feat(apple): PyroWave Phase 5 — native Metal decode on Mac / Apple TV / iPad (§4.7)

The Apple client now decodes PyroWave natively on the presenter's own MTLDevice — no MoltenVK, no upstream C++ in the app. Completes and wires up the decoder whose early working-tree snapshot rode along in 9127c346: - MetalWaveletShaders.swift: wavelet_dequant + idwt hand-ported from the vendored GLSL (STORAGE_MODE 0 only; subgroup scans → 32-wide simdgroups; DCShift spec constant → function constant; precision-1 split: fp16 levels 0-1 / fp32 2-4). - MetalWaveletDecoder.swift: Swift reimplementation of push_packet/decode_packet incl. the Phase-4 chunk-aligned window walk (FRAG chains, zeroed missing shards, the >half-blocks partial rule), init_block_meta's block-index space, and the 42-dequant + 13-idwt dispatch structure with encoder-boundary barriers. SOF-dims changes rebuild the size-dependent resources, which is also the mid-stream resize path. Ring of 4 output plane sets on the presenter's queue. - Presenter: pf_frag_planar (3xR8, the planar_csc.frag twin) + renderPlanar with a shared present tail; ReadyFrame carries an image enum (.video | .planar). - Stage2Pipeline: a dedicated PyroWave pump — no VideoToolbox machinery, no keyframe/re-anchor recovery (all-intra; partials render as localized blur by design), newest-frame-index staleness guard for late partials. - Opt-in: "PyroWave (wired LAN)" codec entry (probe-gated, ≈A13 floor via a real kernel-compile probe), selecting it advertises + prefers the codec and forces the session SDR (HDR/10-bit/4:4:4 caps dropped, plan contract). - Core ABI: punktfunk_connection_shard_payload() — the Welcome's negotiated shard payload, needed by native decoders to walk chunk-aligned AUs. - Validation: golden fixtures generated by the host encoder + upstream's own decoder (pyrowave_dump_golden, RTX 5070 Ti); the Metal decode PSNR-matches at 77-88 dB across all planes for dense AND chunk-aligned AUs, and a hole-punched partial still decodes. Parser unit tests cover the window walk, FRAG chains, broken chains, the half-blocks gate, and the block-index layout. Tests: apple 134 green (mac; iOS/tvOS build), host 312 w/ pyrowave on .21, core 148 w/ quic; clippy/fmt clean. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-15 12:16:43 +02:00
parent a70811043e
commit 739a5f76bf
28 changed files with 826 additions and 81 deletions
@@ -337,9 +337,15 @@ public final class PunktfunkConnection {
    public private(set) var resolvedAudioChannels: UInt8 = 2

    /// The video codec the host resolved for this session (`Welcome.codec`, `PUNKTFUNK_CODEC_*`):
-    /// `2` = HEVC (default / older host), `1` = H.264, `4` = AV1. Build the decoder from THIS. The
-    /// resolved value honors the client's `preferredCodec` when the host could emit it.
+    /// `2` = HEVC (default / older host), `1` = H.264, `4` = AV1, `8` = PyroWave (only when this
+    /// client opted in). Build the decoder from THIS. The resolved value honors the client's
+    /// `preferredCodec` when the host could emit it.
    public private(set) var resolvedCodec: UInt8 = 2 // PUNKTFUNK_CODEC_HEVC
+
+    /// The session's negotiated wire shard payload (`Welcome.shard_payload`, bytes) — the
+    /// parse-window size for `USER_FLAG_CHUNK_ALIGNED` PyroWave AUs (plan §4.4). Other codecs
+    /// never need it.
+    public private(set) var shardPayload: UInt32 = 1408
    /// The resolved codec as a `VideoCodec` (H.264 / HEVC / AV1) — drives the bitstream framing
    /// (Annex-B NAL parsing vs the AV1 OBU repack).
    public var videoCodec: VideoCodec { VideoCodec(wire: resolvedCodec) }
@@ -452,6 +458,9 @@ public final class PunktfunkConnection {
        var codec: UInt8 = 2 // PUNKTFUNK_CODEC_HEVC
        _ = punktfunk_connection_codec(handle, &codec)
        resolvedCodec = codec
+        var shard: UInt32 = 1408
+        _ = punktfunk_connection_shard_payload(handle, &shard)
+        shardPayload = shard
    }

