fix(windows/gamestream): create the virtual display on Windows (Moonlight black screen)

The GameStream video path (open_gs_virtual_source) ran the Linux compositor-
detection state machine on every platform. On Windows detect_active_session()
returns None and vdisplay::detect() bails ("could not detect compositor ...
XDG_CURRENT_DESKTOP=''"), killing the video thread right after RTSP PLAY — so a
Moonlight client paired, negotiated, then black-screened and dropped.

The native punktfunk/1 path already guards this (resolve_compositor returns a
placeholder Compositor on Windows, since vdisplay::open ignores the compositor
arg there and always uses the pf-vdisplay IddCx backend). Mirror that guard in
the GameStream path: short-circuit to a placeholder on Windows, keep the Linux
session detection (apply_session_env/apply_input_env) under cfg(not(windows)).

Validated live: Moonlight -> this box now creates the pf-vdisplay virtual
monitor, attaches the IDD-push ring, and NVENC streams 5120x1440@240.

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

clients/apple/Sources/PunktfunkKit/InputCapture.swift

@@ -107,23 +107,6 @@ public final class InputCapture {
     /// macOS (no GCMouse handlers installed; `sendMouseAbs` is never called there). Main-queue.
     public var gcMouseForwarding = false
 
-    #if os(iOS)
-    /// Whether any device is attached as a `GCMouse` right now. The Magic Keyboard TRACKPAD does
-    /// not always register as a GCMouse on iPadOS (only a standalone mouse does) — when no GCMouse
-    /// is present the relative GCMouse path can't carry pointer motion. Main-queue.
-    public var hasGCMouse: Bool { !mice.isEmpty }
-
-    /// Diagnostic: a one-line description of every attached GCMouse (count + GCDevice identity), so
-    /// PUNKTFUNK_INPUT_DEBUG can reveal whether the trackpad showed up as a mouse at all.
-    public var attachedMiceSummary: String {
-        guard !mice.isEmpty else { return "0 mice" }
-        let parts = mice.map { mouse -> String in
-            "\(mouse.productCategory)/\(mouse.vendorName ?? "?")"
-        }
-        return "\(mice.count) mice: \(parts.joined(separator: ", "))"
-    }
-    #endif
-
     /// Fired on ⌘⎋ (the capture toggle — detected here so it works in both states; the
     /// event itself is swallowed). Main queue.
     public var onToggleCapture: (() -> Void)?
@@ -177,7 +160,13 @@ public final class InputCapture {
             previous.onPreempted?()
         }
         Self.activeCapture = self
-        if let mouse = GCMouse.current { attach(mouse: mouse) }
+        // Attach EVERY connected mouse, not just GCMouse.current. With two pointing devices (e.g.
+        // the iPad's own Magic Keyboard trackpad AND a Universal Control "V-UC Automouse"), only one
+        // is `current` at a time; attaching just that one left the OTHER device's motion handler
+        // uninstalled, so moving it did nothing. Each GCMouse delivers its own deltas through its own
+        // handler, so handling all of them lets either device drive. New arrivals are caught by the
+        // GCMouseDidConnect observer below.
+        for mouse in GCMouse.mice() { attach(mouse: mouse) }
         if let keyboard = GCKeyboard.coalesced { attach(keyboard: keyboard) }
         observers.append(NotificationCenter.default.addObserver(
             forName: .GCMouseDidConnect, object: nil, queue: .main
@@ -411,12 +400,6 @@ public final class InputCapture {
               !mice.contains(where: { $0 === mouse }) // re-delivered on wake — attach once
         else { return }
         mice.append(mouse)
-        #if os(iOS)
-        if inputDebug {
-            inputLog.debug(
-                "GCMouse attached: \(mouse.productCategory, privacy: .public)/\(mouse.vendorName ?? "?", privacy: .public) — now \(self.attachedMiceSummary, privacy: .public)")
-        }
-        #endif
         // macOS drives motion + buttons from NSEvent (StreamLayerView's local monitor →
         // sendMotion/sendMouseButton) because GCMouse's handlers proved unreliable there;
         // installing them too would double-send. iOS keeps GCMouse (raw deltas under

clients/apple/Sources/PunktfunkKit/MetalVideoPresenter.swift

@@ -223,32 +223,39 @@ public final class MetalVideoPresenter {
     }
 
     /// Set the layer's pixel format + colour config for SDR or HDR. MAIN THREAD ONLY. EDR is requested
-    /// on ALL platforms — the property is available on macOS/iOS/tvOS at our deployment floor, and the
+    /// on macOS + iOS (the old `#if os(macOS)` guard left iOS EDR half-engaged). tvOS has NO EDR API
-    /// old `#if os(macOS)` guard left iOS/tvOS EDR half-engaged.
+    /// (`wantsExtendedDynamicRangeContent`/`edrMetadata`/`CAEDRMetadata` are all unavailable there), so
+    /// it gets the PQ pixel format + colour space only — the tvOS compositor tone-maps from those.
     private func configureColor(hdr: Bool) {
         if hdr {
             layer.pixelFormat = .rgba16Float
             layer.colorspace = CGColorSpace(name: CGColorSpace.itur_2100_PQ)
+            #if !os(tvOS)
             layer.wantsExtendedDynamicRangeContent = true
             // Anchor reference white. Re-apply the real grade if one already arrived (0xCE before the
             // flip); otherwise the bare 203-nit anchor. Without this anchor the PQ signal is too bright.
             layer.edrMetadata = makeEDR(lastHdrMeta)
+            #endif
         } else {
             // SDR: gamma-encoded BT.709 [0,1] in an 8-bit drawable; a nil colorspace tags it device/sRGB
             // (the proven SDR path — never showed the "too bright" issue, which was HDR-only).
             layer.pixelFormat = .bgra8Unorm
             layer.colorspace = nil
+            #if !os(tvOS)
             layer.wantsExtendedDynamicRangeContent = false
             layer.edrMetadata = nil
+            #endif
         }
     }
 
+    #if !os(tvOS)
     private func makeEDR(_ meta: PunktfunkConnection.HdrMeta?) -> CAEDRMetadata {
         CAEDRMetadata.hdr10(
             displayInfo: meta?.masteringDisplayColorVolume(),
             contentInfo: meta?.contentLightLevelInfo(),
             opticalOutputScale: hdrReferenceWhiteNits)
     }
+    #endif
 
     /// Update the HDR mastering metadata (drained from the host's 0xCE datagram) to refine the system
     /// tone-map from the real grade. Called from the PUMP thread, so the layer write is hopped to MAIN
@@ -259,7 +266,11 @@ public final class MetalVideoPresenter {
         DispatchQueue.main.async { [weak self] in
             guard let self else { return }
             self.lastHdrMeta = meta
+            // tvOS has no edrMetadata — the cached grade is still kept above (harmless), it just can't
+            // be applied to the layer there. macOS/iOS refine the system tone-map from the real grade.
+            #if !os(tvOS)
             if self.hdrActive { self.layer.edrMetadata = self.makeEDR(meta) }
+            #endif
         }
     }
 

clients/apple/Sources/PunktfunkKit/StreamViewIOS.swift

@@ -11,13 +11,18 @@
 // host mode, so the host's rescale is the identity).
 //
 // A hardware mouse/trackpad is a pointer, not a finger. When the scene is pointer-LOCKED
-// (full-screen + frontmost iPad) GCMouse delivers raw relative deltas and the system hides
+// (full-screen + frontmost iPad, and the user hasn't disabled pointer capture in Settings —
-// the cursor — the gaming-grade path. When it CAN'T lock (Stage Manager, not frontmost,
+// see PointerLockChain, which steers the lock request through SwiftUI's hosting controllers)
-// iPhone) the system shows its own cursor and routes the mouse through UIKit's pointer path:
+// GCMouse delivers raw relative deltas and the system hides the cursor — the gaming-grade path.
-// hover + indirect-pointer touches, which we forward as ABSOLUTE cursor position (+ buttons)
+// InputCapture handles EVERY connected mouse (GCMouse.mice), not just the current one, so a
-// so the host cursor tracks the visible local one. We never forward an indirect pointer as a
+// trackpad + a second pointer (e.g. a Universal Control mouse) both drive. When the scene CAN'T
-// touch — doing so hid the cursor and made the host see taps instead of a moving mouse.
+// lock (Stage Manager, not frontmost, iPhone, capture disabled) the system shows its own cursor
-// GCMouse is gated off whenever the lock isn't held so the two paths can't double-send.
+// and routes the mouse through UIKit's pointer path: hover + indirect-pointer touches, which we
+// forward as ABSOLUTE cursor position (+ buttons) so the host cursor tracks the visible local one.
+// We never forward an indirect pointer as a touch — doing so hid the cursor and made the host see
+// taps instead of a moving mouse. The two paths are mutually exclusive on `gcMouseForwarding`
+// (== locked): GCMouse forwards only WHILE locked, the UIKit indirect path (motion, buttons AND
+// scroll) only while NOT locked — so a pointer that emits both channels under lock can't double-send.
 // Hardware keyboard forwarding shares InputCapture with macOS — auto-engaged when streaming
 // starts, ⌘⎋ toggles (detected from the HID stream; there is no NSEvent monitor here).
 //
@@ -236,32 +241,24 @@ public final class StreamViewController: UIViewController {
             guard self?.captureEnabled == true else { return }
             connection?.send(event)
         }
-        // Indirect pointer (mouse/trackpad with no lock) → absolute cursor + buttons, routed
+        // Indirect pointer (mouse/trackpad) WITHOUT a lock → absolute cursor + buttons + scroll.
-        // through InputCapture so the forwarding gate and release-on-blur apply uniformly.
+        // While the scene is pointer-LOCKED the GCMouse path owns motion AND buttons AND scroll, so
+        // the whole UIKit indirect path is gated off here (`gcMouseForwarding`). The trackpad and a
+        // mouse BOTH report through GCMouse under lock and ALSO emit UIKit indirect-pointer events
+        // (pinned at the locked position) — without this gate a click double-sends (GCMouse + UIKit)
+        // and a second pointer (e.g. a Universal Control mouse) competes with the trackpad. The gate
+        // is the exact mirror of the GCMouse handlers, which fire only while locked.
         streamView.onPointerMoveAbs = { [weak self] p in
-            guard let self else { return }
+            guard let self, self.inputCapture?.gcMouseForwarding == false else { return }
-            if iosInputDebug {
-                // Whether ANY UIKit pointer movement reaches us while the scene is LOCKED tells us
-                // if the trackpad (which may not be a GCMouse) can still be captured via UIKit.
-                iosInputLog.debug(
-                    "UIKit pointer move x=\(p.x, privacy: .public) y=\(p.y, privacy: .public) locked=\(self.pointerLockEngaged() == true, privacy: .public) gcFwd=\(self.inputCapture?.gcMouseForwarding == true, privacy: .public)")
-            }
             self.inputCapture?.sendMouseAbs(
                 x: p.x, y: p.y, surfaceWidth: p.w, surfaceHeight: p.h)
         }
         streamView.onPointerButton = { [weak self] button, down in
-            self?.inputCapture?.sendMouseButton(button, pressed: down)
+            guard let self, self.inputCapture?.gcMouseForwarding == false else { return }
+            self.inputCapture?.sendMouseButton(button, pressed: down)
         }
-        // Trackpad two-finger / wheel scroll → host scroll. The pan recognizer is the
-        // UNLOCKED regime; while locked, GCMouse's scroll handler owns it — mirror the
-        // sendMouseAbs !gcMouseForwarding gate so the two can't double-send.
         streamView.onScroll = { [weak self] dx, dy in
-            guard let self else { return }
+            guard let self, self.inputCapture?.gcMouseForwarding == false else { return }
-            if iosInputDebug {
-                iosInputLog.debug(
-                    "UIKit scroll dx=\(dx, privacy: .public) dy=\(dy, privacy: .public) locked=\(self.pointerLockEngaged() == true, privacy: .public)")
-            }
-            guard self.inputCapture?.gcMouseForwarding == false else { return }
             self.inputCapture?.sendScroll(dx: dx, dy: dy)
         }
 
@@ -472,7 +469,7 @@ public final class StreamViewController: UIViewController {
         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) useGCMouse=\(useGCMouse, privacy: .public) [\(self.inputCapture?.attachedMiceSummary ?? "n/a", privacy: .public)]")
+                "pointer lock isLocked=\(locked, privacy: .public) captured=\(self.captured, privacy: .public)")
         }
     }
     #endif

crates/pf-driver-proto/src/lib.rs

@@ -80,7 +80,14 @@ pub mod control {
         pub width: u32,
         pub height: u32,
         pub refresh_hz: u32,
-        pub _reserved: u32,
+        /// Host-preferred per-client monitor id (`1..=15`) — the EDID serial / IddCx `ConnectorIndex` /
+        /// `ContainerId` the driver names this monitor by. A given client (keyed by its cert fingerprint)
+        /// gets a STABLE id across reconnects, so the OS device path + EDID stay identical and Windows
+        /// reapplies that client's saved per-monitor config (DPI scaling). `0` = AUTO: the driver
+        /// allocates the lowest-free id (the original slot-based behavior — used for anonymous/TOFU and
+        /// GameStream sessions). Byte-compatible with the old `_reserved` (offset 20): an un-upgraded
+        /// driver ignores it (→ auto), which the host detects via [`AddReply::resolved_monitor_id`].
+        pub preferred_monitor_id: u32,
     }
 
     /// `IOCTL_ADD` reply: the OS target id + the adapter LUID the IDD landed on (split low/high to
@@ -91,7 +98,11 @@ pub mod control {
         pub adapter_luid_low: u32,
         pub adapter_luid_high: i32,
         pub target_id: u32,
-        pub _reserved: u32,
+        /// The monitor id the driver ACTUALLY used — echoes [`AddRequest::preferred_monitor_id`] when the
+        /// preference was honored, or the auto-allocated id otherwise. Byte-compatible with the old
+        /// `_reserved` (offset 12): an un-upgraded driver leaves it `0`, so the host can tell its
+        /// preference was ignored (stale driver) and log it instead of silently losing per-client config.
+        pub resolved_monitor_id: u32,
     }
 
     /// `IOCTL_REMOVE` input.
@@ -129,11 +140,13 @@ pub mod control {
         assert!(offset_of!(AddRequest, width) == 8);
         assert!(offset_of!(AddRequest, height) == 12);
         assert!(offset_of!(AddRequest, refresh_hz) == 16);
+        assert!(offset_of!(AddRequest, preferred_monitor_id) == 20);
 
         assert!(size_of::<AddReply>() == 16);
         assert!(offset_of!(AddReply, adapter_luid_low) == 0);
         assert!(offset_of!(AddReply, adapter_luid_high) == 4);
         assert!(offset_of!(AddReply, target_id) == 8);
+        assert!(offset_of!(AddReply, resolved_monitor_id) == 12);
 
         assert!(size_of::<RemoveRequest>() == 8);
         assert!(offset_of!(RemoveRequest, session_id) == 0);
@@ -436,11 +449,25 @@ mod tests {
             width: 3840,
             height: 2160,
             refresh_hz: 120,
-            _reserved: 0,
+            preferred_monitor_id: 7,
         };
         let bytes = bytemuck::bytes_of(&req);
         assert_eq!(bytes.len(), 24);
         assert_eq!(*bytemuck::from_bytes::<control::AddRequest>(bytes), req);
+        // preferred_monitor_id occupies the old `_reserved` slot at offset 20 — byte-compatible.
+        assert_eq!(bytes[20..24], 7u32.to_le_bytes());
+
+        let reply = control::AddReply {
+            adapter_luid_low: 0x1234_5678,
+            adapter_luid_high: -2,
+            target_id: 262,
+            resolved_monitor_id: 7,
+        };
+        let rbytes = bytemuck::bytes_of(&reply);
+        assert_eq!(rbytes.len(), 16);
+        assert_eq!(*bytemuck::from_bytes::<control::AddReply>(rbytes), reply);
+        // resolved_monitor_id occupies the old `_reserved` slot at offset 12 — byte-compatible.
+        assert_eq!(rbytes[12..16], 7u32.to_le_bytes());
     }
 
     #[test]

crates/punktfunk-host/Cargo.toml

@@ -182,6 +182,9 @@ windows = { version = "0.62", features = [
     # Windows service supervisor (src/service.rs): a kill-on-close job object so a service crash never
     # orphans the SYSTEM host it launched into the interactive session.
     "Win32_System_JobObjects",
+    # CoCreateInstance(PolicyConfigClient) — set the default audio playback/recording endpoints via the
+    # undocumented IPolicyConfig (audio/windows/audio_control.rs) so mic + desktop audio auto-wire.
+    "Win32_System_Com",
 ] }
 # The SCM plumbing for the `service` subcommand (define_windows_service! / dispatcher / control
 # handler / ServiceManager install). Wraps the Win32 service API; the supervision loop itself uses

crates/punktfunk-host/src/audio.rs

@@ -42,6 +42,7 @@ pub fn open_audio_capture(channels: u32) -> Result<Box<dyn AudioCapturer>> {
 
 #[cfg(target_os = "windows")]
 pub fn open_audio_capture(channels: u32) -> Result<Box<dyn AudioCapturer>> {
+    audio_control::ensure_wired_once();
     wasapi_cap::WasapiLoopbackCapturer::open(channels)
         .map(|c| Box::new(c) as Box<dyn AudioCapturer>)
 }
@@ -77,6 +78,7 @@ pub fn open_virtual_mic(channels: u32) -> Result<Box<dyn VirtualMic>> {
 
 #[cfg(target_os = "windows")]
 pub fn open_virtual_mic(channels: u32) -> Result<Box<dyn VirtualMic>> {
+    audio_control::ensure_wired_once();
     wasapi_mic::WasapiVirtualMic::open(channels).map(|m| Box::new(m) as Box<dyn VirtualMic>)
 }
 
@@ -85,6 +87,9 @@ pub fn open_virtual_mic(_channels: u32) -> Result<Box<dyn VirtualMic>> {
     anyhow::bail!("virtual mic requires Linux + PipeWire or Windows + a virtual audio device")
 }
 
+#[cfg(target_os = "windows")]
+#[path = "audio/windows/audio_control.rs"]
+mod audio_control;
 #[cfg(target_os = "linux")]
 mod linux;
 #[cfg(target_os = "windows")]

crates/punktfunk-host/src/audio/windows/audio_control.rs

@@ -0,0 +1,227 @@
+//! Windows audio device auto-wiring — production mic + desktop-audio passthrough with zero manual
+//! setup.
+//!
+//! A headless host has no real audio output, so BOTH the desktop-audio loopback ([`super::wasapi_cap`])
+//! and the virtual mic ([`super::wasapi_mic`]) must run on VIRTUAL audio cables — and on DIFFERENT
+//! ones, or the loopback re-captures the injected mic (an infinite echo). The installer bundles
+//! VB-Audio Virtual Cable (the mic target: its "CABLE Input" render endpoint → "CABLE Output" capture)
+//! and the host auto-installs the Steam Streaming pair (a loopback-capable render). This module wires
+//! them up at startup so no manual Sound-settings fiddling is ever needed:
+//!
+//! * default **PLAYBACK**  → a loopback-capable render that is NOT the mic cable (a real output device
+//!   if one exists, else the Steam Streaming Microphone; **never** the Steam Streaming Speakers, whose
+//!   loopback is silent — validated live). This is the endpoint [`super::wasapi_cap`] loopback-captures
+//!   for desktop audio.
+//! * default **RECORDING** → the virtual mic's capture endpoint (VB-Cable "CABLE Output") so host apps
+//!   record the client's mic by default.
+//!
+//! [`super::wasapi_mic::find_device`] then resolves the mic INJECT target to "CABLE Input" — a render
+//! candidate that is NOT the default playback — guaranteeing loopback ≠ mic, so there is no echo.
+//!
+//! Setting a default endpoint uses the undocumented `IPolicyConfig` COM interface (the only way to set
+//! a default device programmatically — neither the `windows` nor `wasapi` crate exposes it; it is the
+//! same call `mmsys.cpl` makes). Opt out with `PUNKTFUNK_KEEP_DEFAULT` to leave the user's chosen
+//! defaults untouched.
+
+// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it.
+#![deny(clippy::undocumented_unsafe_blocks)]
+
+use anyhow::{anyhow, bail, Result};
+use std::ffi::c_void;
+use std::sync::Once;
+use wasapi::Direction;
+
+/// Run the audio device auto-wiring exactly once per process, before the first capturer/mic opens.
+/// Blocks until done so the default playback is set before the loopback captures it. Best-effort:
+/// every failure is logged, never fatal (the host then falls back to whatever the current defaults
+/// are — exactly the pre-wiring behaviour).
+pub(crate) fn ensure_wired_once() {
+    static WIRED: Once = Once::new();
+    WIRED.call_once(|| {
+        if std::env::var_os("PUNKTFUNK_KEEP_DEFAULT").is_some() {
+            tracing::info!("PUNKTFUNK_KEEP_DEFAULT set — leaving the audio default devices untouched");
+            return;
+        }
+        // Run on a dedicated COM-MTA thread so we never collide with the caller's apartment mode
+        // (the capture/mic threads each initialize their own COM separately).
+        let handle = std::thread::Builder::new()
+            .name("pf-audio-wiring".into())
+            .spawn(|| {
+                if wasapi::initialize_mta().ok().is_err() {
+                    tracing::warn!("audio wiring: COM init (MTA) failed — skipping");
+                    return;
+                }
+                if let Err(e) = ensure_audio_wiring() {
+                    tracing::warn!(error = %format!("{e:#}"),
+                        "audio auto-wiring failed — mic/desktop audio may need manual device defaults");
+                }
+            });
+        if let Ok(h) = handle {
+            let _ = h.join();
+        }
+    });
+}
+
+/// `(friendly_name, endpoint_id)` for every ACTIVE endpoint in direction `dir`.
+fn list_endpoints(dir: Direction) -> Vec<(String, String)> {
+    let mut out = Vec::new();
+    let Ok(en) = wasapi::DeviceEnumerator::new() else {
+        return out;
+    };
+    let Ok(coll) = en.get_device_collection(&dir) else {
+        return out;
+    };
+    let Ok(n) = coll.get_nbr_devices() else {
+        return out;
+    };
+    for i in 0..n {
+        if let Ok(dev) = coll.get_device_at_index(i) {
+            let id = dev.get_id().unwrap_or_default();
+            if id.is_empty() {
+                continue;
+            }
+            out.push((dev.get_friendlyname().unwrap_or_default(), id));
+        }
+    }
+    out
+}
+
+/// Pick the loopback + mic-capture devices and set them as the default playback/recording.
+fn ensure_audio_wiring() -> Result<()> {
+    let renders = list_endpoints(Direction::Render);
+    let captures = list_endpoints(Direction::Capture);
+    if renders.is_empty() {
+        bail!("no active render endpoints to wire");
+    }
+
+    // A render is unusable as the desktop-audio loopback if it is a VB-Cable endpoint (reserved for
+    // the mic inject) or the Steam Streaming Speakers (its loopback is silent — validated live).
+    let excluded_loopback =
+        |ln: &str| ln.contains("cable") || ln.contains("steam streaming speakers");
+    // "virtual-ish" = a known virtual cable; a render WITHOUT these markers is a real output device,
+    // the best loopback source (apps render there and the operator can also hear it).
+    let virtualish = |ln: &str| {
+        ln.contains("virtual")
+            || ln.contains("cable")
+            || ln.contains("steam streaming")
+            || ln.contains("voicemeeter")
+    };
+    let loopback = renders
+        .iter()
+        .find(|(n, _)| {
+            let ln = n.to_lowercase();
+            !excluded_loopback(&ln) && !virtualish(&ln)
+        })
+        .or_else(|| {
+            renders
+                .iter()
+                .find(|(n, _)| n.to_lowercase().contains("steam streaming microphone"))
+        })
+        .or_else(|| {
+            renders
+                .iter()
+                .find(|(n, _)| !excluded_loopback(&n.to_lowercase()))
+        });
+
+    // The virtual mic's CAPTURE endpoint host apps record from — VB-Cable "CABLE Output" preferred.
+    let mic_capture = captures
+        .iter()
+        .find(|(n, _)| n.to_lowercase().contains("cable output"))
+        .or_else(|| {
+            captures
+                .iter()
+                .find(|(n, _)| n.to_lowercase().contains("steam streaming microphone"))
+        })
+        .or_else(|| {
+            captures.iter().find(|(n, _)| {
+                let ln = n.to_lowercase();
+                ln.contains("voicemeeter") || ln.contains("virtual")
+            })
+        });
+
+    match loopback {
+        Some((name, id)) => match set_default_endpoint(id) {
+            Ok(()) => tracing::info!(device = %name,
+                "audio wiring: default playback = desktop-audio loopback source"),
+            Err(e) => tracing::warn!(device = %name, error = %format!("{e:#}"),
+                "audio wiring: failed to set the default playback device"),
+        },
+        None => {
+            tracing::warn!("audio wiring: no usable desktop-audio loopback render endpoint found")
+        }
+    }
+    if let Some((name, id)) = mic_capture {
+        match set_default_endpoint(id) {
+            Ok(()) => tracing::info!(device = %name,
+                "audio wiring: default recording = virtual mic (apps record the client's mic)"),
+            Err(e) => tracing::warn!(device = %name, error = %format!("{e:#}"),
+                "audio wiring: failed to set the default recording device"),
+        }
+    }
+    Ok(())
+}
+
+// --- IPolicyConfig (undocumented): set a default audio endpoint by id, for all three roles. ---
+
+/// The `IPolicyConfig` vtable. Only `SetDefaultEndpoint` is called; the 10 methods between `Release`
+/// and it (`GetMixFormat` … `SetPropertyValue`) are placeholders so the slot offset is correct.
+#[repr(C)]
+struct IPolicyConfigVtbl {
+    query_interface: unsafe extern "system" fn(
+        *mut c_void,
+        *const windows::core::GUID,
+        *mut *mut c_void,
+    ) -> windows::core::HRESULT,
+    add_ref: unsafe extern "system" fn(*mut c_void) -> u32,
+    release: unsafe extern "system" fn(*mut c_void) -> u32,
+    _reserved: [*const c_void; 10],
+    set_default_endpoint: unsafe extern "system" fn(
+        *mut c_void,
+        windows::core::PCWSTR,
+        u32,
+    ) -> windows::core::HRESULT,
+    // SetEndpointVisibility follows — unused.
+}
+
+/// Set `device_id` as the default audio endpoint for eConsole/eMultimedia/eCommunications via the
+/// undocumented `IPolicyConfig::SetDefaultEndpoint` (the call `mmsys.cpl` makes). Errs if any role
+/// fails.
+fn set_default_endpoint(device_id: &str) -> Result<()> {
+    use windows::core::{IUnknown, Interface, GUID, PCWSTR};
+    use windows::Win32::System::Com::{CoCreateInstance, CLSCTX_ALL};
+
+    // PolicyConfigClient coclass + IPolicyConfig (Win7+) IID.
+    const CLSID_POLICY_CONFIG: GUID = GUID::from_u128(0x870af99c_171d_4f9e_af0d_e63df40c2bc9);
+    const IID_IPOLICY_CONFIG: GUID = GUID::from_u128(0xf8679f50_850a_41cf_9c72_430f290290c8);
+
+    let wide: Vec<u16> = device_id.encode_utf16().chain(std::iter::once(0)).collect();
+
+    // SAFETY: CoCreateInstance with a valid CLSID returns an owned, refcounted IUnknown. We QI it for
+    // IPolicyConfig; on success (HRESULT ok + non-null pointer) we invoke its SetDefaultEndpoint slot
+    // through the documented vtable layout (3 IUnknown + 10 placeholder methods precede it) with a
+    // NUL-terminated UTF-16 id and an in-range ERole (0..=2), then Release the QI'd pointer. Every
+    // pointer is checked non-null before deref; `unk` is Released by its Drop on scope exit.
+    unsafe {
+        let unk: IUnknown = CoCreateInstance(&CLSID_POLICY_CONFIG, None, CLSCTX_ALL)
+            .map_err(|e| anyhow!("CoCreateInstance(PolicyConfig): {e}"))?;
+        let mut raw: *mut c_void = std::ptr::null_mut();
+        unk.query(&IID_IPOLICY_CONFIG, &mut raw)
+            .ok()
+            .map_err(|e| anyhow!("QueryInterface(IPolicyConfig): {e}"))?;
+        if raw.is_null() {
+            bail!("IPolicyConfig QueryInterface returned null");
+        }
+        let vtbl = *(raw as *const *const IPolicyConfigVtbl);
+        let mut result = Ok(());
+        for role in 0u32..=2 {
+            let hr = ((*vtbl).set_default_endpoint)(raw, PCWSTR(wide.as_ptr()), role);
+            if hr.is_err() {
+                result = hr
+                    .ok()
+                    .map_err(|e| anyhow!("SetDefaultEndpoint(role {role}): {e}"));
+            }
+        }
+        ((*vtbl).release)(raw);
+        result
+    }
+}

crates/punktfunk-host/src/audio/windows/wasapi_mic.rs

@@ -4,10 +4,12 @@
 //! **capture** endpoint then surfaces as a microphone that host apps can record from.
 //!
 //! Target device, by friendly-name substring (first match wins; override with `PUNKTFUNK_MIC_DEVICE`):
-//! "Steam Streaming Microphone" (ships with Steam Remote Play — exactly this purpose), VB-Audio
+//! VB-Audio "CABLE Input" (bundled by the installer — the preferred, dedicated mic target), the
-//! "CABLE Input", VoiceMeeter, or anything with "virtual" in the name. If none is present we
+//! "Steam Streaming Microphone", VoiceMeeter, or anything with "virtual" in the name.
-//! auto-install the Steam Streaming audio pair (see [`install_steam_audio_pair`]); failing that we
+//! [`super::audio_control`] sets the default playback to a DIFFERENT loopback-capable device so the
-//! return an error with install guidance and the host runs without mic passthrough.
+//! chosen mic is never the endpoint the loopback captures. If no candidate is present we auto-install
+//! the Steam Streaming audio pair (see [`install_steam_audio_pair`]); failing that we return an error
+//! with install guidance and the host runs without mic passthrough.
 //!
 //! **Anti-echo guard (the whole point of this being non-trivial).** The desktop-audio plane
 //! ([`super::wasapi_cap`]) loopback-captures the **default render endpoint**. WASAPI loopback
@@ -45,8 +47,8 @@ const MAX_QUEUE_BYTES: usize = (SAMPLE_RATE as usize * 80 / 1000) * BLOCK_ALIGN;
 /// Render-endpoint friendly-name substrings (lowercased) we can write into so the device's capture
 /// endpoint becomes a host mic. Ordered by preference.
 const CANDIDATES: &[&str] = &[
+    "cable input", // VB-Audio Virtual Cable — bundled by the installer; the preferred dedicated mic target
     "steam streaming microphone",
-    "cable input",
     "voicemeeter input",
     "voicemeeter aux input",
     "virtual",

crates/punktfunk-host/src/capture.rs

@@ -59,7 +59,7 @@ pub struct OutputFormat {
     /// Produce GPU-resident D3D11 frames (zero-copy for a GPU encoder — NVENC/AMF/QSV) rather than CPU
     /// staging. `false` **only** for the GPU-less software encoder.
     pub gpu: bool,
-    /// HDR: the capturer converts to 10-bit (IDD-push FP16 → `Rgb10a2`; the DDA secure-desktop HDR hint).
+    /// HDR: the capturer converts to 10-bit (IDD-push FP16 → `P010`, or `Rgb10a2` for a 4:4:4 source).
     /// `false` = 8-bit SDR.
     pub hdr: bool,
     /// Full-chroma 4:4:4 session: the capturer must keep full chroma — deliver packed **RGB**
@@ -380,23 +380,12 @@ pub fn capture_virtual_output(
         .map(|c| Box::new(c) as Box<dyn Capturer>)
 }
 
