+        // "why is my latch a whole refresh" questions; the counters only render when
+        // they are non-zero, so a healthy latency session shows just the mode.
+        if !p.mode.is_empty() {
+            text.push_str(&format!("\npresent: {}", p.mode));
+            // Only once measured — an unproven "vrr no" would be a claim, not a reading.
+            if p.vrr != Cadence::Unknown {
+                text.push_str(&format!(" · vrr {}", p.vrr.label()));
+            }
+            if p.smoothing {
+                text.push_str(" · smoothing");
+            }
+            if p.q_drop > 0 {
+                text.push_str(&format!(" · qdrop {}", p.q_drop));
+            }
+            if p.q_dry > 0 {
+                text.push_str(&format!(" · qdry {}", p.q_dry));
+            }
+            if p.gated > 0 {
+                text.push_str(&format!(" · gated {}", p.gated));
+            }
+            if p.forced > 0 {
+                text.push_str(&format!(" · forced {}", p.forced));
+            }
+        }
     }
     if s.lost > 0 {
         text.push_str(&format!("\nlost {} ({:.1}%)", s.lost, s.lost_pct));
@@ -2393,6 +2775,7 @@ mod tests {
                 e2e_p50_ms: 6.4,
                 e2e_p95_ms: 9.1,
                 display_ms: 1.1,
+                ..Default::default()
             },
         )
     }
@@ -2430,6 +2813,70 @@ mod tests {
             !normal.contains("queue"),
             "host-stage split is Detailed-only"
         );
+        assert!(
+            !detailed.contains("pace 1.1"),
+            "no glass stamps in this sample — the display stage stays unsplit"
+        );
+    }
+
+    /// WP4: with true on-glass stamps the display stage reads as its two halves, the
+    /// live present mode is named, and the engine counters render only when non-zero —
+    /// so a healthy latency session shows the mode and nothing else. Without glass
+    /// stamps (no `VK_KHR_present_wait`) the split is absent rather than a zero latch.
+    #[test]
+    fn detailed_splits_display_into_pace_and_latch() {
+        let (s, mut p) = sample();
+        p.display_ms = 12.4;
+        p.pace_ms = 1.1;
+        p.latch_ms = 11.3;
+        p.mode = "fifo";
+        let split = stats_text(
+            StatsVerbosity::Detailed,
+            "m",
+            &s,
+            &p,
+            false,
+            false,
+            false,
+            None,
+        );
+        assert!(split.contains("display 12.4 ms (pace 1.1 + latch 11.3)"));
+        assert!(split.contains("\npresent: fifo"));
+        assert!(
+            !split.contains("qdrop") && !split.contains("gated") && !split.contains("smoothing"),
+            "quiet counters stay off the HUD: {split}"
+        );
+
+        // The smoothing FIFO and the glass gate surface once they actually do something.
+        p.smoothing = true;
+        p.q_drop = 2;
+        p.q_dry = 1;
+        p.gated = 7;
+        p.forced = 1;
+        let busy = stats_text(
+            StatsVerbosity::Detailed,
+            "m",
+            &s,
+            &p,
+            false,
+            false,
+            false,
+            None,
+        );
+        assert!(busy.contains("present: fifo · smoothing · qdrop 2 · qdry 1 · gated 7 · forced 1"));
+
+        // A tier below Detailed never carries any of it.
+        let normal = stats_text(
+            StatsVerbosity::Normal,
+            "m",
+            &s,
+            &p,
+            false,
+            false,
+            false,
+            None,
+        );
+        assert!(!normal.contains("present:") && !normal.contains("pace"));
     }
 
     /// The honest HDR badges: a PQ stream on the software-decode lane is shown WITHOUT

crates/pf-presenter/src/vk/mod.rs

@@ -33,7 +33,7 @@ mod reconfig;
 mod resources;
 mod setup;
 
-pub use setup::list_adapters;
+pub use setup::{list_adapters, PresentPref};
 
 /// One presenter iteration's video input.
 pub enum FrameInput<'a> {
@@ -247,10 +247,75 @@ impl Presenter {
     /// (the presenter itself never sees them). No-op when timing is inactive.
     pub(crate) fn note_presented(&mut self, pts_ns: u64, decoded_ns: u64) {
         if let (Some(t), Some((sc, id))) = (&self.present_timer, self.last_presented.take()) {
-            t.enqueue(sc, id, pts_ns, decoded_ns);
+            // The submit stamp: `present()` already returned, so "now" is within the
+            // present-call tail — the pace/latch split point.
+            t.enqueue(
+                sc,
+                id,
+                pts_ns,
+                decoded_ns,
+                pf_client_core::session::now_ns(),
+            );
         }
     }
 
+    /// Undisplayed id-carrying presents in flight (0 when timing is inactive) — the
+    /// FIFO glass gate's budget count.
+    pub(crate) fn presents_outstanding(&self) -> usize {
+        self.present_timer.as_ref().map_or(0, |t| t.outstanding())
+    }
+
+    /// Install the run loop's wake for present completions (an SDL event push). No-op
+    /// without present timing — there is nothing to wake on then.
+    pub(crate) fn set_present_wake(&self, cb: Box<dyn Fn() + Send>) {
+        if let Some(t) = &self.present_timer {
+            t.set_wake(cb);
+        }
+    }
+
+    /// The live swapchain present mode, for the stats overlay: a mode is picked from
+    /// what the surface actually offers, so the requested one and this can differ (a
+    /// MAILBOX request lands on FIFO wherever the driver has no mailbox — AMD's Windows
+    /// driver, notably). Showing it is what makes that visible instead of puzzling.
+    pub(crate) fn present_mode_name(&self) -> &'static str {
+        match self.present_mode {
+            vk::PresentModeKHR::MAILBOX => "mailbox",
+            vk::PresentModeKHR::FIFO => "fifo",
+            vk::PresentModeKHR::FIFO_RELAXED => "fifo-relaxed",
+            vk::PresentModeKHR::IMMEDIATE => "immediate",
+            setup::fifo_latest_ready::MODE => "fifo-latest-ready",
+            _ => "other",
+        }
+    }
+
+    /// The active present mode QUEUES presents — the only modes where the swapchain
+    /// itself can become a standing queue, and so the only ones the glass gate governs.
+    ///
+    /// MAILBOX and IMMEDIATE replace/flip and never queue. Nor does
+    /// `FIFO_LATEST_READY`, which retires stale images in the driver: gating on top of it
+    /// would hold frames back to emulate something the presentation engine is already
+    /// doing, paying the serialisation twice.
+    pub(crate) fn needs_glass_gate(&self) -> bool {
+        matches!(
+            self.present_mode,
+            vk::PresentModeKHR::FIFO | vk::PresentModeKHR::FIFO_RELAXED
+        )
+    }
+
+    /// The active present mode shows images ON THE VBLANK GRID — the premise the VRR
+    /// cadence probe rests on ("with VRR off, a present waits for vblank"). The whole
+    /// FIFO family qualifies, `FIFO_LATEST_READY` included: it drops stale images but
+    /// still presents on the refresh boundary. MAILBOX/IMMEDIATE do not, and under them
+    /// the probe reports Unknown rather than calling every session VRR.
+    pub(crate) fn vblank_locked(&self) -> bool {
+        matches!(
+            self.present_mode,
+            vk::PresentModeKHR::FIFO
+                | vk::PresentModeKHR::FIFO_RELAXED
+                | setup::fifo_latest_ready::MODE
+        )
+    }
+
     /// Take the window's completed on-glass samples (empty when timing is inactive).
     pub(crate) fn take_presented_samples(&self) -> Vec<present_timing::PresentedSample> {
         self.present_timer

crates/pf-presenter/src/vk/present_timing.rs

@@ -26,6 +26,9 @@ pub(crate) struct PresentedSample {
     pub pts_ns: u64,
     /// Decode-complete stamp (client clock) — the display-stage anchor.
     pub decoded_ns: u64,
+    /// `vkQueuePresentKHR`-return stamp (client clock) — the pace/latch split point:
+    /// `submitted − decoded` is our pipeline, `displayed − submitted` the vsync latch.
+    pub submitted_ns: u64,
     /// `vkWaitForPresentKHR` completion = the image is visible (client clock).
     pub displayed_ns: u64,
 }
@@ -35,15 +38,24 @@ struct Job {
     present_id: u64,
     pts_ns: u64,
     decoded_ns: u64,
+    submitted_ns: u64,
 }
 
+/// The run loop's wake callback (an SDL event push), shared with the waiter thread.
+type WakeSlot = Arc<Mutex<Option<Box<dyn Fn() + Send>>>>;
+
 /// The waiter: a channel-fed thread turning (swapchain, present-id) pairs into
 /// [`PresentedSample`]s. One frame in flight upstream keeps the queue depth ~1.
 pub(crate) struct PresentTimer {
     tx: Option<mpsc::Sender<Job>>,
-    /// Jobs enqueued but not yet finished — the drain barrier for swapchain teardown.
+    /// Jobs enqueued but not yet finished — the drain barrier for swapchain teardown,
+    /// and the glass gate's "undisplayed presents in flight" count.
     pending: Arc<AtomicUsize>,
     results: Arc<Mutex<Vec<PresentedSample>>>,
+    /// Called by the waiter after each completed wait (sample or not) — the run loop
+    /// installs an SDL wake here so a gate reopen / smoothness slot never waits out the
+    /// event-loop timeout.
+    wake: WakeSlot,
     join: Option<std::thread::JoinHandle<()>>,
 }
 
@@ -52,7 +64,8 @@ impl PresentTimer {
         let (tx, rx) = mpsc::channel::<Job>();
         let pending = Arc::new(AtomicUsize::new(0));
         let results = Arc::new(Mutex::new(Vec::with_capacity(256)));
-        let (pending_t, results_t) = (pending.clone(), results.clone());
+        let wake: WakeSlot = Arc::new(Mutex::new(None));
+        let (pending_t, results_t, wake_t) = (pending.clone(), results.clone(), wake.clone());
         let join = std::thread::Builder::new()
             .name("pf-present-wait".into())
             .spawn(move || {
@@ -69,12 +82,20 @@ impl PresentTimer {
                         results_t.lock().unwrap().push(PresentedSample {
                             pts_ns: job.pts_ns,
                             decoded_ns: job.decoded_ns,
+                            submitted_ns: job.submitted_ns,
                             displayed_ns,
                         });
                     }
                     // SUBOPTIMAL/TIMEOUT/DEVICE_LOST: no sample; the frame still showed
                     // (or the loop is about to find out) — never poison the window.
                     pending_t.fetch_sub(1, Ordering::AcqRel);
+                    // Wake the run loop AFTER the count dropped: what it observes on
+                    // wake is the post-completion state (the gate may now be open).
+                    // Called under the slot lock — the callback is a bare SDL event
+                    // push and never reenters this type.
+                    if let Some(cb) = wake_t.lock().unwrap().as_ref() {
+                        cb();
+                    }
                 }
             })
             .expect("spawn pf-present-wait");
@@ -82,10 +103,23 @@ impl PresentTimer {
             tx: Some(tx),
             pending,
             results,
+            wake,
             join: Some(join),
         }
     }
 
+    /// Install the run loop's wake callback (an SDL event push — thread-safe by design).
+    pub(crate) fn set_wake(&self, cb: Box<dyn Fn() + Send>) {
+        *self.wake.lock().unwrap() = Some(cb);
+    }
+
+    /// Presents handed to the waiter and not yet resolved to glass — the glass gate's
+    /// budget count. (Also counts a wait that will end SUBOPTIMAL/TIMEOUT; those resolve
+    /// within the 250 ms cap, far past the gate's own 100 ms stale force-open.)
+    pub(crate) fn outstanding(&self) -> usize {
+        self.pending.load(Ordering::Acquire)
+    }
+
     /// Hand a successfully submitted present to the waiter.
     pub(crate) fn enqueue(
         &self,
@@ -93,6 +127,7 @@ impl PresentTimer {
         present_id: u64,
         pts_ns: u64,
         decoded_ns: u64,
+        submitted_ns: u64,
     ) {
         if let Some(tx) = &self.tx {
             self.pending.fetch_add(1, Ordering::AcqRel);
@@ -102,6 +137,7 @@ impl PresentTimer {
                     present_id,
                     pts_ns,
                     decoded_ns,
+                    submitted_ns,
                 })
                 .is_err()
             {

crates/pf-presenter/src/vk/setup.rs

@@ -13,10 +13,55 @@ use ash::vk;
 use ash::vk::Handle as _;
 use std::ffi::{c_char, CString};
 
+/// `VK_EXT_present_mode_fifo_latest_ready`, hand-declared: it postdates the Vulkan headers
+/// ash 0.38 is generated from (1.3.281), so there is no binding for it — which is also why
+/// an unenabled driver reports the mode back as the bare number `1000361000`.
+///
+/// The mode is FIFO's tear-free vblank pacing that presents the **latest ready** image at
+/// each refresh and retires the older ones, instead of draining a queue. That is precisely
+/// what [`super::super::present_pace::PresentGate`] emulates in software, done by the
+/// driver — and it matters most exactly where the gate does: on a surface that offers no
+/// MAILBOX, this restores newest-wins behaviour without the app holding frames back.
+pub(crate) mod fifo_latest_ready {
+    use ash::vk;
+
+    /// `VK_EXT_present_mode_fifo_latest_ready` (extension 361).
+    pub(super) const NAME: &std::ffi::CStr = c"VK_EXT_present_mode_fifo_latest_ready";
+    /// `VK_PRESENT_MODE_FIFO_LATEST_READY_EXT`.
+    pub(crate) const MODE: vk::PresentModeKHR = vk::PresentModeKHR::from_raw(1000361000);
+    /// `VK_STRUCTURE_TYPE_PHYSICAL_DEVICE_PRESENT_MODE_FIFO_LATEST_READY_FEATURES_EXT`.
+    const S_TYPE: vk::StructureType = vk::StructureType::from_raw(1000361000);
+
+    /// `VkPhysicalDevicePresentModeFifoLatestReadyFeaturesEXT`. The mode is usable only
+    /// when this feature is enabled at device creation, so the surface advertising the
+    /// mode is NOT on its own permission to request it.
+    #[repr(C)]
+    #[derive(Clone, Copy)]
+    pub(super) struct Features {
+        pub s_type: vk::StructureType,
+        pub p_next: *mut std::ffi::c_void,
+        pub present_mode_fifo_latest_ready: vk::Bool32,
+    }
+
+    impl Default for Features {
+        fn default() -> Features {
+            Features {
+                s_type: S_TYPE,
+                p_next: std::ptr::null_mut(),
+                present_mode_fifo_latest_ready: vk::FALSE,
+            }
+        }
+    }
+}
+
 impl Presenter {
     /// Bring up instance → surface → device → swapchain over an SDL window.
     /// `instance_extensions` comes from `VideoSubsystem::vulkan_instance_extensions()`.
-    pub fn new(window: &sdl3::video::Window, instance_extensions: &[String]) -> Result<Presenter> {
+    pub fn new(
+        window: &sdl3::video::Window,
+        instance_extensions: &[String],
+        pref: PresentPref,
+    ) -> Result<Presenter> {
         // SAFETY: per the Vulkan contract above - a create/allocate call on the live device, over
         // builder structs that are locals outliving the call; the handle it returns is owned by
         // the value being built here.
@@ -176,6 +221,21 @@ impl Presenter {
         // structs through its pNext chain, so any later use of it would pin those borrows —
         // every read of a chained struct below must come after this, have_f2's last use.
         let have_shader_int16 = have_f2.features.shader_int16;
+        // FIFO_LATEST_READY: the surface may list the mode even with the extension
+        // disabled, so the device feature is the real gate on using it.
+        let flr_ok = if has(fifo_latest_ready::NAME) {
+            let mut feat = fifo_latest_ready::Features::default();
+            let mut probe = vk::PhysicalDeviceFeatures2 {
+                p_next: (&mut feat) as *mut _ as *mut std::ffi::c_void,
+                ..Default::default()
+            };
+            // SAFETY: per the Vulkan contract above - a read-only query on the live
+            // instance/device, filling locals returned by value; `feat` outlives the call.
+            unsafe { instance.get_physical_device_features2(pdev, &mut probe) };
+            feat.present_mode_fifo_latest_ready == vk::TRUE
+        } else {
+            false
+        };
         let present_wait_ok = present_wait_exts
             && have_pid.present_id == vk::TRUE
             && have_pwait.present_wait == vk::TRUE;
@@ -273,6 +333,13 @@ impl Presenter {
             dev_exts.push(ash::khr::present_id::NAME.as_ptr());
             dev_exts.push(ash::khr::present_wait::NAME.as_ptr());
         }
+        if flr_ok {
+            dev_exts.push(fifo_latest_ready::NAME.as_ptr());
+        }
+        let mut en_flr = fifo_latest_ready::Features {
+            present_mode_fifo_latest_ready: vk::TRUE,
+            ..Default::default()
+        };
         let mut en_pid = vk::PhysicalDevicePresentIdFeaturesKHR::default().present_id(true);
         let mut en_pwait = vk::PhysicalDevicePresentWaitFeaturesKHR::default().present_wait(true);
 