-/// `PUNKTFUNK_NO_WGC=1` forces the pure single-process DDA (Desktop Duplication) path everywhere: it
-/// skips WGC in [`capture_virtual_output`] AND bypasses the two-process secure-desktop relay (so even a
-/// SYSTEM host captures in-process via DDA, the way Apollo does — one capturer for the normal AND the
-/// secure desktop). For bringing DDA up to parity / validating it on its own; all the WGC code stays
-/// compiled and comes back the moment the flag is unset.
-#[cfg(target_os = "windows")]
-pub(crate) fn wgc_disabled() -> bool {
-    crate::config::config().no_wgc
-}
-
 #[cfg(target_os = "windows")]
 pub fn capture_virtual_output(
     vout: crate::vdisplay::VirtualOutput,
     want: OutputFormat,
-    capture: crate::session_plan::CaptureBackend,
+    _capture: crate::session_plan::CaptureBackend,
 ) -> Result<Box<dyn Capturer>> {
-    use crate::session_plan::CaptureBackend;
     let target = vout.win_capture.clone().ok_or_else(|| {
         anyhow::anyhow!(
             "SudoVDA target not yet an active display (needs a WDDM GPU to activate it)"
@@ -404,97 +393,36 @@ pub fn capture_virtual_output(
     })?;
     let pref = vout.preferred_mode;
     let keep = vout.keepalive;
-    // Full-chroma 4:4:4 needs a full-chroma RGB source. The IDD-push and WGC paths emit subsampled
+    // IDD direct-push is the sole Windows capture path: consume frames straight from the pf-vdisplay
-    // NV12/P010 by default, which can't reconstruct 4:4:4; route a 4:4:4 session to DDA, which delivers
+    // driver's shared ring (in-process, Session 0 — it captures the secure desktop too; no Desktop
-    // RGB (Bgra) when its `chroma_444` flag is set. (IDD-push/WGC 4:4:4 capture is a follow-up.)
+    // Duplication, no WGC helper). A FRESH monitor + ring is created per session: a REUSED monitor's
-    if want.chroma_444 && capture != CaptureBackend::Dda {
+    // swap-chain dies after ~2 sessions and can't be revived. The ring is always FP16 when the display
-        tracing::info!("4:4:4 session — using DDA capture (RGB source) instead of {capture:?}");
+    // is HDR (the driver composes the IDD in FP16); `want.hdr` proactively enables advanced color and
-        return dxgi::DuplCapturer::open(target, pref, keep, want.gpu, false, want.chroma_444)
+    // selects the per-frame conversion (FP16 → P010 vs BGRA → NV12). `IddPushCapturer` takes the
-            .map(|c| Box::new(c) as Box<dyn Capturer>);
+    // keepalive (it owns the virtual display). There is NO fallback (DDA + the WGC relay were removed):
-    }
+    // if it can't open or the driver doesn't attach, the session fails cleanly and the client reconnects.
-    // P2 direct frame push (kill DDA): consume frames straight from the pf-vdisplay driver's shared
+    idd_push::IddPushCapturer::open(target, pref, want.hdr, keep)
-    // ring — no Desktop Duplication, no win32u reparenting hook. Resolved once in the `SessionPlan`
+        .map(|c| Box::new(c) as Box<dyn Capturer>)
-    // (was re-derived from `config().idd_push` here); `IddPush` takes the keepalive (owns the virtual
+        .map_err(|(e, _keep)| e.context("IDD-push capture open (no fallback)"))
-    // display) so there's no fall-through.
+}
-    if capture == CaptureBackend::IddPush {
+
-        // Recreate the monitor + ring per session (fix-teardown): a FRESH monitor reliably gets a
+/// Whether the active capturer can deliver a full-chroma (RGB) source for a 4:4:4 HEVC encode. The
-        // working IddCx swap-chain, whereas a REUSED monitor's swap-chain dies after ~2 sessions and
+/// negotiator gates 4:4:4 on this so the host honestly downgrades to 4:2:0 when the capturer can only
-        // the host can't revive it. The driver's recreate crash (target id resolved to 0) is fixed by
+/// produce subsampled frames. Linux (the portal capturer feeding CPU RGB → `yuv444p`) can; the Windows
-        // stamping target_id onto the monitor context. The ring is always FP16 (the driver composes
+/// IDD-push path delivers subsampled NV12/P010 today, so full-chroma capture there is a follow-up.
-        // the IDD in FP16); `want_hdr` selects the per-frame conversion (FP16 → Rgb10a2 vs Bgra).
+#[cfg(target_os = "linux")]
-        // If IDD-push can't open OR the driver doesn't attach to the ring within a few seconds (e.g. a
+pub(crate) fn capturer_supports_444() -> bool {
-        // hybrid-GPU render mismatch), fall back to DDA so the session is NEVER left black (audit §5.1).
+    true
-        // `open()` hands the keepalive back on failure so DDA can take ownership of the virtual display.
+}
-        match idd_push::IddPushCapturer::open(target.clone(), pref, want.hdr, keep) {
+#[cfg(target_os = "windows")]
-            Ok(c) => return Ok(Box::new(c) as Box<dyn Capturer>),
+pub(crate) fn capturer_supports_444() -> bool {
-            Err((e, keep)) => {
+    // IDD-push 4:4:4 (full-chroma RGB from the FP16 ring) is the next step; until then the sole Windows
-                tracing::warn!(
+    // capturer delivers subsampled NV12/P010 only, so the host honestly negotiates 4:2:0.
-                    error = %format!("{e:#}"),
+    false
-                    "IDD-push open/attach failed — falling back to DDA"
+}
-                );
+#[cfg(not(any(target_os = "linux", target_os = "windows")))]
-                return dxgi::DuplCapturer::open(
+pub(crate) fn capturer_supports_444() -> bool {
-                    target,
+    false
-                    pref,
-                    keep,
-                    want.gpu,
-                    false,
-                    want.chroma_444,
-                )
-                .map(|c| Box::new(c) as Box<dyn Capturer>);
-            }
-        }
-    }
-    // WGC (Windows.Graphics.Capture) is the default: it captures the COMPOSED desktop including the
-    // overlay/independent-flip planes DXGI Desktop Duplication misses (the frozen-HDR-animation bug),
-    // and has no ACCESS_LOST-on-overlay churn. DDA stays available via PUNKTFUNK_CAPTURE=dda and is
-    // the secure-desktop (lock/UAC) fallback (WGC can't capture those). `keep` is moved into the
-    // chosen backend (it owns the SudoVDA keepalive), so there's no open-time auto-fallback. The
-    // backend choice (`dda`/`dxgi`/`PUNKTFUNK_NO_WGC` → DDA, else WGC) is now resolved once in the plan.
-    if capture == CaptureBackend::Dda {
-        return dxgi::DuplCapturer::open(target, pref, keep, want.gpu, false, want.chroma_444)
-            .map(|c| Box::new(c) as Box<dyn Capturer>);
-    }
-    // WGC default, with a watchdog'd DDA fallback. WGC's Direct3D11CaptureFramePool::CreateFreeThreaded
-    // intermittently HANGS on the headless SudoVDA (IddCx) display — a blocking call we can't error out
-    // of in place. So run WGC open on a dedicated thread and bound it: if it doesn't finish in time
-    // (hang) or errors, fall back to the reliable DDA path so the session is NEVER left black. WGC,
-    // when it opens, captures the composed desktop (overlay/MPO-correct HDR — fixes frozen animations);
-    // DDA is the safety net (+ the secure-desktop path). The encode thread is set MTA so the WGC
-    // objects built on the watchdog thread (also MTA) are usable here; the keepalive is handed to WGC
-    // only on success, else to DDA. A hung watchdog thread is abandoned (holds no keepalive).
-    // SAFETY: `RoInitialize` is a combase FFI call that initializes the WinRT apartment for the calling
-    // thread. It takes the `RO_INIT_MULTITHREADED` enum by value and borrows no memory, so there is no
-    // pointer/lifetime/aliasing obligation; it is safe on any thread and idempotent — a second call on a
-    // thread already in a compatible apartment returns S_FALSE / RPC_E_CHANGED_MODE, which we discard.
-    // Runs on the encode thread that goes on to use the WGC (WinRT) objects built by the watchdog thread.
-    unsafe {
-        let _ = windows::Win32::System::WinRT::RoInitialize(
-            windows::Win32::System::WinRT::RO_INIT_MULTITHREADED,
-        );
-    }
-    let (tx, rx) = std::sync::mpsc::channel();
-    let t = target.clone();
-    let _ = std::thread::Builder::new()
-        .name("wgc-open".into())
-        .spawn(move || {
-            let _ = tx.send(wgc::WgcCapturer::open(t, pref));
-        });
-    match rx.recv_timeout(std::time::Duration::from_secs(5)) {
-        Ok(Ok(mut c)) => {
-            c.attach_keepalive(keep);
-            Ok(Box::new(c) as Box<dyn Capturer>)
-        }
-        Ok(Err(e)) => {
-            tracing::warn!(error = %format!("{e:#}"), "WGC open failed — falling back to DDA");
-            dxgi::DuplCapturer::open(target, pref, keep, want.gpu, false, want.chroma_444)
-                .map(|c| Box::new(c) as Box<dyn Capturer>)
-        }
-        Err(_) => {
-            tracing::warn!("WGC open timed out (CreateFreeThreaded hang on the virtual display) — falling back to DDA");
-            dxgi::DuplCapturer::open(target, pref, keep, want.gpu, false, want.chroma_444)
-                .map(|c| Box::new(c) as Box<dyn Capturer>)
-        }
-    }
 }
 
 #[cfg(not(any(target_os = "linux", target_os = "windows")))]
@@ -506,14 +434,9 @@ pub fn capture_virtual_output(
     anyhow::bail!("virtual-output capture requires Linux or Windows")
 }
 
-// Goal-1 stage 6: the Windows backends live under `capture/windows/`, the Linux one under `capture/linux/`
+// Goal-1 stage 6: the Windows backend lives under `capture/windows/`, the Linux one under `capture/linux/`
-// (`#[path]` keeps the module names flat, so every `crate::capture::*` path is unchanged).
+// (`#[path]` keeps the module names flat, so every `crate::capture::*` path is unchanged). Windows capture
-#[cfg(target_os = "windows")]
+// is IDD direct-push only — DXGI Desktop Duplication (DDA) and the WGC two-process relay were removed.
-#[path = "capture/windows/composed_flip.rs"]
-pub mod composed_flip;
-#[cfg(target_os = "windows")]
-#[path = "capture/windows/desktop_watch.rs"]
-pub mod desktop_watch;
 #[cfg(target_os = "windows")]
 #[path = "capture/windows/dxgi.rs"]
 pub mod dxgi;
@@ -522,9 +445,3 @@ pub mod dxgi;
 pub mod idd_push;
 #[cfg(target_os = "linux")]
 mod linux;
-#[cfg(target_os = "windows")]
-#[path = "capture/windows/wgc.rs"]
-pub mod wgc;
-#[cfg(target_os = "windows")]
-#[path = "capture/windows/wgc_relay.rs"]
-pub mod wgc_relay;

crates/punktfunk-host/src/capture/windows/composed_flip.rs

@@ -1,217 +0,0 @@
-//! Force-composed-flip overlay (Windows) — make the secure (Winlogon: UAC / lock / login) desktop
-//! capturable by Desktop Duplication.
-//!
-//! The secure desktop's dialog/wallpaper presents via **fullscreen independent-flip / MPO**: it scans
-//! out directly, bypassing DWM composition, so `IDXGIOutputDuplication::AcquireNextFrame` returns
-//! `DXGI_ERROR_ACCESS_LOST` (born-lost) — there is no composed frame to hand out (the client sees
-//! black). Independent-flip requires the presenting app to own the ENTIRE output: putting ANY other
-//! visible window on that output disqualifies it, forcing DWM to **composite**, which DDA can then
-//! capture. So we keep a tiny, click-through, near-invisible **topmost layered window** alive on the
-//! *current input desktop* (which is Winlogon while the secure desktop is up). On a desktop switch the
-//! window is orphaned, so a dedicated thread tracks the input desktop and recreates it there.
-//!
-//! This is the non-input alternative to "tap a key to wake the lock screen": it needs no SendInput and
-//! no system-wide registry change (it does NOT disable MPO globally — it only nudges OUR output to
-//! composed while a session is live). Effectiveness can be build/driver-dependent; gated by
-//! `PUNKTFUNK_FORCE_COMPOSED` (default ON; set =0 to disable).
-
-// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it (unsafe-proof program).
-#![deny(clippy::undocumented_unsafe_blocks)]
-
-use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
-use windows::core::w;
-use windows::Win32::Foundation::{HWND, LPARAM, LRESULT, WPARAM};
-use windows::Win32::System::LibraryLoader::GetModuleHandleW;
-use windows::Win32::System::StationsAndDesktops::{
-    CloseDesktop, GetUserObjectInformationW, OpenInputDesktop, SetThreadDesktop,
-    DESKTOP_ACCESS_FLAGS, DESKTOP_CONTROL_FLAGS, UOI_NAME,
-};
-use windows::Win32::UI::WindowsAndMessaging::{
-    CreateWindowExW, DefWindowProcW, DestroyWindow, DispatchMessageW, PeekMessageW, RegisterClassW,
-    SetLayeredWindowAttributes, SetWindowPos, ShowWindow, TranslateMessage, HWND_TOPMOST,
-    LWA_ALPHA, MSG, PM_REMOVE, SWP_NOACTIVATE, SWP_NOMOVE, SWP_NOSIZE, SW_SHOWNOACTIVATE,
-    WNDCLASSW, WS_EX_LAYERED, WS_EX_NOACTIVATE, WS_EX_TOOLWINDOW, WS_EX_TOPMOST, WS_EX_TRANSPARENT,
-    WS_POPUP,
-};
-
-/// A running force-composed-flip overlay. Drop signals the thread to tear down its window + exit.
-pub struct ForceComposedFlip {
-    stop: Arc<AtomicBool>,
-}
-
-impl ForceComposedFlip {
-    /// Start the overlay (no-op + `None` if disabled via `PUNKTFUNK_FORCE_COMPOSED=0`).
-    pub fn start() -> Option<Self> {
-        if std::env::var("PUNKTFUNK_FORCE_COMPOSED").as_deref() == Ok("0") {
-            tracing::info!("force-composed-flip overlay disabled (PUNKTFUNK_FORCE_COMPOSED=0)");
-            return None;
-        }
-        let stop = Arc::new(AtomicBool::new(false));
-        let st = stop.clone();
-        std::thread::Builder::new()
-            .name("composed-flip".into())
-            // SAFETY: `run` is this module's `unsafe fn` (it owns a desktop+window lifecycle via Win32
-            // FFI); it takes ownership of `st` (the stop `Arc<AtomicBool>`) and has no caller-side memory
-            // precondition. It is designed to own its thread for its whole duration — exactly the
-            // dedicated `composed-flip` thread spawned here.
-            .spawn(move || unsafe { run(st) })
-            .ok()?;
-        tracing::info!("force-composed-flip overlay started (Winlogon-aware)");
-        Some(ForceComposedFlip { stop })
-    }
-}
-
-impl Drop for ForceComposedFlip {
-    fn drop(&mut self) {
-        self.stop.store(true, Ordering::Relaxed);
-    }
-}
-
-extern "system" fn wndproc(hwnd: HWND, msg: u32, wp: WPARAM, lp: LPARAM) -> LRESULT {
-    // SAFETY: this is the window procedure the OS invokes with the window's own `hwnd` and a real
-    // message `(msg, wp, lp)`. `DefWindowProcW` performs default processing for exactly those
-    // parameters (all passed straight through by value); it borrows no Rust memory and is synchronous.
-    unsafe { DefWindowProcW(hwnd, msg, wp, lp) }
-}
-
-/// Read the current input-desktop name (e.g. "Default" / "Winlogon"); `None` if it can't be read.
-unsafe fn input_desktop_name() -> Option<String> {
-    let desk = OpenInputDesktop(
-        DESKTOP_CONTROL_FLAGS(0),
-        false,
-        DESKTOP_ACCESS_FLAGS(0x0001),
-    )
-    .ok()?;
-    let mut buf = [0u16; 64];
-    let mut needed = 0u32;
-    let ok = GetUserObjectInformationW(
-        windows::Win32::Foundation::HANDLE(desk.0),
-        UOI_NAME,
-        Some(buf.as_mut_ptr() as *mut _),
-        (buf.len() * 2) as u32,
-        Some(&mut needed),
-    )
-    .is_ok();
-    let _ = CloseDesktop(desk);
-    if !ok {
-        return None;
-    }
-    Some(
-        String::from_utf16_lossy(&buf)
-            .trim_end_matches('\u{0}')
-            .to_string(),
-    )
-}
-
-/// Create the tiny topmost layered click-through window on the CURRENT thread's desktop. Caller must
-/// have `SetThreadDesktop`'d to the target input desktop first.
-unsafe fn make_overlay() -> Option<HWND> {
-    let hinst = GetModuleHandleW(None).ok()?;
-    let class = w!("PunktfunkComposedFlip");
-    // RegisterClassW is idempotent-ish: a second register for the same name fails harmlessly; we
-    // ignore the result and rely on the class existing. (One process, so it registers once.)
-    let wc = WNDCLASSW {
-        lpfnWndProc: Some(wndproc),
-        hInstance: hinst.into(),
-        lpszClassName: class,
-        ..Default::default()
-    };
-    let atom = RegisterClassW(&wc);
-    if atom == 0 {
-        let e = windows::Win32::Foundation::GetLastError();
-        // 1410 = ERROR_CLASS_ALREADY_EXISTS is fine (re-register after a desktop switch).
-        if e.0 != 1410 {
-            tracing::warn!(err = e.0, "force-composed-flip: RegisterClassW failed");
-        }
-    }
-    let hwnd = match CreateWindowExW(
-        WS_EX_LAYERED | WS_EX_TRANSPARENT | WS_EX_TOPMOST | WS_EX_NOACTIVATE | WS_EX_TOOLWINDOW,
-        class,
-        w!(""),
-        WS_POPUP,
-        0,
-        0,
-        1,
-        1,
-        None,
-        None,
-        Some(hinst.into()),
-        None,
-    ) {
-        Ok(h) => h,
-        Err(e) => {
-            let le = windows::Win32::Foundation::GetLastError();
-            tracing::warn!(err = %format!("{e:?}"), last = le.0,
-                "force-composed-flip: CreateWindowExW failed");
-            return None;
-        }
-    };
-    // alpha=1: technically visible (so it disqualifies independent-flip) but imperceptible.
-    let _ = SetLayeredWindowAttributes(hwnd, windows::Win32::Foundation::COLORREF(0), 1, LWA_ALPHA);
-    let _ = ShowWindow(hwnd, SW_SHOWNOACTIVATE);
-    let _ = SetWindowPos(
-        hwnd,
-        Some(HWND_TOPMOST),
-        0,
-        0,
-        0,
-        0,
-        SWP_NOMOVE | SWP_NOSIZE | SWP_NOACTIVATE,
-    );
-    Some(hwnd)
-}
-
-unsafe fn run(stop: Arc<AtomicBool>) {
-    let mut cur_desktop: Option<String> = None;
-    let mut hwnd: Option<HWND> = None;
-    let mut ticks: u32 = 0;
-    while !stop.load(Ordering::Relaxed) {
-        // Follow the input desktop: if it changed (Default↔Winlogon), re-attach this thread and
-        // recreate the window there (a window is bound to the desktop it was created on).
-        let name = input_desktop_name();
-        if name != cur_desktop {
-            if let Some(h) = hwnd.take() {
-                let _ = DestroyWindow(h);
-            }
-            if let Ok(desk) = OpenInputDesktop(
-                DESKTOP_CONTROL_FLAGS(0),
-                false,
-                DESKTOP_ACCESS_FLAGS(0x1000_0000), // GENERIC_ALL (incl. DESKTOP_CREATEWINDOW=0x0002)
-            ) {
-                if SetThreadDesktop(desk).is_ok() {
-                    hwnd = make_overlay();
-                    tracing::info!(desktop = ?name, created = hwnd.is_some(),
-                        "force-composed-flip: overlay (re)created on input desktop");
-                }
-                // Leak `desk` while it's the thread desktop (closing the current thread desktop is UB).
-            }
-            cur_desktop = name;
-        }
-        // Re-assert topmost periodically (other windows on the secure desktop can push us down) and
-        // pump our message queue so the window stays responsive/composited.
-        if let Some(h) = hwnd {
-            let _ = SetWindowPos(
-                h,
-                Some(HWND_TOPMOST),
-                0,
-                0,
-                0,
-                0,
-                SWP_NOMOVE | SWP_NOSIZE | SWP_NOACTIVATE,
-            );
-            let mut msg = MSG::default();
-            while PeekMessageW(&mut msg, Some(h), 0, 0, PM_REMOVE).as_bool() {
-                let _ = TranslateMessage(&msg);
-                DispatchMessageW(&msg);
-            }
-        }
-        ticks = ticks.wrapping_add(1);
-        let _ = ticks;
-        std::thread::sleep(std::time::Duration::from_millis(200));
-    }
-    if let Some(h) = hwnd.take() {
-        let _ = DestroyWindow(h);
-    }
-    tracing::info!("force-composed-flip overlay stopped");
-}

crates/punktfunk-host/src/capture/windows/desktop_watch.rs

@@ -1,144 +0,0 @@
-//! Input-desktop watcher (Windows) — the authoritative "normal vs secure desktop" signal for the
-//! two-process secure-desktop design (design/archive/windows-secure-desktop.md).
-//!
-//! Windows switches the *input desktop* to "Winlogon" (the secure desktop) for UAC elevation, the
-//! lock screen and the login screen, and back to "Default" for the normal session. WGC captures only
-//! the normal desktop; DDA-as-SYSTEM captures the secure one. A dedicated thread polls the input
-//! desktop's NAME (WTS session notifications miss UAC entirely, so the name is the reliable signal)
-//! and publishes it as an atomic the capture mux + input path read.
-
-// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it (unsafe-proof program).
-#![deny(clippy::undocumented_unsafe_blocks)]
-
-use std::sync::atomic::{AtomicBool, AtomicU8, Ordering};
-use std::sync::Arc;
-use std::time::Duration;
-use windows::Win32::Foundation::HANDLE;
-use windows::Win32::System::StationsAndDesktops::{
-    CloseDesktop, GetUserObjectInformationW, OpenInputDesktop, DESKTOP_ACCESS_FLAGS,
-    DESKTOP_CONTROL_FLAGS, UOI_NAME,
-};
-
-/// The normal interactive desktop ("Default") — WGC capture applies.
-pub const DESKTOP_NORMAL: u8 = 0;
-/// The secure desktop ("Winlogon": UAC / lock / login) — DDA-as-SYSTEM capture applies.
-pub const DESKTOP_SECURE: u8 = 1;
-
-/// Polls the input-desktop name on its own thread and publishes [`DESKTOP_NORMAL`]/[`DESKTOP_SECURE`].
-pub struct DesktopWatcher {
-    state: Arc<AtomicU8>,
-    stop: Arc<AtomicBool>,
-}
-
-impl DesktopWatcher {
-    pub fn start() -> Self {
-        // Compute the CURRENT desktop synchronously before returning, so the first reader (the capture
-        // mux) sees the real state immediately. Otherwise a session that begins already on the secure
-        // desktop (e.g. a reconnect to a locked box) would read DESKTOP_NORMAL for the first poll
-        // interval and relay one stale normal-desktop frame — the "flash of the login screen" bug.
-        // SAFETY: `is_secure_desktop` is this module's `unsafe fn` — unsafe only because it calls Win32
-        // desktop FFI (`OpenInputDesktop`/`GetUserObjectInformationW`/`CloseDesktop`), with no caller
-        // precondition; it opens, names, and closes the input-desktop handle internally and is safe to
-        // call from any thread (here, on the thread running `DesktopWatcher::start`).
-        let initial = if unsafe { is_secure_desktop() } {
-            DESKTOP_SECURE
-        } else {
-            DESKTOP_NORMAL
-        };
-        let state = Arc::new(AtomicU8::new(initial));
-        let stop = Arc::new(AtomicBool::new(false));
-        let s = state.clone();
-        let st = stop.clone();
-        let _ = std::thread::Builder::new()
-            .name("desktop-watch".into())
-            .spawn(move || {
-                // Debounce: only publish a change after the raw reading has been stable for several
-                // polls. The input desktop flaps Default↔Winlogon transiently during a lock/UAC
-                // transition; publishing every flap makes the capture mux thrash (rebuild storms).
-                const STABLE_POLLS: u32 = 4; // ~80ms
-                let mut published = initial;
-                let mut candidate = initial;
-                let mut stable = 0u32;
-                while !st.load(Ordering::Relaxed) {
-                    // SAFETY: same as in `start` — `is_secure_desktop` is self-contained Win32 desktop
-                    // FFI with no caller precondition, called here on the dedicated `desktop-watch`
-                    // polling thread.
-                    let v = if unsafe { is_secure_desktop() } {
-                        DESKTOP_SECURE
-                    } else {
-                        DESKTOP_NORMAL
-                    };
-                    if v == candidate {
-                        stable = stable.saturating_add(1);
-                    } else {
-                        candidate = v;
-                        stable = 1;
-                    }
-                    if stable >= STABLE_POLLS && candidate != published {
-                        s.store(candidate, Ordering::Release);
-                        published = candidate;
-                        tracing::info!(
-                            desktop = if candidate == DESKTOP_SECURE {
-                                "Winlogon(secure)"
-                            } else {
-                                "Default"
-                            },
-                            "input desktop changed (debounced)"
-                        );
-                    }
-                    std::thread::sleep(Duration::from_millis(20));
-                }
-            });
-        DesktopWatcher { state, stop }
-    }
-
-    /// The shared atomic ([`DESKTOP_NORMAL`]/[`DESKTOP_SECURE`]) for the capture mux to read.
-    pub fn state(&self) -> Arc<AtomicU8> {
-        self.state.clone()
-    }
-
-    /// True when the secure (Winlogon) desktop is the input desktop right now.
-    pub fn is_secure(&self) -> bool {
-        self.state.load(Ordering::Acquire) == DESKTOP_SECURE
-    }
-}
-
-impl Drop for DesktopWatcher {
-    fn drop(&mut self) {
-        self.stop.store(true, Ordering::Relaxed);
-    }
-}
-
-/// True if the current input desktop is "Winlogon" (the secure desktop). Best-effort: if the desktop
-/// can't be opened or named, report not-secure (the safe default — keep WGC/normal capture).
-pub(crate) unsafe fn is_secure_desktop() -> bool {
-    let desk = match OpenInputDesktop(
-        DESKTOP_CONTROL_FLAGS(0),
-        false,
-        DESKTOP_ACCESS_FLAGS(DESKTOP_READOBJECTS),
-    ) {
-        Ok(d) => d,
-        Err(_) => return false,
-    };
-    let mut buf = [0u16; 64];
-    let mut needed = 0u32;
-    let ok = GetUserObjectInformationW(
-        HANDLE(desk.0),
-        UOI_NAME,
-        Some(buf.as_mut_ptr() as *mut _),
-        (buf.len() * 2) as u32,
-        Some(&mut needed),
-    )
-    .is_ok();
-    let _ = CloseDesktop(desk);
-    if !ok {
-        return false;
-    }
-    let name = String::from_utf16_lossy(&buf);
-    name.trim_end_matches('\u{0}')
-        .eq_ignore_ascii_case("Winlogon")
-}
-
-/// `DESKTOP_READOBJECTS` access right (the windows crate exposes it as a typed flag; we need the raw
-/// bit for `OpenInputDesktop`'s access mask).
-const DESKTOP_READOBJECTS: u32 = 0x0001;