@@ -295,6 +362,11 @@ impl Presenter {
         if present_wait_ok {
             en_f2 = en_f2.push_next(&mut en_pid).push_next(&mut en_pwait);
         }
+        if flr_ok {
+            // Hand-rolled struct, so chain it by hand: splice into the pNext list head.
+            en_flr.p_next = en_f2.p_next;
+            en_f2.p_next = (&mut en_flr) as *mut _ as *mut std::ffi::c_void;
+        }
         en_f2.features.shader_int16 = if pyrowave_ok { vk::TRUE } else { vk::FALSE };
 
         let priorities = [1.0f32];
@@ -450,11 +522,17 @@ impl Presenter {
         if let Some(v) = video_export.as_mut() {
             v.d3d11_hdr10 = win_capable && import_rgb10 && hdr10_format.is_some();
         }
-        let present_mode = pick_present_mode(&surface_i, pdev, surface)?;
+        let mut pref = pref;
+        pref.vrr_fifo_opt_in = vrr_fifo_opt_in();
+        pref.fifo_latest_ready = flr_ok;
+        let present_mode = pick_present_mode(&surface_i, pdev, surface, pref)?;
         tracing::info!(
             ?format,
             ?hdr10_format,
             ?present_mode,
+            vsync = pref.vsync,
+            allow_vrr = pref.allow_vrr,
+            fifo_latest_ready = flr_ok,
             hdr_metadata = has_hdr_metadata,
             "swapchain config"
         );
@@ -730,42 +808,275 @@ pub(super) fn pick_formats(
     Ok((sdr, hdr10))
 }
 
-/// MAILBOX when the surface offers it, FIFO otherwise (`PUNKTFUNK_PRESENT_MODE=
-/// fifo|mailbox|immediate|fifo_relaxed` overrides). Both defaults are tear-free, but an
-/// arrival-paced presenter must not block in FIFO's present queue: when the compositor
-/// holds images for a vblank pass (gamescope's composite path) or arrival cadence drifts
-/// against refresh, `acquire_next_image` stalls most of a refresh — a standing 11-13 ms
-/// added to every frame at 60 Hz. MAILBOX never queues more than the newest frame, so the
-/// pipeline stays at decode latency and a late frame is replaced, not waited for.
+/// What the user asked the presentation to be, resolved into a swapchain present mode by
+/// [`present_mode_chain`] (design/desktop-presentation-rebuild.md WP3).
+#[derive(Clone, Copy, Debug, Default)]
+pub struct PresentPref {
+    /// Tear-free presentation (the `vsync` setting, default on).
+    pub vsync: bool,
+    /// Let a variable-refresh display follow the stream cadence (`allow_vrr`, default on).
+    pub allow_vrr: bool,
+    /// Opt-in for the VRR FIFO-first ladder (`PUNKTFUNK_VRR_FIFO=1`). Off by default on
+    /// measured evidence — see [`present_mode_chain`].
+    pub vrr_fifo_opt_in: bool,
+    /// `VK_EXT_present_mode_fifo_latest_ready` is enabled on the device, so the mode may
+    /// be requested. Resolved during device creation; never set by callers.
+    pub fifo_latest_ready: bool,
+    /// The session STARTED fullscreen. The mode is chosen once, at swapchain creation, so
+    /// this is the starting state and an F11 mid-session does not re-pick — consistent
+    /// with the shells' "Display changes apply from the next session" footer, and why
+    /// live present-mode switching is an explicit non-goal.
+    pub fullscreen: bool,
+}
+
+/// The preference ladder, most to least wanted. The caller takes the first entry the
+/// surface actually offers; FIFO ends every chain because the spec guarantees it.
+///
+/// * **V-Sync off** — IMMEDIATE (tears, no wait at all), then FIFO_RELAXED (tears only on
+///   a late frame), then the tear-free modes. Asking for tearing and silently getting
+///   vsync is a lie the stats line now exposes, but the ladder still degrades safely.
+/// * **V-Sync on + VRR allowed + fullscreen + `PUNKTFUNK_VRR_FIFO=1`** — FIFO first. On a
+///   variable-refresh panel with direct scanout the FIFO present IS the flip, so the panel
+///   follows the stream's cadence; MAILBOX would decouple presents from scanout and
+///   re-quantize to the compositor's clock.
+///
+///   **Automatic where a queue-free vblank mode exists, opt-in otherwise.** The history is
+///   worth keeping: this was default-on, then measured on glass (.21, GNOME/Wayland,
+///   NVIDIA, *non*-VRR 60 Hz panel, 2026-08-02) to cost ~27 ms of display stage against
+///   MAILBOX — `28.4 ms (pace 11.8 + latch 16.6)` versus `1.4 ms (0.2 + 1.2)` — because a
+///   plain-FIFO present's on-glass confirmation lands a whole refresh later and the
+///   presenter serialises behind it. It became opt-in on that evidence.
+///
+///   `FIFO_LATEST_READY` removes the cause rather than working around it: the driver
+///   retires stale images, so the vblank-locked path measured **2.6 ms** on the same box —
+///   0.6 ms over MAILBOX instead of 27. So where the device offers it, following the panel
+///   is cheap enough to be the default again; where it does not, the ladder would fall
+///   back to plain FIFO and the regression returns, so it stays behind
+///   `PUNKTFUNK_VRR_FIFO=1` there. The win on a genuine VRR panel is still UNMEASURED —
+///   no VRR display was available — but the cost of trying is now small and bounded.
+/// * **Otherwise** — MAILBOX, then FIFO: the shipped default. MAILBOX never queues more
+///   than the newest frame, so an arrival-paced presenter doesn't block in the present
+///   queue (a measured 11-13 ms standing wait at 60 Hz when the compositor holds images
+///   for a vblank pass, or when arrival cadence drifts against refresh).
 ///
 /// AMD's Windows driver offers no MAILBOX (NVIDIA does), so those clients land on FIFO —
-/// expected, not a client misconfiguration. FIFO_RELAXED is opt-in only: it tears exactly
-/// when a stream frame misses the vblank it was pacing for, which on a drifting arrival
-/// cadence is often — a trade the user must choose, never a silent fallback.
+/// expected, not a misconfiguration, and now visible in the `present:` stats line.
+fn present_mode_chain(pref: PresentPref) -> Vec<vk::PresentModeKHR> {
+    use vk::PresentModeKHR as M;
+    let flr = pref.fifo_latest_ready.then_some(fifo_latest_ready::MODE);
+    let mut chain: Vec<M> = if !pref.vsync {
+        vec![M::IMMEDIATE, M::FIFO_RELAXED, M::MAILBOX]
+    } else if pref.allow_vrr && pref.fullscreen && (pref.fifo_latest_ready || pref.vrr_fifo_opt_in)
+    {
+        // The VRR ladder wants the vblank-locked family; LATEST_READY is that with the
+        // queue removed, so it outranks plain FIFO here too.
+        vec![]
+            .into_iter()
+            .chain(flr)
+            .chain([M::FIFO, M::MAILBOX, M::FIFO_RELAXED, M::IMMEDIATE])
+            .collect()
+    } else {
+        // MAILBOX first (measured good), then LATEST_READY — which is what gives a
+        // MAILBOX-less surface the same newest-wins behaviour, in the driver instead of
+        // in our glass gate.
+        vec![M::MAILBOX]
+            .into_iter()
+            .chain(flr)
+            .chain([M::FIFO_RELAXED, M::IMMEDIATE])
+            .collect()
+    };
+    if !pref.vsync {
+        chain.extend(flr);
+    }
+    // FIFO ends every chain: the spec guarantees it exists, so there is always a landing.
+    chain.push(M::FIFO);
+    chain
+}
+
+/// `PUNKTFUNK_VRR_FIFO=1` — opt into the FIFO-first ladder for variable-refresh panels.
+/// See [`present_mode_chain`] for the measurement that made this opt-in rather than
+/// default.
+fn vrr_fifo_opt_in() -> bool {
+    std::env::var("PUNKTFUNK_VRR_FIFO").is_ok_and(|v| v != "0")
+}
+
+/// Resolve the present mode: `PUNKTFUNK_PRESENT_MODE` pins one outright (the debug lever,
+/// unchanged), otherwise the first entry of [`present_mode_chain`] the surface offers.
 fn pick_present_mode(
     surface_i: &ash::khr::surface::Instance,
     pdev: vk::PhysicalDevice,
     surface: vk::SurfaceKHR,
+    pref: PresentPref,
 ) -> Result<vk::PresentModeKHR> {
     // SAFETY: per the Vulkan contract above - a read-only query on the live instance/device,
     // filling locals returned by value.
     let modes = unsafe { surface_i.get_physical_device_surface_present_modes(pdev, surface) }?;
-    let want = match std::env::var("PUNKTFUNK_PRESENT_MODE").ok().as_deref() {
-        Some("fifo") => vk::PresentModeKHR::FIFO,
-        Some("immediate") => vk::PresentModeKHR::IMMEDIATE,
-        Some("fifo_relaxed") => vk::PresentModeKHR::FIFO_RELAXED,
-        Some("mailbox") | None => vk::PresentModeKHR::MAILBOX,
+    let pinned = match std::env::var("PUNKTFUNK_PRESENT_MODE").ok().as_deref() {
+        Some("fifo") => Some(vk::PresentModeKHR::FIFO),
+        Some("immediate") => Some(vk::PresentModeKHR::IMMEDIATE),
+        Some("fifo_relaxed") => Some(vk::PresentModeKHR::FIFO_RELAXED),
+        Some("mailbox") => Some(vk::PresentModeKHR::MAILBOX),
+        None => None,
         Some(other) => {
             tracing::warn!(
                 value = other,
-                "unknown PUNKTFUNK_PRESENT_MODE (expected fifo|mailbox|immediate|fifo_relaxed) — using mailbox"
+                "unknown PUNKTFUNK_PRESENT_MODE (expected fifo|mailbox|immediate|fifo_relaxed) — following the settings"
             );
-            vk::PresentModeKHR::MAILBOX
+            None
         }
     };
-    Ok(if modes.contains(&want) {
-        want
-    } else {
-        vk::PresentModeKHR::FIFO // always available per spec
-    })
+    if let Some(want) = pinned {
+        if modes.contains(&want) {
+            return Ok(want);
+        }
+        tracing::warn!(
+            ?want,
+            "PUNKTFUNK_PRESENT_MODE not offered by this surface — falling back"
+        );
+    }
+    // What the surface ACTUALLY offers, logged unconditionally. "AMD's Windows driver
+    // has no MAILBOX" is the premise the FIFO glass gate is built on, and it has been
+    // carried in comments rather than measured — present modes are a property of the
+    // (surface, device) pair, so they vary by platform surface, driver version and
+    // fullscreen state, and the only way to settle it is to read it back from real
+    // machines. One line here makes every field log answer the question.
+    tracing::info!(
+        available = ?modes,
+        "surface present modes"
+    );
+    let chain = present_mode_chain(pref);
+    let chosen = chain
+        .iter()
+        .copied()
+        .find(|m| modes.contains(m))
+        .unwrap_or(vk::PresentModeKHR::FIFO); // always available per spec
+                                              // The one line that answers "did V-Sync off actually take?" — a request the surface
+                                              // can't serve is a fact about the driver, and it must not look like our choice.
+    if chosen != chain[0] {
+        tracing::info!(
+            requested = ?chain[0],
+            active = ?chosen,
+            vsync = pref.vsync,
+            allow_vrr = pref.allow_vrr,
+            "the surface does not offer the preferred present mode"
+        );
+    }
+    Ok(chosen)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use vk::PresentModeKHR as M;
+
+    /// The preference ladders (WP3). Every chain must end at FIFO, which the spec
+    /// guarantees exists — a chain whose entries a surface all refuses would otherwise
+    /// have no landing.
+    #[test]
+    fn present_mode_chains_rank_by_intent() {
+        let pref = |vsync, allow_vrr, fullscreen| PresentPref {
+            vsync,
+            allow_vrr,
+            fullscreen,
+            vrr_fifo_opt_in: true, // the ladder under test; the DEFAULT is off (see below)
+            fifo_latest_ready: false,
+        };
+        let flr = fifo_latest_ready::MODE;
+
+        // V-Sync off asks to tear, hardest first, and outranks the VRR rule (tearing
+        // already gives a VRR-like latch, so the two never fight).
+        assert_eq!(present_mode_chain(pref(false, true, true))[0], M::IMMEDIATE);
+        assert_eq!(
+            present_mode_chain(pref(false, false, false))[0],
+            M::IMMEDIATE
+        );
+        assert_eq!(
+            present_mode_chain(pref(false, true, true))[1],
+            M::FIFO_RELAXED,
+            "tears only on a late frame — the gentler tearing rung"
+        );
+
+        // Tear-free + VRR allowed + fullscreen prefers the vblank-locked family — but
+        // ONLY when opted in.
+        assert_eq!(present_mode_chain(pref(true, true, true))[0], M::FIFO);
+        // Without the opt-in the shipped MAILBOX-first default stands: measured on glass
+        // to be ~27 ms of display stage better on a non-VRR panel.
+        assert_eq!(
+            present_mode_chain(PresentPref {
+                vsync: true,
+                allow_vrr: true,
+                fullscreen: true,
+                vrr_fifo_opt_in: false,
+                fifo_latest_ready: false,
+            })[0],
+            M::MAILBOX,
+            "without a queue-free vblank mode the VRR ladder would lead with plain FIFO, \
+             which measured ~27 ms worse — so it stays opt-in there"
+        );
+        assert_eq!(
+            present_mode_chain(PresentPref {
+                vsync: true,
+                allow_vrr: true,
+                fullscreen: true,
+                vrr_fifo_opt_in: false,
+                fifo_latest_ready: true,
+            })[0],
+            fifo_latest_ready::MODE,
+            "with LATEST_READY available, following the panel costs 0.6 ms over MAILBOX \
+             instead of 27 — cheap enough to be automatic"
+        );
+
+        // FIFO_LATEST_READY only appears where the device enabled it, and it outranks
+        // plain FIFO everywhere: it is FIFO's vblank pacing WITHOUT the queue, which is
+        // what a MAILBOX-less surface otherwise needs the software glass gate for.
+        let with_flr = |vsync, allow_vrr, fullscreen| PresentPref {
+            vsync,
+            allow_vrr,
+            fullscreen,
+            vrr_fifo_opt_in: true,
+            fifo_latest_ready: true,
+        };
+        for p in [
+            pref(true, false, false),
+            pref(true, true, true),
+            pref(false, true, true),
+        ] {
+            assert!(
+                !present_mode_chain(p).contains(&flr),
+                "never requested unless the device enabled the extension"
+            );
+        }
+        let default_flr = present_mode_chain(with_flr(true, false, false));
+        assert_eq!(
+            default_flr[0],
+            M::MAILBOX,
+            "MAILBOX still leads by measurement"
+        );
+        assert_eq!(default_flr[1], flr, "then the driver-native newest-wins");
+        assert!(
+            default_flr.iter().position(|m| *m == flr)
+                < default_flr.iter().position(|m| *m == M::FIFO),
+            "LATEST_READY must outrank plain FIFO — it is FIFO minus the standing queue"
+        );
+        assert_eq!(
+            present_mode_chain(with_flr(true, true, true))[0],
+            flr,
+            "the VRR ladder takes the queue-free vblank mode first"
+        );
+
+        // Every ladder can land: FIFO appears in all of them.
+        for p in [
+            pref(true, true, true),
+            pref(true, true, false),
+            pref(true, false, true),
+            pref(false, true, true),
+            pref(false, false, false),
+            with_flr(true, false, false),
+        ] {
+            assert!(
+                present_mode_chain(p).contains(&M::FIFO),
+                "FIFO is the guaranteed landing"
+            );
+        }
+    }
 }

crates/pf-vdisplay/src/lib.rs

@@ -407,13 +407,21 @@ pub fn open(compositor: Compositor) -> Result<Box<dyn VirtualDisplay>> {
         // The pf-vdisplay all-Rust IddCx driver is the sole virtual-display backend (the legacy SudoVDA
         // fallback was removed — its driver is no longer shipped). The compositor arg is moot on Windows.
         let _ = compositor;
-        // `ensure_available` self-heals the hostless-zombie state a WUDFHost crash leaves (adapter
-        // devnode present, interface gone): one device cycle + re-probe before giving up.
-        anyhow::ensure!(
-            driver::ensure_available(),
-            "pf-vdisplay driver interface not found — the pf-vdisplay IddCx driver is not installed or \
-             not loaded (the host installer bundles it; reinstall or check the driver state)"
-        );
+        // `ensure_available` waits out a devnode that is merely coming up (the wake-from-sleep case:
+        // the adapter re-enters D0 and re-registers its interface while a reconnecting client is
+        // already knocking) and self-heals the hostless-zombie state a WUDFHost crash leaves (adapter
+        // devnode present, interface gone) by reloading the adapter.
+        //
+        // `context`, not a replacement message: it reports WHY — how long it waited, whether a reload
+        // ran, how many interface instances were seen and in what state. A flat "the driver is not
+        // installed" is what a field report carried from a box whose driver was installed, started,
+        // and simply mid-resume, and it pointed every reader at the wrong problem.
+        use anyhow::Context as _;
+        driver::ensure_available().context(
+            "pf-vdisplay driver interface not available — the pf-vdisplay IddCx driver is not \
+             installed, not loaded, or did not finish coming back up (the host installer bundles \
+             it; reinstall or check the driver state)",
+        )?;
         Ok(Box::new(driver::PfVdisplayDisplay::new()?))
     }
     #[cfg(not(any(target_os = "linux", target_os = "windows")))]

crates/pf-vdisplay/src/vdisplay/windows/manager.rs

@@ -425,6 +425,20 @@ pub fn control_device_handle() -> Option<HANDLE> {
     VDM.get().and_then(VirtualDisplayManager::device_handle)
 }
 
+/// Retire the cached control handle from OUTSIDE the manager, for a caller that KNOWS the device
+/// died — the adapter-reload recovery in [`crate::driver`], which tears the driver stack down and
+/// back up. Without it the stale handle survives into the next session's `IOCTL_ADD` and is only
+/// recovered by the gone-classified retry one failed IOCTL later.
+///
+/// Takes the `device` mutex, so it must NOT be called from inside it (notably not from
+/// `VdisplayDriver::open`, which `ensure_device` invokes while holding it). No-op before any backend
+/// opened the device.
+pub(crate) fn invalidate_cached_device(why: &str) {
+    if let Some(m) = VDM.get() {
+        m.invalidate_device(&anyhow::anyhow!("{why}"));
+    }
+}
+
 /// Re-commit the CURRENT display config under the manager `state` lock (the sole-topology-mutator
 /// contract of [`force_mode_reenumeration`]). The secure-desktop guard's actuator: the OS only
 /// reverts a path to its software-cursor default ON a mode commit, so standing the hardware-cursor

crates/pf-vdisplay/src/vdisplay/windows/pf_vdisplay.rs

@@ -21,6 +21,7 @@ use std::ffi::c_void;
 use std::mem::size_of;
 use std::os::windows::io::{AsRawHandle, FromRawHandle, OwnedHandle};
 use std::sync::atomic::{AtomicU64, Ordering};
+use std::time::{Duration, Instant};
 
 use anyhow::{Context, Result};
 use windows::core::{GUID, PCWSTR};
@@ -143,31 +144,70 @@ fn reap_ghost_monitors() -> u32 {
     }
 }
 
-/// Kick the pf-vdisplay ADAPTER device (disable → enable) — the in-process equivalent of
-/// `reset-pf-vdisplay.ps1` step 3. A crashed/killed WUDFHost can leave the devnode "started" yet
-/// HOSTLESS (PnP Status OK, no WUDFHost process, zero device-interface instances) — a zombie no
-/// session can open until the stack reloads; on-glass, only a device cycle recovered it. Called by
-/// [`VdisplayDriver::open`] when `open_device` finds no openable interface; the caller retries the
-/// open afterwards. Best-effort + bounded (~7 s inside the script). Returns whether a punktfunk
-/// adapter devnode was found (and therefore cycled) — `false` means the driver genuinely is not
-/// installed and a retry is pointless.
-fn restart_vdisplay_device() -> bool {
+/// What an adapter-cycle attempt actually DID — deliberately NOT the devnode's PnP status afterwards.
+/// The old script reported that status, and a device it had failed to touch at all still reads `OK`,
+/// so a no-op cycle was indistinguishable from a real one in the log (field report 2026-08-02: a
+/// woken host logged `cycled … status=OK` and then failed the session for a missing interface).
+enum AdapterCycle {
+    /// The driver stack was genuinely reloaded. `how` names the lever that worked.
+    Reloaded { how: &'static str, status: String },
+    /// No punktfunk adapter devnode exists at all — the driver is not installed and retrying is
+    /// pointless.
+    NotInstalled,
+    /// A devnode exists but could not be reloaded; carries the reason (already whitespace-collapsed).
+    Refused(String),
+}
+
+/// Reload the pf-vdisplay ADAPTER device — the in-process equivalent of `reset-pf-vdisplay.ps1`
+/// step 3. A crashed/killed WUDFHost can leave the devnode "started" yet HOSTLESS (PnP Status OK, no
+/// WUDFHost process, zero device-interface instances) — a zombie no session can open until the stack
+/// reloads; on-glass, only a device reload recovered it.
+///
+/// Two levers, in order. `Disable-PnpDevice` + `Enable-PnpDevice` is the one `reset-pf-vdisplay.ps1`
+/// uses — but that script stops the host service FIRST, precisely because the host holds the driver's
+/// control device open (its step 1), and a disable can be refused for a device in use. This runs
+/// INSIDE the host, so it structurally cannot take that step: the retired-but-never-closed handles in
+/// [`DeviceSlot`](super::manager) are still open on the very device being disabled. So a refusal is
+/// the expected case here, not the exotic one, and `pnputil /restart-device` — which reloads a device
+/// that is in use — is the fallback. Whichever runs, the failure paths re-enable, so a half-completed
+/// cycle can never leave the adapter DISABLED.
+///
+/// Best-effort + bounded (~6 s inside the script).
+fn reload_vdisplay_adapter() -> AdapterCycle {
     // Mirrors reset-pf-vdisplay.ps1's Get-PfAdapter selector ('punktfunk Virtual Display' is the INF
-    // device description — locale-invariant). Same spawn shape as `reap_ghost_monitors` above.
+    // device description — locale-invariant). Same spawn shape as `reap_ghost_monitors` above; the
+    // reported tokens are ours, so parsing them is locale-invariant too.
+    //
+    // Every step that can fail is `-ErrorAction Stop` inside a `try` — the old script ran the whole
+    // cycle under `SilentlyContinue` and then reported `(Get-PnpDevice …).Status`, which reports the
+    // DEVICE, not the cycle: a disable that was refused left the device untouched, started, and
+    // reading `OK`, so the host logged a successful recovery it had never performed.
+    //
+    // `$LASTEXITCODE = 1` before the pnputil call for the same reason: no native command runs before
+    // it, so an unlaunchable pnputil would otherwise leave the variable holding whatever it held and
+    // let "never ran" read as "returned 0". Pre-seeding a failure means only a real exit 0 reports a
+    // reload. pnputil is resolved by full path — a LocalSystem service's PATH need not include
+    // System32.
     const CYCLE_PS: &str = "$ErrorActionPreference='SilentlyContinue'; \
         $ad = Get-PnpDevice -Class Display | Where-Object { $_.FriendlyName -match 'punktfunk Virtual Display' } | Select-Object -First 1; \
-        if ($ad) { \
-            Disable-PnpDevice -InstanceId $ad.InstanceId -Confirm:$false; Start-Sleep -Seconds 3; \
-            Enable-PnpDevice -InstanceId $ad.InstanceId -Confirm:$false; Start-Sleep -Seconds 3; \
-            $st = (Get-PnpDevice -InstanceId $ad.InstanceId).Status; \
-            if ($st -ne 'OK') { Enable-PnpDevice -InstanceId $ad.InstanceId -Confirm:$false; Start-Sleep -Seconds 2; \
-                $st = (Get-PnpDevice -InstanceId $ad.InstanceId).Status }; \
-            Write-Output $st \
-        } else { Write-Output 'ABSENT' }";
+        if (-not $ad) { Write-Output 'ABSENT'; exit }; \
+        $id = $ad.InstanceId; $err = ''; \
+        try { \
+            Disable-PnpDevice -InstanceId $id -Confirm:$false -ErrorAction Stop; Start-Sleep -Seconds 2; \
+            try { Enable-PnpDevice -InstanceId $id -Confirm:$false -ErrorAction Stop } \
+            catch { Start-Sleep -Seconds 2; Enable-PnpDevice -InstanceId $id -Confirm:$false -ErrorAction Stop }; \
+            Start-Sleep -Seconds 2; \
+            Write-Output ('RELOADED cycle ' + (Get-PnpDevice -InstanceId $id).Status); exit \
+        } catch { $err = ($_.Exception.Message -replace '\\s+', ' ') }; \
+        $pnp = ($env:SystemRoot + '\\System32\\pnputil.exe'); $LASTEXITCODE = 1; \
+        if (Test-Path $pnp) { & $pnp /restart-device $id *> $null }; \
+        if ($LASTEXITCODE -eq 0) { Start-Sleep -Seconds 2; \
+            Write-Output ('RELOADED restart ' + (Get-PnpDevice -InstanceId $id).Status) } \
+        else { Enable-PnpDevice -InstanceId $id -Confirm:$false; Write-Output ('REFUSED ' + $err) }";
     let ps = std::env::var("SystemRoot")
         .map(|r| format!(r"{r}\System32\WindowsPowerShell\v1.0\powershell.exe"))
         .unwrap_or_else(|_| "powershell.exe".to_string());
-    match std::process::Command::new(&ps)
+    let out = match std::process::Command::new(&ps)
         .args([
             "-NoProfile",
             "-NonInteractive",
@@ -178,22 +218,65 @@ fn restart_vdisplay_device() -> bool {
         ])
         .output()
     {
-        Ok(o) => {
-            let status = String::from_utf8_lossy(&o.stdout).trim().to_string();
-            if status == "ABSENT" {
-                tracing::warn!("pf-vdisplay: no adapter devnode to cycle — driver not installed");
-            } else {
-                tracing::warn!(
-                    %status,
-                    "pf-vdisplay: cycled the adapter device (hostless-zombie recovery)"
-                );
-            }
-            status != "ABSENT"
-        }
+        Ok(o) => String::from_utf8_lossy(&o.stdout).trim().to_string(),
         Err(e) => {
-            tracing::warn!(error = %e, "pf-vdisplay: adapter cycle could not spawn powershell");
-            false
+            tracing::warn!(error = %e, "pf-vdisplay: adapter reload could not spawn powershell");
+            return AdapterCycle::Refused(format!("could not spawn powershell: {e}"));
         }
+    };
+    let outcome = classify_reload_output(&out);
+    match &outcome {
+        AdapterCycle::NotInstalled => {
+            tracing::warn!("pf-vdisplay: no adapter devnode to reload — driver not installed");
+        }
+        AdapterCycle::Reloaded { how, status } => tracing::warn!(
+            how,
+            %status,
+            "pf-vdisplay: reloaded the adapter device (hostless-zombie recovery)"
+        ),
+        AdapterCycle::Refused(why) => tracing::warn!(
+            reason = %why,
+            "pf-vdisplay: the adapter devnode exists but could NOT be reloaded — a session cannot \
+             recover from this without a host-service restart or a reboot"
+        ),
+    }
+    outcome
+}
+
+/// Parse [`reload_vdisplay_adapter`]'s script output. Split out to be testable without a box: the
+/// bug this whole change answers was a recovery that MISreported its own outcome, so the decoding of
+/// that outcome is worth pinning down.
+fn classify_reload_output(out: &str) -> AdapterCycle {
+    let out = out.trim();
+    let (verb, rest) = out.split_once(char::is_whitespace).unwrap_or((out, ""));
+    match verb {
+        "ABSENT" => AdapterCycle::NotInstalled,
+        "RELOADED" => {
+            let (how, status) = rest
+                .trim()
+                .split_once(char::is_whitespace)
+                .unwrap_or((rest.trim(), ""));
+            // Held as `&'static str` so the two levers stay distinguishable in a field report:
+            // `restart` means the disable was refused, i.e. something still holds the device open —
+            // worth knowing when a reload does not fix the box.
+            let how: &'static str = if how == "restart" {
+                "pnputil /restart-device"
+            } else {
+                "disable+enable"
+            };
+            AdapterCycle::Reloaded {
+                how,
+                status: status.trim().to_string(),
+            }
+        }
+        // Covers `REFUSED <reason>` and anything unrecognised, including an empty stdout (powershell
+        // died before writing). All of them mean an un-reloaded devnode, which is the only thing
+        // callers act on; the text rides along for the log.
+        _ => AdapterCycle::Refused(if rest.trim().is_empty() {
+            format!("unexpected adapter-reload output: {out:?}")
+        } else {
+            rest.trim().to_string()
+        }),
     }
 }
 
@@ -325,6 +408,55 @@ impl Drop for DevInfoList {
     }
 }
 
+/// What a device-interface enumeration found. The counts are what let [`ensure_available`] tell a
+/// devnode that is MID-TRANSITION (present, interface registered, not started yet — resuming from
+/// sleep, restarting, reloading) apart from one that is genuinely gone. Only the second is worth
+/// answering with device surgery; cycling the first only lengthens the outage it is waiting out.
+struct Probe {
+    /// The control handle, if any interface instance opened.
+    handle: Option<OwnedHandle>,
+    /// Instances seen with `SPINT_ACTIVE` set — the owning device is started.
+    active: u32,
+    /// Instances seen with `SPINT_ACTIVE` clear — registered, but the owning device is not started.
+    inactive: u32,
+    /// The last enumeration/open failure, kept for the diagnostic.
+    last_err: Option<anyhow::Error>,
+}
+
+impl Probe {
+    /// No interface instance of ANY kind. With an adapter devnode present this is the hostless-zombie
+    /// state a WUDFHost crash leaves; with none, the driver is not installed. Either way, waiting
+    /// alone will not fix it.
+    fn is_absent(&self) -> bool {
+        self.handle.is_none() && self.active == 0 && self.inactive == 0
+    }
+
+    /// Why no handle came back, NAMING what was seen — "0 interfaces" and "1 inactive interface" are
+    /// completely different diagnoses (not installed vs. still coming up), and the old message
+    /// collapsed both into "is the driver installed?". Call only on a miss; a hit reports as much.
+    fn into_error(self) -> anyhow::Error {
+        let seen = format!("{} active, {} inactive", self.active, self.inactive);
+        if self.handle.is_some() {
+            return anyhow::anyhow!("pf-vdisplay device interface opened ({seen})");
+        }
+        match self.last_err {
+            Some(e) => e.context(format!("no openable pf-vdisplay device interface ({seen})")),
+            None => anyhow::anyhow!(
+                "no pf-vdisplay device interface found ({seen}) — is the pf-vdisplay driver \
+                 installed and its device started?"
+            ),
+        }
+    }
+
+    /// Consume into the [`open_device`] result.
+    fn into_result(mut self) -> Result<OwnedHandle> {
+        match self.handle.take() {
+            Some(h) => Ok(h),
+            None => Err(self.into_error()),
+        }
+    }
+}
+
 /// Open the pf-vdisplay control device.
 ///
 /// SAFE, and owning. It has no caller obligation — it takes no arguments and every precondition is
@@ -333,26 +465,40 @@ impl Drop for DevInfoList {
 /// this file has already leaked from once (see the wrap-IMMEDIATELY comment in `open`). Returning an
 /// `OwnedHandle` makes the close a `Drop`, so there is exactly one way to get it wrong: not at all.
 fn open_device() -> Result<OwnedHandle> {
+    probe_device().into_result()
+}
+
+/// [`open_device`], reporting WHAT it found rather than only whether it succeeded.
+fn probe_device() -> Probe {
+    let mut probe = Probe {
+        handle: None,
+        active: 0,
+        inactive: 0,
+        last_err: None,
+    };
     // SAFETY: plain SetupAPI enumeration call; the returned list is solely owned by the RAII wrapper.
-    let hdev = DevInfoList(
-        unsafe {
-            SetupDiGetClassDevsW(
-                Some(&PF_VDISPLAY_INTERFACE),
-                PCWSTR::null(),
-                None,
-                DIGCF_DEVICEINTERFACE | DIGCF_PRESENT,
-            )
+    let hdev = match unsafe {
+        SetupDiGetClassDevsW(
+            Some(&PF_VDISPLAY_INTERFACE),
+            PCWSTR::null(),
+            None,
+            DIGCF_DEVICEINTERFACE | DIGCF_PRESENT,
+        )
+    }
+    .context("SetupDiGetClassDevsW(pf-vdisplay) — is the pf-vdisplay driver installed?")
+    {
+        Ok(h) => DevInfoList(h),
+        Err(e) => {
+            probe.last_err = Some(e);
+            return probe;
         }
-        .context("SetupDiGetClassDevsW(pf-vdisplay) — is the pf-vdisplay driver installed?")?,
-    );
+    };
 