crates/punktfunk-host/src/capture/windows/wgc.rs

@@ -1,816 +0,0 @@
-//! Windows.Graphics.Capture (WGC) capture backend — the HDR/animation-correct path.
-//!
-//! Why WGC over DXGI Desktop Duplication: DDA duplicates only the DWM-composed primary surface, so
-//! HDR desktop animations the OS routes onto hardware overlay / independent-flip / MPO planes (Start
-//! menu, Win11 Mica/acrylic, window resize) never enter the surface DDA reads — the stream shows a
-//! frozen desktop ("broken HDR animations"). Engaging WGC capture pulls that content back through DWM
-//! composition, so the surface WGC hands back contains the animations. WGC also has no
-//! ACCESS_LOST-on-overlay-flip churn.
-//!
-//! It reuses the rest of the pipeline UNCHANGED: the frame's GPU texture (the OS already composited
-//! the cursor into it — `IsCursorCaptureEnabled(true)`) goes through the same scRGB→BT.2020-PQ shader
-//! ([`super::dxgi::HdrConverter`]) into a host-owned `R10G10B10A2` texture (HDR) or is copied into a
-//! BGRA texture (SDR), which is handed to NVENC zero-copy (registered by pointer, encoded in place).
-//! Shares the D3D11 device with NVENC via `FramePayload::D3d11`.
-//!
-//! Limitation: WGC cannot capture the secure desktop (lock / UAC / login) — the caller falls back to
-//! the DDA backend ([`super::dxgi::DuplCapturer`]) for those (see capture.rs).
-
-// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it (unsafe-proof program).
-#![deny(clippy::undocumented_unsafe_blocks)]
-
-use super::dxgi::{
-    find_output, hdr_shader_p010_enabled, make_device, nudge_cursor_onto, D3d11Frame, HdrConverter,
-    HdrP010Converter, VideoConverter, WinCaptureTarget,
-};
-use super::{CapturedFrame, Capturer, FramePayload, PixelFormat};
-use anyhow::{bail, Context, Result};
-use std::collections::VecDeque;
-use std::sync::atomic::{AtomicU64, Ordering};
-use std::sync::{Arc, Condvar, Mutex};
-use std::time::{Duration, Instant};
-use windows::core::{IInspectable, Interface};
-use windows::Foundation::{TimeSpan, TypedEventHandler};
-use windows::Graphics::Capture::{
-    Direct3D11CaptureFrame, Direct3D11CaptureFramePool, GraphicsCaptureItem, GraphicsCaptureSession,
-};
-use windows::Graphics::DirectX::DirectXPixelFormat;
-use windows::Win32::Foundation::{CloseHandle, HANDLE};
-use windows::Win32::Graphics::Direct3D11::{
-    ID3D11Device, ID3D11DeviceContext, ID3D11RenderTargetView, ID3D11ShaderResourceView,
-    ID3D11Texture2D, D3D11_BIND_RENDER_TARGET, D3D11_BIND_SHADER_RESOURCE, D3D11_TEXTURE2D_DESC,
-    D3D11_USAGE_DEFAULT,
-};
-use windows::Win32::Graphics::Dxgi::Common::{
-    DXGI_COLOR_SPACE_RGB_FULL_G2084_NONE_P2020, DXGI_FORMAT_R10G10B10A2_UNORM,
-    DXGI_FORMAT_R16G16B16A16_FLOAT, DXGI_SAMPLE_DESC,
-};
-use windows::Win32::Graphics::Dxgi::{IDXGIDevice, IDXGIOutput6};
-use windows::Win32::Security::{ImpersonateLoggedOnUser, RevertToSelf};
-use windows::Win32::System::RemoteDesktop::{WTSGetActiveConsoleSessionId, WTSQueryUserToken};
-use windows::Win32::System::WinRT::Direct3D11::{
-    CreateDirect3D11DeviceFromDXGIDevice, IDirect3DDxgiInterfaceAccess,
-};
-use windows::Win32::System::WinRT::Graphics::Capture::IGraphicsCaptureItemInterop;
-use windows::Win32::System::WinRT::{RoInitialize, RO_INIT_MULTITHREADED};
-
-/// Output texture ring depth. The encode loop pipelines one frame deep (NVENC encodes frame N while
-/// the capturer produces N+1), so two live textures suffice; three gives headroom against a slow
-/// `lock_bitstream` and matches the WGC frame-pool depth.
-// Sized for the deep encode pipeline (`PUNKTFUNK_ENCODE_DEPTH`, default 4, clamped ≤ 6): up to DEPTH
-// frames are in flight in NVENC at once, so the HDR convert ring and the SDR held-frame set must each
-// keep DEPTH(+headroom) live textures, and the WGC pool needs spare buffers beyond what we hold.
-const OUT_RING: usize = 8;
-
-/// SDR zero-copy: how many recent WGC frames to keep alive so NVENC can encode the pool texture in
-/// place (no `CopyResource`). Each in-flight encode reads a distinct frame, so this must exceed the
-/// pipeline depth; the oldest is released once `HELD_FRAMES` newer ones exist.
-const HELD_FRAMES: usize = 8;
-/// WGC frame-pool buffer count. Must exceed `HELD_FRAMES` so the compositor always has free buffers
-/// to render into while we hold frames for in-place (zero-copy) SDR encode.
-const WGC_POOL_BUFFERS: i32 = 10;
-
-/// The host runs as SYSTEM (so the DDA secure-desktop path works), but WGC will NOT activate under
-/// the SYSTEM account (`CreateForMonitor` → 0x80070424). Impersonate the interactive console user
-/// for the WGC activation. Returns the user token (the caller reverts + closes it after activation)
-/// or `None` (no active user, or the host already runs AS the user — WTSQueryUserToken then fails and
-/// WGC works without impersonation). SYSTEM-only; harmless under a user-token host.
-unsafe fn impersonate_active_user() -> Option<HANDLE> {
-    let session = WTSGetActiveConsoleSessionId();
-    if session == 0xFFFF_FFFF {
-        return None;
-    }
-    let mut token = HANDLE::default();
-    if WTSQueryUserToken(session, &mut token).is_ok() {
-        if ImpersonateLoggedOnUser(token).is_ok() {
-            return Some(token);
-        }
-        let _ = CloseHandle(token);
-    }
-    None
-}
-
-/// RAII: reverts the WGC-activation impersonation when it drops (covers every `?` early-return).
-struct Deimpersonate(Option<HANDLE>);
-impl Drop for Deimpersonate {
-    fn drop(&mut self) {
-        if let Some(tok) = self.0.take() {
-            // SAFETY: `RevertToSelf` takes no arguments and undoes the thread impersonation set during
-            // WGC activation; `tok` is the impersonation token `HANDLE` from `impersonate_active_user`,
-            // owned by this `Deimpersonate` and closed exactly once here (taken out of the `Option`, so
-            // no double-close). Both are FFI calls borrowing no Rust memory.
-            unsafe {
-                let _ = RevertToSelf();
-                let _ = CloseHandle(tok);
-            }
-        }
-    }
-}
-
-/// Signal from the free-threaded FrameArrived callback to the encode thread: a monotonically
-/// increasing count of arrived frames + a condvar to wake `next_frame`. The encode thread tracks how
-/// many it has consumed; `TryGetNextFrame` is called exactly `available - consumed` times so we never
-/// hit the empty-pool ambiguity, and draining to the newest keeps latency at one frame.
-struct WgcSignal {
-    available: AtomicU64,
-    mtx: Mutex<()>,
-    cv: Condvar,
-}
-
-pub struct WgcCapturer {
-    device: ID3D11Device,
-    context: ID3D11DeviceContext,
-    // WGC objects — kept alive for the session's lifetime.
-    pool: Direct3D11CaptureFramePool,
-    session: GraphicsCaptureSession,
-    _item: GraphicsCaptureItem,
-    _frame_arrived_token: i64,
-    signal: Arc<WgcSignal>,
-    consumed: u64,
-
-    width: u32,
-    height: u32,
-    timeout_ms: u64,
-    first_frame: bool,
-
-    hdr: bool,
-    /// The source display's static HDR mastering metadata (ST.2086 + content light level), read from
-    /// `IDXGIOutput6::GetDesc1` at open when the output is HDR. Forwarded to the encoder (in-band SEI)
-    /// and the client (0xCE) by the stream loop. `None` when SDR. (The helper relay path also encodes,
-    /// so this is what gives the secure/normal-desktop HDR stream its mastering SEI.)
-    hdr_meta: Option<punktfunk_core::quic::HdrMeta>,
-    hdr_conv: Option<HdrConverter>,
-    fp16_src: Option<ID3D11Texture2D>,
-    fp16_srv: Option<ID3D11ShaderResourceView>,
-    /// `PUNKTFUNK_HDR_SHADER_P010` path: emit P010 (BT.2020 PQ 10-bit limited range) DIRECTLY from our
-    /// own shader (`HdrP010Converter`) so NVENC takes native P010 and skips its SM-side RGB→YUV CSC.
-    /// Gated by [`hdr_shader_p010_enabled`] AND `self.hdr`; `None`/empty when off → the existing R10 +
-    /// VideoProcessor paths run unchanged. `p010_disabled` latches a runtime failure (e.g. a driver
-    /// that rejects the planar plane RTV) so we fall back to the R10 path and stop retrying.
-    hdr_p010_conv: Option<HdrP010Converter>,
-    p010_out: Vec<ID3D11Texture2D>,
-    p010_idx: usize,
-    p010_disabled: bool,
-    /// Ring of host-owned output textures (BGRA for SDR, R10G10B10A2 for HDR), rotated per processed
-    /// frame. A ring — not one texture — is required because the encode loop is PIPELINED: NVENC
-    /// encodes frame N (in place, registered by pointer) while this capturer produces frame N+1, so
-    /// N+1 must land in a DIFFERENT texture or it clobbers the in-flight encode. (`fp16_src` stays
-    /// single: it's only touched within the D3D11 immediate context, whose op ordering already
-    /// serializes the convert's read against the next copy's write — NVENC's async engine read is the
-    /// only consumer that escapes that ordering, and it reads the ring output, never `fp16_src`.)
-    out_ring: Vec<ID3D11Texture2D>,
-    ring_idx: usize,
-    /// Video-processor RGB→YUV converter (off the 3D engine where possible) + its NV12/P010 output
-    /// ring. Preferred path: the OS-composited capture (cursor already in it) is converted DIRECTLY to
-    /// NVENC's native YUV — no `CopyResource`, no cursor draw, and NVENC skips its internal RGB→YUV.
-    /// `None`/error → falls back to the legacy SDR-zero-copy / HDR-shader paths.
-    video_conv: Option<VideoConverter>,
-    yuv_out: Vec<ID3D11Texture2D>,
-    yuv_idx: usize,
-    yuv_is_hdr: bool,
-    vp_disabled: bool,
-    /// SDR zero-copy: the recent WGC frames we hand to NVENC in place. Held so the pool doesn't
-    /// recycle the texture mid-encode; the oldest is released once `HELD_FRAMES` newer ones exist.
-    held: VecDeque<Direct3D11CaptureFrame>,
-    /// Last presentable GPU texture + format, repeated when no new frame arrived (static desktop).
-    last_present: Option<(ID3D11Texture2D, PixelFormat)>,
-
-    /// Owns the SudoVDA keepalive once attached (after WGC is confirmed open) — dropping the capturer
-    /// then REMOVEs the virtual output. `None` between open and attach so a WGC-open failure leaves
-    /// the keepalive with the caller for the DDA fallback.
-    _keepalive: Option<Box<dyn Send>>,
-}
-
-// SAFETY: like `DuplCapturer`. `WgcCapturer` holds D3D11 (free-threaded device/context) plus WGC WinRT
-// objects (`Direct3D11CaptureFramePool` etc., created free-threaded via `CreateFreeThreaded`). COM/WinRT
-// reference counting is interlocked, and the capturer is owned + used by exactly one encode thread,
-// moved to it once and never shared (no `Sync`), so transferring ownership across threads is sound. The
-// free-threaded `FrameArrived` callback touches only the `Arc<WgcSignal>` (itself `Send + Sync`), not
-// the capturer's COM fields.
-unsafe impl Send for WgcCapturer {}
-
-impl WgcCapturer {
-    /// Open WGC capture. Does NOT take the keepalive — the caller attaches it via
-    /// [`attach_keepalive`](Self::attach_keepalive) only after open succeeds, so a failure leaves the
-    /// keepalive with the caller to hand to the DDA fallback.
-    pub fn open(target: WinCaptureTarget, preferred: Option<(u32, u32, u32)>) -> Result<Self> {
-        // SAFETY: runs on the thread opening the WGC session. `RoInitialize` inits this thread's WinRT
-        // apartment (idempotent; result ignored). `impersonate_active_user()` and `find_output()` are
-        // this module's `unsafe fn`s whose contracts (call on the activating thread; pass a GDI name)
-        // are met, and the impersonation is reverted by `_deimp`'s Drop on every return path. Every
-        // COM/WinRT call thereafter operates on an object obtained + `?`-checked earlier in this same
-        // block on this single thread — the `IDXGIOutput1` from `find_output`, the device/context from
-        // `make_device`, the factory/interop/item/pool/session — and the `TypedEventHandler` closure
-        // captures an `Arc<WgcSignal>` (Send+Sync) by move. No raw pointers are dereferenced; borrowed
-        // locals outlive their synchronous calls.
-        unsafe {
-            // WGC is WinRT — the calling thread needs a COM/WinRT apartment for the GraphicsCaptureItem
-            // activation factory (RoGetActivationFactory). Initialize MTA; ignore "already initialized"
-            // / "changed mode" (another component on this thread may have init'd a compatible apartment).
-            let ro = RoInitialize(RO_INIT_MULTITHREADED);
-            // Impersonate the interactive user for the duration of WGC activation (host runs as
-            // SYSTEM; WGC won't activate under SYSTEM). Reverted by the guard's Drop on return. The
-            // WGC objects, once created, are accessed from the (SYSTEM) encode thread thereafter.
-            let imp = impersonate_active_user();
-            let _deimp = Deimpersonate(imp);
-            tracing::info!(ro_result = ?ro, impersonated = imp.is_some(), "WGC: RoInitialize(MTA)");
-            // The SudoVDA output appears a beat after the display is created — settle-retry like DDA.
-            let deadline = Instant::now() + Duration::from_millis(2000);
-            let (adapter, output) = loop {
-                if let Some(n) = crate::win_display::resolve_gdi_name(target.target_id) {
-                    if let Ok(found) = find_output(&n) {
-                        break found;
-                    }
-                }
-                if let Ok(found) = find_output(&target.gdi_name) {
-                    break found;
-                }
-                if Instant::now() >= deadline {
-                    bail!(
-                        "WGC: no DXGI output for SudoVDA target {} yet",
-                        target.target_id
-                    );
-                }
-                std::thread::sleep(Duration::from_millis(100));
-            };
-
-            let (device, context) = make_device(&adapter)?;
-            let od = output.GetDesc().context("output GetDesc")?;
-            let hmonitor = od.Monitor;
-
-            // HDR iff the output's colour space is BT.2020 PQ (G2084) — matches the DDA FP16 detection.
-            // From the same desc, read the source display's mastering metadata (ST.2086) when HDR.
-            let desc1 = output
-                .cast::<IDXGIOutput6>()
-                .ok()
-                .and_then(|o6| o6.GetDesc1().ok());
-            let hdr = desc1
-                .as_ref()
-                .map(|d1| d1.ColorSpace == DXGI_COLOR_SPACE_RGB_FULL_G2084_NONE_P2020)
-                .unwrap_or(false);
-            let hdr_meta = if hdr {
-                desc1.as_ref().map(|d| {
-                    crate::hdr::hdr_meta_from_display(
-                        (d.RedPrimary[0], d.RedPrimary[1]),
-                        (d.GreenPrimary[0], d.GreenPrimary[1]),
-                        (d.BluePrimary[0], d.BluePrimary[1]),
-                        (d.WhitePoint[0], d.WhitePoint[1]),
-                        d.MaxLuminance,
-                        d.MinLuminance,
-                        0, // MaxCLL: GetDesc1 has no content light level (Apollo zeroes it)
-                        0, // MaxFALL
-                    )
-                })
-            } else {
-                None
-            };
-
-            // Wrap our D3D11 device as a WinRT IDirect3DDevice so the frame pool allocates on it (the
-            // pool textures land on our device → CopyResource + NVENC are same-device, no readback).
-            let dxgi_device: IDXGIDevice = device.cast().context("ID3D11Device as IDXGIDevice")?;
-            let inspectable: IInspectable = CreateDirect3D11DeviceFromDXGIDevice(&dxgi_device)
-                .context("CreateDirect3D11DeviceFromDXGIDevice")?;
-            let d3d_device: windows::Graphics::DirectX::Direct3D11::IDirect3DDevice = inspectable
-                .cast()
-                .context("IInspectable as IDirect3DDevice")?;
-
-            tracing::info!(hdr, "WGC: device ready, creating capture item");
-            // GraphicsCaptureItem for the monitor (the SudoVDA output enumerates as a normal monitor).
-            let interop: IGraphicsCaptureItemInterop =
-                windows::core::factory::<GraphicsCaptureItem, IGraphicsCaptureItemInterop>()
-                    .context("GraphicsCaptureItem interop factory")?;
-            let item: GraphicsCaptureItem = interop
-                .CreateForMonitor(hmonitor)
-                .context("CreateForMonitor")?;
-            let size = item.Size().context("item Size")?;
-            let (width, height) = (size.Width.max(0) as u32, size.Height.max(0) as u32);
-            tracing::info!(
-                width,
-                height,
-                "WGC: capture item created, creating frame pool"
-            );
-
-            let pixel_format = if hdr {
-                DirectXPixelFormat::R16G16B16A16Float // scRGB FP16 — same surface DDA gives on HDR
-            } else {
-                DirectXPixelFormat::B8G8R8A8UIntNormalized
-            };
-            // Extra buffers: SDR zero-copy holds the last `HELD_FRAMES` frames (encoded in place), so
-            // the pool needs headroom beyond that for the producer to keep rendering at 240 Hz.
-            let pool = Direct3D11CaptureFramePool::CreateFreeThreaded(
-                &d3d_device,
-                pixel_format,
-                WGC_POOL_BUFFERS,
-                size,
-            )
-            .context("CreateFreeThreaded frame pool")?;
-
-            let signal = Arc::new(WgcSignal {
-                available: AtomicU64::new(0),
-                mtx: Mutex::new(()),
-                cv: Condvar::new(),
-            });
-            let sig = signal.clone();
-            let handler = TypedEventHandler::<Direct3D11CaptureFramePool, IInspectable>::new(
-                move |_pool, _arg| {
-                    sig.available.fetch_add(1, Ordering::Release);
-                    sig.cv.notify_one();
-                    Ok(())
-                },
-            );
-            let token = pool.FrameArrived(&handler).context("FrameArrived")?;
-
-            tracing::info!("WGC: creating capture session");
-            let session = pool
-                .CreateCaptureSession(&item)
-                .context("CreateCaptureSession")?;
-            // OS composites the cursor into the frame (HDR-correct, no manual composite pass).
-            let _ = session.SetIsCursorCaptureEnabled(true);
-            // Drop the yellow capture border (best-effort — older builds reject it).
-            let _ = session.SetIsBorderRequired(false);
-            // Lift the 60 Hz cap: allow up to the client's refresh (Win11 24H2+; below that this is a
-            // no-op and WGC caps ~60). 100 ns ticks per frame.
-            let refresh = preferred
-                .map(|(_, _, hz)| hz)
-                .filter(|&hz| hz > 0)
-                .unwrap_or(60);
-            let ticks = (10_000_000i64 / refresh.max(1) as i64).max(1);
-            let _ = session.SetMinUpdateInterval(TimeSpan { Duration: ticks });
-            tracing::info!("WGC: StartCapture");
-            session.StartCapture().context("StartCapture")?;
-            // WGC fires FrameArrived on CHANGE; a static desktop may never deliver the first frame
-            // (→ black, then the next_frame deadline ends the session). Nudge the cursor onto the
-            // output to force the first composition change, exactly like the DDA path does.
-            nudge_cursor_onto(&output);
-
-            let timeout_ms = (2000 / refresh.max(1) as u64).max(8);
-            tracing::info!(
-                width,
-                height,
-                hdr,
-                refresh,
-                "WGC capture started ({})",
-                if hdr {
-                    "HDR FP16→BT.2020 PQ"
-                } else {
-                    "SDR BGRA"
-                }
-            );
-
-            Ok(Self {
-                device,
-                context,
-                pool,
-                session,
-                _item: item,
-                _frame_arrived_token: token,
-                signal,
-                consumed: 0,
-                width,
-                height,
-                timeout_ms,
-                first_frame: true,
-                hdr,
-                hdr_meta,
-                hdr_conv: None,
-                fp16_src: None,
-                fp16_srv: None,
-                hdr_p010_conv: None,
-                p010_out: Vec::new(),
-                p010_idx: 0,
-                p010_disabled: false,
-                out_ring: Vec::new(),
-                ring_idx: 0,
-                video_conv: None,
-                yuv_out: Vec::new(),
-                yuv_idx: 0,
-                yuv_is_hdr: false,
-                vp_disabled: std::env::var_os("PUNKTFUNK_NO_VIDEO_PROCESSOR").is_some(),
-                held: VecDeque::new(),
-                last_present: None,
-                _keepalive: None,
-            })
-        }
-    }
-
-    /// Take ownership of the SudoVDA keepalive once the WGC session is confirmed open.
-    pub fn attach_keepalive(&mut self, keepalive: Box<dyn Send>) {
-        self._keepalive = Some(keepalive);
-    }
-
-    /// Block until a new frame arrives (cv), then drain `TryGetNextFrame` to the NEWEST queued frame
-    /// (skip stale → one-frame latency). Returns `None` on timeout (no new frame → caller repeats).
-    fn wait_and_drain(&mut self) -> Option<Direct3D11CaptureFrame> {
-        let wait_ms = if self.first_frame {
-            2000
-        } else {
-            self.timeout_ms
-        };
-        {
-            let mut g = self.signal.mtx.lock().unwrap();
-            while self.signal.available.load(Ordering::Acquire) <= self.consumed {
-                let (ng, res) = self
-                    .signal
-                    .cv
-                    .wait_timeout(g, Duration::from_millis(wait_ms))
-                    .unwrap();
-                g = ng;
-                if res.timed_out() {
-                    return None;
-                }
-            }
-        }
-        let target = self.signal.available.load(Ordering::Acquire);
-        let mut last = None;
-        while self.consumed < target {
-            if let Ok(f) = self.pool.TryGetNextFrame() {
-                last = Some(f);
-            }
-            self.consumed += 1;
-        }
-        last
-    }
-
-    unsafe fn ensure_fp16_src(&mut self) -> Result<()> {
-        if self.fp16_src.is_some() {
-            return Ok(());
-        }
-        let desc = tex_desc(
-            self.width,
-            self.height,
-            DXGI_FORMAT_R16G16B16A16_FLOAT,
-            (D3D11_BIND_RENDER_TARGET.0 | D3D11_BIND_SHADER_RESOURCE.0) as u32,
-        );
-        let mut t = None;
-        self.device
-            .CreateTexture2D(&desc, None, Some(&mut t))
-            .context("CreateTexture2D(wgc fp16 src)")?;
-        let t = t.context("fp16 src")?;
-        let mut srv = None;
-        self.device
-            .CreateShaderResourceView(&t, None, Some(&mut srv))?;
-        self.fp16_srv = Some(srv.context("fp16 srv")?);
-        self.fp16_src = Some(t);
-        Ok(())
-    }
-
-    /// Lazily allocate the HDR output texture ring (R10G10B10A2, the convert pass's render target →
-    /// NVENC input), `RENDER_TARGET`-bindable. SDR is zero-copy (encodes the WGC pool texture in
-    /// place) and uses no ring.
-    unsafe fn ensure_out_ring(
-        &mut self,
-        format: windows::Win32::Graphics::Dxgi::Common::DXGI_FORMAT,
-    ) -> Result<()> {
-        if !self.out_ring.is_empty() {
-            return Ok(());
-        }
-        let desc = tex_desc(
-            self.width,
-            self.height,
-            format,
-            D3D11_BIND_RENDER_TARGET.0 as u32,
-        );
-        for _ in 0..OUT_RING {
-            let mut t = None;
-            self.device
-                .CreateTexture2D(&desc, None, Some(&mut t))
-                .context("CreateTexture2D(wgc out ring)")?;
-            self.out_ring.push(t.context("wgc out ring tex")?);
-        }
-        Ok(())
-    }
-
-    /// Convert `input` (the OS-composited WGC pool texture: BGRA or scRGB FP16) → NVENC's native YUV
-    /// (NV12 / P010) on the video processor. Returns the YUV texture (from a ring so consecutive
-    /// encodes don't collide), or `None` to fall back to the legacy RGB paths.
-    unsafe fn convert_to_yuv(
-        &mut self,
-        input: &ID3D11Texture2D,
-        hdr: bool,
-    ) -> Option<ID3D11Texture2D> {
-        if self.vp_disabled {
-            return None;
-        }
-        if self.video_conv.is_none() || self.yuv_out.is_empty() || self.yuv_is_hdr != hdr {
-            self.video_conv = None;
-            self.yuv_out.clear();
-            self.yuv_idx = 0;
-            let vc = match VideoConverter::new(
-                &self.device,
-                &self.context,
-                self.width,
-                self.height,
-                hdr,
-            ) {
-                Ok(vc) => vc,
-                Err(e) => {
-                    tracing::warn!(error = %format!("{e:#}"),
-                        "WGC: video processor unavailable — falling back to RGB path");
-                    self.vp_disabled = true;
-                    return None;
-                }
-            };
-            let fmt = if hdr {
-                windows::Win32::Graphics::Dxgi::Common::DXGI_FORMAT_P010
-            } else {
-                windows::Win32::Graphics::Dxgi::Common::DXGI_FORMAT_NV12
-            };
-            let desc = tex_desc(
-                self.width,
-                self.height,
-                fmt,
-                D3D11_BIND_RENDER_TARGET.0 as u32,
-            );
-            for _ in 0..OUT_RING {
-                let mut t = None;
-                if self
-                    .device
-                    .CreateTexture2D(&desc, None, Some(&mut t))
-                    .is_err()
-                {
-                    tracing::warn!("WGC: CreateTexture2D(YUV) failed — falling back to RGB path");
-                    self.vp_disabled = true;
-                    self.yuv_out.clear();
-                    return None;
-                }
-                let Some(tex) = t else {
-                    self.vp_disabled = true;
-                    self.yuv_out.clear();
-                    return None;
-                };
-                self.yuv_out.push(tex);
-            }
-            self.video_conv = Some(vc);
-            self.yuv_is_hdr = hdr;
-            tracing::info!(
-                hdr,
-                "WGC: video-processor YUV path active ({})",
-                if hdr { "P010" } else { "NV12" }
-            );
-        }
-        let slot = self.yuv_idx;
-        self.yuv_idx = (self.yuv_idx + 1) % self.yuv_out.len();
-        let out = self.yuv_out[slot].clone();
-        if let Err(e) = self.video_conv.as_ref()?.convert(input, &out) {
-            tracing::warn!(error = %format!("{e:#}"),
-                "WGC: VideoProcessorBlt failed — falling back to RGB path");
-            self.vp_disabled = true;
-            self.video_conv = None;
-            self.yuv_out.clear();
-            return None;
-        }
-        Some(out)
-    }
-
-    /// `PUNKTFUNK_HDR_SHADER_P010` path: convert the OS-composited FP16 scRGB capture DIRECTLY to a
-    /// host-owned P010 texture (BT.2020 PQ, 10-bit limited range) via [`HdrP010Converter`] — two
-    /// shader passes writing the P010 planes. NVENC then takes native P010 and skips its internal
-    /// RGB→YUV CSC. Returns the next ring slot's P010 texture, or `Err` if the converter / a planar
-    /// plane RTV fails (the caller latches `p010_disabled` and falls back to the R10 path).
-    unsafe fn hdr_to_p010(&mut self, src: &ID3D11Texture2D) -> Result<ID3D11Texture2D> {
-        let slot = self.p010_idx;
-        // Lazily allocate the FP16 source (shared with the R10 path) + the P010 output ring.
-        self.ensure_fp16_src()?;
-        let fp16 = self.fp16_src.clone().context("fp16 src")?;
-        self.context.CopyResource(&fp16, src);
-        if self.p010_out.is_empty() {
-            let desc = tex_desc(
-                self.width,
-                self.height,
-                windows::Win32::Graphics::Dxgi::Common::DXGI_FORMAT_P010,
-                D3D11_BIND_RENDER_TARGET.0 as u32,
-            );
-            for _ in 0..OUT_RING {
-                let mut t = None;
-                self.device
-                    .CreateTexture2D(&desc, None, Some(&mut t))
-                    .context("CreateTexture2D(wgc p010 ring)")?;
-                self.p010_out.push(t.context("wgc p010 ring tex")?);
-            }
-        }
-        self.p010_idx = (self.p010_idx + 1) % self.p010_out.len();
-        let out = self.p010_out[slot].clone();
-        if self.hdr_p010_conv.is_none() {
-            self.hdr_p010_conv = Some(HdrP010Converter::new(&self.device)?);
-        }
-        let srv = self.fp16_srv.clone().context("fp16 srv")?;
-        self.hdr_p010_conv.as_ref().unwrap().convert(
-            &self.device,
-            &self.context,
-            &srv,
-            &out,
-            self.width,
-            self.height,
-        )?;
-        Ok(out)
-    }
-
-    fn process_frame(&mut self, frame: Direct3D11CaptureFrame) -> Result<CapturedFrame> {
-        // SAFETY: runs on the capturer's single owning thread. `frame` is a live
-        // `Direct3D11CaptureFrame` from `self.pool`; `frame.Surface().cast::<IDirect3DDxgiInterfaceAccess
-        // >().GetInterface()` yields the frame's backing `ID3D11Texture2D`, which belongs to
-        // `self.device` (the pool was created on it via `CreateDirect3D11DeviceFromDXGIDevice`). Every
-        // helper called here — `hdr_to_p010`, `convert_to_yuv`, `ensure_fp16_src`, `ensure_out_ring`,
-        // `HdrConverter::convert`, `CopyResource`, `CreateRenderTargetView` — operates on
-        // `self.device`/`self.context` and that same-device texture, so all resources share one device.
-        // The frame is held in `self.held` until its async GPU read completes for the zero-copy paths.
-        // Single-threaded immediate-context use; borrowed textures/SRVs/RTVs outlive each synchronous call.
-        unsafe {
-            let surface = frame.Surface().context("frame Surface")?;
-            let access: IDirect3DDxgiInterfaceAccess = surface
-                .cast()
-                .context("surface as IDirect3DDxgiInterfaceAccess")?;
-            let src: ID3D11Texture2D = access
-                .GetInterface()
-                .context("GetInterface ID3D11Texture2D")?;
-
-            // GATED P010-shader path (`PUNKTFUNK_HDR_SHADER_P010`): for HDR, emit P010 (BT.2020 PQ
-            // 10-bit limited range) DIRECTLY from our shader so NVENC takes native P010 and skips its
-            // SM-side RGB→YUV CSC. Runs BEFORE the R10 + VideoProcessor path. A converter/plane-RTV
-            // failure latches `p010_disabled` → we fall through to the unchanged R10 path for the rest
-            // of the session. Default OFF → none of this executes and behaviour is byte-for-byte as
-            // today.
-            if self.hdr && !self.p010_disabled && hdr_shader_p010_enabled() {
-                match self.hdr_to_p010(&src) {
-                    Ok(p010) => {
-                        // The P010 output is host-owned (the ring), and the FP16 CopyResource read
-                        // `src` synchronously on the immediate context before the shader passes — so we
-                        // do NOT need to hold `frame` past here (unlike the SDR/R10 in-place paths).
-                        // Dropping it returns the pool buffer to WGC immediately.
-                        drop(frame);
-                        self.last_present = Some((p010.clone(), PixelFormat::P010));
-                        return Ok(self.d3d11_frame(p010, PixelFormat::P010));
-                    }
-                    Err(e) => {
-                        tracing::warn!(error = %format!("{e:#}"),
-                            "WGC: HDR P010 shader path failed — disabling it, falling back to R10");
-                        self.p010_disabled = true;
-                        self.hdr_p010_conv = None;
-                        self.p010_out.clear();
-                    }
-                }
-            }
-
-            // Preferred path: convert the OS-composited capture (cursor already in it) DIRECTLY to
-            // NVENC's native YUV on the video processor — no CopyResource, no cursor draw, and NVENC
-            // skips its internal RGB→YUV (the contended 3D step). WGC's multi-buffer pool + held set
-            // means reading the pool texture directly does NOT serialize (unlike DDA's single-frame
-            // model). The frame is held until the async Blt finishes. (HDR: the video processor can't
-            // ingest FP16 scRGB, so the Blt fails and we fall back to the R10 path below; the
-            // `PUNKTFUNK_HDR_SHADER_P010` branch above is the off-the-SM HDR path.)
-            if let Some(yuv) = self.convert_to_yuv(&src, self.hdr) {
-                let fmt = if self.hdr {
-                    PixelFormat::P010
-                } else {
-                    PixelFormat::Nv12
-                };
-                self.last_present = Some((yuv.clone(), fmt));
-                let out = self.d3d11_frame(yuv, fmt);
-                self.held.push_back(frame);
-                while self.held.len() > HELD_FRAMES {
-                    self.held.pop_front();
-                }
-                return Ok(out);
-            }
-
-            // --- fallback (video processor unavailable) ---
-            if self.hdr {
-                // Next ring slot — the in-flight encode reads the slot we handed out last time, so
-                // this capture must land in a different one (see `out_ring`).
-                let slot = self.ring_idx;
-                self.ring_idx = (self.ring_idx + 1) % OUT_RING;
-                // FP16 (cursor already composited by the OS) → BT.2020 PQ 10-bit for NVENC.
-                self.ensure_fp16_src()?;
-                let fp16 = self.fp16_src.clone().context("fp16 src")?;
-                self.context.CopyResource(&fp16, &src);
-                self.ensure_out_ring(DXGI_FORMAT_R10G10B10A2_UNORM)?;
-                let out = self.out_ring[slot].clone();
-                if self.hdr_conv.is_none() {
-                    self.hdr_conv = Some(HdrConverter::new(&self.device)?);
-                }
-                let srv = self.fp16_srv.clone().context("fp16 srv")?;
-                let mut rtv: Option<ID3D11RenderTargetView> = None;
-                self.device
-                    .CreateRenderTargetView(&out, None, Some(&mut rtv))?;
-                let rtv = rtv.context("hdr10 rtv")?;
-                self.hdr_conv.as_ref().unwrap().convert(
-                    &self.context,
-                    &srv,
-                    &rtv,
-                    self.width,
-                    self.height,
-                );
-                self.last_present = Some((out.clone(), PixelFormat::Rgb10a2));
-                Ok(self.d3d11_frame(out, PixelFormat::Rgb10a2))
-            } else {
-                // SDR ZERO-COPY: hand NVENC the WGC pool texture DIRECTLY — no `CopyResource`. The
-                // per-frame copy otherwise queues on the graphics engine behind a GPU-saturating game
-                // and stalls `lock_bitstream` ~20 ms (NVENC sits idle waiting for its input). Encoding
-                // the pool texture in place removes that graphics-queue dependency (Apollo's model).
-                // We must keep the frame alive until its async encode finishes, so retain the last
-                // `HELD_FRAMES`; the pool has spare buffers so the producer never starves.
-                self.last_present = Some((src.clone(), PixelFormat::Bgra));
-                let out = self.d3d11_frame(src, PixelFormat::Bgra);
-                self.held.push_back(frame);
-                while self.held.len() > HELD_FRAMES {
-                    self.held.pop_front();
-                }
-                Ok(out)
-            }
-        }
-    }
-
-    fn d3d11_frame(&self, texture: ID3D11Texture2D, format: PixelFormat) -> CapturedFrame {
-        CapturedFrame {
-            width: self.width,
-            height: self.height,
-            pts_ns: now_ns(),
-            format,
-            payload: FramePayload::D3d11(D3d11Frame {
-                texture,
-                device: self.device.clone(),
-            }),
-        }
-    }
-}
-
-impl Capturer for WgcCapturer {
-    fn hdr_meta(&self) -> Option<punktfunk_core::quic::HdrMeta> {
-        self.hdr_meta
-    }
-
-    fn next_frame(&mut self) -> Result<CapturedFrame> {
-        let overall = Instant::now() + Duration::from_secs(20);
-        loop {
-            if let Some(frame) = self.wait_and_drain() {
-                self.first_frame = false;
-                return self.process_frame(frame);
-            }
-            // No new frame within the wait — repeat the last presented frame (static desktop).
-            if let Some((tex, fmt)) = &self.last_present {
-                return Ok(self.d3d11_frame(tex.clone(), *fmt));
-            }
-            if Instant::now() > overall {
-                bail!("no WGC frame within 20s (SudoVDA monitor not lit / no capture access?)");
-            }
-        }
-    }
-
-    fn try_latest(&mut self) -> Result<Option<CapturedFrame>> {
-        let target = self.signal.available.load(Ordering::Acquire);
-        if target <= self.consumed {
-            return Ok(None);
-        }
-        let mut last = None;
-        while self.consumed < target {
-            if let Ok(f) = self.pool.TryGetNextFrame() {
-                last = Some(f);
-            }
-            self.consumed += 1;
-        }
-        match last {
-            Some(frame) => self.process_frame(frame).map(Some),
-            None => Ok(None),
-        }
-    }
-    // set_active: the trait default (no-op) is correct — WGC keeps its session running across the
-    // active/idle gate (cheap; the frame pool just recycles), like the DDA duplication.
-}
-
-impl Drop for WgcCapturer {
-    fn drop(&mut self) {
-        let _ = self.session.Close();
-        let _ = self.pool.Close();
-        // _keepalive drops after, REMOVEing the SudoVDA monitor.
-    }
-}
-
-fn tex_desc(
-    width: u32,
-    height: u32,
-    format: windows::Win32::Graphics::Dxgi::Common::DXGI_FORMAT,
-    bind: u32,
-) -> D3D11_TEXTURE2D_DESC {
-    D3D11_TEXTURE2D_DESC {
-        Width: width,
-        Height: height,
-        MipLevels: 1,
-        ArraySize: 1,
-        Format: format,
-        SampleDesc: DXGI_SAMPLE_DESC {
-            Count: 1,
-            Quality: 0,
-        },
-        Usage: D3D11_USAGE_DEFAULT,
-        BindFlags: bind,
-        CPUAccessFlags: 0,
-        MiscFlags: 0,
-    }
-}
-
-fn now_ns() -> u64 {
-    std::time::SystemTime::now()
-        .duration_since(std::time::UNIX_EPOCH)
-        .map(|d| d.as_nanos() as u64)
-        .unwrap_or(0)
-}