     // Enumerate EVERY interface instance, not just index 0: after a driver upgrade a present-but-
     // failed devnode (Code 10) can hold index 0 while the LIVE node's interface sits at a later
     // index — the old single-index read then failed every session with "driver not installed"
     // even though a working interface existed. `SPINT_ACTIVE` filters dead interfaces (an interface
     // is active only while its owning device is started); the first active + openable one wins.
-    let mut inactive = 0u32;
-    let mut last_err: Option<anyhow::Error> = None;
     for index in 0..64u32 {
         let mut idata = SP_DEVICE_INTERFACE_DATA {
             cbSize: size_of::<SP_DEVICE_INTERFACE_DATA>() as u32,
@@ -367,9 +513,10 @@ fn open_device() -> Result<OwnedHandle> {
             break; // ERROR_NO_MORE_ITEMS — no further candidates
         }
         if idata.Flags & SPINT_ACTIVE == 0 {
-            inactive += 1;
+            probe.inactive += 1;
             continue;
         }
+        probe.active += 1;
         let mut required = 0u32;
         // SAFETY: sizing call — null buffer plus a valid `required` out-param; the expected
         // ERROR_INSUFFICIENT_BUFFER "failure" is ignored and only `required` is consumed.
@@ -409,20 +556,18 @@ fn open_device() -> Result<OwnedHandle> {
                 })
         };
         match opened {
-            // SAFETY: `h` is the handle `CreateFileW` just returned to THIS call and nothing else
-            // holds it, so transferring it into the `OwnedHandle` gives it a single owner that
-            // closes it exactly once on drop.
-            Ok(h) => return Ok(unsafe { OwnedHandle::from_raw_handle(h.0 as _) }),
+            Ok(h) => {
+                // SAFETY: `h` is the handle `CreateFileW` just returned to THIS call and nothing
+                // else holds it, so transferring it into the `OwnedHandle` gives it a single owner
+                // that closes it exactly once on drop.
+                probe.handle = Some(unsafe { OwnedHandle::from_raw_handle(h.0 as _) });
+                return probe;
+            }
             // A raced-away or wedged device — remember the error, try the next interface.
-            Err(e) => last_err = Some(e),
+            Err(e) => probe.last_err = Some(e),
         }
     }
-    Err(last_err.unwrap_or_else(|| {
-        anyhow::anyhow!(
-            "no ACTIVE pf-vdisplay device interface found ({inactive} inactive) — is the \
-             pf-vdisplay driver installed and its device started?"
-        )
-    }))
+    probe
 }
 
 /// The pf-vdisplay IOCTL surface behind the shared [`VirtualDisplayManager`](super::manager::VirtualDisplayManager)
@@ -435,29 +580,14 @@ impl VdisplayDriver for PfVdisplayDriver {
     }
 
     unsafe fn open(&self, reap_orphans: bool) -> Result<(OwnedHandle, u32, u32)> {
-        let device = match open_device() {
-            Ok(d) => d,
-            Err(first) => {
-                // No openable interface. If a WUDFHost crash left the devnode a hostless zombie
-                // (validated on-glass: PnP Status OK, zero interface instances), a device cycle
-                // reloads the stack — kick it once and retry the open over a short arrival window.
-                if !restart_vdisplay_device() {
-                    return Err(first); // no adapter devnode at all — genuinely not installed
-                }
-                let mut reopened = Err(first);
-                for _ in 0..8 {
-                    std::thread::sleep(std::time::Duration::from_millis(500));
-                    match open_device() {
-                        Ok(d) => {
-                            reopened = Ok(d);
-                            break;
-                        }
-                        Err(e) => reopened = Err(e),
-                    }
-                }
-                reopened.context("pf-vdisplay interface still absent after an adapter cycle")?
-            }
-        };
+        // A short re-probe, and deliberately NO adapter reload — this replaces the second, impatient
+        // copy of the recovery that used to live here. Session bring-up already ran the full
+        // `ensure_available` before constructing the backend, so anything left for this open to
+        // absorb is a race, not a wedge. `hw_cursor_capable` also lands here, mid client handshake,
+        // where a reload's tens of seconds would be entirely the wrong trade for one capability bool
+        // — and where reloading would deadlock besides, since `ensure_device` calls us holding the
+        // manager's `device` mutex (see the `RECOVERY` ordering contract).
+        let device = wait_for_interface(BRIEF_RETRY, false).0?;
         // `open_device` hands back an `OwnedHandle`, so every `?` below closes the device exactly
         // once by construction — the shape this used to reach by wrapping the raw handle here, and
         // which leaked whenever GET_INFO itself failed before that wrap was moved up.
@@ -879,25 +1009,159 @@ pub fn is_available() -> bool {
     open_device().is_ok()
 }
 
-/// [`is_available`], with self-heal: an interface-less driver whose adapter devnode EXISTS is the
-/// hostless-zombie state a WUDFHost crash leaves behind (validated on-glass — PnP reports Status OK
-/// with no WUDFHost process and zero interface instances, and every session fails at this gate until
-/// the device reloads). Cycle the adapter once and re-probe over a short arrival window. A genuinely
-/// uninstalled driver (no adapter devnode) fails fast without the wait.
-pub fn ensure_available() -> bool {
-    if is_available() {
-        return true;
+/// How often the interface is re-probed while waiting.
+const PROBE_INTERVAL: Duration = Duration::from_millis(500);
+
+/// How long a devnode whose interface exists but is NOT-READY (no active instance, or `CreateFileW`
+/// refused) is given to come up on its own before the adapter is reloaded.
+///
+/// This is the wake-from-sleep window. Resuming re-enters D0 and re-registers the interface while
+/// the rest of the resume storm is still running, and a client reconnecting a second after wake
+/// arrives inside that gap — which the old code, probing exactly ONCE, answered by disabling and
+/// re-enabling a display adapter that was seconds from being ready anyway.
+const NOT_READY_GRACE: Duration = Duration::from_secs(15);
+
+/// How long a fully ABSENT interface is given before the adapter is reloaded. Short — a hostless
+/// devnode does not heal itself, and that is the case this recovery exists for — but non-zero, so a
+/// resume that briefly de-registers the interface is not met with device surgery either.
+const ABSENT_SETTLE: Duration = Duration::from_secs(3);
+
+/// How long the interface is given to ARRIVE after a reload.
+///
+/// Was 4 s, which a quiet box meets and a box still finishing a resume does not: PnP is contended
+/// right after wake. Field report 2026-08-02 — a woken host logged a successful adapter cycle and
+/// then failed the session 4 s later for a missing interface, and the client could not connect.
+const ARRIVAL_AFTER_RELOAD: Duration = Duration::from_secs(15);
+
+/// Hard ceiling on the whole wait, so display prep can never block for an unbounded sum of the
+/// windows above. Without it a devnode wedged NOT-READY costs the full grace, then the reload, then
+/// the full arrival window before failing — the pathological case paying nearly a minute per session.
+/// Patience for a device that is coming back is the point; patience for one that never will is not.
+const TOTAL_BUDGET: Duration = Duration::from_secs(30);
+
+/// The budget a caller that must NOT stall gives the interface: no adapter reload, just a short
+/// re-probe to ride out a race. [`VdisplayDriver::open`] uses it — by the time the manager opens,
+/// session bring-up has already run the full [`ensure_available`] above, and the OTHER path that
+/// reaches it (`manager::hw_cursor_capable`, a best-effort capability answer during the client
+/// handshake) must never hold the Welcome for tens of seconds to decide one bool.
+const BRIEF_RETRY: Duration = Duration::from_secs(3);
+
+/// Serializes the recovery so N sessions racing in after a wake perform ONE adapter reload between
+/// them rather than N interleaved ones — each of which tears down the stack the others are waiting
+/// on. The second caller through typically finds the interface already up and returns at once.
+///
+/// Taken ONLY by [`ensure_available`], which holds no manager lock, and released before the retire
+/// hook below takes the manager's `device` mutex. That is what keeps the lock order one-way:
+/// [`VdisplayDriver::open`] runs *inside* that same `device` mutex, so if it could also take this
+/// lock the two orders would invert and deadlock. It cannot — it never reloads.
+static RECOVERY: std::sync::Mutex<()> = std::sync::Mutex::new(());
+
+/// [`is_available`], with self-heal — and with PATIENCE, which is the part that matters after a
+/// wake from sleep.
+///
+/// Returns the reason on failure instead of a bare `false`: the caller used to replace it with a
+/// flat "the driver is not installed", which is what a field report showed on a box whose driver was
+/// installed, started, and merely mid-resume.
+pub fn ensure_available() -> Result<()> {
+    // Poisoning carries no meaning here — the guard protects a `()`, not state a panic could leave
+    // inconsistent — so a previous panic must not wedge every later session out of recovery.
+    let (result, reloaded) = {
+        let _serialize = RECOVERY.lock().unwrap_or_else(|e| e.into_inner());
+        wait_for_interface(NOT_READY_GRACE, true)
+    };
+    // OUTSIDE the recovery lock, by the ordering contract on `RECOVERY`. A reload tore the driver
+    // stack down and back up, so any control handle a previous session cached is dead by
+    // construction — retire it while we know that for certain, rather than leaving the next session
+    // to discover it by having an IOCTL fail. No-op before any backend opened the device.
+    if reloaded {
+        super::manager::invalidate_cached_device(
+            "the pf-vdisplay adapter was reloaded (hostless-zombie recovery)",
+        );
     }
-    if !restart_vdisplay_device() {
-        return false;
-    }
-    for _ in 0..8 {
-        std::thread::sleep(std::time::Duration::from_millis(500));
-        if is_available() {
-            return true;
+    result.map(|_| ())
+}
+
+/// Wait for an openable control interface, reloading the adapter if `reload` and the devnode looks
+/// genuinely hostless. Returns the handle (so the manager's own open can keep it) alongside whether
+/// a reload ran.
+///
+/// Two distinguishable states hide behind "cannot open the interface", and they want opposite
+/// treatment:
+///
+/// * **Not ready** — instances are registered but none is active (or the open is refused). The
+///   devnode is THERE and coming up: resuming from sleep, restarting, reloading. It heals itself;
+///   reloading the adapter underneath it only lengthens the outage.
+/// * **Absent** — no instance at all. With an adapter devnode present this is the hostless-zombie
+///   state a WUDFHost crash leaves (validated on-glass: PnP Status OK, no WUDFHost process, zero
+///   interface instances). Only a reload clears it.
+///
+/// So: probe, wait out a not-ready device, reload an absent one after a short settle, and give the
+/// interface a real arrival window afterwards. A reload is still attempted once at the end of
+/// `not_ready_grace`, so a devnode wedged not-ready (a failed start) recovers exactly as it did
+/// before. A genuinely uninstalled driver — no adapter devnode — still fails FAST, with no wait.
+fn wait_for_interface(not_ready_grace: Duration, reload: bool) -> (Result<OwnedHandle>, bool) {
+    let started = Instant::now();
+    let mut deadline = started + not_ready_grace;
+    let mut absent_since: Option<Instant> = None;
+    let mut reloaded = false;
+    loop {
+        let mut probe = probe_device();
+        if let Some(h) = probe.handle.take() {
+            if reloaded || started.elapsed() > PROBE_INTERVAL {
+                tracing::info!(
+                    waited_ms = started.elapsed().as_millis() as u64,
+                    reloaded,
+                    "pf-vdisplay: control interface available"
+                );
+            }
+            return (Ok(h), reloaded);
         }
+        // Track how long we have seen NOTHING. Reset by any sighting, so a device that flickers
+        // between absent and not-ready is treated as the transition it is.
+        if probe.is_absent() {
+            absent_since.get_or_insert_with(Instant::now);
+        } else {
+            absent_since = None;
+        }
+        let absent_long_enough = absent_since.is_some_and(|t| t.elapsed() >= ABSENT_SETTLE);
+        if reload && !reloaded && (absent_long_enough || Instant::now() >= deadline) {
+            match reload_vdisplay_adapter() {
+                // No devnode at all — waiting cannot conjure a driver. Fail immediately rather than
+                // burning the arrival window on a box that simply does not have it installed.
+                AdapterCycle::NotInstalled => {
+                    let e = Err(probe.into_error()).context(
+                        "no punktfunk virtual-display adapter devnode exists — the driver is not \
+                         installed",
+                    );
+                    return (e, reloaded);
+                }
+                AdapterCycle::Refused(why) => {
+                    let e = Err(probe.into_error()).context(format!(
+                        "the pf-vdisplay adapter devnode could not be reloaded ({why})"
+                    ));
+                    return (e, reloaded);
+                }
+                AdapterCycle::Reloaded { .. } => {
+                    reloaded = true;
+                    absent_since = None;
+                    deadline = (Instant::now() + ARRIVAL_AFTER_RELOAD).min(started + TOTAL_BUDGET);
+                }
+            }
+        }
+        if Instant::now() >= deadline {
+            let e = Err(probe.into_error()).context(format!(
+                "the pf-vdisplay control interface did not appear within {:?}{}",
+                started.elapsed(),
+                if reloaded {
+                    " (including an adapter reload)"
+                } else {
+                    ""
+                }
+            ));
+            return (e, reloaded);
+        }
+        std::thread::sleep(PROBE_INTERVAL);
     }
-    false
 }
 
 #[cfg(test)]
@@ -906,6 +1170,96 @@ mod tests {
     use std::thread;
     use std::time::Duration;
 
+    /// The recovery must not be able to claim success it did not achieve. This is the whole bug:
+    /// the old script ran the cycle under `SilentlyContinue` and reported `(Get-PnpDevice).Status`,
+    /// so a device whose disable had been REFUSED — untouched, still started — reported `OK`, and
+    /// the host logged `cycled the adapter device … status=OK` while nothing had been cycled at all
+    /// (field report 2026-08-02). A refusal must decode as a refusal, carrying its reason.
+    #[test]
+    fn a_refused_reload_is_not_reported_as_a_reload() {
+        let refused =
+            classify_reload_output("REFUSED This device cannot be disabled because it is in use.");
+        match refused {
+            AdapterCycle::Refused(why) => {
+                assert!(why.contains("in use"), "the reason must survive: {why:?}")
+            }
+            other => panic!("a refused reload decoded as {}", variant(&other)),
+        }
+        // A bare device status — what the OLD script emitted on every path — must NEVER decode as a
+        // successful reload now, however healthy it looks.
+        for stale in ["OK", "Error", "Unknown"] {
+            assert!(
+                matches!(classify_reload_output(stale), AdapterCycle::Refused(_)),
+                "{stale:?} is a device status, not a reload outcome"
+            );
+        }
+    }
+
+    /// The outcomes callers branch on: `NotInstalled` fails a session fast, `Reloaded` earns the
+    /// arrival window, and the lever that worked stays visible in the log (`restart` means the
+    /// disable was refused and something still holds the device open).
+    #[test]
+    fn reload_outcomes_decode() {
+        assert!(matches!(
+            classify_reload_output("ABSENT"),
+            AdapterCycle::NotInstalled
+        ));
+        match classify_reload_output("RELOADED cycle OK") {
+            AdapterCycle::Reloaded { how, status } => {
+                assert_eq!(how, "disable+enable");
+                assert_eq!(status, "OK");
+            }
+            other => panic!("expected Reloaded, got {}", variant(&other)),
+        }
+        match classify_reload_output("RELOADED restart OK\r\n") {
+            AdapterCycle::Reloaded { how, status } => {
+                assert_eq!(how, "pnputil /restart-device");
+                assert_eq!(status, "OK");
+            }
+            other => panic!("expected Reloaded, got {}", variant(&other)),
+        }
+        // powershell died before writing anything — an un-reloaded devnode, so `Refused`, not a
+        // silent success.
+        assert!(matches!(
+            classify_reload_output("   "),
+            AdapterCycle::Refused(_)
+        ));
+    }
+
+    /// `is_absent` is what decides between WAITING and performing device surgery, so the two states
+    /// it separates are pinned here. An interface that is registered but not yet ACTIVE is a devnode
+    /// mid-transition — the wake-from-sleep case — and reloading the adapter under it only lengthens
+    /// the outage it is already recovering from.
+    #[test]
+    fn only_a_total_absence_counts_as_absent() {
+        let probe = |active, inactive| Probe {
+            handle: None,
+            active,
+            inactive,
+            last_err: None,
+        };
+        assert!(probe(0, 0).is_absent(), "no instances at all = absent");
+        assert!(
+            !probe(0, 1).is_absent(),
+            "a registered-but-inactive instance is a device coming up, not a missing one"
+        );
+        assert!(
+            !probe(1, 0).is_absent(),
+            "an active instance we merely failed to open is not a missing device"
+        );
+        // And the diagnostic names what was seen — the old message collapsed every one of these
+        // into "is the driver installed?", which sent a field report down the wrong path.
+        assert!(probe(0, 2).into_error().to_string().contains("2 inactive"));
+    }
+
+    fn variant(c: &AdapterCycle) -> &'static str {
+        match c {
+            AdapterCycle::Reloaded { .. } => "Reloaded",
+            AdapterCycle::NotInstalled => "NotInstalled",
+            AdapterCycle::Refused(_) => "Refused",
+        }
+    }
+
     /// Live hardware round trip — `#[ignore]`d (needs the pf-vdisplay driver installed); run with
     /// `cargo test -p pf-vdisplay -- --ignored live_create_drop`. Exercises the real trait path: open -> create -> hold -> drop (REMOVE).
     #[test]

crates/punktfunk-core/src/packet/packetize.rs

@@ -73,9 +73,9 @@ pub struct StreamedAu {
     pts_ns: u64,
     user_flags: u32,
     /// Bytes not yet sealed into a block: the sub-shard remainder plus anything below the
-    /// slice-flush threshold. The final block always has ≥ 1 byte (flushes emit only whole
-    /// shards and never drain to empty on a slice that ends the AU — `finish_streamed` seals
-    /// whatever remains).
+    /// slice-flush threshold. The final block always has ≥ 1 byte — flushes emit only whole
+    /// shards, and a flush that WOULD empty this keeps one shard back (see `push_streamed`),
+    /// so `finish_streamed` always has something real to seal.
     pending: Vec<u8>,
     /// Sentinel blocks already emitted.
     blocks_out: u16,
@@ -418,7 +418,18 @@ impl Packetizer {
                     "streamed AU exceeds the negotiated max_frame_bytes",
                 ));
             }
-            let k = whole.min(self.fec.max_data_per_block as usize);
+            // Never drain `pending` to EMPTY. [`finish_streamed`] must have bytes left to seal,
+            // or the final block degenerates to a single zero-padded filler shard whose derived
+            // base (`total_data − 1`) overlaps the block flushed just now — which the receiver's
+            // retro-validation correctly reads as a lying header and kills the whole AU. It bites
+            // exactly when the AU's length is a multiple of `shard_payload` (~1 in 1408 frames on
+            // a 1500-MTU link), and only on the slice arm: the legacy `must_flush` is a strict
+            // `>`, so its remainder is never empty. Keeping one whole shard back costs nothing —
+            // it rides out in the final block, which has to exist regardless.
+            let mut k = whole.min(self.fec.max_data_per_block as usize);
+            if k > 1 && k == whole && au.pending.len() == whole * payload {
+                k -= 1;
+            }
             let sof = !au.opened;
             let (bi, pts, uf) = (au.blocks_out, au.pts_ns, au.user_flags);
             let fi = au.frame_index;

crates/punktfunk-core/src/packet/reassemble.rs

@@ -467,14 +467,33 @@ impl Reassembler {
             return Ok(None);
         }
 
-        // First packet of a frame allocates its whole (zeroed) buffer, budget-gated; later
-        // packets must agree with its geometry. A sentinel-opened (streamed) frame allocates at
-        // the limits' maximum — its real size doesn't exist yet.
-        let buf_len = if sentinel {
-            total_data_max * shard_bytes
+        // How many shards of frame buffer THIS packet proves the frame needs. A sentinel carries
+        // no total, but it does pin its own block's extent — a slice sentinel by its wire base,
+        // a legacy one by its full-K position — and that is what the buffer must cover to place
+        // the shard. The frame grows as later blocks reveal more, and the final (non-sentinel)
+        // block's totals settle it.
+        //
+        // ⚠ NOT `total_data_max` (= the negotiated `max_frame_bytes`, 8-64 MiB): that shape
+        // shipped in 0.23.0 and was survivable only while sentinels were rare — the streamed
+        // path emitted one solely for an AU exceeding a whole FEC block (~281 KB). The slice
+        // wire flushes at `MIN_STREAM_BLOCK_SHARDS`, so EVERY ordinary AU became sentinel-opened
+        // and every one of them committed the full ceiling: a multi-megabyte zeroed allocation
+        // per access unit, and an in-flight budget (`IN_FLIGHT_BUF_FACTOR × max_frame_bytes`)
+        // exhausted after ~3 concurrent frames — beyond which every packet of every further
+        // frame was dropped outright. On a jittery link that is a permanent loss storm.
+        let need_shards = if sentinel && slice_stream {
+            frame_bytes / shard_bytes + data_shards
+        } else if sentinel {
+            // Legacy sentinels are full-K uniform blocks (firewall-enforced), so the block's
+            // index alone gives its end.
+            (block_idx + 1).saturating_mul(lim.max_data_shards)
         } else {
-            total_data * shard_bytes
-        };
+            total_data
+        }
+        .min(total_data_max);
+        // First packet of a frame allocates its (zeroed) buffer, budget-gated; later packets must
+        // agree with its geometry.
+        let buf_len = need_shards * shard_bytes;
         let frame = match win.frames.entry(hdr.frame_index) {
             std::collections::hash_map::Entry::Occupied(e) => e.into_mut(),
             std::collections::hash_map::Entry::Vacant(e) => {
@@ -602,6 +621,21 @@ impl Reassembler {
             drop(stats);
             return Ok(None);
         }
+        // Grow to this packet's proven extent. A streamed frame opens at whichever block arrived
+        // first and learns its real size from the final block's totals (or a later, higher
+        // sentinel base) — reorder means either can come first, so the buffer is sized by
+        // whatever the frame has proven so far. Never shrinks: the totals only settle the frame's
+        // END, and completion truncates to `frame_bytes` anyway. The budget is re-checked here
+        // for exactly the reason it is checked at open — growth commits memory too.
+        if buf_len > frame.buf.len() {
+            let delta = buf_len - frame.buf.len();
+            if *in_flight_bytes + delta > IN_FLIGHT_BUF_FACTOR * lim.max_frame_bytes {
+                drop(stats);
+                return Ok(None);
+            }
+            *in_flight_bytes += delta;
+            frame.buf.resize(buf_len, 0);
+        }
         let FrameBuf {
             buf,
             blocks,

crates/punktfunk-core/src/packet/tests.rs

@@ -941,8 +941,9 @@ fn slice_config() -> Config {
 
 /// Slice chunks chosen to exercise every packetizer path: an exact-shard slice, a slice with
 /// a sub-shard remainder, a slice below [`MIN_STREAM_BLOCK_SHARDS`] that must accumulate,
-/// and a finish tail. 1023 B total → blocks (K, base-shard): (20, 0), (25, 20), (18, 45),
-/// final (1, 63) with block_count 4.
+/// and a finish tail. 1023 B total → blocks (K, base-shard): (19, 0), (26, 19), (18, 45),
+/// final (1, 63) with block_count 4. Chunk 0 is an exact 20-shard multiple and flushes 19:
+/// a flush never drains `pending` to empty, so `finish_streamed` always seals real bytes.
 fn slice_chunks() -> Vec<Vec<u8>> {
     [320usize, 403, 100, 200]
         .iter()
@@ -1007,7 +1008,8 @@ fn slice_streamed_wire_shape_and_roundtrip() {
     assert_eq!(src.len(), 1023);
     // (block_index, K, base bytes) — chunk 2 (100 B) accumulated instead of flushing (6
     // whole shards < MIN_STREAM_BLOCK_SHARDS) and rode into block 2 with chunk 3's bytes.
-    let expect = [(0u16, 20u16, 0u32), (1, 25, 320), (2, 18, 720)];
+    // Block 0 keeps one shard back (chunk 0 is an exact multiple), which rides into block 1.
+    let expect = [(0u16, 19u16, 0u32), (1, 26, 304), (2, 18, 720)];
     for p in &pkts {
         let h = PacketHeader::read_from_bytes(&p[..HEADER_LEN]).unwrap();
         assert_ne!(
@@ -1478,15 +1480,24 @@ fn parts_flow_for_legacy_streamed_frames() {
     assert!(got.last().unwrap().complete);
 }
 
-/// A sentinel first-packet commits a MAX-sized frame buffer, so the in-flight budget must
-/// bite after IN_FLIGHT_BUF_FACTOR frames — the amplification bound for one-datagram opens.
+/// A one-datagram open commits only the buffer its OWN header proves it needs, and the
+/// in-flight budget still bounds the ones that claim a lot.
+///
+/// Both halves matter. A sentinel that claims little must cost little: sizing every
+/// sentinel-opened frame at `max_frame_bytes` (the 0.23.0 shape) was survivable only while
+/// sentinels were rare, and the slice wire made every ordinary AU one — after which the budget
+/// was spent on ~3 frames and everything else on the link was dropped. A sentinel that claims a
+/// lot must still be bounded: its wire base can point near the frame ceiling, which is the
+/// amplification this budget exists for.
 #[test]
-fn streamed_open_amplification_is_budget_bounded() {
-    let mut r = Reassembler::new(limits());
+fn streamed_open_commits_its_own_extent_and_stays_bounded() {
     let coder = coder_for(FecScheme::Gf8);
+    // limits(): shard 16 B, max_data_shards 8, max_frame_bytes 4096 → budget = 4 × 4096.
+    // Modest legacy sentinels (block 0, full K = 8 → 128 B each): far more than
+    // IN_FLIGHT_BUF_FACTOR of them must fit, because none of them claims the ceiling.
+    let mut r = Reassembler::new(limits());
     let stats = StatsCounters::default();
-    // limits(): max_frame_bytes 4096 → each sentinel open commits 4096 B; budget = 4×4096.
-    for fi in 0..5u32 {
+    for fi in 0..32u32 {
         let mut h = base_header();
         h.block_count = 0;
         h.frame_bytes = 0;
@@ -1498,10 +1509,35 @@ fn streamed_open_amplification_is_budget_bounded() {
             .unwrap()
             .is_none());
     }
+    assert_eq!(
+        stats.snapshot().packets_dropped,
+        0,
+        "ordinary one-datagram opens must not exhaust the in-flight budget"
+    );
+
+    // A SLICE sentinel whose wire base sits just under the ceiling really does commit a
+    // max-sized frame (base 3968 B + K 8 = 256 shards = 4096 B) — four fit the budget, the
+    // fifth must be refused.
+    let mut r = Reassembler::new(limits());
+    let stats = StatsCounters::default();
+    for fi in 0..5u32 {
+        let mut h = base_header();
+        h.user_flags = USER_FLAG_SLICE_STREAM;
+        h.block_count = 0;
+        h.frame_bytes = 4096 - 8 * 16;
+        h.block_index = 1;
+        h.data_shards = 8;
+        h.recovery_shards = 0;
+        h.frame_index = fi;
+        assert!(r
+            .push(&packet(h), coder.as_ref(), &stats)
+            .unwrap()
+            .is_none());
+    }
     assert_eq!(
         stats.snapshot().packets_dropped,
         1,
-        "the fifth max-sized open must be refused by the in-flight budget"
+        "the fifth ceiling-claiming open must be refused by the in-flight budget"
     );
 }
 
@@ -1612,3 +1648,124 @@ fn streamed_second_final_with_different_totals_is_rejected() {
         .expect("frame completes under the first pinned totals");
     assert_eq!(got.data.len(), 160);
 }
+
+/// Production-shaped slice geometry: a 1500-MTU shard payload and the smallest frame ceiling
+/// the QUIC handshake ever negotiates (`max_frame_bytes` is clamped to ≥ 8 MiB there).
+fn prod_slice_config() -> Config {
+    use crate::config::{FecConfig, ProtocolPhase, Role};
+    Config {
+        role: Role::Host,
+        phase: ProtocolPhase::P2Punktfunk,
+        fec: FecConfig {
+            scheme: FecScheme::Gf16,
+            fec_percent: 20,
+            max_data_per_block: 200,
+        },
+        shard_payload: crate::config::mtu1500_shard_payload(),
+        max_frame_bytes: 8 << 20,
+        encrypt: false,
+        key: SessionKey::Aes128Gcm([0u8; 16]),
+        salt: [0u8; 4],
+        loopback_drop_period: 0,
+    }
+}
+
+/// Packetize one streamed AU of `chunks`, each chunk an encoder slice boundary.
+fn streamed_packets_with(
+    cfg: &Config,
+    frame_index: u32,
+    pts_ns: u64,
+    slice: bool,
+    chunks: &[usize],
+) -> (Vec<Vec<u8>>, Vec<u8>) {
+    let coder = coder_for(cfg.fec.scheme);
+    let mut pk = Packetizer::new(cfg);
+    let uf = if slice { USER_FLAG_SLICE_STREAM } else { 0 };
+    let mut au = pk.begin_streamed(pts_ns, uf, Some(frame_index));
+    let (mut pkts, mut src) = (Vec::new(), Vec::new());
+    let sink = |pkts: &mut Vec<Vec<u8>>, h: &PacketHeader, b: &[u8]| {
+        let mut p = Vec::with_capacity(HEADER_LEN + b.len());
+        p.extend_from_slice(h.as_bytes());
+        p.extend_from_slice(b);
+        pkts.push(p);
+    };
+    for (c, &n) in chunks.iter().enumerate() {
+        let data: Vec<u8> = (0..n).map(|i| (c * 57 + i * 131 + 7) as u8).collect();
+        src.extend_from_slice(&data);
+        pk.push_streamed(&mut au, &data, true, coder.as_ref(), |h, b| {
+            sink(&mut pkts, h, b);
+            Ok(())
+        })
+        .unwrap();
+    }
+    pk.finish_streamed(au, coder.as_ref(), |h, b| {
+        sink(&mut pkts, h, b);
+        Ok(())
+    })
+    .unwrap();
+    (pkts, src)
+}
+
+/// An AU whose length is an exact multiple of the shard payload must still reassemble.
+///
+/// Regression: the slice flush drained `pending` to empty, so `finish_streamed` sealed a final
+/// block of one zero-padded FILLER shard. Its derived base (`total_data − 1`) overlapped the
+/// sentinel block flushed a moment earlier, the receiver's retro-validation read that as a lying
+/// header, and the whole AU was destroyed — one frame in every `shard_payload` (~12 s at 120 fps),
+/// each costing a re-anchor freeze and a recovery keyframe.
+#[test]
+fn slice_streamed_exact_shard_multiple_completes() {
+    let cfg = prod_slice_config();
+    let coder = coder_for(FecScheme::Gf16);
+    let payload = cfg.shard_payload;
+    for shards in [16usize, 29, 30, 64] {
+        let (pkts, src) = streamed_packets_with(&cfg, 1, 1000, true, &[shards * payload]);
+        // Whatever the block split, the final block must carry real bytes — never a lone
+        // zero-pad shard sitting on top of the previous block's range.
+        let mut r = Reassembler::new(ReassemblerLimits::from_config(&cfg));
+        let stats = StatsCounters::default();
+        let f = push_all(&mut r, coder.as_ref(), &stats, &pkts)
+            .unwrap_or_else(|| panic!("{shards}-shard AU (exact multiple) must complete"));
+        assert_eq!(f.data, src, "{shards}-shard AU must be byte-identical");
+    }
+    // ...and the sweep around one of them, so an off-by-one in the keep-back can't hide.
+    for extra in 0..3usize {
+        let n = 30 * payload + extra;
+        let (pkts, src) = streamed_packets_with(&cfg, 2, 2000, true, &[n]);
+        let mut r = Reassembler::new(ReassemblerLimits::from_config(&cfg));
+        let stats = StatsCounters::default();
+        let f = push_all(&mut r, coder.as_ref(), &stats, &pkts)
+            .unwrap_or_else(|| panic!("{n}-byte AU must complete"));
+        assert_eq!(f.data, src);
+    }
+}
+
+/// A slice-streamed frame must cost the reassembler its OWN size, not the negotiated ceiling.
+///
+/// Regression: sentinel-opened frames allocated `max_frame_bytes` (8-64 MiB) each. Since the
+/// slice wire makes every ordinary AU sentinel-opened, the in-flight budget
+/// (`IN_FLIGHT_BUF_FACTOR × max_frame_bytes`) was spent after ~3 concurrent frames and every
+/// packet of every further frame was dropped outright — a permanent loss storm on any link with
+/// normal reorder, plus a multi-megabyte zeroing per access unit.
+#[test]
+fn slice_streamed_in_flight_budget_matches_legacy() {
+    let cfg = prod_slice_config();
+    let coder = coder_for(FecScheme::Gf16);
+    // A normal 40 KB access unit, opened but not completed — the shape a link with reorder
+    // holds several of at once.
+    for slice in [false, true] {
+        let mut r = Reassembler::new(ReassemblerLimits::from_config(&cfg));
+        let stats = StatsCounters::default();
+        for i in 0..12u32 {
+            let (pkts, _) = streamed_packets_with(&cfg, i, 1_000_000 * i as u64, slice, &[40_000]);
+            r.push(&pkts[0], coder.as_ref(), &stats).unwrap();
+        }
+        assert_eq!(
+            stats
+                .packets_dropped
+                .load(std::sync::atomic::Ordering::Relaxed),
+            0,
+            "slice={slice}: 12 ordinary AUs in flight must fit the in-flight budget"
+        );
+    }
+}

crates/punktfunk-core/src/phase.rs

@@ -1,9 +1,105 @@
 //! Circular (directional) statistics for phase-locked capture (design/phase-locked-capture.md):
-//! the client-side half of the controller's v2 error signal. Pure math, no features — shared so
-//! every vsync-aware presenter (Android today, iOS next) computes the SAME statistic the host
+//! the client-side half of the controller's v2 error signal, plus the panel-grid learner every
+//! vsync-aware presenter paces against. Pure math, no features — shared so every presenter
+//! (Android today, iOS and the desktop session client next) computes the SAME statistic the host
 //! controller was tuned against, and so the controller's simulation tests can generate their
 //! synthetic reports through the identical code path.
 