crates/punktfunk-host/src/capture/windows/wgc_relay.rs

@@ -1,484 +0,0 @@
-//! Host-side WGC helper relay (Windows two-process secure-desktop design,
-//! design/archive/windows-secure-desktop.md — step 4).
-//!
-//! WGC won't activate under the SYSTEM account, so the SYSTEM host can't capture the normal desktop
-//! itself. Instead it spawns `punktfunk-host wgc-helper` in the **interactive user session** (so WGC works)
-//! via `CreateProcessAsUserW`, with the helper's **stdout** redirected to an anonymous pipe the host
-//! reads. The helper ships framed Annex-B access units; this module parses them back into AUs the
-//! host relays onto the live QUIC session (same `EncodedFrame` flow, just sourced over a pipe instead
-//! of a local encoder). A second pipe carries a tiny **control** channel to the helper (stdin: force
-//! keyframe), and the helper's **stderr** is forwarded line-by-line into host tracing so its logs are
-//! visible from the SYSTEM host's console.
-//!
-//! Wire framing (must match `wgc_helper::write_au`): per AU
-//! `[u32 magic "PFAU" LE][u32 len LE][u64 pts_ns LE][u8 keyframe][len bytes data]`.
-
-// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it (unsafe-proof program).
-#![deny(clippy::undocumented_unsafe_blocks)]
-
-use crate::capture::dxgi::WinCaptureTarget;
-use anyhow::{bail, Context, Result};
-use std::io::{BufRead, BufReader, Read};
-use std::sync::mpsc::{Receiver, SyncSender};
-use std::sync::Mutex;
-use windows::core::PWSTR;
-use windows::Win32::Foundation::SetHandleInformation;
-use windows::Win32::Foundation::{CloseHandle, HANDLE};
-use windows::Win32::Foundation::{HANDLE_FLAGS, HANDLE_FLAG_INHERIT};
-use windows::Win32::Security::{
-    DuplicateTokenEx, SecurityImpersonation, TokenPrimary, SECURITY_ATTRIBUTES, TOKEN_ALL_ACCESS,
-};
-use windows::Win32::System::Environment::{CreateEnvironmentBlock, DestroyEnvironmentBlock};
-use windows::Win32::System::Pipes::CreatePipe;
-use windows::Win32::System::RemoteDesktop::{WTSGetActiveConsoleSessionId, WTSQueryUserToken};
-use windows::Win32::System::Threading::{
-    CreateProcessAsUserW, TerminateProcess, CREATE_NO_WINDOW, CREATE_UNICODE_ENVIRONMENT,
-    PROCESS_INFORMATION, STARTF_USESTDHANDLES, STARTUPINFOW,
-};
-
-/// Must match [`crate::wgc_helper`]'s `AU_MAGIC` ("PFAU").
-const AU_MAGIC: u32 = 0x5046_4155;
-
-/// One access unit relayed from the helper, in the helper's (= the host's, same machine) monotonic
-/// clock — `pts_ns` is directly comparable to the host's `now_ns()`.
-pub struct RelayAu {
-    pub data: Vec<u8>,
-    pub pts_ns: u64,
-    pub keyframe: bool,
-}
-
-/// A running USER-session WGC helper whose AUs the SYSTEM host relays. Drop kills the child + closes
-/// the pipes; the reader threads then end on the broken pipe.
-pub struct HelperRelay {
-    proc: HANDLE,
-    thread: HANDLE,
-    /// Host write end of the helper's stdin — control commands (force keyframe). Mutex so the relay
-    /// can be shared while the encode thread requests keyframes.
-    stdin_w: Mutex<HANDLE>,
-    /// Parsed AUs from the helper's stdout reader thread.
-    rx: Receiver<RelayAu>,
-}
-
-// SAFETY: every field is itself `Send`: the `proc`/`thread` `HANDLE`s are process-global kernel
-// handle values (plain integers valid from any thread, owned for the relay's lifetime and closed once
-// on Drop), `stdin_w` is a `Mutex<HANDLE>`, and `rx` is an mpsc `Receiver<RelayAu>` (which is `Send`).
-// The relay is moved to one thread and owned there, so transferring it across threads is sound.
-unsafe impl Send for HelperRelay {}
-// NOTE: `HelperRelay` is deliberately NOT `Sync`. Its `rx: Receiver<RelayAu>` is `!Sync` (std mpsc
-// is single-consumer), and the relay is only ever a single-owner local in the punktfunk1 two-process
-// mux loop — never shared by `&` across threads — so `Sync` is neither sound nor needed. (A prior
-// `unsafe impl Sync` here asserted more than the fields support; removed.)
-
-/// Control byte on the helper's stdin: force the next encoded frame to be an IDR (client decode
-/// recovery). Mirrors `enc.request_keyframe()` in the single-process path.
-const CTL_KEYFRAME: u8 = 0x01;
-
-impl HelperRelay {
-    /// Spawn the helper in the interactive user session and start relaying its AUs. `target` is the
-    /// SudoVDA output the host already created (captured by GDI name only — the helper never touches
-    /// display topology). `(w, h, hz)` is the negotiated mode; `bitrate_kbps` the negotiated bitrate.
-    pub fn spawn(
-        target: &WinCaptureTarget,
-        mode: (u32, u32, u32),
-        bitrate_kbps: u32,
-        bit_depth: u8,
-    ) -> Result<HelperRelay> {
-        let exe = std::env::current_exe().context("current_exe for helper spawn")?;
-        let exe = exe.to_string_lossy().into_owned();
-        let (w, h, hz) = mode;
-        // CreateProcessAsUserW takes a single mutable command line (argv[0] = exe).
-        let cmdline = format!(
-            "\"{exe}\" wgc-helper --gdi \"{}\" --target-id {} --mode {w}x{h}x{hz} --bitrate {bitrate_kbps} --bit-depth {bit_depth}",
-            target.gdi_name, target.target_id
-        );
-        tracing::info!(cmd = %cmdline, "spawning WGC helper in user session");
-
-        // SAFETY: `spawn_inner` is an `unsafe fn` only because it drives raw Win32 token/pipe/process
-        // FFI; it imposes no caller-side memory precondition beyond valid arguments. `cmdline` is a live
-        // `&str` borrowed for the synchronous call and `(w, h, hz)` are plain `u32`s. It validates its
-        // own runtime requirements (active console session, SYSTEM token) and returns `Err` otherwise.
-        unsafe { spawn_inner(&cmdline, w, h, hz) }
-    }
-
-    /// Receive the next relayed AU. Distinguishes a `Timeout` (helper slow/stalled — keep waiting)
-    /// from `Disconnected` (helper exited → its stdout closed → reader thread ended → channel
-    /// dropped), which returns *immediately* and means the relay must stop, not spin.
-    pub fn recv_timeout(
-        &self,
-        dur: std::time::Duration,
-    ) -> Result<RelayAu, std::sync::mpsc::RecvTimeoutError> {
-        self.rx.recv_timeout(dur)
-    }
-
-    /// Non-blocking receive — used to drain stale buffered AUs (encoded while the secure desktop was
-    /// the live source) before resuming the relay. `Ok` while AUs remain, `Err` once empty.
-    pub fn try_recv(&self) -> Result<RelayAu, std::sync::mpsc::TryRecvError> {
-        self.rx.try_recv()
-    }
-
-    /// Ask the helper's encoder for an IDR on the next frame (client decode recovery). Best-effort:
-    /// a write failure means the helper is gone — the caller's recv loop will see the disconnect.
-    pub fn request_keyframe(&self) {
-        let h = self.stdin_w.lock().unwrap();
-        let mut written = 0u32;
-        // SAFETY: `*h` is the host's write end of the helper's stdin pipe — a live `HANDLE` owned by
-        // this `HelperRelay` (held under the `stdin_w` Mutex, locked here), closed only in Drop.
-        // `WriteFile` reads the 1-byte `&[CTL_KEYFRAME]` buffer and writes the byte count into
-        // `written`; both are live locals that outlive the synchronous call. A failure (helper gone) is
-        // discarded as documented.
-        unsafe {
-            let _ = windows::Win32::Storage::FileSystem::WriteFile(
-                *h,
-                Some(&[CTL_KEYFRAME]),
-                Some(&mut written),
-                None,
-            );
-        }
-    }
-}
-
-impl Drop for HelperRelay {
-    fn drop(&mut self) {
-        // SAFETY: `self.proc`/`self.thread` are the child process/thread `HANDLE`s from
-        // `CreateProcessAsUserW`, and `stdin_w` is the host's pipe write end — all owned by this
-        // `HelperRelay` and closed exactly once here in Drop (no double-close). `TerminateProcess` and
-        // the three `CloseHandle`s are FFI calls taking those handles by value, borrowing no Rust memory.
-        unsafe {
-            // Terminate the child first so its WGC capture + NVENC session tear down, then close our
-            // handles (the reader threads end on the resulting broken pipe).
-            let _ = TerminateProcess(self.proc, 1);
-            let _ = CloseHandle(*self.stdin_w.lock().unwrap());
-            let _ = CloseHandle(self.proc);
-            let _ = CloseHandle(self.thread);
-        }
-        tracing::info!("WGC helper relay torn down");
-    }
-}
-
-/// Inheritable anonymous pipe (read, write). The caller marks whichever end the host keeps as
-/// non-inheritable so the child only inherits its own end.
-unsafe fn make_pipe() -> Result<(HANDLE, HANDLE)> {
-    let mut read = HANDLE::default();
-    let mut write = HANDLE::default();
-    let sa = SECURITY_ATTRIBUTES {
-        nLength: std::mem::size_of::<SECURITY_ATTRIBUTES>() as u32,
-        lpSecurityDescriptor: std::ptr::null_mut(),
-        bInheritHandle: true.into(),
-    };
-    CreatePipe(&mut read, &mut write, Some(&sa), 0).context("CreatePipe")?;
-    Ok((read, write))
-}
-
-/// Mark a handle non-inheritable (the host keeps it; the child must not get a copy).
-unsafe fn no_inherit(h: HANDLE) {
-    let _ = SetHandleInformation(h, HANDLE_FLAG_INHERIT.0, HANDLE_FLAGS(0));
-}
-
-/// Build a child environment block: the target session's block (so DLL/PATH/SystemRoot resolve) with
-/// this process's `PUNKTFUNK_*` vars overlaid, so the child runs with the SAME settings this process
-/// has (`PUNKTFUNK_ENCODER=nvenc`, `PUNKTFUNK_ZEROCOPY`, …) instead of the target shell's. Returns a
-/// UTF-16, double-null-terminated block suitable for `CREATE_UNICODE_ENVIRONMENT`. Shared by the WGC
-/// helper spawn (here) and the Windows service launching the host into the active session.
-pub(crate) unsafe fn merged_env_block(user_block: *const u16) -> Vec<u16> {
-    // Parse the user block ("VAR=VALUE\0" … "\0") into entries.
-    let mut entries: Vec<String> = Vec::new();
-    if !user_block.is_null() {
-        let mut p = user_block;
-        loop {
-            let mut len = 0isize;
-            while *p.offset(len) != 0 {
-                len += 1;
-            }
-            if len == 0 {
-                break; // the trailing empty string = end of block
-            }
-            let slice = std::slice::from_raw_parts(p, len as usize);
-            entries.push(String::from_utf16_lossy(slice));
-            p = p.offset(len + 1);
-        }
-    }
-    // Overlay "our" settings — PUNKTFUNK_* and RUST_LOG — dropping whatever the target block had.
-    let is_ours = |k: &str| k.starts_with("PUNKTFUNK_") || k == "RUST_LOG";
-    entries.retain(|e| !is_ours(e.split('=').next().unwrap_or("")));
-    for (k, v) in std::env::vars().filter(|(k, _)| is_ours(k)) {
-        entries.push(format!("{k}={v}"));
-    }
-    // Serialize back to a UTF-16 double-null-terminated block.
-    let mut block: Vec<u16> = Vec::new();
-    for e in entries {
-        block.extend(e.encode_utf16());
-        block.push(0);
-    }
-    block.push(0);
-    block
-}
-
-unsafe fn spawn_inner(cmdline: &str, w: u32, h: u32, hz: u32) -> Result<HelperRelay> {
-    // The user token of the active console session (requires the host to be SYSTEM).
-    let session = WTSGetActiveConsoleSessionId();
-    if session == 0xFFFF_FFFF {
-        bail!("no active console session (WTSGetActiveConsoleSessionId)");
-    }
-    let mut user_token = HANDLE::default();
-    WTSQueryUserToken(session, &mut user_token)
-        .context("WTSQueryUserToken (host must run as SYSTEM)")?;
-
-    // A primary token for CreateProcessAsUserW.
-    let mut primary = HANDLE::default();
-    let dup = DuplicateTokenEx(
-        user_token,
-        TOKEN_ALL_ACCESS,
-        None,
-        SecurityImpersonation,
-        TokenPrimary,
-        &mut primary,
-    );
-    let _ = CloseHandle(user_token);
-    dup.context("DuplicateTokenEx(TokenPrimary)")?;
-
-    // The user's environment block (PATH, USERPROFILE, SystemRoot → DLL resolution), MERGED with the
-    // host's PUNKTFUNK_* vars. CreateProcessAsUserW would otherwise give the helper the *user's* env
-    // only, dropping PUNKTFUNK_ENCODER=nvenc / PUNKTFUNK_ZEROCOPY/… that the host runs with — so the
-    // helper would fall back to the software (H.264-only) encoder. We parse the user block, strip any
-    // PUNKTFUNK_* it has, append the host's, and pass the merged block.
-    let mut env_block: *mut core::ffi::c_void = std::ptr::null_mut();
-    let _ = CreateEnvironmentBlock(&mut env_block, Some(primary), false);
-    let merged_env = merged_env_block(env_block as *const u16);
-    if !env_block.is_null() {
-        let _ = DestroyEnvironmentBlock(env_block);
-    }
-
-    // Three pipes: stdout (helper→host AUs), stdin (host→helper control), stderr (helper→host logs).
-    let (out_r, out_w) = make_pipe().context("stdout pipe")?;
-    let (in_r, in_w) = make_pipe().context("stdin pipe")?;
-    let (err_r, err_w) = make_pipe().context("stderr pipe")?;
-    // The host keeps out_r / in_w / err_r — none inheritable; the child inherits out_w/in_r/err_w.
-    no_inherit(out_r);
-    no_inherit(in_w);
-    no_inherit(err_r);
-
-    let mut si = STARTUPINFOW {
-        cb: std::mem::size_of::<STARTUPINFOW>() as u32,
-        dwFlags: STARTF_USESTDHANDLES,
-        hStdInput: in_r,
-        hStdOutput: out_w,
-        hStdError: err_w,
-        ..Default::default()
-    };
-    // WGC needs the interactive desktop.
-    let mut desktop: Vec<u16> = "winsta0\\default\0".encode_utf16().collect();
-    si.lpDesktop = PWSTR(desktop.as_mut_ptr());
-
-    let mut cmd: Vec<u16> = cmdline.encode_utf16().chain(std::iter::once(0)).collect();
-    let mut pi = PROCESS_INFORMATION::default();
-
-    let created = CreateProcessAsUserW(
-        Some(primary),
-        None,
-        Some(PWSTR(cmd.as_mut_ptr())),
-        None,
-        None,
-        true, // inherit handles (the child's std ends)
-        CREATE_UNICODE_ENVIRONMENT | CREATE_NO_WINDOW,
-        Some(merged_env.as_ptr() as *const core::ffi::c_void),
-        None,
-        &si,
-        &mut pi,
-    );
-
-    // Clean up regardless of outcome: the child now owns its inherited ends; close our copies.
-    let _ = CloseHandle(out_w);
-    let _ = CloseHandle(in_r);
-    let _ = CloseHandle(err_w);
-    let _ = CloseHandle(primary);
-
-    if let Err(e) = created {
-        let _ = CloseHandle(out_r);
-        let _ = CloseHandle(in_w);
-        let _ = CloseHandle(err_r);
-        return Err(e).context("CreateProcessAsUserW(wgc-helper)");
-    }
-    tracing::info!(pid = pi.dwProcessId, mode = %format!("{w}x{h}@{hz}"), "WGC helper spawned");
-
-    // The helper does the WGC capture + NVENC encode, but it runs under the user's UAC-FILTERED token
-    // (no SE_INC_BASE_PRIORITY), so it can't raise its OWN GPU scheduling-priority class — under a
-    // GPU-saturating game NVENC then gets starved (the "240→40 fps in-game collapse"). The SYSTEM host
-    // holds the privilege, so stamp the HIGH GPU priority class onto the child here, right after spawn
-    // (the process-level class applies to the GPU contexts the helper creates afterwards).
-    crate::capture::dxgi::set_child_gpu_priority_class(pi.hProcess);
-
-    // stderr → host tracing, line by line.
-    let err_handle = HandleReader(err_r);
-    std::thread::Builder::new()
-        .name("wgc-helper-log".into())
-        .spawn(move || {
-            let r = BufReader::new(err_handle);
-            for line in r.lines() {
-                match line {
-                    Ok(l) if !l.trim().is_empty() => tracing::info!(target: "wgc_helper", "{l}"),
-                    Ok(_) => {}
-                    Err(_) => break,
-                }
-            }
-        })
-        .ok();
-
-    // stdout → parsed AUs. Bounded so a stalled relay applies backpressure (the pipe then fills and
-    // the helper blocks on write — the same backpressure the single-process channel gives).
-    let (tx, rx) = std::sync::mpsc::sync_channel::<RelayAu>(3);
-    let out_handle = HandleReader(out_r);
-    std::thread::Builder::new()
-        .name("wgc-helper-au".into())
-        .spawn(move || au_reader(out_handle, tx))
-        .ok();
-
-    Ok(HelperRelay {
-        proc: pi.hProcess,
-        thread: pi.hThread,
-        stdin_w: Mutex::new(in_w),
-        rx,
-    })
-}
-
-/// Parse the AU framing off the helper's stdout and forward each AU. Ends (returns) when the pipe
-/// breaks (helper exit) or the channel's receiver is dropped (relay torn down).
-fn au_reader(mut r: HandleReader, tx: SyncSender<RelayAu>) {
-    loop {
-        let mut hdr = [0u8; 4 + 4 + 8 + 1];
-        if r.read_exact(&mut hdr).is_err() {
-            break;
-        }
-        let magic = u32::from_le_bytes([hdr[0], hdr[1], hdr[2], hdr[3]]);
-        if magic != AU_MAGIC {
-            tracing::error!(
-                magic = format!("{magic:#x}"),
-                "WGC helper AU stream desync — aborting relay"
-            );
-            break;
-        }
-        let len = u32::from_le_bytes([hdr[4], hdr[5], hdr[6], hdr[7]]) as usize;
-        let pts_ns = u64::from_le_bytes([
-            hdr[8], hdr[9], hdr[10], hdr[11], hdr[12], hdr[13], hdr[14], hdr[15],
-        ]);
-        let keyframe = hdr[16] != 0;
-        // Bound the allocation — a corrupt length must not OOM the host. 64 MiB is far above any real
-        // AU (a 5K keyframe is a few MB).
-        if len > 64 * 1024 * 1024 {
-            tracing::error!(len, "WGC helper AU length implausible — aborting relay");
-            break;
-        }
-        let mut data = vec![0u8; len];
-        if r.read_exact(&mut data).is_err() {
-            break;
-        }
-        if tx
-            .send(RelayAu {
-                data,
-                pts_ns,
-                keyframe,
-            })
-            .is_err()
-        {
-            break; // relay dropped
-        }
-    }
-}
-
-/// Minimal `Read` over a Win32 pipe HANDLE (the windows crate doesn't impl `Read` on HANDLE).
-struct HandleReader(HANDLE);
-// SAFETY: `HandleReader` owns a single pipe `HANDLE` (a process-global kernel handle value, valid from
-// any thread). It is moved into the dedicated reader thread and used only there (and closed once on
-// Drop), never shared — so transferring ownership across threads is sound.
-unsafe impl Send for HandleReader {}
-impl Read for HandleReader {
-    fn read(&mut self, buf: &mut [u8]) -> std::io::Result<usize> {
-        let mut read = 0u32;
-        // SAFETY: `self.0` is the live read end of an anonymous pipe owned by this `HandleReader`
-        // (closed only in Drop). `ReadFile` fills the caller-provided `buf` (writing at most `buf.len()`
-        // bytes) and stores the count in `read`; both outlive the synchronous call. A broken pipe
-        // surfaces as `Err` and is mapped to EOF below.
-        let ok = unsafe {
-            windows::Win32::Storage::FileSystem::ReadFile(self.0, Some(buf), Some(&mut read), None)
-        };
-        match ok {
-            Ok(()) => Ok(read as usize),
-            // A broken pipe (helper exited) reads as ERROR_BROKEN_PIPE → report EOF (0).
-            Err(_) => Ok(0),
-        }
-    }
-}
-impl Drop for HandleReader {
-    fn drop(&mut self) {
-        // SAFETY: `self.0` is the pipe `HANDLE` this `HandleReader` owns; `CloseHandle` (an FFI call
-        // taking the handle by value) is invoked exactly once here in Drop, so there is no double-close.
-        unsafe {
-            let _ = CloseHandle(self.0);
-        }
-    }
-}
-
-/// Is this process running as the LOCAL SYSTEM account? Used to decide whether the two-process
-/// secure-desktop path applies (only SYSTEM can `WTSQueryUserToken` + capture the Winlogon desktop).
-pub fn running_as_system() -> bool {
-    use windows::Win32::Security::{GetTokenInformation, TokenUser, TOKEN_QUERY, TOKEN_USER};
-    use windows::Win32::System::Threading::{GetCurrentProcess, OpenProcessToken};
-    // SAFETY: `OpenProcessToken(GetCurrentProcess(), TOKEN_QUERY, &mut token)` opens the current-process
-    // token (the pseudo-handle is always valid) into `token`, which is closed once before each return.
-    // The first `GetTokenInformation` (null buffer) queries the required `len`; `buf` is then a
-    // `Vec<u8>` of exactly `len` bytes and the second call fills it, so `&*(buf.as_ptr() as *const
-    // TOKEN_USER)` reads a `TOKEN_USER` the kernel just wrote into a sufficiently-sized buffer (the
-    // variable-length SID it points at also lies within `buf`, which outlives the borrow).
-    // `is_local_system_sid` is this module's `unsafe fn`, given that in-buffer `PSID`. Safe on any thread.
-    unsafe {
-        let mut token = HANDLE::default();
-        if OpenProcessToken(GetCurrentProcess(), TOKEN_QUERY, &mut token).is_err() {
-            return false;
-        }
-        let mut len = 0u32;
-        let _ = GetTokenInformation(token, TokenUser, None, 0, &mut len);
-        if len == 0 {
-            let _ = CloseHandle(token);
-            return false;
-        }
-        let mut buf = vec![0u8; len as usize];
-        let ok = GetTokenInformation(
-            token,
-            TokenUser,
-            Some(buf.as_mut_ptr() as *mut _),
-            len,
-            &mut len,
-        )
-        .is_ok();
-        let _ = CloseHandle(token);
-        if !ok {
-            return false;
-        }
-        let tu = &*(buf.as_ptr() as *const TOKEN_USER);
-        // The well-known LocalSystem SID is S-1-5-18.
-        is_local_system_sid(tu.User.Sid)
-    }
-}
-
-/// True iff `sid` is S-1-5-18 (LocalSystem).
-unsafe fn is_local_system_sid(sid: windows::Win32::Security::PSID) -> bool {
-    use windows::Win32::Security::{
-        GetSidIdentifierAuthority, GetSidSubAuthority, GetSidSubAuthorityCount, IsValidSid,
-    };
-    if !IsValidSid(sid).as_bool() {
-        return false;
-    }
-    let auth = GetSidIdentifierAuthority(sid);
-    if auth.is_null() {
-        return false;
-    }
-    // NT Authority = {0,0,0,0,0,5}.
-    let a = (*auth).Value;
-    if a != [0, 0, 0, 0, 0, 5] {
-        return false;
-    }
-    let count = *GetSidSubAuthorityCount(sid);
-    if count != 1 {
-        return false;
-    }
-    *GetSidSubAuthority(sid, 0) == 18 // SECURITY_LOCAL_SYSTEM_RID
-}

crates/punktfunk-host/src/config.rs

@@ -6,8 +6,8 @@
 //!
 //! **Goal-1 stages 1–2** (`design/windows-host-rewrite.md` §2.2): stage 1 stood this up; stage 2 migrated the
 //! genuinely-constant operator/dispatch knobs onto it (the dispatch-disagreement bug class: `idd_push`,
-//! `capture_backend`, `encoder_pref`, `render_adapter`, `no_wgc`, the vdisplay backend select — plus the
+//! `encoder_pref`, `render_adapter`, the vdisplay backend select — plus the plan-named
-//! plan-named `secure_dda`/`idd_depth`/`zerocopy`/`ten_bit`/`four_four_four` and the multi-site `perf`/`compositor`/
+//! `idd_depth`/`zerocopy`/`ten_bit`/`four_four_four` and the multi-site `perf`/`compositor`/
 //! `video_source`/`gamepad`). `SessionPlan` (stage 3) consumes it as the single owner of the
 //! capture/topology/encoder decision.
 //!
@@ -36,27 +36,17 @@ use std::sync::OnceLock;
 /// derived `Debug` impl, so the parser can stay a single platform-neutral function.
 #[derive(Debug, Clone, Default)]
 pub struct HostConfig {
-    /// `PUNKTFUNK_IDD_PUSH` — capture from the pf-vdisplay driver's shared ring (in-process Session-0
+    /// `PUNKTFUNK_IDD_PUSH` — IDD direct-push monitor mode (the per-session monitor + ring recreate and
-    /// capture; no WGC helper). **Value-aware** (`0`/`false`/`no`/`off`/empty ⇒ off, else on); unset ⇒ off.
+    /// the discrete-render-GPU pin in [`crate::vdisplay::manager`]). IDD-push is the sole Windows capture
-    /// The installer's default `host.env` sets it on, so a fresh install runs the validated IDD-push path
+    /// path (DXGI Desktop Duplication and the WGC relay were removed), so this should stay on — the
-    /// (it falls back to DDA if the driver can't attach — see [`crate::capture`]). NOT a bare presence flag
+    /// installer's `host.env` sets it. **Value-aware** (`0`/`false`/`no`/`off`/empty ⇒ off, else on);
-    /// (so an operator can turn it OFF in `host.env` with `=0`, which a `var_os` presence check can't).
+    /// unset ⇒ off. NOT a bare presence flag (so an operator can turn it OFF with `=0`).
     pub idd_push: bool,
     /// `PUNKTFUNK_ENCODER` — explicit encoder-backend override (lowercased; empty = auto-detect by GPU vendor).
     pub encoder_pref: String,
-    /// `PUNKTFUNK_NO_HELPER` — never spawn the user-session WGC helper.
-    pub no_helper: bool,
-    /// `PUNKTFUNK_FORCE_HELPER` — force the WGC helper even when not running as SYSTEM.
-    pub force_helper: bool,
-    /// `PUNKTFUNK_NO_WGC` — force the pure single-process DDA path (skip WGC and the two-process relay).
-    pub no_wgc: bool,
-    /// `PUNKTFUNK_CAPTURE` — explicit Windows capture-backend override (lowercased; `dda`/`dxgi` vs the WGC default).
-    pub capture_backend: String,
     /// `PUNKTFUNK_RENDER_ADAPTER` — discrete render-GPU pin by description substring (`Some` even when empty:
     /// the empty string still counts as "set" for the presence checks, and the value reader filters it).
     pub render_adapter: Option<String>,
-    /// `PUNKTFUNK_SECURE_DDA` — enable the experimental DDA-on-secure-desktop (Winlogon/UAC) mux leg.
-    pub secure_dda: bool,
     /// `PUNKTFUNK_IDD_DEPTH` — IDD-push pipeline depth override (default 2; the call site clamps to its `OUT_RING`).
     pub idd_depth: usize,
     /// `PUNKTFUNK_ZEROCOPY` — opt into the Windows D3D11 zero-copy encode path (presence semantics; see module docs).
@@ -103,14 +93,7 @@ impl HostConfig {
             encoder_pref: std::env::var("PUNKTFUNK_ENCODER")
                 .unwrap_or_default()
                 .to_ascii_lowercase(),
-            no_helper: flag("PUNKTFUNK_NO_HELPER"),
-            force_helper: flag("PUNKTFUNK_FORCE_HELPER"),
-            no_wgc: flag("PUNKTFUNK_NO_WGC"),
-            capture_backend: std::env::var("PUNKTFUNK_CAPTURE")
-                .unwrap_or_default()
-                .to_ascii_lowercase(),
             render_adapter: val("PUNKTFUNK_RENDER_ADAPTER"),
-            secure_dda: flag("PUNKTFUNK_SECURE_DDA"),
             idd_depth: val("PUNKTFUNK_IDD_DEPTH")
                 .and_then(|s| s.parse::<usize>().ok())
                 .unwrap_or(2),

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

@@ -213,14 +213,26 @@ fn open_gs_virtual_source(
     let compositor = if let Some(c) = app.and_then(|a| a.compositor) {
         c
     } else {
-        let active = crate::vdisplay::detect_active_session();
+        // Windows has a single virtual-display backend (pf-vdisplay); `vdisplay::open` ignores the
-        crate::vdisplay::apply_session_env(&active);
+        // compositor arg there, so short-circuit the Linux session-detection state machine with a
-        let c = crate::vdisplay::compositor_for_kind(active.kind)
+        // placeholder — mirrors `punktfunk1::resolve_compositor`. Without this, the Linux `detect()`
-            .map(Ok)
+        // below bails on Windows ("could not detect compositor … XDG_CURRENT_DESKTOP=''"), which
-            .unwrap_or_else(crate::vdisplay::detect)
+        // killed the GameStream video thread → black screen (the native plane was already guarded).
-            .context("detect compositor")?;
+        #[cfg(target_os = "windows")]
-        crate::vdisplay::apply_input_env(c);
+        {
-        c
+            crate::vdisplay::Compositor::Kwin
+        }
+        #[cfg(not(target_os = "windows"))]
+        {
+            let active = crate::vdisplay::detect_active_session();
+            crate::vdisplay::apply_session_env(&active);
+            let c = crate::vdisplay::compositor_for_kind(active.kind)
+                .map(Ok)
+                .unwrap_or_else(crate::vdisplay::detect)
+                .context("detect compositor")?;
+            crate::vdisplay::apply_input_env(c);
+            c
+        }
     };
     let mut vd = crate::vdisplay::open(compositor).context("open virtual display")?;
     // Carry the resolved launch command on the backend instance (per-session) rather than a

crates/punktfunk-host/src/main.rs

@@ -56,9 +56,6 @@ mod spike;
 mod stats_recorder;
 mod vdisplay;
 #[cfg(target_os = "windows")]
-#[path = "windows/wgc_helper.rs"]
-mod wgc_helper;
-#[cfg(target_os = "windows")]
 #[path = "windows/win_adapter.rs"]
 mod win_adapter;
 #[cfg(target_os = "windows")]
@@ -392,35 +389,6 @@ fn real_main() -> Result<()> {
                 paired_store: None,
             })
         }
-        // USER-session WGC helper (Windows two-process secure-desktop design): capture the EXISTING
-        // SudoVDA via WGC + NVENC, stream AUs on stdout to the SYSTEM host. Spawned by the host
-        // (CreateProcessAsUser), not run by hand. See design/archive/windows-secure-desktop.md.
-        #[cfg(target_os = "windows")]
-        Some("wgc-helper") => {
-            let get = |flag: &str| {
-                args.iter()
-                    .skip_while(|a| *a != flag)
-                    .nth(1)
-                    .map(String::as_str)
-            };
-            let (width, height, fps) = get("--mode")
-                .and_then(|m| {
-                    let p: Vec<u32> = m.split('x').filter_map(|s| s.parse().ok()).collect();
-                    (p.len() == 3).then(|| (p[0], p[1], p[2]))
-                })
-                .unwrap_or((1920, 1080, 60));
-            wgc_helper::run(wgc_helper::HelperOptions {
-                target_id: get("--target-id").and_then(|s| s.parse().ok()).unwrap_or(0),
-                gdi_name: get("--gdi").unwrap_or("").to_string(),
-                width,
-                height,
-                fps,
-                bitrate_kbps: get("--bitrate")
-                    .and_then(|s| s.parse().ok())
-                    .unwrap_or(20000),
-                bit_depth: get("--bit-depth").and_then(|s| s.parse().ok()).unwrap_or(8),
-            })
-        }
         // Windows service control: install/uninstall/start/stop/status + the SCM `run` entry point.
         // Replaces the ad-hoc launch chain — `service install` registers an auto-start SYSTEM service
         // that launches the host into the active interactive session.