+/// Plausible panel periods: ~24 Hz to ~500 Hz. A spacing outside this is a clock glitch, not a
+/// display mode, and must never reach the estimate.
+const PANEL_PERIOD_RANGE_NS: std::ops::RangeInclusive<i64> = 2_000_000..=42_000_000;
+
+/// Spacings within this of the estimate are the same grid — absorbs ordinary timeline jitter.
+const PANEL_GRID_TOLERANCE_NS: i64 = 200_000;
+
+/// Consecutive WIDER observations required before the estimate grows. One stray wide sample is a
+/// scheduling hiccup; eight in a row (~66 ms at 120 Hz) is a display that really did slow down.
+const PANEL_WIDEN_STREAK: u8 = 8;
+
+/// The panel's true refresh period, learned from observed vsync/frame-timeline spacing.
+///
+/// A presenter subdivides its release targets onto this grid, so an estimate FINER than the panel
+/// makes it aim at instants that never arrive and release faster than the display consumes —
+/// which is why the estimate has to be able to move both ways.
+///
+/// Seeding is the reason this is not simply "believe the last sample". The platform's *configured*
+/// mode is not the panel: under a per-uid frame-rate override a 120 Hz panel reports 60
+/// (`Display.getRefreshRate` returns the override — observed on-glass, A024), and the app's own
+/// choreographer callbacks arrive at the down-rated rate while the panel scans at its own. The
+/// mode TABLE is honest about what the panel *can* do, so it is the seed; the timeline spacing is
+/// honest about what it is *doing*, so it is the correction.
+///
+/// The asymmetry is deliberate. **Narrowing is immediate**: a finer real grid is always safe to
+/// subdivide onto, and it is the down-rate case the seed most often gets wrong. **Widening needs
+/// [`PANEL_WIDEN_STREAK`] consecutive agreeing observations** and then adopts the *narrowest* of
+/// them, because a wide sample is far more likely to be a missed callback than a mode change.
+///
+/// ⚠ 0.23.0 shipped this learner as narrow-only, seeded from the display mode the app *requests*
+/// (`preferredDisplayModeId` is a hint the system may refuse). A refused 120 Hz switch therefore
+/// left the presenter pacing a 60 Hz panel on an 8.33 ms grid with no way back — permanently.
+#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+pub struct PanelGrid {
+    period_ns: i64,
+    widen_streak: u8,
+    /// Narrowest wider-than-estimate spacing seen during the current streak.
+    widen_candidate: i64,
+}
+
+impl PanelGrid {
+    /// Seed from the display mode's refresh rate (`0` = unknown — the first plausible observation
+    /// then sets the estimate outright).
+    pub fn seeded(hz: i32) -> PanelGrid {
+        PanelGrid {
+            period_ns: if hz > 0 { 1_000_000_000 / hz as i64 } else { 0 },
+            widen_streak: 0,
+            widen_candidate: 0,
+        }
+    }
+
+    /// The learned period, or `0` while unknown.
+    pub fn period_ns(&self) -> i64 {
+        self.period_ns
+    }
+
+    /// Fold one observed grid spacing. Returns `true` when [`period_ns`](Self::period_ns) changed.
+    pub fn observe(&mut self, spacing_ns: i64) -> bool {
+        if !PANEL_PERIOD_RANGE_NS.contains(&spacing_ns) {
+            return false; // implausible — a clock glitch, not a display mode
+        }
+        if self.period_ns == 0 {
+            self.reset_streak();
+            self.period_ns = spacing_ns;
+            return true;
+        }
+        if spacing_ns < self.period_ns - PANEL_GRID_TOLERANCE_NS {
+            self.reset_streak();
+            self.period_ns = spacing_ns;
+            return true;
+        }
+        if spacing_ns > self.period_ns + PANEL_GRID_TOLERANCE_NS {
+            self.widen_streak = self.widen_streak.saturating_add(1);
+            self.widen_candidate = if self.widen_candidate == 0 {
+                spacing_ns
+            } else {
+                self.widen_candidate.min(spacing_ns)
+            };
+            if self.widen_streak >= PANEL_WIDEN_STREAK {
+                self.period_ns = self.widen_candidate;
+                self.reset_streak();
+                return true;
+            }
+            return false;
+        }
+        self.reset_streak(); // this sample agreed — the run of wider ones is broken
+        false
+    }
+
+    fn reset_streak(&mut self) {
+        self.widen_streak = 0;
+        self.widen_candidate = 0;
+    }
+}
+
 /// Circular (vector-mean) statistics of latch samples against a display period: the mean latch
 /// mod the period (ns) and the coherence (‰).
 ///
@@ -90,3 +186,111 @@ mod tests {
         assert!(circular_latch(&[1_000; 16], 0).is_none());
     }
 }
+
+#[cfg(test)]
+mod panel_grid_tests {
+    use super::*;
+
+    const P120: i64 = 8_333_333;
+    const P60: i64 = 16_666_666;
+
+    #[test]
+    fn seeds_from_the_mode_and_reports_unknown_without_one() {
+        assert_eq!(PanelGrid::seeded(120).period_ns(), 8_333_333);
+        assert_eq!(PanelGrid::seeded(0).period_ns(), 0);
+        let mut g = PanelGrid::seeded(0);
+        assert!(
+            g.observe(P120),
+            "the first plausible sample sets an unseeded grid"
+        );
+        assert_eq!(g.period_ns(), P120);
+    }
+
+    #[test]
+    fn narrows_immediately_when_the_panel_is_faster_than_the_mode_said() {
+        // The down-rate case: the mode table read 60, the timelines run at 120.
+        let mut g = PanelGrid::seeded(60);
+        assert!(g.observe(P120));
+        assert_eq!(g.period_ns(), P120, "a finer real grid is adopted at once");
+    }
+
+    /// The 0.23.0 bug: `preferredDisplayModeId` is a request, so a refused 120 Hz switch seeds a
+    /// 120 Hz grid on a panel that is really running 60. The narrow-only learner could never
+    /// climb back, and the presenter aimed at instants the panel never reached.
+    #[test]
+    fn widens_back_out_when_the_requested_mode_was_refused() {
+        let mut g = PanelGrid::seeded(120);
+        for i in 0..PANEL_WIDEN_STREAK - 1 {
+            assert!(!g.observe(P60), "sample {i} must not widen on its own");
+            assert_eq!(g.period_ns(), P120);
+        }
+        assert!(
+            g.observe(P60),
+            "a sustained run of wider spacings widens the grid"
+        );
+        assert_eq!(g.period_ns(), P60);
+    }
+
+    #[test]
+    fn one_stray_wide_sample_never_widens() {
+        let mut g = PanelGrid::seeded(120);
+        for _ in 0..40 {
+            assert!(!g.observe(P60));
+            assert!(!g.observe(P120)); // an agreeing sample breaks the run
+        }
+        assert_eq!(
+            g.period_ns(),
+            P120,
+            "alternating samples must not accumulate"
+        );
+    }
+
+    #[test]
+    fn widening_adopts_the_narrowest_of_the_run() {
+        let mut g = PanelGrid::seeded(120);
+        // A run of wide spacings that includes some very wide outliers.
+        let run = [
+            P60,
+            33_000_000,
+            P60 + 400_000,
+            41_000_000,
+            P60,
+            P60,
+            P60,
+            P60,
+        ];
+        for s in run {
+            g.observe(s);
+        }
+        assert_eq!(
+            g.period_ns(),
+            P60,
+            "the estimate takes the narrowest of the run, never an outlier"
+        );
+    }
+
+    #[test]
+    fn implausible_spacings_are_ignored_entirely() {
+        let mut g = PanelGrid::seeded(120);
+        for _ in 0..100 {
+            assert!(!g.observe(0));
+            assert!(!g.observe(-1));
+            assert!(!g.observe(1_000_000)); // 1000 Hz — below the range floor
+            assert!(!g.observe(100_000_000)); // 10 Hz — above the ceiling
+        }
+        assert_eq!(g.period_ns(), P120);
+    }
+
+    #[test]
+    fn a_transient_narrow_glitch_self_heals() {
+        // Narrowing is immediate, so a glitch DOES poison the estimate — the point is that it is
+        // no longer permanent (0.23.0's learner had no way back).
+        let mut g = PanelGrid::seeded(120);
+        assert!(g.observe(2_100_000), "a glitch narrows the estimate");
+        assert_eq!(g.period_ns(), 2_100_000);
+        for _ in 0..PANEL_WIDEN_STREAK {
+            g.observe(P120);
+        }
+        assert_eq!(g.period_ns(), P120, "and the real grid wins it back");
+    }
+}

crates/punktfunk-host/src/capture.rs

@@ -110,6 +110,11 @@ pub fn capture_virtual_output(
     vout: crate::vdisplay::VirtualOutput,
     want: OutputFormat,
     _capture: crate::session_plan::CaptureBackend,
+    // The output's compositor rewrites `SPA_META_Cursor` on every buffer (KWin), so an id-0 meta
+    // is an authoritative "pointer hidden" — the caller derives it from the backend that created
+    // `vout` (which also covers registry-pooled reuse: a kept display only ever matches its own
+    // backend). See `pf_capture`'s `cursor_id0_hides` contract.
+    cursor_id0_hides: bool,
 ) -> Result<Box<dyn Capturer>> {
     // The portal negotiates its own pixel format, so `want.gpu` gates GPU zero-copy capture (the
     // capture backend is always the portal — the `CaptureBackend` arg is a Windows-only dispatch)
@@ -132,6 +137,7 @@ pub fn capture_virtual_output(
         want.hdr,
         zero_copy_policy(want.pyrowave, want.nv12_native),
         vout.expect_exact_dims,
+        cursor_id0_hides,
     )
 }
 
@@ -171,6 +177,9 @@ pub fn capture_virtual_output(
     vout: crate::vdisplay::VirtualOutput,
     want: OutputFormat,
     _capture: crate::session_plan::CaptureBackend,
+    // Linux-only fact (the PipeWire cursor-meta contract); the IDD-push path has no
+    // `SPA_META_Cursor` and its own CURSOR_SUPPRESSED hide source.
+    _cursor_id0_hides: bool,
 ) -> Result<Box<dyn Capturer>> {
     let target = vout.win_capture.clone().ok_or_else(|| {
         anyhow::anyhow!(
@@ -285,6 +294,7 @@ pub fn capture_virtual_output(
     _vout: crate::vdisplay::VirtualOutput,
     _want: OutputFormat,
     _capture: crate::session_plan::CaptureBackend,
+    _cursor_id0_hides: bool,
 ) -> Result<Box<dyn Capturer>> {
     anyhow::bail!("virtual-output capture requires Linux or Windows")
 }

crates/punktfunk-host/src/devtest.rs

@@ -559,6 +559,7 @@ pub fn mirror_test(args: &[String]) -> Result<()> {
         vout,
         fmt,
         crate::session_plan::CaptureBackend::resolve(),
+        compositor == crate::vdisplay::Compositor::Kwin,
     )
     .context("attach a capturer to the mirrored monitor")?;
     cap.set_active(true);

crates/punktfunk-host/src/gamestream/stream.rs

@@ -570,6 +570,7 @@ fn open_gs_mirror_source(
         vout,
         pf_frame::OutputFormat::resolve(cfg.hdr, crate::zerocopy::enabled()),
         crate::session_plan::CaptureBackend::resolve(),
+        compositor == crate::vdisplay::Compositor::Kwin,
     )
     .context("attach a capturer to the mirrored monitor")
 }
@@ -782,6 +783,7 @@ fn open_gs_virtual_source(
         vout,
         capture::OutputFormat::resolve(cfg.hdr, crate::encode::resolved_backend_is_gpu()),
         crate::session_plan::CaptureBackend::resolve(),
+        compositor == crate::vdisplay::Compositor::Kwin,
     )
     .context("capture virtual output")?;
     capturer.set_active(true);

crates/punktfunk-host/src/native/stream.rs

@@ -1815,6 +1815,10 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
     // on purpose — it survives every in-loop rebuild path (session switch, mode/stall rebuilds,
     // encoder backoff), so a mid-stream rebuild keeps the acquired lock.
     let mut phase_ctl = PhaseController::new();
+    // Frame-driven wire-rate cap (see [`PaceBudget`]): a loop local like `phase_ctl`, and for the
+    // same reason — it must survive every in-loop rebuild path so a mid-stream rebuild can't
+    // reopen the overshoot. Bounded burst (CAP) is all a rebuild gap can buy.
+    let mut pace = PaceBudget::new(std::time::Instant::now());
     // The session's video frame numbering, owned HERE (the wire `frame_index` of the next AU this
     // loop hands to the send thread; the packetizer seals with exactly this via `seal_frame_at`).
     // A submission's future index is predicted as `au_seq + inflight.len()` — exact because AUs
@@ -3117,8 +3121,12 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
         // up to here. Each in-flight frame carries its own (capture_ns, deadline) for when it's polled.
         // Frame-driven mode (T1.1) re-anchors to the ACTUAL submit — arrivals are the clock, and a
         // fixed `+= interval` grid would drift against them and squeeze the pacing budget; the
-        // legacy tick keeps its fixed grid (with the catch-up reset in the tail).
+        // legacy tick keeps its fixed grid (with the catch-up reset in the tail). The rate-cap
+        // charge lives under the same guard as the tail's gate: the legacy tick paces by its grid
+        // alone, and charging it without ever accruing would bank unbounded debt that stalls the
+        // loop if a rebuild later flips the capturer to arrival-wait.
         next = if frame_driven_enabled() && capturer.supports_arrival_wait() {
+            pace.charge();
             std::time::Instant::now() + interval
         } else {
             next + interval
@@ -3477,9 +3485,12 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
             // T1.1 frame-driven trigger: instead of sleeping out the whole tick and then
             // SAMPLING (which holds a frame that arrived just after the previous sample for up
             // to a full interval — ~half on average), sleep only to the rate floor and then
-            // wake on the capture's actual arrival. The 0.9×interval floor caps the encode
-            // rate at ~1.11× target when the source runs faster (compositor Hz > session fps);
-            // the +0.5×interval keepalive keeps a static desktop re-encoding (bitrate shape,
+            // wake on the capture's actual arrival. The 0.9×interval floor leaves per-gap jitter
+            // headroom; the `pace` budget pins the long-run AVERAGE at the pacing rate — the
+            // floor alone let a source that always has a frame pending (an HZ_MULT-overdriven
+            // display under uncapped content) settle at 0.9-interval spacing, 1.11× the
+            // negotiated rate on the wire, frames the client's panel can only drop. The
+            // +0.5×interval keepalive keeps a static desktop re-encoding (bitrate shape,
             // client liveness) at 1.5×interval cadence and bounds control-servicing latency.
             //
             // Anchor the floor to THIS frame's arrival (`t_cap`), not to `next` — `next` is
@@ -3489,9 +3500,12 @@ pub(super) fn virtual_stream(ctx: SessionContext, prepared: Option<PreparedDispl
             // period becomes interval + encode (≈158 fps off a 240 Hz source; 360 Hz → ~200).
             // An async encoder (NVENC) returns from submit in ≈0, so t_cap ≈ post-submit and this
             // is a no-op for it — which is why H.26x already holds full rate. Arrival-anchoring
-            // lets the synchronous encode overlap the interval; the ≥0.9×interval spacing from
-            // the last grab still caps the rate at ~1.11× target.
-            let earliest = t_cap + interval.mul_f32(0.9);
+            // lets the synchronous encode overlap the interval; the budget, not the floor, is
+            // what bounds the sustained rate.
+            let earliest = std::cmp::max(
+                t_cap + interval.mul_f32(0.9),
+                pace.earliest(std::time::Instant::now(), interval),
+            );
             if let Some(d) = earliest.checked_duration_since(std::time::Instant::now()) {
                 std::thread::sleep(d);
             }
@@ -4001,6 +4015,59 @@ fn pacing_hz(session_hz: u32, achieved_hz: u32) -> u32 {
     achieved_hz.min(session_hz).max(1)
 }
 