crates/punktfunk-host/src/punktfunk1.rs

@@ -755,14 +755,18 @@ async fn serve_session(
         // opens a tiny encoder; it runs only when both opt-ins are set and is cached after the first.
         let host_wants_444 = crate::config::config().four_four_four;
         let client_supports_444 = hello.video_caps & punktfunk_core::quic::VIDEO_CAP_444 != 0;
-        let single_process = crate::session_plan::resolve_topology()
+        // The active capturer must be able to deliver a full-chroma (RGB) source — the honest-downgrade
-            == crate::session_plan::SessionTopology::SingleProcess;
+        // gate. Linux's portal capturer can; the Windows IDD-push path delivers subsampled NV12/P010
+        // today (full-chroma IDD-push capture is a follow-up), so it returns false there and the host
+        // negotiates 4:2:0. (Replaces the old `single_process` gate — single-process is now the only
+        // topology, and 4:4:4 routed to DDA, which was removed.)
+        let capture_supports_444 = crate::capture::capturer_supports_444();
         // The GPU probe opens a real (tiny) encoder on first use, so run it off the reactor like the
         // compositor probe above (blocking probes → spawn_blocking). Short-circuit so it only runs when
         // the cheap gates already pass. The result is cached process-wide (a negative latches until
         // restart — acceptable: a GPU either supports HEVC 4:4:4 or it doesn't, and a transient open
         // failure here is rare since the session's own encoder isn't open yet).
-        let gpu_supports_444 = if host_wants_444 && client_supports_444 && single_process {
+        let gpu_supports_444 = if host_wants_444 && client_supports_444 && capture_supports_444 {
             tokio::task::spawn_blocking(|| {
                 crate::encode::can_encode_444(crate::encode::Codec::H265)
             })
@@ -780,7 +784,7 @@ async fn serve_session(
             chroma = ?chroma,
             host_wants_444,
             client_supports_444,
-            single_process,
+            capture_supports_444,
             "encode chroma"
         );
 
@@ -2696,7 +2700,7 @@ fn session_watcher_loop(tx: std::sync::mpsc::Sender<SessionSwitch>, stop: Arc<At
     }
 }
 
-/// All per-session inputs for [`virtual_stream`] / [`virtual_stream_relay`], bundled so the session entry
+/// All per-session inputs for [`virtual_stream`], bundled so the session entry
 /// is one moved value instead of a 13-positional-argument `#[allow(too_many_arguments)]` signature
 /// (Goal-1 stage 4, plan §2.4). Everything is **owned** — the receivers move in (`virtual_stream` is their
 /// only consumer) — so the whole context moves into the stream thread and the borrow plumbing disappears.
@@ -2744,8 +2748,9 @@ struct SessionContext {
 }
 
 fn virtual_stream(ctx: SessionContext) -> Result<()> {
-    // This thread runs the capture+encode loop (single-process: Linux / synthetic / NO_WGC DDA) — or
+    // This thread runs the capture+encode loop (single-process — the only topology: Linux portal /
-    // tail-calls the relay below. Elevate it so a CPU-heavy game can't deschedule our GPU submission.
+    // synthetic, Windows in-process IDD-push). Elevate it so a CPU-heavy game can't deschedule our GPU
+    // submission.
     boost_thread_priority(true);
     // Resolve the per-session capture / topology / encoder decision ONCE (Goal-1 stage 3): the deployed
     // path now reads this typed `SessionPlan` instead of re-deriving from config at each dispatch site
@@ -2753,14 +2758,6 @@ fn virtual_stream(ctx: SessionContext) -> Result<()> {
     // only per-session input — capture/topology/encoder are otherwise pure functions of `HostConfig`.
     let plan = crate::session_plan::SessionPlan::resolve(ctx.bit_depth, ctx.chroma);
     tracing::info!(?plan, "resolved session plan");
-    // Windows two-process secure-desktop path: when the host runs as SYSTEM (required for the secure
-    // desktop + SendInput), WGC can't activate in-process, so we capture the normal desktop via a
-    // helper spawned in the user session and relay its AUs. (Single-process WGC/DDA is used as the
-    // user, and stays the path on Linux.) See design/archive/windows-secure-desktop.md.
-    #[cfg(target_os = "windows")]
-    if plan.topology == crate::session_plan::SessionTopology::TwoProcessRelay {
-        return virtual_stream_relay(ctx);
-    }
     // Single-process path: unpack the context into the locals the loop below uses (names unchanged, so the
     // body is byte-for-byte the same; the receivers are now owned but `try_recv()` is identical).
     let SessionContext {
@@ -2795,6 +2792,11 @@ fn virtual_stream(ctx: SessionContext) -> Result<()> {
     // host-lifetime VirtualDisplayManager (§2.5). It does NO monitor work, so it must precede the IDD-push
     // preempt below (which reaches the manager) — otherwise `vdm()` is called before init and panics.
     let mut vd = crate::vdisplay::open(compositor)?;
+    // Per-client STABLE monitor identity (Phase 2): hand the backend the connecting client's cert
+    // fingerprint so a freshly CREATED virtual monitor gets this client's persistent id — Windows then
+    // reapplies the client's saved per-monitor config (DPI scaling) on reconnect. No-op on Linux backends
+    // and for anonymous/GameStream clients (no fingerprint → the driver auto-allocates).
+    vd.set_client_identity(endpoint::peer_fingerprint(&conn));
     // IDD-push reconnect preempt (the dance now lives in the manager, Goal-1 §2.5): serialize setup so a
     // reconnect FLOOD can't run concurrent monitor create/teardown, STOP the prior session + WAIT for it
     // to release its monitor (instead of tearing a monitor out from under a still-live session), and
@@ -2810,20 +2812,7 @@ fn virtual_stream(ctx: SessionContext) -> Result<()> {
     #[cfg(target_os = "windows")]
     drop(_idd_setup_guard);
 
-    // Windows single-process DDA path (PUNKTFUNK_NO_WGC=1): the SudoVDA virtual display, isolated as the
+    // Windows: capture is live — launch the requested library title into the
-    // SOLE active output, goes into fullscreen independent-flip (one plane on one display) which Desktop
-    // Duplication cannot capture → the born-lost ACCESS_LOST storm we measured on the RTX4090+iGPU box
-    // (hook verified-firing, DPI=2, yet 100% DuplicateOutput1 E_ACCESSDENIED + born-lost). A tiny topmost
-    // layered overlay disqualifies independent-flip and forces DWM composition, which DDA CAN capture.
-    // (Apollo never hits this because it runs WITH a physical monitor attached — multi-display is already
-    // DWM-composited; we isolate to sole-display, so we must force composition ourselves.) Unlike the WGC
-    // relay path — where WGC owns the normal desktop and the overlay is secure-only — here DDA owns the
-    // normal desktop too, so it must run unconditionally. Held for the session; Drop tears it down.
-    // Best-effort; disable with PUNKTFUNK_FORCE_COMPOSED=0.
-    #[cfg(target_os = "windows")]
-    let _composed_flip = crate::capture::composed_flip::ForceComposedFlip::start();
-
-    // Windows: capture is live (and composition forced) — launch the requested library title into the
     // interactive user session so it renders onto the captured desktop and grabs foreground. Linux
     // nests its launch in gamescope instead (the handshake `PUNKTFUNK_GAMESCOPE_APP` path). Best-effort:
     // a launch failure (no recipe for the kind, no interactive user) leaves the user on the desktop.
@@ -3295,480 +3284,6 @@ fn virtual_stream(ctx: SessionContext) -> Result<()> {
     Ok(())
 }
 
-/// Windows two-process video stream: the SYSTEM host creates the SudoVDA virtual output (and holds
-/// its keepalive = the sole topology/isolation owner), spawns the WGC helper in the user session to
-/// capture+encode the NORMAL desktop, and relays the helper's AUs onto the QUIC data plane via the
-/// same send thread as the single-process path. A [`DesktopWatcher`](crate::capture::desktop_watch)
-/// muxes the source: while the input desktop is Winlogon (UAC / lock / login — which WGC can't
-/// capture), the host captures it with its OWN DDA encoder; back on Default it resumes the relay.
-/// Every source switch latches a "wait for IDR" so the client's decoder resumes on a keyframe (the
-/// two encoders keep independent infinite-GOP state). Reconfigure rebuilds the output + re-spawns the
-/// helper at the new mode (and drops the stale-target DDA); keyframe requests forward to the active
-/// source.
-#[cfg(target_os = "windows")]
-fn virtual_stream_relay(ctx: SessionContext) -> Result<()> {
-    use crate::capture::dxgi::WinCaptureTarget;
-    use crate::capture::wgc_relay::HelperRelay;
-    use crate::capture::Capturer; // trait methods (set_active/next_frame) on the concrete DuplCapturer
-
-    // Unpack the context (names unchanged so the body is identical). The relay doesn't yet send the
-    // source's 0xCE HDR metadata — the helper's in-band SEI carries it (a Windows follow-up) — so `conn`
-    // is held unused.
-    let SessionContext {
-        session,
-        mode,
-        seconds,
-        stop,
-        reconfig,
-        keyframe,
-        compositor,
-        bitrate_kbps,
-        bit_depth,
-        // The two-process WGC relay encodes 4:2:0 in v1 — the handshake's `single_process` gate already
-        // forced `chroma` to Yuv420 for this topology, so the helper + secure-desktop DDA stay 4:2:0.
-        chroma: _,
-        probe_rx,
-        probe_result_tx,
-        fec_target,
-        conn: _conn,
-        stats,
-        client_label,
-        launch,
-    } = ctx;
-    tracing::info!(
-        ?mode,
-        bitrate_kbps,
-        bit_depth,
-        "punktfunk/1 two-process stream (SYSTEM host + user-session WGC helper)"
-    );
-
-    let mut vd = crate::vdisplay::open(compositor)?;
-
-    // Create the SudoVDA output + spawn a helper capturing it by GDI name. Returns the keepalive
-    // (held for the output's life — the sole isolation owner), the running relay, the capture target
-    // (so the host can also open DDA on it for the secure desktop), and the achieved refresh.
-    type Built = (Box<dyn Send>, HelperRelay, WinCaptureTarget, u32);
-    let build = |vd: &mut Box<dyn crate::vdisplay::VirtualDisplay>,
-                 mode: punktfunk_core::Mode|
-     -> Result<Built> {
-        let vout = vd.create(mode).context("create virtual output")?;
-        let effective_hz = vout
-            .preferred_mode
-            .map(|(_, _, hz)| hz)
-            .filter(|&hz| hz > 0)
-            .unwrap_or(mode.refresh_hz);
-        let target = vout.win_capture.clone().ok_or_else(|| {
-            anyhow!("SudoVDA target not yet an active display (needs a WDDM GPU to activate it)")
-        })?;
-        // HDR is driven by the SudoVDA monitor's ACTUAL advanced-color state, not the handshake bit
-        // depth: the whole pipeline follows the monitor (WGC captures FP16 when HDR is on; NVENC forces
-        // Main10 + BT.2020 PQ from the 10-bit capture format regardless of the negotiated depth; the
-        // client auto-detects PQ from the HEVC VUI). So:
-        //   - a negotiated 10-bit session PROACTIVELY enables HDR on the monitor (below), but
-        //   - we must NEVER force HDR *off* here — that would wipe out a user's deliberate Windows HDR
-        //     toggle on the virtual display on every build (the "HDR doesn't persist" bug). Leaving the
-        //     monitor's state alone lets a user-enabled HDR session flow through end-to-end.
-        // The secure-desktop HDR drop (for the DDA leg) keys off the monitor's real state in the mux loop.
-        #[cfg(target_os = "windows")]
-        if bit_depth >= 10 {
-            // SAFETY: `set_advanced_color` is marked `unsafe` only because it drives the Win32 CCD API
-            // internally; it takes `target_id` by value (Copy `u32` — this session's live SudoVDA
-            // monitor's CCD target id) and sizes + owns every buffer it hands the OS on its own stack.
-            // We pass no pointers, so nothing must outlive the call and there is no aliasing; an
-            // unknown/absent target id simply returns false.
-            unsafe {
-                if crate::win_display::set_advanced_color(target.target_id, true) {
-                    // Let the colorspace change settle before WGC creates its capture item / detects HDR.
-                    std::thread::sleep(std::time::Duration::from_millis(250));
-                }
-            }
-        }
-        let relay = HelperRelay::spawn(
-            &target,
-            (mode.width, mode.height, effective_hz),
-            bitrate_kbps,
-            bit_depth,
-        )
-        .context("spawn WGC helper")?;
-        Ok((vout.keepalive, relay, target, effective_hz))
-    };
-
-    let (mut _keepalive, mut relay, mut target, mut effective_hz) = build(&mut vd, mode)?;
-    let mut cur_mode = mode;
-
-    // Capture is live (the WGC helper is relaying) — launch the requested library title into the
-    // interactive user session so it renders onto the captured desktop and grabs foreground.
-    // Best-effort: a failure (no recipe for the kind, no interactive user) leaves the user on the desktop.
-    if let Some(id) = launch.as_deref() {
-        if let Err(e) = crate::library::launch_title(id) {
-            tracing::warn!(launch_id = id, error = %e, "could not launch requested library title");
-        }
-    }
-
-    // O3.1: optionally observe the IDD-push ring alongside WGC (WGC = the presentation trigger) to
-    // confirm the 0257 driver pushes frames into a HOST-created ring. Diagnostic only; gated.
-    if std::env::var_os("PUNKTFUNK_IDD_PUSH_OBSERVE").is_some() {
-        crate::capture::idd_push::spawn_observer(
-            target.clone(),
-            Some((cur_mode.width, cur_mode.height, effective_hz)),
-        );
-    }
-
-    // The host's own DDA capturer+encoder for the SECURE (Winlogon) desktop, which WGC — and thus the
-    // helper — cannot capture. Opened lazily on the first secure transition (so a session that never
-    // hits a UAC/lock screen never pays for a second NVENC session), then kept for fast re-switch.
-    struct DdaPipe {
-        cap: Box<dyn crate::capture::Capturer>,
-        enc: Box<dyn crate::encode::Encoder>,
-        frame: crate::capture::CapturedFrame,
-    }
-    // Note: takes the dimensions as args rather than capturing `cur_mode` — `cur_mode` is reassigned
-    // on reconfig, and a closure holding a shared borrow of it for the whole fn would forbid that.
-    let open_dda =
-        |target: &WinCaptureTarget, w: u32, h: u32, hz: u32, hdr: bool| -> Result<DdaPipe> {
-            // The host already holds the real keepalive (sole isolation owner), so DDA gets a no-op one.
-            // `hdr` requests an FP16 DuplicateOutput1 so the secure desktop is captured in HDR (→ BT.2020
-            // PQ Main10) instead of black — legacy DuplicateOutput can't capture an HDR/FP16 desktop.
-            let mut cap = crate::capture::dxgi::DuplCapturer::open(
-                target.clone(),
-                Some((w, h, hz)),
-                Box::new(()),
-                // The relay's host encoder is GPU (NVENC/AMF/QSV unless software) — pass `gpu` in (Goal-1
-                // stage 5) so the DDA capturer doesn't re-derive it.
-                crate::capture::gpu_encode(),
-                hdr,
-                false, // the two-process relay path is 4:2:0 in v1
-            )
-            .context("open DDA for secure desktop")?;
-            cap.set_active(true);
-            let frame = cap.next_frame().context("DDA first frame")?;
-            let enc = crate::encode::open_video(
-                crate::encode::Codec::H265,
-                frame.format,
-                frame.width,
-                frame.height,
-                hz,
-                bitrate_kbps as u64 * 1000,
-                frame.is_cuda(),
-                bit_depth,
-                // Secure-desktop DDA on the two-process relay path: 4:2:0 in v1 (matches the helper).
-                crate::encode::ChromaFormat::Yuv420,
-            )
-            .context("open video encoder for DDA")?;
-            Ok(DdaPipe {
-                cap: Box::new(cap),
-                enc,
-                frame,
-            })
-        };
-
-    let perf = crate::config::config().perf;
-    let burst_cap = std::env::var("PUNKTFUNK_PACE_BURST_KB")
-        .ok()
-        .and_then(|s| s.parse::<usize>().ok())
-        .unwrap_or(128)
-        * 1024;
-
-    // Same encode|send split as the single-process path: this thread relays AUs, a dedicated send
-    // thread owns the Session and does FEC+seal+paced-send. The relay encodes in the helper process,
-    // so this path's FrameMsgs carry no cap/submit/encode split (those stages stay 0 in the sample);
-    // the send thread still emits fps/goodput/pacing/loss from `session.stats()`.
-    let send_stats = SendStats {
-        rec: stats,
-        width: mode.width,
-        height: mode.height,
-        fps: effective_hz,
-        codec: "hevc",
-        client: client_label,
-        bitrate_kbps,
-    };
-    let (frame_tx, frame_rx) = std::sync::mpsc::sync_channel::<FrameMsg>(3);
-    let send_thread = std::thread::Builder::new()
-        .name("punktfunk-send".into())
-        .spawn({
-            let stop = stop.clone();
-            move || {
-                send_loop(
-                    session,
-                    frame_rx,
-                    probe_rx,
-                    probe_result_tx,
-                    stop,
-                    perf,
-                    burst_cap,
-                    fec_target,
-                    send_stats,
-                )
-            }
-        })
-        .context("spawn send thread")?;
-
-    // Test hook: PUNKTFUNK_SECURE_TEST_PERIOD_MS=N drives a square-wave secure/normal toggle every N ms
-    // instead of the real watcher — exercises the mid-session helper↔DDA mux without a live UAC/lock.
-    let secure_test_ms: Option<u128> = std::env::var("PUNKTFUNK_SECURE_TEST_PERIOD_MS")
-        .ok()
-        .and_then(|s| s.parse().ok())
-        .filter(|&n| n > 0);
-    // Switching to the host DDA on the secure (Winlogon) desktop is OPT-IN: DDA can't reliably capture
-    // the secure desktop's HDR independent-flip (it storms ACCESS_LOST → black), whereas the WGC helper
-    // STAYS LIVE through a lock/UAC. So by default the mux keeps WGC the whole time (no DesktopWatcher
-    // switch, no overlay). Enable the experimental DDA-on-secure path with PUNKTFUNK_SECURE_DDA=1.
-    let dda_secure = crate::config::config().secure_dda || secure_test_ms.is_some();
-    // The authoritative Default↔Winlogon signal (requires SYSTEM to read the Winlogon desktop name);
-    // only needed when the DDA-on-secure path is enabled.
-    let watcher = dda_secure.then(crate::capture::desktop_watch::DesktopWatcher::start);
-    // Force-composed-flip overlay (only with DDA-on-secure): keeps the secure desktop out of fullscreen
-    // independent-flip so DDA can duplicate it. Off by default to avoid touching the normal desktop.
-    let _composed_flip = dda_secure
-        .then(crate::capture::composed_flip::ForceComposedFlip::start)
-        .flatten();
-    let start = std::time::Instant::now();
-
-    let mut interval = std::time::Duration::from_secs_f64(1.0 / effective_hz.max(1) as f64);
-    let deadline = std::time::Instant::now() + std::time::Duration::from_secs(seconds as u64);
-    let mut sent: u64 = 0;
-    // Mux state: which source is live, the lazily-opened DDA pipe, a DDA pacing clock, and a
-    // "wait for the next IDR before forwarding" latch set on every source switch (the client's
-    // decoder must resume on a keyframe — the two encoders keep independent infinite-GOP state).
-    let mut dda: Option<DdaPipe> = None;
-    let mut on_secure = false;
-    let mut next = std::time::Instant::now();
-    let mut await_idr = false;
-    // Step 6 relaunch watchdog: how many times in a row the helper has died without producing a frame.
-    // A console disconnect/reconnect or a helper crash kills it; we respawn (the new helper picks up
-    // the now-active session via WTSGetActiveConsoleSessionId). Reset on the first relayed frame; only
-    // give up (end the stream) after a run of failures spanning a few seconds.
-    let mut helper_fails = 0u32;
-    const MAX_HELPER_FAILS: u32 = 20;
-
-    // Build a FrameMsg + hand it to the send thread; returns false if the send thread is gone (caller
-    // breaks the loop). Kept as a macro (not a closure) so each use borrows `frame_tx`/`sent`/`interval`
-    // at its own site without a long-lived capture, and `break 'outer` stays a literal at the call site
-    // (a `break 'outer` inside the macro body risks label-hygiene resolution failures).
-    macro_rules! forward {
-        ($data:expr, $capture_ns:expr, $keyframe:expr) => {{
-            let flags = if $keyframe {
-                (FLAG_PIC | FLAG_SOF) as u32
-            } else {
-                FLAG_PIC as u32
-            };
-            let capture_ns = $capture_ns;
-            let encode_us = (now_ns().saturating_sub(capture_ns) / 1000) as u32;
-            let msg = FrameMsg {
-                data: $data,
-                capture_ns,
-                flags,
-                deadline: std::time::Instant::now() + interval,
-                encode_us,
-                cap_us: 0,
-                submit_us: 0,
-                wait_us: 0,
-                repeat: false,
-                was_measured: false,
-            };
-            let ok = frame_tx.send(msg).is_ok();
-            if ok {
-                sent += 1;
-            }
-            ok
-        }};
-    }
-
-    'outer: while !stop.load(Ordering::SeqCst) && std::time::Instant::now() < deadline {
-        // Mode switch: rebuild the output + re-spawn the helper at the new mode (drop the old relay +
-        // keepalive only after the new pair is up, so a failed rebuild keeps the current stream). The
-        // DDA pipe (on the old target) is dropped — it reopens on the next secure transition.
-        let mut want = None;
-        while let Ok(m) = reconfig.try_recv() {
-            want = Some(m);
-        }
-        if let Some(new_mode) = want {
-            tracing::info!(?new_mode, "two-process: rebuilding for mode switch");
-            match build(&mut vd, new_mode) {
-                Ok((ka, rl, tg, hz)) => {
-                    relay = rl; // drops the old relay (kills old helper) ...
-                    _keepalive = ka; // ... then releases the old output
-                    target = tg;
-                    effective_hz = hz;
-                    cur_mode = new_mode;
-                    dda = None; // old-target DDA is stale; reopen on next secure
-                    interval = std::time::Duration::from_secs_f64(1.0 / hz.max(1) as f64);
-                }
-                Err(e) => {
-                    tracing::error!(error = %format!("{e:#}"), ?new_mode,
-                        "two-process mode-switch rebuild failed — staying on the current mode");
-                }
-            }
-        }
-        // Coalesce client decode-recovery keyframe requests and forward to the active source.
-        let mut want_kf = false;
-        while keyframe.try_recv().is_ok() {
-            want_kf = true;
-        }
-
-        // Source mux: capture the secure (Winlogon) desktop via the host's DDA, the normal desktop via
-        // the helper relay. On a switch, latch await_idr + force the now-active source to emit an IDR
-        // so the client resumes cleanly.
-        let secure = dda_secure
-            && match secure_test_ms {
-                Some(p) => (start.elapsed().as_millis() / p) % 2 == 1,
-                None => watcher.as_ref().is_some_and(|w| w.is_secure()),
-            };
-        if secure != on_secure {
-            on_secure = secure;
-            await_idr = true;
-            tracing::info!(
-                to = if secure {
-                    "secure(DDA)"
-                } else {
-                    "normal(WGC relay)"
-                },
-                "two-process: source switch"
-            );
-            if secure {
-                // Capture the secure (Winlogon) desktop in its NATIVE colorspace. Don't try to drop the
-                // SudoVDA out of HDR for the DDA leg — display-config changes are denied on the secure
-                // desktop (the drop just churned + still went black). Instead, if the monitor is in HDR,
-                // open DDA in HDR (FP16 DuplicateOutput1 → BT.2020 PQ Main10); the normal-desktop DDA
-                // overlay/flip issues that drove us to WGC don't apply to the composed Winlogon UI.
-                // SAFETY: `advanced_color_enabled` is `unsafe` only because it queries the Win32 CCD
-                // API; it takes `target_id` by value (the live SudoVDA monitor's CCD target id) and
-                // allocates + owns every buffer it passes the OS internally. No caller pointer is
-                // involved, so nothing must outlive the call and there is no aliasing; a missing
-                // target id just yields false.
-                let hdr = unsafe { crate::win_display::advanced_color_enabled(target.target_id) };
-                dda = None; // reopen to capture the secure desktop
-                match open_dda(&target, cur_mode.width, cur_mode.height, effective_hz, hdr) {
-                    Ok(mut p) => {
-                        tracing::info!(hdr, "two-process: opened DDA for the secure desktop");
-                        p.enc.request_keyframe();
-                        dda = Some(p);
-                    }
-                    Err(e) => {
-                        tracing::error!(error = %format!("{e:#}"),
-                            "two-process: DDA open failed — secure desktop will freeze on last frame");
-                    }
-                }
-                next = std::time::Instant::now();
-            } else {
-                // Returning to the normal desktop: RESUME from the still-alive WGC helper. Do NOT
-                // recreate the SudoVDA monitor or respawn the helper — build()'s vd.create() is an
-                // IOCTL_REMOVE+ADD of the monitor (the audible disconnect/connect chime + the
-                // teardown/recreate kernel stress that broke DDA, now applied to the mux). The monitor +
-                // helper persist for the WHOLE session; only the host-DDA leg opens (secure) and closes
-                // (normal). Apply the DDA learning here: reuse, don't tear down.
-                dda = None; // free the secure DDA encoder; the relay (helper) is the source again
-                while relay.try_recv().is_ok() {} // drop secure-dwell backlog
-                relay.request_keyframe(); // client decoder resumes on the helper's next IDR
-                                          // Nothing to restore: we no longer toggle the SudoVDA's HDR state for the DDA leg, so the
-                                          // monitor's colorspace is unchanged and the still-alive WGC helper just resumes.
-                next = std::time::Instant::now();
-            }
-        }
-        if want_kf {
-            if secure {
-                if let Some(d) = dda.as_mut() {
-                    d.enc.request_keyframe();
-                }
-            } else {
-                relay.request_keyframe();
-            }
-            await_idr = true;
-        }
-
-        if secure {
-            // DDA capture+encode for the secure desktop, paced to the frame interval.
-            let Some(d) = dda.as_mut() else {
-                std::thread::sleep(interval);
-                continue;
-            };
-            if let Some(f) = d.cap.try_latest().context("DDA capture")? {
-                d.frame = f;
-            }
-            let capture_ns = now_ns();
-            d.enc.submit(&d.frame).context("DDA encoder submit")?;
-            next += interval;
-            while let Some(au) = d.enc.poll().context("DDA encoder poll")? {
-                if await_idr && !au.keyframe {
-                    continue;
-                }
-                await_idr = false;
-                if !forward!(au.data, capture_ns, au.keyframe) {
-                    break 'outer; // send thread gone
-                }
-            }
-            match next.checked_duration_since(std::time::Instant::now()) {
-                Some(dur) => std::thread::sleep(dur),
-                None => next = std::time::Instant::now(),
-            }
-        } else {
-            // Relay the helper's AUs for the normal desktop. Timeout → keep servicing the loop;
-            // Disconnected → the helper exited (step 6 adds the relaunch watchdog).
-            let au = match relay.recv_timeout(std::time::Duration::from_millis(500)) {
-                Ok(au) => au,
-                Err(std::sync::mpsc::RecvTimeoutError::Timeout) => {
-                    if stop.load(Ordering::SeqCst) {
-                        break;
-                    }
-                    tracing::warn!("two-process: no AU from helper within 500ms");
-                    continue;
-                }
-                Err(std::sync::mpsc::RecvTimeoutError::Disconnected) => {
-                    // The helper exited (crash, or a console disconnect killed its session). REBUILD
-                    // the whole output + helper (not just respawn on the old target): an abruptly-killed
-                    // helper leaves the SudoVDA's DXGI output briefly unresolvable ("no DXGI output for
-                    // target N yet"), and a console reconnect needs a fresh output in the new session —
-                    // `build` recreates both. Back off so a hard-failing rebuild (e.g. no active session
-                    // yet) doesn't spin; give up only after a sustained run of failures.
-                    helper_fails += 1;
-                    if helper_fails > MAX_HELPER_FAILS {
-                        tracing::error!(
-                            fails = helper_fails,
-                            "two-process: WGC helper keeps dying — ending stream"
-                        );
-                        break;
-                    }
-                    std::thread::sleep(std::time::Duration::from_millis(500));
-                    match build(&mut vd, cur_mode) {
-                        Ok((ka, rl, tg, hz)) => {
-                            tracing::warn!(
-                                fails = helper_fails,
-                                "two-process: WGC helper exited — rebuilt output + helper"
-                            );
-                            relay = rl;
-                            _keepalive = ka;
-                            target = tg;
-                            effective_hz = hz;
-                            dda = None; // old-target DDA is stale
-                            interval = std::time::Duration::from_secs_f64(1.0 / hz.max(1) as f64);
-                            await_idr = true; // resume on the new helper's opening IDR
-                        }
-                        Err(e) => {
-                            tracing::warn!(error = %format!("{e:#}"), fails = helper_fails,
-                                "two-process: helper rebuild failed — will retry");
-                        }
-                    }
-                    continue;
-                }
-            };
-            if await_idr && !au.keyframe {
-                continue; // skip stale deltas until the post-switch IDR
-            }
-            await_idr = false;
-            helper_fails = 0; // a frame flowed → the helper is healthy again
-                              // The helper's pts_ns is on this machine's monotonic clock (same `now_ns()` source).
-            if !forward!(au.data, au.pts_ns, au.keyframe) {
-                break 'outer; // send thread gone
-            }
-        }
-    }
-    drop(frame_tx);
-    let _ = send_thread.join();
-    drop(watcher);
-    tracing::info!(sent, "punktfunk/1 two-process stream complete");
-    Ok(())
-}
-
 /// One mode's capture/encode pipeline: (capturer, encoder, first frame, frame interval).
 /// Dropping the capturer tears down the PipeWire stream and the virtual output with it.
 type Pipeline = (
@@ -3800,6 +3315,23 @@ fn build_pipeline_with_retry(
     // 30-60s to produce its first frame, and a first-connect timeout would tear down the warm
     // session (forcing another cold start on reconnect). A genuinely permanent failure still fails
     // fast via `is_permanent_build_error`; only transient "no frame yet" retries consume the budget.
+    // IDD-push only: HOLD one monitor lease across all build attempts. A failed attempt's capturer
+    // drop releases ITS lease, but this held lease keeps the shared monitor Active (refs >= 1), so the
+    // next attempt's `vd.create` JOINS it (refcount++) instead of finding it Lingering and tripping the
+    // IDD-push reconnect PREEMPT (teardown + recreate). That preempt-per-retry was the REMOVE→ADD churn
+    // that exhausts the IddCx monitor-slot pool and wedges ADD at 0x80070490 — one ADD per cold start
+    // now, not one per attempt. Non-IDD-push backends (Linux portal, WGC) don't use the refcount manager
+    // and aren't churn-wedge-prone, so they keep create-per-attempt (a held lease there would allocate a
+    // second virtual output). Dropped when this fn returns — on success the Pipeline's own lease keeps
+    // the monitor Active; on failure refs falls to 0 → Lingering → linger-timeout teardown.
+    let _retry_hold = if matches!(plan.capture, crate::session_plan::CaptureBackend::IddPush) {
+        Some(
+            vd.create(mode)
+                .context("acquire virtual output for the session (retry-hold lease)")?,
+        )
+    } else {
+        None
+    };
     const MAX_ATTEMPTS: u32 = 8;
     let mut backoff = std::time::Duration::from_millis(500);
     for attempt in 1..=MAX_ATTEMPTS {

crates/punktfunk-host/src/session_plan.rs

@@ -26,12 +26,9 @@ pub enum CaptureBackend {
     /// Linux: the xdg ScreenCast portal → PipeWire (the only Linux capture path).
     Portal,
     /// Windows: IDD direct-push — frames pulled straight from the pf-vdisplay driver's shared ring
-    /// (in-process, Session 0; no Desktop Duplication, no WGC helper).
+    /// (in-process, Session 0; captures the secure desktop too). The sole Windows capture path —
+    /// DXGI Desktop Duplication (DDA) and the WGC two-process relay were removed.
     IddPush,
-    /// Windows: DXGI Desktop Duplication (`PUNKTFUNK_CAPTURE=dda|dxgi` or `PUNKTFUNK_NO_WGC`).
-    Dda,
-    /// Windows: Windows.Graphics.Capture (the composed-desktop default), with a DDA watchdog fallback.
-    Wgc,
 }
 
 impl CaptureBackend {
@@ -42,20 +39,10 @@ impl CaptureBackend {
         CaptureBackend::Portal
     }
 
-    /// Windows precedence (identical to the pre-stage-3 `capture_virtual_output` branch order):
+    /// Windows: IDD direct-push is the sole capture path (DDA + the WGC two-process relay were removed).
-    /// IDD-push wins; else an explicit `dda`/`dxgi` request or `PUNKTFUNK_NO_WGC` selects DDA; else WGC.
     #[cfg(target_os = "windows")]
     pub fn resolve() -> Self {
-        let cfg = crate::config::config();
+        CaptureBackend::IddPush
-        if cfg.idd_push {
-            CaptureBackend::IddPush
-        } else if matches!(cfg.capture_backend.as_str(), "dda" | "dxgi")
-            || crate::capture::wgc_disabled()
-        {
-            CaptureBackend::Dda
-        } else {
-            CaptureBackend::Wgc
-        }
     }
 
     #[cfg(not(any(target_os = "linux", target_os = "windows")))]
@@ -67,11 +54,9 @@ impl CaptureBackend {
 /// How a session is structured across processes.
 #[derive(Clone, Copy, Debug, PartialEq, Eq)]
 pub enum SessionTopology {
-    /// One process captures + encodes (Linux; Windows non-SYSTEM / IDD-push / `NO_WGC`).
+    /// One process captures + encodes. The only topology: Linux (portal) and Windows (in-process
+    /// IDD-push in Session 0). The SYSTEM-host + user-session WGC relay was removed with DDA/WGC.
     SingleProcess,
-    /// SYSTEM host + a user-session WGC helper relay (the Windows normal-desktop path under SYSTEM,
-    /// where in-process WGC can't activate). See `virtual_stream_relay`.
-    TwoProcessRelay,
 }
 
 /// The resolved encode backend (recorded for logging / stages 4–5; the per-session encoder open still
@@ -103,8 +88,8 @@ pub struct SessionPlan {
     pub encoder: EncoderBackend,
     /// Handshake-negotiated encode bit depth (8, or 10 = HEVC Main10).
     pub bit_depth: u8,
-    /// The IDD-push HDR hint (`bit_depth >= 10`) — the want-HDR flag the capturer was passed before.
+    /// The IDD-push HDR hint (`bit_depth >= 10`) — the want-HDR flag handed to the capturer so it
-    /// Non-IDD-push Windows backends ignore it and auto-detect HDR from the monitor; Linux is 8-bit.
+    /// proactively enables advanced color on the virtual display. Linux is 8-bit (HDR blocked upstream).
     pub hdr: bool,
     /// Handshake-negotiated chroma subsampling (4:2:0, or full-chroma 4:4:4 when the client + host +
     /// GPU all support it). Resolved before the Welcome; `Yuv420` on every backend that declined it.
@@ -151,26 +136,8 @@ impl SessionPlan {
     }
 }
 
-/// Process topology. On Windows this is the former `punktfunk1::should_use_helper` logic verbatim; on
+/// Process topology. Single-process is the only topology now: Linux (portal) and Windows (in-process
-/// every other platform the session is always single-process.
+/// IDD-push in Session 0). The Windows SYSTEM-host + user-session WGC relay was removed with DDA/WGC.
-#[cfg(target_os = "windows")]
-pub(crate) fn resolve_topology() -> SessionTopology {
-    let cfg = crate::config::config();
-    // `NO_HELPER`/`NO_WGC` force single-process; IDD-push captures in-process in Session 0 (no helper);
-    // otherwise the helper runs when forced or when we're SYSTEM (in-process WGC can't activate there).
-    let helper = if cfg.no_helper || crate::capture::wgc_disabled() || cfg.idd_push {
-        false
-    } else {
-        cfg.force_helper || crate::capture::wgc_relay::running_as_system()
-    };
-    if helper {
-        SessionTopology::TwoProcessRelay
-    } else {
-        SessionTopology::SingleProcess
-    }
-}
-
-#[cfg(not(target_os = "windows"))]
 pub(crate) fn resolve_topology() -> SessionTopology {
     SessionTopology::SingleProcess
 }

crates/punktfunk-host/src/vdisplay.rs

@@ -58,6 +58,12 @@ pub trait VirtualDisplay: Send {
     /// sessions can't stomp each other's launch target. Default: no-op (backends that attach to an
     /// existing session / don't spawn a nested command ignore it; only gamescope's spawn path uses it).
     fn set_launch_command(&mut self, _cmd: Option<String>) {}
+    /// Set the connecting client's cert fingerprint so the backend can give that client a STABLE virtual
+    /// monitor identity across reconnects — Windows then reapplies the client's saved per-monitor config
+    /// (notably DPI scaling). Carried on the backend instance; set once before [`create`](Self::create).
+    /// Default: no-op — only the Windows pf-vdisplay backend uses it (Linux compositors own their virtual
+    /// output identity). `None` = anonymous/unpaired/GameStream → the backend's auto (slot-based) identity.
+    fn set_client_identity(&mut self, _fingerprint: Option<[u8; 32]>) {}
 }
 
 /// Compositors punktfunk knows how to drive (plan §6).
@@ -641,6 +647,9 @@ pub fn start_restore_worker() -> std::sync::Arc<()> {
 #[cfg(target_os = "linux")]
 #[path = "vdisplay/linux/gamescope.rs"]
 mod gamescope;
+#[cfg(target_os = "windows")]
+#[path = "vdisplay/windows/identity.rs"]
+pub(crate) mod identity;
 #[cfg(target_os = "linux")]
 #[path = "vdisplay/linux/kwin.rs"]
 mod kwin;

crates/punktfunk-host/src/vdisplay/windows/identity.rs

@@ -0,0 +1,172 @@
+//! Per-client → stable monitor-id map for pf-vdisplay (Phase 2: per-client display-config persistence).
+//!
+//! Windows keys per-monitor config — notably DPI **scaling** (`HKCU\Control Panel\Desktop\PerMonitorSettings`)
+//! — on the monitor's EDID identity AND its OS device path (whose per-connector discriminator is the IddCx
+//! `ConnectorIndex` → target UID). The pf-vdisplay driver seeds BOTH the EDID serial and the `ConnectorIndex`
+//! from a single monitor `id`. So for Windows to REAPPLY a given client's saved scaling on reconnect, that
+//! client must get the SAME `id` every time. This map assigns each client (keyed by its cert fingerprint) a
+//! STABLE id and the host passes it as [`AddRequest::preferred_monitor_id`](pf_driver_proto::control::AddRequest).
+//!
+//! The id space is bounded to `1..=15` because the driver uses the id as the IddCx `ConnectorIndex`, which
+//! must stay `< MaxMonitorsSupported` (16). When more than 15 distinct clients are remembered, the
+//! LEAST-RECENTLY-USED entry is evicted and its id reused (that evicted client simply re-establishes its
+//! scaling once on its next connect). The map persists to `%ProgramData%\punktfunk\pf-vdisplay-identity.json`
+//! so ids — and therefore the client→config association — survive host restarts.
+//!
+//! Anonymous/TOFU and GameStream sessions have no fingerprint and resolve to id `0` (auto) upstream, never
+//! reaching this map — they keep the driver's lowest-free slot behavior unchanged.
+
+use std::path::PathBuf;
+
+use serde::{Deserialize, Serialize};
+
+/// Max stable id. The driver uses the id as the IddCx `ConnectorIndex`, which must stay
+/// `< MaxMonitorsSupported` (16) — so ids run `1..=15`.
+const MAX_ID: u32 = 15;
+
+#[derive(Serialize, Deserialize, Default)]
+struct Store {
+    /// Monotonic most-recently-used counter (the entry with the highest `seen` is the MRU). Persisted so
+    /// the LRU ordering survives host restarts.
+    tick: u64,
+    entries: Vec<Entry>,
+}
+
+#[derive(Serialize, Deserialize)]
+struct Entry {
+    /// Lower-hex client cert fingerprint (the map key).
+    fp: String,
+    /// The client's stable monitor id (`1..=15`).
+    id: u32,
+    /// MRU stamp (compared against [`Store::tick`]).
+    seen: u64,
+}
+
+/// Persistent fingerprint → stable-id map (see the module docs).
+pub(crate) struct MonitorIdentityMap {
+    path: PathBuf,
+    store: Store,
+}
+
+impl MonitorIdentityMap {
+    /// Load the persisted map (empty on first run / unreadable / parse failure — a fresh map just
+    /// re-derives ids, costing a client one scaling re-set the first time).
+    pub(crate) fn load() -> Self {
+        let path = crate::gamestream::config_dir().join("pf-vdisplay-identity.json");
+        let mut store = std::fs::read(&path)
+            .ok()
+            .and_then(|b| serde_json::from_slice::<Store>(&b).ok())
+            .unwrap_or_default();
+        // SANITIZE a hand-edited / corrupt / cross-version file before trusting it: resolve()'s found-entry
+        // branch returns the stored id verbatim, so an out-of-range id (0 = the "auto" sentinel, or
+        // > MAX_ID) or a duplicate id/fp would flow straight into preferred_monitor_id. Drop out-of-range
+        // ids and dedup by BOTH fp and id (keeping the most-recently-seen on a clash) so no two fingerprints
+        // can map to the same id. (The driver also rejects a live-colliding id as a backstop.)
+        store.entries.sort_by_key(|e| std::cmp::Reverse(e.seen));
+        let mut seen_fp = std::collections::HashSet::new();
+        let mut seen_id = std::collections::HashSet::new();
+        store.entries.retain(|e| {
+            (1..=MAX_ID).contains(&e.id) && seen_fp.insert(e.fp.clone()) && seen_id.insert(e.id)
+        });
+        Self { path, store }
+    }
+
+    /// The stable id (`1..=15`) for the client fingerprint `fp`: its remembered id, or a freshly assigned
+    /// one (lowest free, else LRU-evict at the cap). Bumps the entry to MRU and persists.
+    pub(crate) fn resolve(&mut self, fp: [u8; 32]) -> u32 {
+        let key: String = fp.iter().map(|b| format!("{b:02x}")).collect();
+        self.store.tick = self.store.tick.wrapping_add(1);
+        let now = self.store.tick;
+
+        if let Some(e) = self.store.entries.iter_mut().find(|e| e.fp == key) {
+            e.seen = now;
+            let id = e.id;
+            self.persist();
+            return id;
+        }
+
+        // New client: prefer the lowest free id in 1..=MAX_ID; if all are taken, evict the LRU entry and
+        // reuse its id (the evicted client re-establishes its scaling once on its next connect).
+        let id = (1..=MAX_ID)
+            .find(|i| !self.store.entries.iter().any(|e| e.id == *i))
+            .unwrap_or_else(|| {
+                let lru = self
+                    .store
+                    .entries
+                    .iter()
+                    .enumerate()
+                    .min_by_key(|(_, e)| e.seen)
+                    .map(|(i, _)| i)
+                    .expect("entries are non-empty whenever every id 1..=MAX_ID is taken");
+                let evicted = self.store.entries.remove(lru);
+                evicted.id
+            });
+        self.store.entries.push(Entry {
+            fp: key,
+            id,
+            seen: now,
+        });
+        self.persist();
+        id
+    }
+
+    /// Persist atomically (temp file + rename). Best-effort: a write failure just means a restart may
+    /// re-derive an id (one scaling re-set). Not a credential, so a plain (non-ACL'd) write is fine.
+    fn persist(&self) {
+        let Ok(bytes) = serde_json::to_vec_pretty(&self.store) else {
+            return;
+        };
+        if let Some(dir) = self.path.parent() {
+            let _ = std::fs::create_dir_all(dir);
+        }
+        let tmp = self.path.with_extension("json.tmp");
+        if std::fs::write(&tmp, &bytes).is_ok() {
+            let _ = std::fs::rename(&tmp, &self.path);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    fn fp(n: u8) -> [u8; 32] {
+        let mut f = [0u8; 32];
+        f[0] = n;
+        f
+    }
+
+    #[test]
+    fn stable_across_calls_and_distinct_per_client() {
+        let mut m = MonitorIdentityMap {
+            path: std::env::temp_dir().join(format!("pf-id-test-{}.json", std::process::id())),
+            store: Store::default(),
+        };
+        let a1 = m.resolve(fp(1));
+        let b = m.resolve(fp(2));
+        let a2 = m.resolve(fp(1));
+        assert_eq!(a1, a2, "same client → same id");
+        assert_ne!(a1, b, "distinct clients → distinct ids");
+        assert!((1..=MAX_ID).contains(&a1) && (1..=MAX_ID).contains(&b));
+        let _ = std::fs::remove_file(&m.path);
+    }
+
+    #[test]
+    fn lru_eviction_reuses_an_id_at_the_cap() {
+        let mut m = MonitorIdentityMap {
+            path: std::env::temp_dir().join(format!("pf-id-lru-{}.json", std::process::id())),
+            store: Store::default(),
+        };
+        // Fill all 15 ids (clients 1..=15), then touch client 2 so client 1 is the LRU.
+        for n in 1..=15u8 {
+            m.resolve(fp(n));
+        }
+        let _ = m.resolve(fp(2));
+        // A 16th client evicts the LRU (client 1) and reuses its id; ids stay bounded.
+        let id16 = m.resolve(fp(16));
+        assert!((1..=MAX_ID).contains(&id16));
+        assert_eq!(m.store.entries.len(), 15, "cap holds at 15 entries");
+        assert!(m.store.entries.iter().all(|e| (1..=MAX_ID).contains(&e.id)));
+        let _ = std::fs::remove_file(&m.path);
+    }
+}

crates/punktfunk-host/src/vdisplay/windows/manager.rs

@@ -59,8 +59,9 @@ pub(crate) trait VdisplayDriver: Send + Sync {
     /// # Safety
     /// Issues setup-API + `DeviceIoControl` calls; runs in the caller's apartment.
     unsafe fn open(&self) -> Result<(OwnedHandle, u32)>;
-    /// ADD a virtual monitor at `mode`, pinning the IDD render GPU to `render_luid` first if `Some`.
+    /// ADD a virtual monitor at `mode`, pinning the IDD render GPU to `render_luid` first if `Some`, and
-    /// Returns the REMOVE key + target id + the adapter LUID the driver actually used.
+    /// requesting `preferred_monitor_id` (the host's per-client stable id; `0` = auto). Returns the REMOVE
+    /// key + target id + the adapter LUID the driver actually used.
     ///
     /// # Safety
     /// `dev` must be the live control handle from [`open`](Self::open).
@@ -69,6 +70,7 @@ pub(crate) trait VdisplayDriver: Send + Sync {
         dev: HANDLE,
         mode: Mode,
         render_luid: Option<LUID>,
+        preferred_monitor_id: u32,
     ) -> Result<AddedMonitor>;
     /// REMOVE the monitor identified by `key`.
     ///
@@ -134,6 +136,10 @@ pub(crate) struct VirtualDisplayManager {
     /// The current IDD-push session's stop flag; a new connection signals the prior one to release its
     /// monitor before the fresh one is created (was the `IDD_SESSION_STOP` global in `punktfunk1`).
     idd_session_stop: Mutex<Option<Arc<AtomicBool>>>,
+    /// Persistent per-client (cert-fingerprint) → stable monitor-id map. A monitor CREATE resolves the
+    /// connecting client's id here, so the client keeps the same EDID serial + IddCx ConnectorIndex across
+    /// reconnects and Windows reapplies its saved per-monitor config (DPI scaling). See [`super::identity`].
+    identity_map: Mutex<super::identity::MonitorIdentityMap>,
 }
 
 static VDM: OnceLock<VirtualDisplayManager> = OnceLock::new();
@@ -149,6 +155,7 @@ pub(crate) fn init(driver: Box<dyn VdisplayDriver>) -> &'static VirtualDisplayMa
         state: Mutex::new(MgrState::Idle),
         setup_lock: Mutex::new(()),
         idd_session_stop: Mutex::new(None),
+        identity_map: Mutex::new(super::identity::MonitorIdentityMap::load()),
     })
 }
 
@@ -196,30 +203,40 @@ impl VirtualDisplayManager {
     }
 
     /// Acquire the shared monitor for a new session: preempt-recreate under IDD-push, join a live one
-    /// (refcount++), reuse a lingering one, or create one. The returned [`MonitorLease`] releases the
+    /// (refcount++), reuse a lingering one, or create one. `client_fp` (the connecting client's cert
-    /// refcount on drop.
+    /// fingerprint; `None` = anonymous/GameStream) gives a freshly CREATED monitor a STABLE per-client id
-    pub(crate) fn acquire(&'static self, mode: Mode) -> Result<VirtualOutput> {
+    /// (so Windows reapplies that client's saved per-monitor config); JOIN and lingering-reuse keep the
+    /// existing monitor's id. The returned [`MonitorLease`] releases the refcount on drop.
+    pub(crate) fn acquire(
+        &'static self,
+        mode: Mode,
+        client_fp: Option<[u8; 32]>,
+    ) -> Result<VirtualOutput> {
         self.ensure_linger_timer();
         let mut state = self.state.lock().unwrap();
         let dev = self.ensure_device()?;
 
-        // IDD-push: a new connection while a monitor is live is a single-client RECONNECT (the prior
+        // IDD-push: a new connection while a monitor is LINGERING is a single-client RECONNECT (the
-        // client is gone). A REUSED IddCx swap-chain is DEAD, so joining it hands a black screen —
+        // prior session fully released). A REUSED IddCx swap-chain is DEAD, so reusing it hands a black
-        // PREEMPT: tear the old monitor down (its key/topology are restored) and create a fresh one. The
+        // screen — PREEMPT: tear the lingering monitor down (its key/topology are restored) and create a
-        // old session's lease is gen-stamped, so its later drop is a no-op and can't tear down the new one.
+        // fresh one. The old session's lease is gen-stamped, so its later drop is a no-op.
-        if idd_push_mode() && matches!(*state, MgrState::Active { .. } | MgrState::Lingering { .. })
+        //
-        {
+        // ONLY Lingering, NOT Active: an Active monitor still has a lease held — that's the build-retry
-            if let MgrState::Active { mon, .. } | MgrState::Lingering { mon, .. } =
+        // path (`build_pipeline_with_retry` holds one lease across all attempts) or a concurrent session,
-                std::mem::replace(&mut *state, MgrState::Idle)
+        // NOT a reconnect. Preempting Active would tear a live session down AND churn REMOVE→ADD on every
+        // retry — the per-cold-start monitor churn that exhausts the IddCx slot pool and wedges ADD at
+        // 0x80070490. Active falls through to the JOIN path below (refcount++, no ADD).
+        if idd_push_mode() && matches!(*state, MgrState::Lingering { .. }) {
+            if let MgrState::Lingering { mon, .. } = std::mem::replace(&mut *state, MgrState::Idle)
             {
                 tracing::info!(
                     old_target = mon.target_id,
-                    "IDD-push reconnect — preempting the prior session, recreating a fresh monitor"
+                    "IDD-push reconnect — preempting the lingering monitor, recreating a fresh one"
                 );
                 // SAFETY: `teardown` requires `dev` to be the live control handle; `dev` is the value
                 // `ensure_device()` returned above (the device is cached in the `OnceLock` and never
-                // closed for the manager's lifetime). `mon` was moved out of the prior `Active`/
+                // closed for the manager's lifetime). `mon` was moved out of the prior `Lingering`
-                // `Lingering` state by `mem::replace`, so it is exclusively owned here — no aliasing.
+                // state by `mem::replace`, so it is exclusively owned here — no aliasing.
                 unsafe { self.teardown(dev, mon) };
                 // Let the OS finish the ASYNC monitor departure before the next ADD; a back-to-back
                 // REMOVE→ADD races the teardown and the ADD IOCTL is rejected under reconnect churn.
@@ -264,7 +281,7 @@ impl VirtualDisplayManager {
             // SAFETY: `create_monitor` requires `dev` to be the live control handle; `dev` is the
             // handle `ensure_device()` returned above (cached in the `OnceLock`, never closed for the
             // manager's lifetime), and we hold the `state` lock.
-            MgrState::Idle => unsafe { self.create_monitor(dev, mode)? },
+            MgrState::Idle => unsafe { self.create_monitor(dev, mode, client_fp)? },
             MgrState::Active { .. } => unreachable!("handled above"),
         };
         let out = self.output_for(&mon);
@@ -291,12 +308,26 @@ impl VirtualDisplayManager {
     ///
     /// # Safety
     /// `dev` must be the live control handle.
-    unsafe fn create_monitor(&'static self, dev: HANDLE, mode: Mode) -> Result<Monitor> {
+    unsafe fn create_monitor(
+        &'static self,
+        dev: HANDLE,
+        mode: Mode,
+        client_fp: Option<[u8; 32]>,
+    ) -> Result<Monitor> {
+        // Resolve the connecting client's STABLE per-client monitor id (so Windows reapplies its saved
+        // per-monitor config — DPI scaling — on reconnect); `None`/anonymous → 0 = the driver
+        // auto-allocates the lowest-free id (the original slot-based behavior).
+        let preferred_id = client_fp
+            .map(|fp| self.identity_map.lock().unwrap().resolve(fp))
+            .unwrap_or(0);
         // SAFETY: `create_monitor`'s own `# Safety` contract guarantees `dev` is the live control
         // handle; we forward it unchanged to `add_monitor`, whose precondition is exactly that.
         // `resolve_render_pin()` returns an `Option<LUID>` by value (plain `Copy`), so no borrowed
         // memory crosses the call.
-        let added = unsafe { self.driver.add_monitor(dev, mode, resolve_render_pin())? };
+        let added = unsafe {
+            self.driver
+                .add_monitor(dev, mode, resolve_render_pin(), preferred_id)?
+        };
 
         // Mandatory keepalive: ping inside the watchdog window or the driver tears all displays down.
         // The pinger reaches the singleton for both the device + the driver — no raw-handle smuggle.
@@ -510,25 +541,62 @@ impl VirtualDisplayManager {
         let prev = self.idd_session_stop.lock().unwrap().replace(stop);
         if let Some(prev_stop) = prev {
             prev_stop.store(true, Ordering::SeqCst);
-            self.wait_for_monitor_released(Duration::from_secs(3));
+            if !self.wait_for_monitor_released(Duration::from_secs(3)) {
+                // TIMEOUT: the prior session is STILL Active (a wedged/slow teardown). `acquire`'s preempt
+                // is now Lingering-only (so build-retries JOIN the held monitor instead of churning
+                // REMOVE→ADD), which means the upcoming `_retry_hold` acquire would JOIN this stuck monitor
+                // and reuse its DEAD IddCx swap-chain → a full-session black screen with no self-heal until
+                // this session disconnects. Force-preempt it HERE instead. This runs at most ONCE per
+                // session (we hold `setup_lock`), so — unlike preempting inside `acquire` — it does not
+                // reintroduce the per-retry churn. The next `acquire` then sees `Idle` and creates a fresh
+                // monitor; the stale session's gen-stamped lease release is a no-op.
+                if let Some(dev) = self.device_handle() {
+                    let taken = {
+                        let mut state = self.state.lock().unwrap();
+                        match std::mem::replace(&mut *state, MgrState::Idle) {
+                            MgrState::Active { mon, .. } => Some(mon),
+                            // Raced to Lingering/Idle between the wait and here — restore + nothing stuck.
+                            other => {
+                                *state = other;
+                                None
+                            }
+                        }
+                    };
+                    if let Some(mon) = taken {
+                        tracing::warn!(
+                            old_target = mon.target_id,
+                            "IDD-push setup: force-preempting the stuck-Active prior monitor (its IddCx swap-chain is dead)"
+                        );
+                        // SAFETY: `teardown` requires `dev` to be the live control handle; `dev` is the
+                        // cached process-lifetime `OwnedHandle` from `device_handle()` (the `Some` checked
+                        // above). `mon` was moved out of the `Active` state under the `state` lock, so it is
+                        // exclusively owned here — no aliasing.
+                        unsafe { self.teardown(dev, mon) };
+                        // Let the OS finish the ASYNC departure before the next ADD (mirrors the acquire()
+                        // Lingering-preempt settle).
+                        thread::sleep(Duration::from_millis(400));
+                    }
+                }
+            }
         }
         guard
     }
 
     /// Wait (up to `timeout`) for the active monitor to be RELEASED (the MGR is no longer `Active`).
     /// Used by the IDD-push reconnect preempt: after signalling the old session to stop, wait here so it
-    /// tears its monitor down cleanly before we acquire a fresh one.
+    /// tears its monitor down cleanly before we acquire a fresh one. Returns `true` if it released, `false`
-    pub(crate) fn wait_for_monitor_released(&self, timeout: Duration) {
+    /// on timeout (the prior session is still `Active` — the caller force-preempts it).
+    pub(crate) fn wait_for_monitor_released(&self, timeout: Duration) -> bool {
         let deadline = Instant::now() + timeout;
         loop {
             if !matches!(*self.state.lock().unwrap(), MgrState::Active { .. }) {
-                return;
+                return true;
             }
             if Instant::now() >= deadline {
                 tracing::warn!(
-                    "IDD-push preempt: prior session didn't release the monitor within {timeout:?} — proceeding"
+                    "IDD-push preempt: prior session didn't release the monitor within {timeout:?} — force-preempting"
                 );
-                return;
+                return false;
             }
             thread::sleep(Duration::from_millis(25));
         }

crates/punktfunk-host/src/vdisplay/windows/pf_vdisplay.rs

@@ -75,6 +75,65 @@ unsafe fn ioctl(h: HANDLE, code: u32, input: &[u8], output: &mut [u8]) -> Result
     Ok(returned)
 }
 
+/// Reap the ghost (NOT-present) "punktfunk" virtual-monitor device nodes that `IddCxMonitorDeparture`
+/// leaves behind. Each departed monitor leaves a not-present "Generic Monitor (punktfunk)" PDO that keeps
+/// pinning an OS VidPN target against the IddCx adapter's fixed monitor-slot budget; once ~16 accumulate,
+/// `IOCTL_ADD` wedges at 0x80070490 (`ERROR_NOT_FOUND`) and every session black-screens until a manual
+/// reset/reboot. Removing the not-present PDOs frees the slots — the in-process equivalent of
+/// `reset-pf-vdisplay.ps1` step 2 (proven on-box). Best-effort + idempotent: only NOT-present nodes
+/// (`Status != OK`) are removed, so the LIVE session's monitor (`Status OK`) is never touched; any
+/// failure is logged and swallowed. Returns the number removed.
+fn reap_ghost_monitors() -> u32 {
+    // Mirrors reset-pf-vdisplay.ps1 step 2. powershell is always present for the SYSTEM service; the
+    // matched tokens ('OK', 'punktfunk', the InstanceId) are locale-invariant, so this is safe on a
+    // non-English box (unlike a .ps1 *file* read in the machine codepage).
+    const REAP_PS: &str = "$ErrorActionPreference='SilentlyContinue'; \
+        $g = Get-PnpDevice -Class Monitor | Where-Object { $_.Status -ne 'OK' -and $_.FriendlyName -match 'punktfunk' }; \
+        $n = 0; foreach ($d in $g) { pnputil /remove-device $d.InstanceId *> $null; if ($LASTEXITCODE -eq 0) { $n++ } }; \
+        Write-Output $n";
+    // Resolve powershell by full path — the LocalSystem service's PATH is not guaranteed to include
+    // System32 — with a bare-name fallback.
+    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)
+        .args([
+            "-NoProfile",
+            "-NonInteractive",
+            "-ExecutionPolicy",
+            "Bypass",
+            "-Command",
+            REAP_PS,
+        ])
+        .output()
+    {
+        Ok(o) => {
+            let n = String::from_utf8_lossy(&o.stdout)
+                .trim()
+                .parse::<u32>()
+                .unwrap_or(0);
+            if n > 0 {
+                tracing::warn!(
+                    reaped = n,
+                    "pf-vdisplay: reaped ghost (not-present) virtual-monitor nodes — IddCx slot-exhaustion prevention"
+                );
+            }
+            n
+        }
+        Err(e) => {
+            tracing::warn!(error = %e, "pf-vdisplay: ghost-monitor reap could not spawn powershell");
+            0
+        }
+    }
+}
+
+/// True if `e`'s chain carries the IddCx monitor-slot-exhaustion wedge HRESULT (0x80070490,
+/// `ERROR_NOT_FOUND`) — the `IOCTL_ADD` failure that ghost-PDO accumulation produces. The hex code is
+/// locale-invariant (the OS message text is not), so we match on it.
+fn is_slot_exhaustion_wedge(e: &anyhow::Error) -> bool {
+    format!("{e:#}").contains("0x80070490")
+}
+
 /// Pin the pf-vdisplay IddCx's RENDER GPU to `luid` (the analogue of Apollo's `SetRenderAdapter`). No
 /// output buffer. Issued on the driver handle BEFORE `IOCTL_ADD` to steer which GPU the new target
 /// renders on — on a multi-adapter box this stops DXGI from reparenting the virtual output onto a
@@ -193,6 +252,12 @@ impl VdisplayDriver for PfVdisplayDriver {
         } else {
             tracing::warn!("pf-vdisplay IOCTL_CLEAR_ALL failed on startup (continuing)");
         }
+        // CLEAR_ALL only departs the driver's own (in-process) monitor list; it can NOT remove the
+        // OS-side not-present "Generic Monitor (punktfunk)" PDOs that a previous host-run's monitor
+        // departures left behind. Reap those here so a fresh host start begins with a clean IddCx
+        // monitor-slot budget — prevents the 0x80070490 slot-exhaustion wedge from carrying across
+        // restarts (the reason a restart's CLEAR_ALL alone never recovered it before).
+        reap_ghost_monitors();
         Ok((
             // SAFETY: `device` is the valid handle from `open_device`, still owned here and NOT closed
             // on this success path (the error paths above close it and return). `from_raw_handle`'s
@@ -208,6 +273,7 @@ impl VdisplayDriver for PfVdisplayDriver {
         dev: HANDLE,
         mode: Mode,
         render_luid: Option<LUID>,
+        preferred_monitor_id: u32,
     ) -> Result<AddedMonitor> {
         let session_id = next_session_id();
         let add = control::AddRequest {
@@ -215,7 +281,7 @@ impl VdisplayDriver for PfVdisplayDriver {
             width: mode.width,
             height: mode.height,
             refresh_hz: mode.refresh_hz,
-            _reserved: 0,
+            preferred_monitor_id,
         };
         // SET_RENDER_ADAPTER (opt-in; pf-vdisplay IMPLEMENTS it). Non-fatal on failure: the driver reports
         // its real render LUID in the shared header, so the host binds correctly even if this is ignored.
@@ -238,13 +304,47 @@ impl VdisplayDriver for PfVdisplayDriver {
         // borrows the local `AddRequest` (alive across this synchronous call) as the input bytes, and
         // `out` is a stack `[u8; size_of::<AddReply>()]` whose length bounds the kernel's write — both
         // buffers outlive the call.
-        unsafe { ioctl(dev, control::IOCTL_ADD, bytemuck::bytes_of(&add), &mut out) }
+        let add_res = unsafe { ioctl(dev, control::IOCTL_ADD, bytemuck::bytes_of(&add), &mut out) };
-            .with_context(|| {
+        let add_res = match add_res {
-                format!(
+            Err(e) if is_slot_exhaustion_wedge(&e) => {
-                    "pf-vdisplay ADD {}x{}@{}",
+                // The IddCx monitor-slot pool is exhausted by accumulated ghost (departed-but-not-present)
-                    mode.width, mode.height, mode.refresh_hz
+                // virtual-monitor PDOs → ADD failed 0x80070490. Reap the ghosts in-process and retry ONCE
-                )
+                // so the wedge SELF-HEALS instead of hard-failing every session until a manual reset/reboot
-            })?;
+                // (the long-standing failure mode). pnputil removal is synchronous; a brief settle lets the
+                // OS recompute the adapter's monitor budget before the retry.
+                let reaped = reap_ghost_monitors();
+                tracing::warn!(
+                    reaped,
+                    "pf-vdisplay ADD wedged (0x80070490 ERROR_NOT_FOUND) — reaped ghost monitor nodes, retrying ADD"
+                );
+                // pnputil removal is durable (the ghosts are gone permanently), but the OS reclaims the
+                // IddCx VidPN-target slots via ASYNC PnP teardown that can lag the synchronous pnputil
+                // return. Retry the ADD a few times (300 ms apart, NO re-reap — the ghosts are already
+                // removed) to ride out that variable reclaim latency rather than guess one magic settle.
+                // ~1.5 s worst case, only on the rare wedge path.
+                let mut res = Err(anyhow::anyhow!("pf-vdisplay ADD retry loop did not run"));
+                for _ in 0..5 {
+                    std::thread::sleep(std::time::Duration::from_millis(300));
+                    // SAFETY: identical to the first IOCTL_ADD above — `dev` is the live control handle
+                    // (`add_monitor`'s contract), and `bytemuck::bytes_of(&add)` + `&mut out` borrow locals
+                    // that outlive this synchronous call.
+                    res = unsafe {
+                        ioctl(dev, control::IOCTL_ADD, bytemuck::bytes_of(&add), &mut out)
+                    };
+                    if res.is_ok() {
+                        break;
+                    }
+                }
+                res
+            }
+            other => other,
+        };
+        add_res.with_context(|| {
+            format!(
+                "pf-vdisplay ADD {}x{}@{}",
+                mode.width, mode.height, mode.refresh_hz
+            )
+        })?;
         // `pod_read_unaligned` (NOT `from_bytes`): `out` is a stack `[u8; N]` with no guaranteed 4-byte
         // alignment, and `from_bytes` PANICS on a mismatch. This copies into an aligned `AddReply`.
         let reply: control::AddReply =
@@ -261,6 +361,25 @@ impl VdisplayDriver for PfVdisplayDriver {
             reply.target_id,
             luid.LowPart
         );
+        // Per-client identity diagnostic: did the driver honor the host's preferred (stable) monitor id?
+        // A pre-Phase-2 driver leaves resolved_monitor_id=0 (it ignored the field); a current driver echoes
+        // the id it actually used. A mismatch means this session fell back to an auto id, so Windows won't
+        // reapply this client's saved per-monitor config (scaling) until it gets its stable id back.
+        if preferred_monitor_id != 0 {
+            if reply.resolved_monitor_id == preferred_monitor_id {
+                tracing::info!(
+                    monitor_id = preferred_monitor_id,
+                    "pf-vdisplay: per-client monitor id honored (stable identity → saved config persists)"
+                );
+            } else {
+                tracing::warn!(
+                    preferred = preferred_monitor_id,
+                    resolved = reply.resolved_monitor_id,
+                    "pf-vdisplay: preferred monitor id NOT honored (live-id collision, or a pre-Phase-2 \
+                     driver) — per-client config persistence degraded to auto identity this session"
+                );
+            }
+        }
         if let Some(pin) = render_luid {
             if luid.LowPart == pin.LowPart && luid.HighPart == pin.HighPart {
                 tracing::info!("pf-vdisplay ADD render adapter matches the pinned GPU (pin took)");
@@ -309,14 +428,19 @@ impl VdisplayDriver for PfVdisplayDriver {
     }
 }
 