+/// Long-run rate limiter for the frame-driven trigger (T1.1): pins the AVERAGE encode rate at the
+/// pacing rate while the 0.9×interval arrival floor keeps its jitter headroom.
+///
+/// The floor alone bounds only each gap, so a source that always has a frame pending — a display
+/// overdriven by `PUNKTFUNK_VDISPLAY_HZ_MULT`, uncapped content — settles at 0.9-interval spacing:
+/// 1.11× the negotiated rate on the wire (field report: 132 fps on a 120 fps session, frames the
+/// client's 120 Hz panel can only drop). Credit accrues at one frame per interval of real elapsed
+/// time (capped at [`Self::CAP`]) and every submitted frame spends one; a grab may run early only
+/// against banked credit, so per-gap jitter still passes while the average cannot exceed the
+/// pacing rate. A source at or below the pacing rate banks credit faster than it spends and is
+/// never delayed.
+struct PaceBudget {
+    /// Banked frames, in `[-1.0, CAP]`. Transiently dips below 0 when a grab spent credit it had
+    /// only partly banked; the owed fraction is repaid before the next grab.
+    credit: f32,
+    /// When credit last accrued (the previous [`Self::earliest`] call).
+    last: std::time::Instant,
+}
+
+impl PaceBudget {
+    /// Burst allowance: at most this many frames may follow a stall back-to-back before the
+    /// bucket re-gates. One frame of instant catch-up plus the floor's own headroom.
+    const CAP: f32 = 1.25;
+
+    fn new(now: std::time::Instant) -> PaceBudget {
+        PaceBudget {
+            credit: Self::CAP,
+            last: now,
+        }
+    }
+
+    /// Accrue the elapsed credit and return the earliest instant the next grab may run: `now`
+    /// once a full frame is banked, else the missing fraction of an interval out.
+    fn earliest(
+        &mut self,
+        now: std::time::Instant,
+        interval: std::time::Duration,
+    ) -> std::time::Instant {
+        let secs = interval.as_secs_f32();
+        if secs > 0.0 {
+            let accrued = now.duration_since(self.last).as_secs_f32() / secs;
+            self.credit = (self.credit + accrued).min(Self::CAP);
+        }
+        self.last = now;
+        now + interval.mul_f32((1.0 - self.credit).max(0.0))
+    }
+
+    /// One frame submitted — spend its credit.
+    fn charge(&mut self) {
+        self.credit -= 1.0;
+    }
+}
+
 /// Adopt the rate a freshly built pipeline's encoder was actually opened at.
 ///
 /// The session's own `bitrate_kbps` is the number every later decision reads — the ABR controller's
@@ -4122,9 +4189,19 @@ fn build_pipeline(
     // VIDEO_CAP_10BIT + host opted in via PUNKTFUNK_10BIT) is our HDR path → BT.2020 PQ Rgb10a2;
     // otherwise the FP16 IDD frames are converted to 8-bit SDR. (Ignored by non-IDD-push backends,
     // which auto-detect HDR from the monitor state.)
-    let mut capturer =
-        crate::capture::capture_virtual_output(vout, plan.output_format(), plan.capture)
-            .context("capture virtual output")?;
+    //
+    // KWin rewrites `SPA_META_Cursor` on every buffer, so its id-0 metas are an authoritative
+    // "pointer hidden" the cursor blend/forward must honor — without this, the composited arrow
+    // outlives every in-game/Big Picture hide (0.22.0 field report). Derived from the backend
+    // (correct for pooled reuse too — a kept display only matches its own backend).
+    let cursor_id0_hides = vd.name() == pf_vdisplay::Compositor::Kwin.id();
+    let mut capturer = crate::capture::capture_virtual_output(
+        vout,
+        plan.output_format(),
+        plan.capture,
+        cursor_id0_hides,
+    )
+    .context("capture virtual output")?;
     // gamescope (Phase C): gamescope paints no `SPA_META_Cursor`, so hand the capturer a way to
     // reach gamescope's nested Xwaylands — it reads the pointer over X11 (XFixes shape +
     // QueryPointer position) and feeds `cursor()`, which the encode loop composites.
@@ -4270,6 +4347,105 @@ mod tests {
         assert_eq!(pacing_hz(60, 0), 1);
     }
 
+    /// Drive [`PaceBudget`] against a source that ALWAYS has a frame pending (the overdriven
+    /// display + uncapped content case): each cycle grabs the instant the gate opens, the next
+    /// `earliest` call runs right after (encode folded into the wait, like the loop). Returns the
+    /// grab instants.
+    fn grab_saturated(
+        b: &mut PaceBudget,
+        start: std::time::Instant,
+        interval: std::time::Duration,
+        n: usize,
+    ) -> Vec<std::time::Instant> {
+        let mut now = start;
+        let mut grabs = Vec::with_capacity(n);
+        for _ in 0..n {
+            let gate = b.earliest(now, interval);
+            let grab = gate.max(now);
+            b.charge();
+            grabs.push(grab);
+            now = grab;
+        }
+        grabs
+    }
+
+    #[test]
+    fn pace_budget_pins_a_saturated_source_at_the_interval() {
+        let interval = std::time::Duration::from_millis(10);
+        let t0 = std::time::Instant::now();
+        let mut b = PaceBudget::new(t0);
+        let grabs = grab_saturated(&mut b, t0, interval, 120);
+        // Whatever the initial credit bought, the total may exceed the on-rate schedule by at
+        // most the burst cap — 120 grabs span no less than (120 - 1 - CAP) intervals.
+        let span = grabs[119].duration_since(grabs[0]);
+        assert!(
+            span >= interval.mul_f32(120.0 - 1.0 - PaceBudget::CAP),
+            "span {span:?} admits more than CAP frames of overshoot"
+        );
+        // And the steady state is EXACTLY the interval: past the warmup, consecutive grabs are
+        // one interval apart (not 0.9 — the 132-fps bug).
+        for w in grabs[20..].windows(2) {
+            let gap = w[1].duration_since(w[0]);
+            assert!(
+                gap >= interval.mul_f32(0.999) && gap <= interval.mul_f32(1.001),
+                "steady-state gap {gap:?} != interval {interval:?}"
+            );
+        }
+    }
+
+    #[test]
+    fn pace_budget_never_delays_an_on_rate_or_slow_source() {
+        let interval = std::time::Duration::from_millis(10);
+        let t0 = std::time::Instant::now();
+        let mut b = PaceBudget::new(t0);
+        // A source at half the pacing rate (a 60 fps game on a 120 fps session): every arrival
+        // banks two frames of credit and spends one — the gate is always already open.
+        let mut now = t0;
+        for _ in 0..50 {
+            now += interval * 2;
+            assert_eq!(
+                b.earliest(now, interval),
+                now,
+                "slow source must not be gated"
+            );
+            b.charge();
+        }
+        // Exactly on-rate: still never gated (credit hovers at the cap, never below 1).
+        let mut b = PaceBudget::new(t0);
+        let mut now = t0;
+        for _ in 0..50 {
+            now += interval;
+            assert_eq!(
+                b.earliest(now, interval),
+                now,
+                "on-rate source must not be gated"
+            );
+            b.charge();
+        }
+    }
+
+    #[test]
+    fn pace_budget_burst_after_a_stall_is_capped() {
+        let interval = std::time::Duration::from_millis(10);
+        let t0 = std::time::Instant::now();
+        let mut b = PaceBudget::new(t0);
+        // Settle into the gated steady state, then stall the source for 10 intervals.
+        let grabs = grab_saturated(&mut b, t0, interval, 20);
+        let stall_end = grabs[19] + interval * 10;
+        // However long the stall, the recovery may run ahead of the on-rate schedule by at most
+        // CAP frames: the second post-stall grab is already re-gated.
+        let after = grab_saturated(&mut b, stall_end, interval, 3);
+        assert_eq!(after[0], stall_end, "first post-stall grab is immediate");
+        assert!(
+            after[1].duration_since(after[0]) >= interval.mul_f32(2.0 - PaceBudget::CAP),
+            "second post-stall grab spent more than the burst cap"
+        );
+        assert!(
+            after[2].duration_since(after[1]) >= interval.mul_f32(0.999),
+            "third post-stall grab must be back on the interval grid"
+        );
+    }
+
     #[test]
     fn display_mode_multiplier_scales_only_the_refresh() {
         // Default (no env set in the test process) is 1× — the identity, which is what every

crates/punktfunk-host/src/spike.rs

@@ -118,6 +118,7 @@ pub fn run(opts: Options) -> Result<()> {
                 vout,
                 capture::OutputFormat::resolve(false, crate::encode::resolved_backend_is_gpu()),
                 crate::session_plan::CaptureBackend::resolve(),
+                compositor == crate::vdisplay::Compositor::Kwin,
             )
             .context("capture virtual output")?
         }

docs-site/content/docs/automation.md

@@ -237,6 +237,13 @@ the session, gives it back if anything crashes, and tells you which half of the
 it isn't working. That is the supported route, and the rest of this section is only for people who
 would rather not install a plugin.
 
+**Turn off controller forwarding on the couch.** Whatever route you take below, the client that
+hands the device over should stop *also* forwarding it: Settings → **Forward controllers**, off
+([Client settings](/docs/client-settings#input)). Otherwise the host ends up with two controllers
+for one pair of hands and games read both. On Linux and Windows it matters twice over — while the
+client has the pad open it has *claimed* the device node, and VirtualHere cannot bind a device
+somebody else is holding.
+
 **The two sides.** VirtualHere is a server/client pair, and you run both: the **server on the couch**
 (where the device is plugged in) shares it, and the **client on the host** mounts it. The client's
 `-t` flag is a one-shot IPC to the already-running client — `-t LIST` prints every visible device

docs-site/content/docs/client-settings.md

@@ -15,8 +15,10 @@ The Linux, Windows, Mac, iPhone/iPad and Android apps group settings the same wa
 **Display**, **Input**, **Audio**, **Controllers** — under *Preferences* on Linux and *Settings*
 elsewhere. The Apple TV app shows one scrolling list instead, and so does any client's settings
 screen reached with a controller. A controller-driven launch (Steam Deck Gaming Mode) opens the
-client's **console home**, whose settings screen is one steppable list; the Decky plugin has a
-smaller section of its own. The console home is part of the client — it is not the host's
+client's **console home**, whose settings screen is one steppable list; the Decky plugin's Settings
+tab covers the same store in the same groups and the same order, as a left rail of categories the
+way SteamOS's own Settings looks. The console home is part of the
+client — it is not the host's
 [web console](/docs/web-console).
 
 Linux stores them in `~/.config/punktfunk/client-gtk-settings.json`, the same file the Decky plugin
@@ -43,8 +45,9 @@ and your client scales what it gets — see
 
 **Match window** — *default: off.* The stream mode follows your window instead, and each resize
 renegotiates the host's display and encoder, so a windowed session stays pixel-exact. Fullscreen
-degenerates to the display's native mode. Offered by the Linux, Windows, Mac, iPhone/iPad and console
-home screens; not by Android or Decky.
+degenerates to the display's native mode. Offered by the Linux, Windows, Mac, iPhone/iPad, console
+home and Decky screens (on Decky it sits in the Resolution picker, and Gaming-Mode streams are
+always fullscreen, so it lands on native); not by Android.
 
 **Refresh rate** — *default: Native*, the refresh of the display your window is on. The Apple app
 stores an explicit rate (60 Hz by default): iPhone and iPad offer the rates the device can display,
@@ -69,8 +72,8 @@ link. The stops run 0.5× to 4×. The result is floored to an even size and capp
 
 **Video codec** — *default: Automatic.* A soft preference: the host emits your choice when it can
 also produce it, otherwise the best codec you both speak, in the order HEVC → AV1 → H.264.
-**PyroWave** is never auto-picked — pick it explicitly on Linux, Windows, the console home, or an
-Apple device whose decode probe passes; anywhere else it isn't offered, and asking for it lands on
+**PyroWave** is never auto-picked — pick it explicitly on Linux, Windows, the console home, Decky, or
+an Apple device whose decode probe passes; anywhere else it isn't offered, and asking for it lands on
 that same order. See [PyroWave](/docs/pyrowave). The Android and Apple apps hide AV1 unless the
 device has a hardware AV1 decoder; Android never offers PyroWave.
 
@@ -82,9 +85,38 @@ Full detail: [HDR](/docs/hdr).
 **Full chroma (4:4:4)** — *default: off.* Crisp small text and thin lines, at more bandwidth. It
 needs HEVC or PyroWave, the host's own 4:4:4 policy left on, a capture path that delivers full
 chroma, and a GPU that can encode it; if any gate fails the host says 4:2:0 before your decoder is
-built. **Today only the Apple app actually advertises 4:4:4**, and only when its hardware decode
-probe passes — the Linux and Windows apps store the toggle but their session doesn't advertise the
-capability yet, so it has no effect there. Android, Decky and the console home don't offer it.
+built. The Apple, Linux and Windows apps all advertise it (Apple additionally requires its hardware
+decode probe to pass). The console home and Decky offer the toggle; Android doesn't.
+
+**Prioritize** — *default: Lowest latency.* What the client optimizes for when a decoded frame is
+ready. **Lowest latency** shows every frame the moment the display can take it, so a network hiccup
+becomes an occasional repeated or skipped frame. **Smoothness** holds a small buffer that evens
+those hiccups out, at that buffer's worth of added delay. Linux and Windows apps, the console home
+and Decky; the Apple and Android apps have carried the same setting for a while, and it is stored
+under the same name, so a [profile](/docs/profiles-and-links) means the same thing on every device.
+
+**Smoothness buffer** — *default: Automatic (two frames).* Only shown under **Smoothness**. How
+many frames are held back before showing. Each frame absorbs roughly one screen refresh of network
+hiccup and costs one refresh of delay — so on a 120 Hz screen, two frames is about 17 ms of extra
+delay bought against 17 ms of jitter. If you never see stutter, you don't need this. Wherever
+**Prioritize** is offered, and greyed out until you pick Smoothness.
+
+**V-Sync** — *default: on.* Tear-free presentation. Turning it off asks the GPU to show each frame
+the instant it's ready instead of waiting for the screen's next refresh: the lowest delay a display
+can give you, at the cost of visible tearing on fast motion. It is **best-effort** — not every
+driver or compositor offers a tearing mode, and where none is available the stream stays tear-free.
+The Detailed [stats overlay](/docs/stats) names the mode actually in use, so you can tell "off"
+from "off but unavailable". Linux and Windows apps, the console home and Decky.
+
+**Follow variable refresh rate** — *default: on.* On a VRR / FreeSync / G-Sync screen, let the panel
+refresh in step with the stream rather than on a fixed cadence — which removes the wait between a
+frame being ready and the screen being willing to show it. Applies to **fullscreen** sessions (a
+windowed one is at the compositor's mercy) and is harmless on a fixed-refresh screen. It needs a
+graphics driver that offers the modern queue-free display mode; on an older driver it does nothing
+unless you also set `PUNKTFUNK_VRR_FIFO=1` (see [configuration](/docs/configuration)), because the
+older way of following a panel costs noticeable latency on a fixed-refresh screen. The stats overlay
+reports `vrr yes` once it has *measured* that the panel really is following. Linux and Windows apps,
+the console home and Decky.
 
 **Host compositor** — *default: Automatic.* Which backend a **Linux** host uses to drive the virtual
 output. Advisory: a host without that backend quietly auto-detects instead.
@@ -96,7 +128,7 @@ stereo. The count the host will really send comes back in the handshake, and you
 decoder from *that*, never from the request. What surround means differs by host: a **Linux** host
 claims a sink advertising exactly that many channels, so applications produce real surround, while a
 **Windows** host loopback-captures your current output endpoint and lets Windows convert it — so 5.1
-from a stereo endpoint is an upmix, not new channels. Offered everywhere except the Decky plugin.
+from a stereo endpoint is an upmix, not new channels. Offered everywhere.
 