-/// The Windows pf-vdisplay virtual-display backend. A marker — the lifecycle lives in the shared
+/// The Windows pf-vdisplay virtual-display backend. Near-stateless — the lifecycle lives in the shared
-/// [`VirtualDisplayManager`](super::manager::VirtualDisplayManager).
+/// [`VirtualDisplayManager`](super::manager::VirtualDisplayManager); it only carries the connecting
-pub struct PfVdisplayDisplay;
+/// client's fingerprint so the manager can assign a STABLE per-client monitor id (config persistence).
+pub struct PfVdisplayDisplay {
+    /// The connecting client's cert fingerprint (`None` = anonymous/GameStream → the manager's auto id).
+    /// Set by [`set_client_identity`](VirtualDisplay::set_client_identity) before `create`.
+    client_fp: Option<[u8; 32]>,
+}
 
 impl PfVdisplayDisplay {
     pub fn new() -> Result<Self> {
         super::manager::init(Box::new(PfVdisplayDriver)).open_backend()?;
-        Ok(Self)
+        Ok(Self { client_fp: None })
     }
 }
 
@@ -325,8 +449,12 @@ impl VirtualDisplay for PfVdisplayDisplay {
         "pf-vdisplay"
     }
 
+    fn set_client_identity(&mut self, fingerprint: Option<[u8; 32]>) {
+        self.client_fp = fingerprint;
+    }
+
     fn create(&mut self, mode: Mode) -> Result<VirtualOutput> {
-        super::manager::vdm().acquire(mode)
+        super::manager::vdm().acquire(mode, self.client_fp)
     }
 }
 

crates/punktfunk-host/src/windows/interactive.rs

@@ -5,9 +5,8 @@
 //! activation, and each store's auth/entitlement context resolve — the process must run in the
 //! interactive session under the **logged-in user's** token, not SYSTEM and not session 0.
 //!
-//! This is the same `WTSGetActiveConsoleSessionId → WTSQueryUserToken → DuplicateTokenEx →
+//! This is the standard `WTSGetActiveConsoleSessionId → WTSQueryUserToken → DuplicateTokenEx →
-//! CreateProcessAsUserW(winsta0\\default)` primitive the WGC helper relay uses
+//! CreateProcessAsUserW(winsta0\\default)` primitive, used for the library launch path
-//! ([`crate::capture::wgc_relay`]), factored out for the library launch path
 //! ([`crate::library::launch_title`]).
 //!
 //! IMPORTANT — use the **user** token (`WTSQueryUserToken`), NOT a session-retargeted SYSTEM token
@@ -36,7 +35,7 @@ use windows::Win32::System::Threading::{
 ///
 /// Fire-and-forget: the launched game/launcher outlives this call, so the host does not track the
 /// child — its handles are closed before returning (the process keeps running). The environment is
-/// the user's block merged with the host's `PUNKTFUNK_*`/`RUST_LOG` (same merge the WGC helper uses),
+/// the user's block merged with the host's `PUNKTFUNK_*`/`RUST_LOG` (see [`merged_env_block`]),
 /// so `host.env` settings propagate.
 ///
 /// Requires the host to run as SYSTEM (`WTSQueryUserToken` needs `SE_TCB`). Fails when no interactive
@@ -75,7 +74,7 @@ unsafe fn spawn_inner(cmdline: &str, workdir: Option<&Path>) -> Result<u32> {
     // with the host's PUNKTFUNK_*/RUST_LOG vars — same shared helper the WGC helper + service spawns use.
     let mut env_block: *mut core::ffi::c_void = std::ptr::null_mut();
     let _ = CreateEnvironmentBlock(&mut env_block, Some(primary), false);
-    let merged_env = crate::capture::wgc_relay::merged_env_block(env_block as *const u16);
+    let merged_env = merged_env_block(env_block as *const u16);
     if !env_block.is_null() {
         let _ = DestroyEnvironmentBlock(env_block);
     }
@@ -124,3 +123,48 @@ unsafe fn spawn_inner(cmdline: &str, workdir: Option<&Path>) -> Result<u32> {
     let _ = CloseHandle(pi.hThread);
     Ok(pid)
 }
+
+/// Build the environment block for a process launched into the interactive session: the target
+/// session's block (`user_block`, from `CreateEnvironmentBlock`) with this process's `PUNKTFUNK_*`
+/// vars overlaid, so the child runs with the SAME settings this process has
+/// (`PUNKTFUNK_ENCODER=nvenc`, `PUNKTFUNK_ZEROCOPY`, …) instead of the target shell's. Returns a
+/// UTF-16, double-null-terminated block suitable for `CREATE_UNICODE_ENVIRONMENT`. Shared by the
+/// interactive library launch (here) and the Windows service launching the host into the active
+/// session ([`crate::service`]).
+///
+/// # Safety
+/// `user_block` must be either null or a valid pointer to a UTF-16, double-null-terminated
+/// environment block (the `CreateEnvironmentBlock` output), readable for its whole length.
+pub(crate) unsafe fn merged_env_block(user_block: *const u16) -> Vec<u16> {
+    // Parse the user block ("VAR=VALUE\0" … "\0") into entries.
+    let mut entries: Vec<String> = Vec::new();
+    if !user_block.is_null() {
+        let mut p = user_block;
+        loop {
+            let mut len = 0isize;
+            while *p.offset(len) != 0 {
+                len += 1;
+            }
+            if len == 0 {
+                break; // the trailing empty string = end of block
+            }
+            let slice = std::slice::from_raw_parts(p, len as usize);
+            entries.push(String::from_utf16_lossy(slice));
+            p = p.offset(len + 1);
+        }
+    }
+    // Overlay "our" settings — PUNKTFUNK_* and RUST_LOG — dropping whatever the target block had.
+    let is_ours = |k: &str| k.starts_with("PUNKTFUNK_") || k == "RUST_LOG";
+    entries.retain(|e| !is_ours(e.split('=').next().unwrap_or("")));
+    for (k, v) in std::env::vars().filter(|(k, _)| is_ours(k)) {
+        entries.push(format!("{k}={v}"));
+    }
+    // Serialize back to a UTF-16 double-null-terminated block.
+    let mut block: Vec<u16> = Vec::new();
+    for e in entries {
+        block.extend(e.encode_utf16());
+        block.push(0);
+    }
+    block.push(0);
+    block
+}

crates/punktfunk-host/src/windows/service.rs

@@ -3,12 +3,12 @@
 //! for the ad-hoc PsExec / VBS / scheduled-task launch chain used during bring-up.
 //!
 //! Why a supervisor and not just "run the host as a service": the host must run **as SYSTEM in the
-//! interactive session** (session 1+). Desktop Duplication of the secure (Winlogon/UAC/lock) desktop
+//! interactive session** (session 1+). Capturing the secure (Winlogon/UAC/lock) desktop and
-//! and `SendInput` both need SYSTEM; capture and injection both need the *interactive* session, which
+//! `SendInput` both need SYSTEM; capture and injection both need the *interactive* session, which
 //! a plain session-0 service is not in. So this service (itself in session 0) never captures — it
 //! duplicates its own LocalSystem token, retargets it to the active console session, and
-//! `CreateProcessAsUserW`s the host there. This is the Sunshine/Apollo model. The host in turn spawns
+//! `CreateProcessAsUserW`s the host there. This is the Sunshine/Apollo model. The host captures the
-//! the WGC helper into the *user* session (see `capture::wgc_relay`) — two nested launches.
+//! virtual display in-process via IDD direct-push (no helper process).
 //!
 //! Subcommands (Windows only):
 //! ```text
@@ -230,8 +230,9 @@ fn run_service() -> Result<()> {
     let _ = SESSION_EVENT.set(session_owned);
 
     // The control handler captures nothing — it reaches the events through the statics, so it stays
-    // `Fn + Send + 'static`. Session lock/unlock are handled inside the host (DesktopWatcher), so we
+    // `Fn + Send + 'static`. Lock/unlock is handled by the in-process IDD-push capture (the driver
-    // only flag console connect/disconnect/logon — the events that change the active session.
+    // composes the secure desktop into the ring), so we only flag console connect/disconnect/logon —
+    // the events that change the active session.
     let handler = move |control| -> ServiceControlHandlerResult {
         match control {
             ServiceControl::Stop | ServiceControl::Preshutdown | ServiceControl::Shutdown => {
@@ -517,10 +518,10 @@ unsafe fn spawn_host(
     .context("SetTokenInformation(TokenSessionId)")?;
 
     // 2) The session's environment block, merged with this process's PUNKTFUNK_*/RUST_LOG (so the
-    //    host runs with host.env's settings, not a bare block). Same merge the WGC helper uses.
+    //    host runs with host.env's settings, not a bare block). Same merge the interactive launch uses.
     let mut env_block: *mut c_void = std::ptr::null_mut();
     let _ = CreateEnvironmentBlock(&mut env_block, Some(primary), false);
-    let merged = crate::capture::wgc_relay::merged_env_block(env_block as *const u16);
+    let merged = crate::interactive::merged_env_block(env_block as *const u16);
     if !env_block.is_null() {
         let _ = DestroyEnvironmentBlock(env_block);
     }

crates/punktfunk-host/src/windows/wgc_helper.rs

@@ -1,346 +0,0 @@
-//! USER-session WGC helper (Windows) — part of the two-process secure-desktop design
-//! (design/archive/windows-secure-desktop.md).
-//!
-//! WGC won't activate under the SYSTEM account, but the host must run as SYSTEM for the secure
-//! desktop. So the SYSTEM host spawns THIS helper in the interactive user session
-//! (`CreateProcessAsUserW`) to do the WGC capture + NVENC encode that needs the user token, and the
-//! helper ships the encoded Annex-B access units back over its **stdout** pipe (which the host
-//! inherits + reads). The host relays them on the live QUIC session while the normal desktop is up,
-//! and switches to its own DDA encoder on the secure desktop. The helper captures the SAME SudoVDA
-//! output **by GDI name only** — it never creates a virtual output / touches display topology (a
-//! second topology owner would re-trigger the ACCESS_LOST born-lost storm).
-//!
-//! Wire framing on stdout, per AU: `[u32 len LE][u64 pts_ns LE][u8 keyframe][len bytes data]`.
-
-// Every `unsafe` block in this file carries a `// SAFETY:` proof; enforce it (unsafe-proof program).
-#![deny(clippy::undocumented_unsafe_blocks)]
-
-use crate::capture::{dxgi::WinCaptureTarget, wgc::WgcCapturer, Capturer};
-use crate::encode::{self, Codec};
-use anyhow::{Context, Result};
-use std::io::{Read, Write};
-use std::sync::atomic::{AtomicBool, Ordering};
-use std::sync::Arc;
-
-pub struct HelperOptions {
-    pub target_id: u32,
-    pub gdi_name: String,
-    pub width: u32,
-    pub height: u32,
-    pub fps: u32,
-    pub bitrate_kbps: u32,
-    /// Negotiated encode bit depth (8, or 10 = HEVC Main10). HDR auto-upgrades to 10 from the
-    /// captured frame's `Rgb10a2` format regardless.
-    pub bit_depth: u8,
-}
-
-/// AU framing magic + version, so the host can resync / detect a helper crash on its stdout stream.
-const AU_MAGIC: u32 = 0x5046_4155; // "PFAU"
-
-/// Control byte the host writes on our stdin to force the next frame to be an IDR. Must match
-/// `wgc_relay::CTL_KEYFRAME`.
-const CTL_KEYFRAME: u8 = 0x01;
-
-pub fn run(opts: HelperOptions) -> Result<()> {
-    tracing::info!(
-        target_id = opts.target_id,
-        gdi = %opts.gdi_name,
-        mode = format!("{}x{}@{}", opts.width, opts.height, opts.fps),
-        "WGC helper starting (user session)"
-    );
-
-    // This thread does WGC capture + video-processor convert + NVENC submit — the GPU-submitting hot
-    // path. Elevate its OS priority so a CPU-heavy game can't deschedule it and delay submission (which
-    // would leave our HIGH GPU priority with nothing queued to prioritise). Apollo's capture thread is
-    // likewise CRITICAL.
-    crate::punktfunk1::boost_thread_priority(true);
-
-    // Capture the EXISTING SudoVDA output by GDI name / target id — do NOT create one (the host owns
-    // the virtual output + its isolate/restore; a second topology owner breaks DDA recovery).
-    let target = WinCaptureTarget {
-        adapter_luid: 0,
-        gdi_name: opts.gdi_name.clone(),
-        target_id: opts.target_id,
-    };
-    let mut cap =
-        WgcCapturer::open(target, Some((opts.width, opts.height, opts.fps))).context("WGC open")?;
-    cap.set_active(true);
-
-    // O3 present-trigger experiment: spawn a thread that PRESENTS a D3D swapchain to the virtual
-    // display (a present SOURCE), testing whether that — unlike WGC's READ — makes the OS assign the
-    // driver's IddCx swap-chain (so the driver's run_core runs + can push). Gated; diagnostic.
-    if std::env::var_os("PUNKTFUNK_PRESENT_TRIGGER").is_some() {
-        let (w, h) = (opts.width, opts.height);
-        std::thread::Builder::new()
-            .name("pf-present-trigger".into())
-            .spawn(move || {
-                tracing::info!("present-trigger: starting D3D present loop on the virtual display");
-                // SAFETY: `present_trigger` is unsafe only for its Win32/D3D11 FFI; it has no caller
-                // preconditions (it creates and exclusively owns its own window, device, and swapchain on
-                // this dedicated thread), so the call is sound.
-                if let Err(e) = unsafe { present_trigger(w, h) } {
-                    tracing::warn!("present-trigger error: {e:#}");
-                }
-            })
-            .ok();
-    }
-
-    // First frame establishes the real dimensions + whether the desktop is HDR (the encoder derives
-    // Main10/HDR from the frame's PixelFormat::Rgb10a2). Then open NVENC on the capture device.
-    let first = cap.next_frame().context("first WGC frame")?;
-    let (w, h) = (first.width, first.height);
-    let mut enc = encode::open_video(
-        Codec::H265,
-        first.format,
-        w,
-        h,
-        opts.fps,
-        opts.bitrate_kbps as u64 * 1000,
-        false,          // not cuda
-        opts.bit_depth, // 8, or 10 = Main10 (HDR auto-upgrades from the Rgb10a2 frame regardless)
-        // The two-process WGC relay helper encodes 4:2:0 in v1 (4:4:4 over the relay is a follow-up);
-        // the host gates 4:4:4 to the single-process topology.
-        encode::ChromaFormat::Yuv420,
-    )
-    .context("open NVENC")?;
-
-    // Control channel: the host writes a single byte on our stdin to force an IDR (client decode
-    // recovery), mirroring `enc.request_keyframe()` in the single-process path. A reader thread sets
-    // a flag the encode loop checks; stdin EOF (host gone) just stops the thread.
-    let kf = Arc::new(AtomicBool::new(false));
-    {
-        let kf = kf.clone();
-        std::thread::Builder::new()
-            .name("wgc-helper-ctl".into())
-            .spawn(move || {
-                let mut stdin = std::io::stdin();
-                let mut byte = [0u8; 1];
-                while let Ok(n) = stdin.read(&mut byte) {
-                    if n == 0 {
-                        break; // host closed our stdin
-                    }
-                    if byte[0] == CTL_KEYFRAME {
-                        kf.store(true, Ordering::Relaxed);
-                    }
-                }
-            })
-            .ok();
-    }
-
-    // Binary stdout — lock it once + write framed AUs. A short write / broken pipe means the host
-    // (parent) went away → exit cleanly so the host's relaunch watchdog can respawn us.
-    let stdout = std::io::stdout();
-    let mut out = stdout.lock();
-
-    // FIXED-CADENCE encode loop (mirrors the single-process `punktfunk1::virtual_stream` loop). The
-    // host runs as SYSTEM and relays our AUs; to deliver a STEADY `fps` to the client (the "fixed 240"
-    // goal) we must NOT gate on WGC's content-driven FrameArrived — `WgcCapturer::next_frame` blocks up
-    // to its ~8 ms static-repeat timeout when the desktop is quiet, capping a barely-changing desktop
-    // ~125 fps regardless of the GPU. Instead we pace to `1/fps` and take the FRESHEST frame with the
-    // non-blocking `try_latest`, repeating the last one when nothing newer arrived. Depth-1: NVENC's
-    // `poll` (lock_bitstream) blocks until the just-submitted frame is encoded, so exactly one frame is
-    // in flight per iteration. A deeper pipeline was measured to only stack latency under a
-    // GPU-saturating game (the encodes serialize on the contended GPU anyway) — the in-game lever is
-    // the GPU scheduling priority the SYSTEM host stamps on us, not pipeline depth.
-    let interval = std::time::Duration::from_secs_f64(1.0 / opts.fps.max(1) as f64);
-
-    let perf = crate::config::config().perf;
-    let mut frames = 0u64;
-    let mut repeats = 0u64; // frames where no newer capture had arrived (duplicate re-encode)
-    let mut cap_ns = 0u64; // time in try_latest (capture + video-processor convert)
-    let mut encode_ns = 0u64; // time blocked in lock_bitstream
-    let mut write_ns = 0u64; // time writing the AU to the stdout pipe (relay backpressure)
-    let mut window = std::time::Instant::now();
-
-    // `frame` is held across iterations and repeated when `try_latest` has nothing newer, so a static
-    // desktop still clocks `fps`. The capturer's held-set / output ring keep its texture alive across
-    // the repeat; reassigning `frame` on a fresh capture drops the prior one (already drained by poll).
-    let mut frame = first;
-    let mut next = std::time::Instant::now();
-    loop {
-        if kf.swap(false, Ordering::Relaxed) {
-            enc.request_keyframe();
-        }
-        // Freshest captured frame, or repeat the last (no new composition: static desktop / between a
-        // game's presents). Non-blocking, so the cadence is OURS, not WGC's event rate.
-        let t0 = std::time::Instant::now();
-        match cap.try_latest().context("WGC try_latest")? {
-            Some(f) => frame = f,
-            None => repeats += 1,
-        }
-        if perf {
-            cap_ns += t0.elapsed().as_nanos() as u64;
-        }
-        enc.submit(&frame).context("encoder submit")?;
-        // Drain the just-submitted frame. NVENC's poll blocks in lock_bitstream until it's encoded, so
-        // this returns exactly one AU (then None) — depth-1, no accumulation.
-        loop {
-            let p0 = std::time::Instant::now();
-            let polled = enc.poll().context("encoder poll")?;
-            if perf {
-                encode_ns += p0.elapsed().as_nanos() as u64;
-            }
-            let Some(au) = polled else { break };
-            let w0 = std::time::Instant::now();
-            let wrote = write_au(&mut out, &au);
-            if perf {
-                write_ns += w0.elapsed().as_nanos() as u64;
-            }
-            if wrote.is_err() {
-                tracing::info!("WGC helper: stdout closed (host gone) — exiting");
-                return Ok(());
-            }
-        }
-        // Pace to this frame's due time. If we're already past it (encode couldn't keep up under a
-        // GPU-saturating game), skip the sleep and re-baseline so we don't spiral into catch-up.
-        next += interval;
-        match next.checked_duration_since(std::time::Instant::now()) {
-            Some(d) => std::thread::sleep(d),
-            None => next = std::time::Instant::now(),
-        }
-
-        if perf {
-            frames += 1;
-            let since = window.elapsed();
-            if since.as_secs() >= 2 {
-                let secs = since.as_secs_f64();
-                let per = |ns: u64| format!("{:.2}", ns as f64 / frames as f64 / 1e6);
-                tracing::info!(
-                    fps = format!("{:.1}", frames as f64 / secs),
-                    repeats,
-                    cap_ms = per(cap_ns),
-                    encode_ms = per(encode_ns),
-                    write_ms = per(write_ns),
-                    "WGC helper perf (fixed-cadence depth-1; encode_ms=lock_bitstream; repeats=duplicated frames)"
-                );
-                frames = 0;
-                repeats = 0;
-                cap_ns = 0;
-                encode_ns = 0;
-                write_ns = 0;
-                window = std::time::Instant::now();
-            }
-        }
-    }
-}
-
-fn write_au(out: &mut impl Write, au: &encode::EncodedFrame) -> std::io::Result<()> {
-    out.write_all(&AU_MAGIC.to_le_bytes())?;
-    out.write_all(&(au.data.len() as u32).to_le_bytes())?;
-    out.write_all(&au.pts_ns.to_le_bytes())?;
-    out.write_all(&[au.keyframe as u8])?;
-    out.write_all(&au.data)?;
-    out.flush()
-}
-
-/// O3 present-trigger experiment (see the gated call in `run`). Creates a small swapchain-backed
-/// window on the virtual display (the CCD-isolated primary) and presents continuously — an active
-/// present SOURCE on the display — to test whether that makes the OS assign the driver's IddCx
-/// swap-chain (which WGC's read does not). Runs forever on its own thread.
-///
-/// # Safety
-/// Win32/D3D11 FFI; called once on a dedicated helper thread.
-unsafe fn present_trigger(disp_w: u32, disp_h: u32) -> Result<()> {
-    use windows::core::{w, Interface};
-    use windows::Win32::Foundation::{HMODULE, HWND, LPARAM, LRESULT, WPARAM};
-    use windows::Win32::Graphics::Direct3D::D3D_DRIVER_TYPE_HARDWARE;
-    use windows::Win32::Graphics::Direct3D11::{
-        D3D11CreateDevice, ID3D11Device, ID3D11DeviceContext, ID3D11RenderTargetView,
-        ID3D11Texture2D, D3D11_CREATE_DEVICE_BGRA_SUPPORT, D3D11_SDK_VERSION,
-    };
-    use windows::Win32::Graphics::Dxgi::Common::{DXGI_FORMAT_B8G8R8A8_UNORM, DXGI_SAMPLE_DESC};
-    use windows::Win32::Graphics::Dxgi::{
-        IDXGIAdapter, IDXGIDevice, IDXGIFactory2, DXGI_PRESENT, DXGI_SWAP_CHAIN_DESC1,
-        DXGI_SWAP_EFFECT_FLIP_DISCARD, DXGI_USAGE_RENDER_TARGET_OUTPUT,
-    };
-    use windows::Win32::System::LibraryLoader::GetModuleHandleW;
-    use windows::Win32::UI::WindowsAndMessaging::{
-        CreateWindowExW, DefWindowProcW, DispatchMessageW, PeekMessageW, RegisterClassW,
-        ShowWindow, MSG, PM_REMOVE, SW_SHOWNOACTIVATE, WNDCLASSW, WS_EX_NOACTIVATE, WS_EX_TOPMOST,
-        WS_POPUP, WS_VISIBLE,
-    };
-
-    unsafe extern "system" fn wndproc(h: HWND, m: u32, wp: WPARAM, lp: LPARAM) -> LRESULT {
-        DefWindowProcW(h, m, wp, lp)
-    }
-
-    let hinst: HMODULE = GetModuleHandleW(None)?;
-    let cls = w!("pfPresentTrigger");
-    let wc = WNDCLASSW {
-        lpfnWndProc: Some(wndproc),
-        hInstance: hinst.into(),
-        lpszClassName: cls,
-        ..Default::default()
-    };
-    RegisterClassW(&wc);
-    // Small window at the top-left of the (primary = virtual) display so it barely obscures the
-    // captured desktop; topmost + no-activate so it doesn't steal focus.
-    let win_w = disp_w.min(96) as i32;
-    let win_h = disp_h.min(96) as i32;
-    let hwnd: HWND = CreateWindowExW(
-        WS_EX_TOPMOST | WS_EX_NOACTIVATE,
-        cls,
-        w!("pf-present"),
-        WS_POPUP | WS_VISIBLE,
-        0,
-        0,
-        win_w,
-        win_h,
-        None,
-        None,
-        Some(hinst.into()),
-        None,
-    )?;
-    let _ = ShowWindow(hwnd, SW_SHOWNOACTIVATE);
-
-    let mut device: Option<ID3D11Device> = None;
-    let mut context: Option<ID3D11DeviceContext> = None;
-    D3D11CreateDevice(
-        None,
-        D3D_DRIVER_TYPE_HARDWARE,
-        HMODULE::default(),
-        D3D11_CREATE_DEVICE_BGRA_SUPPORT,
-        None,
-        D3D11_SDK_VERSION,
-        Some(&mut device),
-        None,
-        Some(&mut context),
-    )?;
-    let device = device.context("present-trigger d3d11 device")?;
-    let context = context.context("present-trigger d3d11 context")?;
-
-    let dxgi_dev: IDXGIDevice = device.cast()?;
-    let adapter: IDXGIAdapter = dxgi_dev.GetAdapter()?;
-    let factory: IDXGIFactory2 = adapter.GetParent()?;
-    let scd = DXGI_SWAP_CHAIN_DESC1 {
-        Width: win_w as u32,
-        Height: win_h as u32,
-        Format: DXGI_FORMAT_B8G8R8A8_UNORM,
-        SampleDesc: DXGI_SAMPLE_DESC {
-            Count: 1,
-            Quality: 0,
-        },
-        BufferUsage: DXGI_USAGE_RENDER_TARGET_OUTPUT,
-        BufferCount: 2,
-        SwapEffect: DXGI_SWAP_EFFECT_FLIP_DISCARD,
-        ..Default::default()
-    };
-    let swapchain = factory.CreateSwapChainForHwnd(&device, hwnd, &scd, None, None)?;
-    tracing::info!("present-trigger: swapchain created on the virtual display; presenting");
-
-    let mut frame = 0u32;
-    loop {
-        let mut msg = MSG::default();
-        while PeekMessageW(&mut msg, None, 0, 0, PM_REMOVE).as_bool() {
-            let _ = DispatchMessageW(&msg);
-        }
-        let back: ID3D11Texture2D = swapchain.GetBuffer(0)?;
-        let mut rtv: Option<ID3D11RenderTargetView> = None;
-        device.CreateRenderTargetView(&back, None, Some(&mut rtv))?;
-        let rtv = rtv.context("present-trigger rtv")?;
-        let c = (frame % 120) as f32 / 120.0;
-        context.ClearRenderTargetView(&rtv, &[c, 0.1, 0.2, 1.0]);
-        let _ = swapchain.Present(1, DXGI_PRESENT(0));
-        frame = frame.wrapping_add(1);
-    }
-}

packaging/windows/README.md

@@ -65,6 +65,16 @@ read it from `%ProgramData%\punktfunk\web-password`.
 - **Virtual gamepads need no prerequisite.** The DualSense / DualShock 4 / Xbox 360 (XUSB) UMDF drivers
   are **bundled** in the installer (the *Install the virtual gamepad drivers* task) and
   `pnputil`-installed. **ViGEmBus is no longer used.**
+- **The streaming microphone uses VB-CABLE**, bundled + silently installed by the installer (the *Install
+  VB-CABLE virtual audio* task). The host writes the client's mic into VB-CABLE's input; its `CABLE
+  Output` capture endpoint surfaces as a host mic. A Windows audio device can only be created by a
+  **kernel-mode** driver (no UMDF path exists), so unlike our self-signed UMDF drivers we cannot ship our
+  own — VB-CABLE is a vendor-signed cable that loads with no test-signing. It is **donationware** by
+  VB-Audio, redistributed under VB-Audio's bundling grant (only the single base cable); see
+  `licenses/VB-CABLE-NOTICE.txt`. The package binary is **not** in the repo — supply it to the packer via
+  `-VbCableDir` / `$env:VBCABLE_DIR` (the extracted official package, containing `VBCABLE_Setup_x64.exe`).
+  Absent → the installer is built without it and the host falls back to auto-installing the Steam
+  Streaming pair. *(Endgame: attestation-sign our own MIT virtual-audio driver to drop this dependency.)*
 
 ## Files here
 
@@ -74,6 +84,7 @@ read it from `%ProgramData%\punktfunk\web-password`.
 | `pack-host-installer.ps1` | Orchestrator: cert + sign exe, **build + sign the drivers from source**, stage them + FFmpeg + the **web console** (`.output` + bun) + the HDR layer, run ISCC, sign setup.exe. |
 | `build-pf-vdisplay.ps1` | Build pf-vdisplay from source (the `drivers/` workspace) + clear FORCE_INTEGRITY + sign `.dll`/`.cat` + export `.cer`. |
 | `build-gamepad-drivers.ps1` | Sign + catalog the gamepad drivers (`pf-dualsense` + `pf-xusb`) from the same workspace build (`-SkipBuild`), one shared cert. |
+| `install-vbcable.ps1` | On-target: seed VB-Audio's cert into `TrustedPublisher`, silently install the bundled VB-CABLE (`-i -h`). Run by the installer's *Install VB-CABLE virtual audio* task; idempotent + always exits 0 (non-fatal). |
 | `clear-force-integrity.ps1` | Clear the `/INTEGRITYCHECK` PE bit so a self-signed driver loads (reused by every driver build). |
 | `stage-pf-vdisplay.ps1` | Stage the just-built pf-vdisplay bundle + fetch/verify the **pinned** nefcon release. |
 | `../../scripts/windows/web-run.cmd` | The `PunktfunkWeb` task action: loads the mgmt token + login password env, runs the bundled `bun` on the Nitro server (`:3000`). |

packaging/windows/drivers/.gitignore

@@ -0,0 +1 @@
+target

packaging/windows/drivers/pf-vdisplay/src/control.rs

@@ -133,9 +133,13 @@ unsafe fn add(request: WDFREQUEST) {
         complete(request, STATUS_INVALID_PARAMETER);
         return;
     }
-    let Some((target_id, luid_low, luid_high)) =
+    let Some((monitor_id, target_id, luid_low, luid_high)) = crate::monitor::create_monitor(
-        crate::monitor::create_monitor(req.session_id, req.width, req.height, req.refresh_hz)
+        req.session_id,
-    else {
+        req.width,
+        req.height,
+        req.refresh_hz,
+        req.preferred_monitor_id,
+    ) else {
         complete(request, STATUS_NOT_FOUND);
         return;
     };
@@ -143,7 +147,7 @@ unsafe fn add(request: WDFREQUEST) {
         adapter_luid_low: luid_low,
         adapter_luid_high: luid_high,
         target_id,
-        _reserved: 0,
+        resolved_monitor_id: monitor_id,
     };
     // SAFETY: `request` is the framework WDFREQUEST.
     unsafe { write_output_complete(request, &reply) };

packaging/windows/drivers/pf-vdisplay/src/monitor.rs

@@ -7,7 +7,7 @@
 use std::sync::Mutex;
 use std::time::{Duration, Instant};
 
-use wdk_sys::iddcx;
+use wdk_sys::{WDFOBJECT, call_unsafe_wdf_function_binding, iddcx};
 
 /// One resolution with the refresh rates it supports.
 #[derive(Clone)]
@@ -69,10 +69,23 @@ unsafe impl Send for MonitorObject {}
 /// heavy per-monitor resources on device removal is instead done explicitly ([`cleanup_for_device_removal`]).
 pub static MONITOR_MODES: Mutex<Vec<MonitorObject>> = Mutex::new(Vec::new());
 
+/// Lock [`MONITOR_MODES`], recovering the guard on poison instead of failing. DEFENSIVE ONLY: this driver
+/// workspace builds with `panic = "abort"` (packaging/windows/drivers/Cargo.toml), so a panic while the
+/// lock is held aborts the process WITHOUT unwinding — `MutexGuard::drop` never runs, the poison flag is
+/// never set, and `.lock()` can never return `Err`. The `into_inner()` arm is therefore currently
+/// unreachable; it is retained to consolidate the lock pattern and to stay correct if the panic strategy
+/// ever becomes `unwind` (the guarded data is a plain `Vec` with no cross-field invariant a half-completed
+/// panic could corrupt, so recovering the guard is sound). NOTE: this does NOT explain the observed ADD
+/// 0x80070490 wedge — that is ghost-monitor slot-budget exhaustion (the arrival-failure `WdfObjectDelete`
+/// teardown above + the host-side reap), not lock poisoning.
+fn lock_monitors() -> std::sync::MutexGuard<'static, Vec<MonitorObject>> {
+    MONITOR_MODES.lock().unwrap_or_else(|e| e.into_inner())
+}
+
 /// True if any virtual monitor currently exists — the host-gone watchdog only reaps when there's
 /// something to reap (see [`crate::control::start_watchdog`]).
 pub fn has_monitors() -> bool {
-    MONITOR_MODES.lock().map(|l| !l.is_empty()).unwrap_or(false)
+    !lock_monitors().is_empty()
 }
 
 /// Depart every monitor that has existed at least `grace` — the host-gone watchdog reap
@@ -85,9 +98,7 @@ pub fn reap_orphaned(grace: Duration) -> usize {
         Option<iddcx::IDDCX_MONITOR>,
         Option<crate::swap_chain_processor::SwapChainProcessor>,
     )> = {
-        let Ok(mut lock) = MONITOR_MODES.lock() else {
+        let mut lock = lock_monitors();
-            return 0;
-        };
         let mut taken = Vec::new();
         let mut i = 0;
         while i < lock.len() {
@@ -138,7 +149,8 @@ pub fn display_info(
     // Compute in u64 then saturate the u32 rational numerators: the old u32 `refresh*(h+4)^2` overflows
     // for a large mode (e.g. 8K@240), which panics→aborts the extern-"C" mode DDI in a debug build.
     // Identical for every real mode; only an absurd (also now bounds-rejected) mode saturates.
-    let clock_rate: u64 = u64::from(refresh_rate) * u64::from(height + 4) * u64::from(height + 4) + 1000;
+    let clock_rate: u64 =
+        u64::from(refresh_rate) * u64::from(height + 4) * u64::from(height + 4) + 1000;
     let clock_rate_u32 = u32::try_from(clock_rate).unwrap_or(u32::MAX);
     let mut si = pod_init!(wdk_sys::DISPLAYCONFIG_VIDEO_SIGNAL_INFO);
     si.pixelRate = clock_rate;
@@ -264,9 +276,7 @@ pub fn set_swap_chain_processor(
     object: iddcx::IDDCX_MONITOR,
     proc: crate::swap_chain_processor::SwapChainProcessor,
 ) -> Option<crate::swap_chain_processor::SwapChainProcessor> {
-    let Ok(mut lock) = MONITOR_MODES.lock() else {
+    let mut lock = lock_monitors();
-        return Some(proc);
-    };
     if let Some(m) = lock.iter_mut().find(|m| m.object == Some(object)) {
         m.swap_chain_processor.replace(proc)
     } else {
@@ -290,15 +300,17 @@ pub fn take_swap_chain_processor(
         .take()
 }
 
-/// `IOCTL_ADD`: create + arrive a virtual monitor at `width`x`height`@`refresh`. Returns the OS
+/// `IOCTL_ADD`: create + arrive a virtual monitor at `width`x`height`@`refresh` for `session_id`, naming it
-/// `(target_id, adapter_luid_low, adapter_luid_high)` for the [`AddReply`](pf_driver_proto::control::AddReply),
+/// by `preferred_id` (the host's per-client stable id; `0` = auto-allocate). Returns the resolved
-/// or `None` on failure (no adapter yet / IddCx error).
+/// `(monitor_id, target_id, adapter_luid_low, adapter_luid_high)` for the
+/// [`AddReply`](pf_driver_proto::control::AddReply), or `None` on failure (no adapter yet / IddCx error).
 pub fn create_monitor(
     session_id: u64,
     width: u32,
     height: u32,
     refresh: u32,
-) -> Option<(u32, u32, i32)> {
+    preferred_id: u32,
+) -> Option<(u32, u32, u32, i32)> {
     let adapter = crate::adapter::adapter()?;
     // Single identity per session (E1): if the host re-ADDs a still-live `session_id` (it shouldn't), depart
     // the stale monitor first, so one session maps to exactly one monitor (no duplicate EDID/target lingers).
@@ -307,7 +319,9 @@ pub fn create_monitor(
         .map(|l| l.iter().any(|m| m.session_id == session_id))
         .unwrap_or(false)
     {
-        dbglog!("[pf-vd] create_monitor: session {session_id} already live — departing the stale monitor");
+        dbglog!(
+            "[pf-vd] create_monitor: session {session_id} already live — departing the stale monitor"
+        );
         remove_monitor(session_id);
     }
     let mut modes = vec![Mode {
@@ -317,17 +331,17 @@ pub fn create_monitor(
     }];
     modes.extend(default_modes());
 
-    // Register the (pending) monitor so the mode DDIs can find it by EDID-serial id before arrival, under a
+    // Register the (pending) monitor so the mode DDIs can find it by EDID-serial id before arrival. The id
-    // REUSED id (the lowest not currently live). Reclaiming the id on REMOVE — instead of a monotonic
+    // seeds the EDID serial + IddCx ConnectorIndex + ContainerId — i.e. the monitor's OS IDENTITY. Honor the
-    // counter — keeps the connector index / EDID serial / container GUID bounded, so IddCx reuses the same
+    // host's per-client `preferred_id` when it is valid + not currently live, so a given client gets a
-    // OS target slot on a fresh ADD rather than leaving a ghost monitor node behind (the slot-exhaustion
+    // STABLE identity across reconnects (→ Windows reapplies its saved per-monitor DPI scaling); else fall
-    // wedge: sustained ADD/REMOVE churn eventually makes ADD fail 0x80070490 ERROR_NOT_FOUND). Allocated
+    // back to the lowest-free id (auto — the original slot-based behavior). A bounded reused id (vs a
-    // under the lock with the push so two concurrent ADDs can't pick the same id.
+    // monotonic counter) keeps IddCx reusing the same OS target slot rather than leaving a ghost monitor
+    // node behind (the slot-exhaustion wedge). Allocated under the lock with the push so two concurrent ADDs
+    // can't pick the same id.
     let id = {
-        let Ok(mut lock) = MONITOR_MODES.lock() else {
+        let mut lock = lock_monitors();
-            return None;
+        let id = resolve_id(&lock, preferred_id);
-        };
-        let id = alloc_monitor_id(&lock);
         lock.push(MonitorObject {
             object: None,
             id,
@@ -379,7 +393,8 @@ pub fn create_monitor(
         return None;
     }
     let monitor = create_out.MonitorObject;
-    if let Ok(mut lock) = MONITOR_MODES.lock() {
+    {
+        let mut lock = lock_monitors();
         if let Some(m) = lock.iter_mut().find(|m| m.id == id) {
             m.object = Some(monitor);
         }
@@ -391,6 +406,24 @@ pub fn create_monitor(
     let st = unsafe { wdk_iddcx::IddCxMonitorArrival(monitor, &mut arrival_out) };
     dbglog!("[pf-vd] IddCxMonitorArrival(id={id}) -> {st:#x}");
     if !wdk_iddcx::nt_success(st) {
+        // Arrival failed on a monitor we already CREATED. It must be torn down with `WdfObjectDelete`:
+        // `IddCxMonitorDeparture` is only valid for an ARRIVED monitor, so departing here would be a
+        // no-op that LEAKS the IddCx monitor object and permanently pins its slot against the adapter's
+        // `MaxMonitorsSupported` budget — the leak that, asymmetric with the create-failure path just
+        // above (which only reclaims the id, having no object to delete), accelerates the ADD 0x80070490
+        // wedge. Reclaim the id FIRST (drop the `MONITOR_MODES` entry that still holds this handle) so a
+        // concurrent `clear_all`/`reap_orphaned` can't grab + depart the handle we're about to delete,
+        // THEN delete the object — `monitor` is a local copy of the handle, valid across both.
+        dbglog!(
+            "[pf-vd] IddCxMonitorArrival(id={id}) FAILED — reclaiming the id + deleting the created monitor"
+        );
+        remove_by_id(id);
+        // SAFETY: `monitor` is the just-created (not-yet-arrived) IddCx monitor handle, now owned solely
+        // here (its `MONITOR_MODES` entry was just removed); `WdfObjectDelete` takes a `WDFOBJECT` (a raw
+        // handle cast, as in the swap-chain / device-cleanup teardowns).
+        unsafe {
+            call_unsafe_wdf_function_binding!(WdfObjectDelete, monitor as WDFOBJECT);
+        }
         return None;
     }
 
@@ -399,14 +432,15 @@ pub fn create_monitor(
         arrival_out.OsAdapterLuid.LowPart,
         arrival_out.OsAdapterLuid.HighPart,
     );
-    if let Ok(mut lock) = MONITOR_MODES.lock() {
+    {
+        let mut lock = lock_monitors();
         if let Some(m) = lock.iter_mut().find(|m| m.id == id) {
             m.target_id = target_id;
             m.adapter_luid_low = luid_low;
             m.adapter_luid_high = luid_high;
         }
     }
-    Some((target_id, luid_low, luid_high))
+    Some((id, target_id, luid_low, luid_high))
 }
 
 /// `IOCTL_REMOVE`: depart + drop the monitor for `session_id`. Returns true if one was removed.
@@ -415,9 +449,7 @@ pub fn remove_monitor(session_id: u64) -> bool {
     // (which RAII-joins its worker thread) only AFTER the lock guard is released — joining a worker
     // while holding `MONITOR_MODES` would head-block the whole control plane / risk a self-deadlock.
     let (monitor, processor) = {
-        let Ok(mut lock) = MONITOR_MODES.lock() else {
+        let mut lock = lock_monitors();
-            return false;
-        };
         let Some(pos) = lock.iter().position(|m| m.session_id == session_id) else {
             return false;
         };
@@ -441,9 +473,7 @@ pub fn clear_all() {
         Option<iddcx::IDDCX_MONITOR>,
         Option<crate::swap_chain_processor::SwapChainProcessor>,
     )> = {
-        let Ok(mut lock) = MONITOR_MODES.lock() else {
+        let mut lock = lock_monitors();
-            return;
-        };
         lock.drain(..)
             .map(|mut m| (m.object, m.swap_chain_processor.take()))
             .collect()
@@ -467,9 +497,7 @@ pub fn clear_all() {
 /// though the per-devnode WUDFHost (`ProcessSharingDisabled`) would also reap them when it exits.
 pub fn cleanup_for_device_removal() {
     let mut drained: Vec<Option<crate::swap_chain_processor::SwapChainProcessor>> = {
-        let Ok(mut lock) = MONITOR_MODES.lock() else {
+        let mut lock = lock_monitors();
-            return;
-        };
         lock.drain(..)
             .map(|mut m| m.swap_chain_processor.take())
             .collect()
@@ -483,8 +511,20 @@ pub fn cleanup_for_device_removal() {
 
 /// Drop a pending entry by id (create failed before arrival).
 fn remove_by_id(id: u32) {
-    if let Ok(mut lock) = MONITOR_MODES.lock() {
+    lock_monitors().retain(|m| m.id != id);
-        lock.retain(|m| m.id != id);
+}
+
+/// Resolve the id to name a new monitor by: honor the host's `preferred` per-client id when it is in the
+/// valid range (`1..=15`, so the IddCx `ConnectorIndex` = id stays `< MaxMonitorsSupported` = 16) AND not
+/// currently live (two live monitors MUST have distinct ids/connectors); otherwise fall back to
+/// [`alloc_monitor_id`] (auto, lowest-free). NEVER auto-departs a colliding live monitor — that would tear
+/// down an unrelated concurrent client — so the live-uniqueness invariant is preserved even against a host
+/// bug. `preferred == 0` (anonymous/TOFU/GameStream) always falls through to auto. Caller holds `MONITOR_MODES`.
+fn resolve_id(modes: &[MonitorObject], preferred: u32) -> u32 {
+    if (1..=15).contains(&preferred) && !modes.iter().any(|m| m.id == preferred) {
+        preferred
+    } else {
+        alloc_monitor_id(modes)
     }
 }
 

packaging/windows/install-vbcable.ps1

@@ -0,0 +1,97 @@
+<#
+.SYNOPSIS
+  Silently install the bundled VB-Audio Virtual Cable (the punktfunk virtual microphone) on the host.
+
+.DESCRIPTION
+  punktfunk pipes the streaming client's microphone into a virtual audio cable's render endpoint; the
+  cable's capture endpoint ("CABLE Output") then surfaces as a host microphone that games/apps record
+  from (see crates/punktfunk-host/src/audio/windows/wasapi_mic.rs). On a headless host there is no real
+  audio output, so a virtual cable is required. We bundle the OFFICIAL base VB-CABLE package (VB-Audio,
+  https://vb-cable.com) and install it unattended:
+
+    1. If a "CABLE Input"/"CABLE Output" endpoint already exists, do nothing (idempotent).
+    2. Pre-seed VB-Audio's Authenticode signing certificate (read from the bundled signed driver) into
+       LocalMachine\TrustedPublisher, so the kernel-driver-publisher prompt is suppressed and the
+       install is fully silent (required for the SYSTEM/Session-0 service install).
+    3. Run the official silent installer: VBCABLE_Setup_x64.exe -i -h  (arm64: the same exe name in the
+       arm64 package; x86 falls back to VBCABLE_Setup.exe).
+    4. Wait briefly for the audio subsystem to register the new endpoint.
+
+  VB-CABLE is donationware by VB-Audio Software, redistributed here under VB-Audio's bundling grant
+  (https://vb-audio.com/Services/licensing.htm); see {app}\licenses\VB-CABLE-NOTICE.txt. Only the base
+  single cable is bundled (A+B / C+D are not redistributable).
+
+  Best-effort: any failure is logged and returns a non-zero exit, but the caller (the installer) treats
+  it as non-fatal - the host still runs (mic passthrough then needs a manually-installed cable, and the
+  host falls back to auto-installing the Steam Streaming pair).
+
+.PARAMETER Dir
+  The staged VB-CABLE package directory (contains VBCABLE_Setup_x64.exe + the signed driver files).
+#>
+[CmdletBinding()]
+param(
+    [Parameter(Mandatory = $true)][string]$Dir
+)
+$ErrorActionPreference = 'Stop'
+$ProgressPreference = 'SilentlyContinue'
+
+function Test-CablePresent {
+    # An active render OR capture endpoint named "CABLE ..." means VB-CABLE is already installed.
+    $eps = Get-PnpDevice -Class AudioEndpoint -ErrorAction SilentlyContinue |
+        Where-Object { $_.Status -eq 'OK' -and $_.FriendlyName -match 'CABLE (Input|Output|In)' }
+    return [bool]$eps
+}
+
+if (Test-CablePresent) {
+    Write-Host 'VB-CABLE already installed (CABLE endpoint present) - skipping.'
+    exit 0
+}
+
+if (-not (Test-Path -LiteralPath $Dir)) { throw "VB-CABLE package dir not found: $Dir" }
+
+# Pick the silent installer for this architecture. The x64 package ships both; arm64 ships an arm64
+# VBCABLE_Setup_x64.exe (VB-Audio's naming); fall back to the 32-bit setup if that's all that's staged.
+$setup = $null
+foreach ($name in @('VBCABLE_Setup_x64.exe', 'VBCABLE_Setup.exe')) {
+    $p = Join-Path $Dir $name
+    if (Test-Path -LiteralPath $p) { $setup = $p; break }
+}
+if (-not $setup) { throw "no VBCABLE_Setup*.exe under $Dir" }
+Write-Host "VB-CABLE silent installer: $setup"
+
+# --- pre-seed VB-Audio's signing cert into LocalMachine\TrustedPublisher (unattended driver install) ---
+# Read the Authenticode signer from a bundled signed file (prefer a driver .sys/.cat; fall back to the
+# setup exe). Importing it into TrustedPublisher makes Windows install the signed driver with no prompt.
+try {
+    $signed = Get-ChildItem -LiteralPath $Dir -Recurse -Include '*.sys', '*.cat', '*.exe' -ErrorAction SilentlyContinue |
+        ForEach-Object { Get-AuthenticodeSignature -LiteralPath $_.FullName -ErrorAction SilentlyContinue } |
+        Where-Object { $_.Status -eq 'Valid' -and $_.SignerCertificate } |
+        Select-Object -First 1
+    if ($signed -and $signed.SignerCertificate) {
+        $store = New-Object System.Security.Cryptography.X509Certificates.X509Store('TrustedPublisher', 'LocalMachine')
+        $store.Open('ReadWrite')
+        $store.Add($signed.SignerCertificate)
+        $store.Close()
+        Write-Host "seeded VB-Audio cert into LocalMachine\TrustedPublisher (subject=$($signed.SignerCertificate.Subject))"
+    }
+    else {
+        Write-Warning 'no valid Authenticode signer found in the VB-CABLE package - the driver-publisher prompt may appear (install may stall under SYSTEM)'
+    }
+}
+catch {
+    Write-Warning "could not pre-seed the VB-Audio cert: $($_.Exception.Message)"
+}
+
+# --- run the official silent install: -i (install) -h (hidden) -----------------------------------
+# VB-Audio documents these switches; the process returns before the endpoint is fully registered.
+$proc = Start-Process -FilePath $setup -ArgumentList '-i', '-h' -Wait -PassThru -WindowStyle Hidden
+Write-Host "VBCABLE setup exit code: $($proc.ExitCode)"
+
+# Give the audio subsystem time to enumerate the new endpoint, then verify.
+for ($i = 0; $i -lt 10; $i++) {
+    Start-Sleep -Seconds 1
+    if (Test-CablePresent) { Write-Host 'VB-CABLE installed - CABLE endpoint present.'; exit 0 }
+}
+Write-Warning 'VB-CABLE setup ran but no CABLE endpoint appeared yet (a reboot may be required).'
+# Non-fatal: the device often appears after the next session/reboot; the host retries mic open with backoff.
+exit 0

packaging/windows/licenses/VB-CABLE-NOTICE.txt

@@ -0,0 +1,26 @@
+VB-CABLE Virtual Audio Device — Attribution
+===========================================
+
+The punktfunk host installer bundles and silently installs VB-CABLE, the virtual
+audio cable used as the streaming virtual microphone (the client's mic is written
+into VB-CABLE's input, and its "CABLE Output" capture endpoint surfaces as a host
+microphone that games and apps record from).
+
+  VB-CABLE is a product of VB-Audio Software.
+  Origin:  https://vb-cable.com  (https://vb-audio.com)
+  VB-CABLE is DONATIONWARE — all participations are welcome.
+  Please consider donating to VB-Audio if you find it useful:
+    https://vb-audio.com/Cable/
+
+VB-CABLE is redistributed here, unmodified (the official base VB-CABLE package),
+under VB-Audio's distribution grant for bundling the base cable with another
+application; see VB-Audio's licensing terms:
+    https://vb-audio.com/Services/licensing.htm
+
+Only the single base VB-CABLE is bundled. VB-CABLE A+B and C+D are not
+redistributed. VB-Audio retains all rights to VB-CABLE; punktfunk claims no
+ownership of it.
+
+To remove VB-CABLE, use its own uninstaller (VBCABLE_Setup_x64.exe -u -h) or the
+"VB-Audio Virtual Cable" entry in Windows "Apps & features"; uninstalling the
+punktfunk host does not remove VB-CABLE.

packaging/windows/pack-host-installer.ps1

@@ -28,6 +28,7 @@ param(
     [string]$FfmpegDir = $env:FFMPEG_DIR,                           # bundle its bin\*.dll (amf-qsv build)
     [string]$WebDir = $env:WEB_OUTPUT_DIR,                          # built web .output tree -> bundle the mgmt console
     [string]$BunExe = $env:BUN_EXE,                                # portable bun.exe runtime for the console
+    [string]$VbCableDir = $env:VBCABLE_DIR,                         # official base VB-CABLE package -> bundle the virtual mic
     [switch]$NoDriver,                                              # build without the bundled pf-vdisplay driver
     [switch]$NoSign                                                 # skip signing (local debug)
 )
@@ -189,6 +190,29 @@ if (-not $NoDriver) {
     Write-Host "==> built + staged gamepad UMDF drivers -> $gpStage"
 }
 
+# --- stage the official base VB-CABLE package (the streaming virtual microphone) --------------
+# VB-CABLE is the virtual audio cable the host writes the client's mic into (its capture endpoint then
+# surfaces as a host microphone). We bundle + silently install the OFFICIAL base VB-CABLE package
+# (VB-Audio donationware, redistributed under VB-Audio's bundling grant - see the VB-CABLE notice added
+# to the licenses payload). The package binary is NOT in the repo (it's a signed third-party blob,
+# shipped intact); supply it via -VbCableDir / $env:VBCABLE_DIR pointing at the extracted official
+# package (must contain VBCABLE_Setup_x64.exe). Absent -> installer built WITHOUT the bundled cable; the
+# host then auto-installs the Steam Streaming pair as a fallback and mic passthrough needs a manual cable.
+if ($VbCableDir -and (Test-Path $VbCableDir) -and (Get-ChildItem -Path $VbCableDir -Filter 'VBCABLE_Setup*.exe' -ErrorAction SilentlyContinue)) {
+    $vbStage = Join-Path $OutDir 'vbcable'
+    if (Test-Path $vbStage) { Remove-Item -Recurse -Force $vbStage }
+    New-Item -ItemType Directory -Force -Path $vbStage | Out-Null
+    Copy-Item (Join-Path $VbCableDir '*') $vbStage -Recurse -Force
+    # The on-target installer script (seeds VB-Audio's cert into TrustedPublisher, runs -i -h) ships
+    # alongside the package so it's extracted to the same {tmp}\vbcable dir.
+    Copy-Item (Join-Path $here 'install-vbcable.ps1') $vbStage -Force
+    $defines += "/DAudioCableStageDir=$vbStage"
+    # Attribution: VB-Audio's bundling grant requires we surface VB-CABLE's origin + donationware status.
+    Copy-Item (Join-Path $here 'licenses\VB-CABLE-NOTICE.txt') -Destination $licStage -Force
+    Write-Host "==> bundling VB-CABLE (virtual mic) from $VbCableDir -> $vbStage"
+}
+else { Write-Host "no -VbCableDir/`$env:VBCABLE_DIR (or no VBCABLE_Setup*.exe in it) -> installer built WITHOUT the bundled VB-CABLE virtual mic" }
+
 # --- stage the FFmpeg shared DLLs (AMD/Intel AMF/QSV build) ------------------------------------
 # A host built with --features amf-qsv link-imports avcodec/avutil/swscale/... so the shared DLLs
 # MUST sit next to the exe (it won't start otherwise). Bundle them from $FfmpegDir\bin - the same

packaging/windows/punktfunk-host.iss

@@ -41,6 +41,12 @@
 #ifdef GamepadStageDir
   #define WithGamepad
 #endif
+; AudioCableStageDir (the official base VB-CABLE package + install-vbcable.ps1) is optional - present
+; when the VB-CABLE package was supplied to the packer. It is the streaming virtual microphone; on a
+; headless host (no real audio output) a virtual cable is required for mic + desktop-audio passthrough.
+#ifdef AudioCableStageDir
+  #define WithAudioCable
+#endif
 ; FfmpegBin (a dir of FFmpeg shared DLLs) is optional - present when the host is built with
 ; --features amf-qsv (the AMD/Intel AMF/QSV encode backend link-imports the FFmpeg libs).
 #ifdef FfmpegBin
@@ -93,6 +99,9 @@ Name: "installdriver"; Description: "Install the pf-vdisplay virtual display dri
 #ifdef WithGamepad
 Name: "installgamepad"; Description: "Install the virtual gamepad drivers (DualSense / DualShock 4 / Xbox 360 - no ViGEmBus needed)"
 #endif
+#ifdef WithAudioCable
+Name: "installaudiocable"; Description: "Install VB-CABLE virtual audio (microphone passthrough - VB-Audio donationware, www.vb-cable.com)"
+#endif
 #ifdef WithVkLayer
 Name: "installhdrlayer"; Description: "Install the HDR Vulkan layer (lets Vulkan games like Doom use HDR on the virtual display)"
 #endif
@@ -132,6 +141,10 @@ Source: "{#StageDir}\*"; DestDir: "{tmp}\pfvdisplay"; Flags: deleteafterinstall
 ; The built-from-source UMDF gamepad drivers + install-gamepad-drivers.ps1, extracted to {tmp}, removed after.
 Source: "{#GamepadStageDir}\*"; DestDir: "{tmp}\gamepad"; Flags: deleteafterinstall recursesubdirs createallsubdirs; Tasks: installgamepad
 #endif
+#ifdef WithAudioCable
+; The official base VB-CABLE package + install-vbcable.ps1, extracted to {tmp}, removed after install.
+Source: "{#AudioCableStageDir}\*"; DestDir: "{tmp}\vbcable"; Flags: deleteafterinstall recursesubdirs createallsubdirs; Tasks: installaudiocable
+#endif
 #ifdef WithVkLayer
 ; The HDR Vulkan implicit layer (cdylib + its JSON manifest) laid into {app}\vklayer and registered
 ; below. The manifest's library_path is ".\pf_vkhdr_layer.dll" (relative to the JSON), so the two
@@ -160,6 +173,15 @@ Filename: "{app}\punktfunk-host.exe"; Parameters: "driver install --gamepad --di
   StatusMsg: "Installing the virtual gamepad drivers..."; \
   Flags: runhidden waituntilterminated; Tasks: installgamepad
 #endif
+#ifdef WithAudioCable
+; Silently install the bundled VB-CABLE (the streaming virtual microphone). Best-effort: install-vbcable.ps1
+; always exits 0 (a missing cable just disables mic passthrough; the host falls back + retries), so a
+; cable hiccup never fails the whole install.
+Filename: "powershell.exe"; \
+  Parameters: "-NoProfile -ExecutionPolicy Bypass -File ""{tmp}\vbcable\install-vbcable.ps1"" -Dir ""{tmp}\vbcable"""; \
+  StatusMsg: "Installing VB-CABLE virtual audio (microphone passthrough)..."; \
+  Flags: runhidden waituntilterminated; Tasks: installaudiocable
+#endif
 ; Register (or re-point, on upgrade - idempotent) the SYSTEM service from its FINAL {app} location:
 ; service install records current_exe() as the SCM binPath, so it must run from {app}, not {tmp}.
 Filename: "{app}\punktfunk-host.exe"; Parameters: "service install"; WorkingDir: "{app}"; \

web/web-run.cmd

@@ -0,0 +1,46 @@
+@echo off
+rem punktfunk web console launcher - DEV layout (in-repo tree). The PunktfunkWeb scheduled task
+rem (boot trigger, SYSTEM, restart-on-failure) runs this at startup. It sources the host's mgmt bearer
+rem token + the console login password from %ProgramData%\punktfunk\, points the /api proxy at the
+rem host's loopback HTTPS mgmt API, and runs the self-contained (no-node_modules) Nitro server on :3000.
+rem %~dp0 = <repo>\web\ .
+rem
+rem DEV vs the installed launcher (scripts\windows\web-run.cmd): the dev host service runs from
+rem target\release (not the installed {app} tree), so this runs the in-repo web\.output with the
+rem system node instead of {app}\bun\bun.exe + {app}\web\.output. Rebuild after a web change with
+rem `bun run build` in web\ ; no edit needed here.
+setlocal EnableExtensions
+
+set "PFDATA=%ProgramData%\punktfunk"
+set "TOKENFILE=%PFDATA%\mgmt-token"
+set "PWFILE=%PFDATA%\web-password"
+
+rem The host's `serve` writes the mgmt token on first run. Until it exists the proxy has no credential,
+rem so fail and let the task's restart-on-failure retry (mirrors the installed launcher / Linux unit).
+if not exist "%TOKENFILE%" (
+  echo [punktfunk-web] mgmt token not present yet at "%TOKENFILE%" - waiting for the host service.
+  exit /b 1
+)
+
+rem Both files are single KEY=VALUE lines: PUNKTFUNK_MGMT_TOKEN=... and PUNKTFUNK_UI_PASSWORD=... .
+rem Split on the first '=' and import each into the environment.
+for /f "usebackq tokens=1* delims==" %%A in ("%TOKENFILE%") do set "%%A=%%B"
+if exist "%PWFILE%" for /f "usebackq tokens=1* delims==" %%A in ("%PWFILE%") do set "%%A=%%B"
+
+rem Fixed deployment wiring (the Windows analogue of scripts/punktfunk-web.service).
+set "PORT=3000"
+set "HOST=0.0.0.0"
+set "PUNKTFUNK_MGMT_URL=https://127.0.0.1:47990"
+set "NODE_TLS_REJECT_UNAUTHORIZED=0"
+
+set "NODE=C:\Users\Public\node-v22.11.0-win-x64\node.exe"
+set "SERVER=%~dp0.output\server\index.mjs"
+if not exist "%NODE%" (
+  echo [punktfunk-web] node runtime missing at "%NODE%".
+  exit /b 1
+)
+if not exist "%SERVER%" (
+  echo [punktfunk-web] built server missing at "%SERVER%" - build it: cd web ^&^& bun run build
+  exit /b 1
+)
+"%NODE%" "%SERVER%"