 **Microphone** — *default: off on Linux, Windows, Android, the console home and Decky; on in the
 Apple app.* Sends this device's microphone to the host's virtual mic. On Linux and Windows the
@@ -110,22 +142,44 @@ from an echo-cancelled PipeWire source when your desktop provides one, on **Wind
 for the Communications stream category so the endpoint's processing engages, and on **Apple** and
 **Android** the platform's voice-processing mode. Turn it off if your microphone already runs its
 own processing, or if the canceller makes your voice sound thin. The row sits under the microphone
-toggle and greys out while the microphone is off. Offered by the Linux, Windows, Apple, Android and
-console-home clients; Decky has no toggle. What it can and can't fix is in
+toggle and greys out while the microphone is off. Offered by the Linux, Windows, Apple, Android,
+console-home and Decky clients. What it can and can't fix is in
 [Why do I hear myself](/docs/echo).
 
 **Speaker** and **Microphone** device pickers — *default: System default.* Which endpoint stream
-audio plays out of, and which input feeds the uplink. Only the Linux app (PipeWire nodes) and the
-**Mac** app (which also has a microphone *channel* picker) have these — iPhone, iPad, Apple TV,
-Android, Decky and the console home have none, and the Windows app has none and ignores a stored
+audio plays out of, and which input feeds the uplink. Only the Linux app (PipeWire nodes), the
+**Mac** app (which also has a microphone *channel* picker) and **Decky** have these — iPhone, iPad,
+Apple TV, Android and the console home have none, and the Windows app has none and ignores a stored
 speaker choice. On Linux, a device that has since disappeared keeps a "(not detected)" entry rather
-than silently snapping back to the default; the Mac shows it as "Unavailable device".
+than silently snapping back to the default; the Mac shows it as "Unavailable device" and Decky as
+"(not connected)". Decky reads the endpoint list from the client's session binary, so a client
+older than the two-binary split leaves these pickers on Automatic.
 
 ## Input
 
-Touch modes, mouse modes and the in-stream chords have their own page: [Input](/docs/input). Four
+Touch modes, mouse modes and the in-stream chords have their own page: [Input](/docs/input). Five
 more settings are worth naming here.
 
+**Forward controllers** — *default: on*, on every client. Off, the controllers connected to *this*
+device are not sent to the host at all. That is what you want when your controller already reaches
+the host by some other route — [USB passthrough](/docs/automation#recipe-full-controller-passthrough-virtualhere)
+such as VirtualHere, or simply a pad plugged into the host itself. Leaving forwarding on in that
+situation hands the host two controllers for one pair of hands, and games read both: a stick drifts
+because the second pad is centred, or a menu takes every input twice.
+
+On Linux and Windows it does more than stay quiet. Opening a controller is what *claims* it — the
+client's SDL takes the device node — and a claimed device is one a passthrough tool cannot bind. So
+with this off the session never opens the controller at all, which is precisely what leaves it free
+for VirtualHere to hand over. The consequence to know: the
+[controller escape chord](/docs/input#leaving-with-a-controller) is read off forwarded pads, so it is
+unavailable on those two while this is off — leave a stream with the keyboard chord or the client's
+own UI. The Apple and Android apps claim nothing, so their chords keep working either way; the
+Android app does stop its DualSense and Steam Controller 2 USB captures, which *do* claim the
+device.
+
+The rows below it — which pad, and what type — have nothing to act on while this is off, and every
+client greys them out to say so.
+
 **Gamepad type** (*Controller type* on Apple, Android and the console home) — *default: Automatic*,
 which matches each physical controller. The pickers offer Xbox 360, Xbox One, DualSense and
 DualShock 4 everywhere, plus Steam Deck on Linux, Android, the console home and Decky. Your client
@@ -139,8 +193,10 @@ which forwards *every* connected controller, each as its own player, on Linux, W
 console home. Pinning one restricts the session to that controller alone — single-player. The Android
 app has no such picker.
 
-**Capture system shortcuts** — *default: on.* Offered by the Linux and Windows apps only; Windows
-spells the row out as *Capture system shortcuts (Alt+Tab, Win, …)*. On, Alt+Tab and the Windows key
+**Capture system shortcuts** — *default: on.* Offered by the Linux and Windows apps, the console home
+and Decky; Windows spells the row out as *Capture system shortcuts (Alt+Tab, Win, …)*. On a Deck it
+matters only for a keyboard you attached yourself, for the reason the paragraph below gives: Gaming
+Mode is gamescope, which has nothing to hold back. On, Alt+Tab and the Windows key
 (Super on Linux) reach the host while the stream has input captured. Off, they act on this machine
 instead — what you want when the stream shares a screen with local work. Either way the chords come
 back the moment you release capture with **Ctrl+Alt+Shift+Q**, the window loses focus, or the stream
@@ -159,17 +215,22 @@ the wlroots compositors all do, and X11 sessions grab the keyboard directly. Und
 Wake-on-LAN and waits for it to boot — only for a host whose MAC address this client has already
 learned. Turn it off for hosts you reach over a VPN, where "offline" usually means "not reachable by
 broadcast" and the wake only adds a delay. The Linux, Windows, Apple and Android apps have this
-toggle. The console home has no toggle — it offers wake as an explicit action on an offline host
-instead — and the Decky plugin always sends a wake before a stream starts. See
+toggle, as do the console home and Decky — and note that the Decky plugin sends a wake of its own
+before a stream starts whatever this setting says, so on a Deck it governs the client's connect
+rather than the launch. The console home also offers wake as an explicit action on an offline host.
+See
 [Wake-on-LAN](/docs/wake-on-lan).
 
 **Show game library** — *default: off on Linux and Windows; on in the Apple and Android apps.* Browse
-a paired host's games and launch one directly; the Windows app still labels it experimental. There is
-no toggle in the console home or in Decky. See [Game library](/docs/game-library).
+a paired host's games and launch one directly; the Windows app still labels it experimental. The
+console home and Decky have the toggle too — on Decky it governs the *client's* screens, since the
+plugin's own library browser works either way. See [Game library](/docs/game-library).
 
 **Start streams in fullscreen** — *default: on.* On Linux and Windows, F11 or Alt+Enter leaves
 fullscreen live. On a Mac the setting is **Fullscreen while streaming**, and the window comes back
-when you return to the host list. iPhone, iPad, Apple TV and Android have no equivalent.
+when you return to the host list. The console home and Decky carry the row for the desktop client
+that shares the store — a Gaming-Mode launch is fullscreen whatever it says. iPhone, iPad, Apple TV
+and Android have no equivalent.
 
 ## Overlay
 
@@ -177,7 +238,8 @@ when you return to the host list. iPhone, iPad, Apple TV and Android have no equ
 superset of the one before. This setting only picks the tier a session *starts* at — you can cycle
 them live in-stream, with a shortcut that differs by platform. The Apple app additionally lets you
 choose which corner the overlay sits in (Top Left, Top Right, Bottom Left, Bottom Right). The Decky
-plugin has no stats setting. The shortcuts, and every number in the overlay, are in
+plugin has the tier picker too, in its Settings section. The shortcuts, and every number in the
+overlay, are in
 [Understanding the stats overlay](/docs/stats).
 
 ## Settings that are facts about your device
@@ -189,11 +251,14 @@ stay global and **cannot be put in a settings profile**:
   vendor-ordered and falls back on its own; change it only when debugging, and note that
   `PUNKTFUNK_DECODER` overrides it
   ([Configuration](/docs/configuration#client-side-native-clients)). The decoder picker is on Linux,
-  Windows and in the console home; the GPU picker on Windows, and on Linux only when the machine has
-  more than one adapter. The Apple and Android apps have neither.
+  Windows, in the console home and in Decky; the GPU picker on Windows, and on Linux and Decky only
+  when the machine has more than one adapter — which a Deck doesn't, so the row isn't there. The
+  Apple and Android apps have neither.
 - **Speaker** and **Microphone** device pickers — this device's audio endpoints.
 - **Forwarded controller** — which physical pad is in your hands. The *type* the host creates is a
-  preference and can live in a profile; which pad you hold cannot.
+  preference and can live in a profile; which pad you hold cannot. **Forward controllers** is a
+  preference too, and does live in a profile — a work profile can decline to forward what a game
+  profile forwards.
 - **Auto-wake on connect** and **Show game library** — decisions about this device and this network,
   not about how a given host is streamed.
 

docs-site/content/docs/configuration.md

@@ -242,6 +242,9 @@ A few knobs are read by the native **clients**, not the host:
 | `PUNKTFUNK_OSD_SCALE` | multiplier, e.g. `1.5` *(default `1`)* | Size of the in-stream overlay — the stats OSD, the capture hint and the start banner. They already follow your display's scaling setting (200 % display → twice the pixels), so set this only to nudge that: bigger for a TV across the room, smaller if your compositor reports an aggressive scale. Clamped to 0.5×–4×, and a line that would run off the screen is shrunk to fit. |
 | `PUNKTFUNK_NO_AEC` | `1` | Turn the microphone's echo cancellation off for this run, whatever **Echo cancellation** says in [client settings](/docs/client-settings#audio). One-way: it can only switch the processing off, never back on, and the setting is the normal way to control it. Linux and Windows clients. |
 | `PUNKTFUNK_PRESENT_MODE` | `mailbox` *(default)* · `fifo` · `immediate` · `fifo_relaxed` | How decoded frames meet the display (the Vulkan present mode). The default prefers MAILBOX — tear-free without queueing behind the vertical refresh — and falls back to FIFO (classic vsync) where the driver doesn't offer it. **AMD's Windows driver offers no MAILBOX**, so those clients run FIFO, which adds a standing frame-pacing wait (up to one refresh interval). `immediate` removes that wait but can tear; `fifo_relaxed` only tears when a frame is late. If your latency floor matters more than tearing, try `immediate` and judge by eye. |
+| `PUNKTFUNK_PRESENTER` | `arrival` | Turn the frame-pacing engine off for this run: frames present the instant they decode, exactly as they did before the **Prioritize** setting existed. A diagnostic — if a pacing change is suspected of causing judder or added delay, this switches it off without reinstalling anything. Linux and Windows clients. |
+| `PUNKTFUNK_VRR_FIFO` | `1` | Force the display mode used to follow a **variable-refresh (VRR / FreeSync / G-Sync)** screen, on graphics drivers too old to offer the modern one. You almost certainly don't need this: where the driver supports the modern mode — which is what **Follow variable refresh rate** in [client settings](/docs/client-settings#video) uses — following the panel is already automatic and costs almost nothing. On an older driver the only way to follow the panel is a mode that measured roughly 27 ms *worse* on a fixed-refresh screen, so it stays off unless you ask for it, and it's only worth asking if you genuinely have a VRR screen and play fullscreen. Check the Detailed [stats overlay](/docs/stats): `vrr yes` means the panel really is following the stream. Linux and Windows clients. |
+| `PUNKTFUNK_PRESENT_DEBUG` | `1` | Log the presenter's own 1-second summary (display mode, buffer drops, pacing counters) every second, even when nothing is going wrong. Without it the line appears only when there is something to report. |
 | `PUNKTFUNK_ABR_PROBE_KBPS` | kbps, e.g. `900000` | The startup link-capacity probe's burst target (default 2 Gbps — deliberately above any plausible link so the burst measures the link, not itself). Lower it on links the burst shouldn't slam, or when the measured ceiling comes out wrong for your setup. |
 | `PUNKTFUNK_ABR_PROBE` | `0` | Skip the startup link-capacity probe entirely. The adaptive-bitrate climb ceiling then stays at the negotiated starting rate — a blunt instrument; prefer `PUNKTFUNK_ABR_MAX_MBPS`. |
 | `PUNKTFUNK_ABR_MAX_MBPS` | Mbps, e.g. `300` | Hard cap on the adaptive bitrate's climb ceiling, whatever the startup probe measured. The escape hatch when adaptive sessions keep climbing past what your client's **decoder** can sustain (periodic hitch + "receive backlog stopped draining" in the client log). An explicit bitrate setting still bypasses ABR entirely. |

docs-site/content/docs/input.md

@@ -92,6 +92,12 @@ an Xbox pad), held on any connected pad.
 - **Android** — holding it about a second disconnects. A quick press does nothing; the moment the
   chord completes a **Hold to quit…** cue appears so you know it registered.
 
+The chord is read off the pads a client forwards, so turning
+[**Forward controllers**](/docs/client-settings#input) off takes it away on **Linux and Windows** —
+there the client stops opening the controller at all, which is the point of the setting. Use
+**Ctrl+Alt+Shift+D** or the client's own UI to leave instead. The Apple and Android apps keep
+watching for the chord either way.
+
 ## Mouse modes
 
 There are two, and they are a per-client setting called **Mouse input**:

docs-site/content/docs/stats.md

@@ -62,8 +62,9 @@ differently. Linux · Windows · Steam Deck:
 
 ```
 1920×1080@120 · 120 fps · 24.3 Mb/s · target 30 Mb/s (auto) · vulkan · HDR
-e2e 14.2/19.8 ms (p50/p95) · host 3.1 · net 6.7 · decode 2.1 · display 2.3 ms
+e2e 14.2/19.8 ms (p50/p95) · host 3.1 · net 6.7 · decode 2.1 · display 2.3 ms (pace 0.6 + latch 1.7)
 host: queue 0.6 · encode 1.8 · xfer 0.2 · pace 0.5 ms
+present: mailbox
 lost 3 (2.4%)
 ```
 
@@ -109,10 +110,11 @@ lost 3 (2.4%)
   which otherwise reads as inexplicable judder plus a refresh of extra latency.
 - **Line 2 — the headline.** `end-to-end` (`e2e` on Linux/Windows) is the *directly
   measured* time from host capture to the endpoint named at the end of the line —
-  `capture→on-glass` or `capture→displayed`. Linux/Windows don't spell the endpoint out,
-  because their presenter always measures to the present instant. `p50` = the typical
-  frame (median), `p95` = the slow outliers. This is the one number that summarizes your
-  stream.
+  `capture→on-glass` or `capture→displayed`. On Linux/Windows the endpoint is the moment
+  the frame is genuinely **visible** wherever the GPU driver can report it (most can);
+  where it can't, the measurement stops at the instant the frame is handed to the display
+  and so reads slightly optimistic. `p50` = the typical frame (median), `p95` = the slow
+  outliers. This is the one number that summarizes your stream.
 - **Line 3 — where the time goes.** The first four stages **tile the end-to-end interval** —
   each starts where the previous one ends, so they add up to the headline. The two extra
   terms under them are not extra time: one is excluded from the total, the other sits inside a
@@ -123,7 +125,12 @@ lost 3 (2.4%)
     reassembly on your device.
   - `decode` — received → decoded, on your device.
   - `display` — decoded → displayed: waiting for the right screen refresh, rendering,
-    and vsync.
+    and vsync. On Linux/Windows it splits into `(pace + latch)` when your driver reports
+    true on-glass timing: **pace** is Punktfunk's own work — getting the decoded frame
+    submitted — and **latch** is the wait for the display to take it. A large `latch` is
+    the screen's refresh cycle, not the stream; a large `pace` is us. (`pace` is also the
+    fair number to compare against an iPhone or iPad, whose figure already has its
+    equivalent of `latch` removed.)
   - `os present` *(iOS and tvOS)* — the fixed depth of the OS present pipeline, which is
     excluded from both the headline and `display` and printed here so you can add it
     back.
@@ -143,6 +150,15 @@ lost 3 (2.4%)
   encode … · xfer … · pace …` — splitting the host's own share into its stages, when the
   host reports them.
 
+  Linux/Windows Detailed also carries a **`present:`** line naming how frames are reaching
+  your screen: the display mode in use (`mailbox`, `fifo`, `fifo-latest-ready`, …), `vrr yes`/`vrr no` once the
+  client has *measured* whether your screen is following the stream's cadence (it is
+  reported only when measured — no guess from what the display claims), and, when the
+  [presentation setting](/docs/client-settings#video) is *Smoothness*, the word
+  `smoothing`. Counters join it only when they're doing something — `qdrop`/`qdry` mean
+  the smoothing buffer overflowed or ran dry (a jittery link), and `gated`/`forced`
+  belong to the pacing that keeps frames from stacking up behind the display.
+
   (Stage values are per-stage medians, so they sum only *approximately* to the
   headline median — percentiles aren't perfectly additive. The headline is measured
   directly, never computed as a sum.)

tools/cursor-probe/src/main.rs

@@ -88,6 +88,7 @@ mod linux {
             false,
             policy,
             vout.expect_exact_dims,
+            compositor == pf_vdisplay::Compositor::Kwin,
         )
         .context("attach the PipeWire capturer")?;
         cap.set_active(true);