    /// A bandwidth speed-test measurement (see `startSpeedTest`). Partial until `done`.
@@ -790,6 +799,15 @@ public final class PunktfunkConnection {
    public static let codecH264: UInt8 = UInt8(PUNKTFUNK_CODEC_H264)
    public static let codecHEVC: UInt8 = UInt8(PUNKTFUNK_CODEC_HEVC)
    public static let codecAV1: UInt8 = UInt8(PUNKTFUNK_CODEC_AV1)
+    /// PyroWave (opt-in wired-LAN wavelet codec, 8-bit SDR): the host only ever resolves it
+    /// when the client both advertises the bit AND names it `preferredCodec` — never
+    /// auto-selected. Decoded by the Metal wavelet decoder, not VideoToolbox.
+    public static let codecPyroWave: UInt8 = UInt8(PUNKTFUNK_CODEC_PYROWAVE)
+
+    /// `AccessUnit.flags` bit: the AU is shard-aligned self-delimiting chunks (the wire's
+    /// `USER_FLAG_CHUNK_ALIGNED`, PyroWave datagram-aligned mode §4.4) — walk it
+    /// window-by-window at `shardPayload`. (The C `#define` doesn't import into Swift.)
+    public static let userFlagChunkAligned: UInt32 = 64

    /// Static HDR mastering metadata (SMPTE ST.2086 + content light level) the host sent for an HDR
    /// session. Mirrors the wire/ABI `PunktfunkHdrMeta`; primaries are in ST.2086 **G, B, R** order,
@@ -27,8 +27,10 @@ public enum DefaultsKey {
    /// Requested audio channel count: 2 (stereo), 6 (5.1) or 8 (7.1). The host clamps to what it
    /// can capture; the resolved count drives the in-core decode + AVAudioEngine layout.
    public static let audioChannels = "punktfunk.audioChannels"
-    /// Preferred video codec: `"auto"` (host decides), `"hevc"`, or `"h264"`. A soft preference —
-    /// the host emits it when it can, else falls back. Drives the decoder via `Welcome.codec`.
+    /// Preferred video codec: `"auto"` (host decides), `"hevc"`, `"h264"`, `"av1"`, or
+    /// `"pyrowave"` (the opt-in wired-LAN wavelet codec — picking it advertises AND prefers it,
+    /// and forces the session SDR). A soft preference — the host emits it when it can, else
+    /// falls back. Drives the decoder via `Welcome.codec`.
    public static let codec = "punktfunk.codec"
    public static let micEnabled = "punktfunk.micEnabled"
    public static let speakerUID = "punktfunk.speakerUID"
@@ -543,19 +543,24 @@ public enum AV1 {

 extension VideoCodec {
    /// Codec-dispatching format-description refresh: the AV1 path keys on an in-band sequence
-    /// header, the NAL codecs on in-band parameter sets — one call site in each pump.
+    /// header, the NAL codecs on in-band parameter sets — one call site in each pump. PyroWave
+    /// has no CoreMedia representation at all (its pump feeds the Metal wavelet decoder raw).
    public func formatDescription(fromKeyframe au: Data) -> CMVideoFormatDescription? {
-        self == .av1
-            ? AV1.formatDescription(fromKeyframe: au)
-            : AnnexB.formatDescription(fromIDR: au, codec: self)
+        switch self {
+        case .av1: return AV1.formatDescription(fromKeyframe: au)
+        case .pyrowave: return nil
+        default: return AnnexB.formatDescription(fromIDR: au, codec: self)
+        }
    }

    /// Codec-dispatching sample wrap (see `formatDescription(fromKeyframe:)`).
    public func sampleBuffer(
        au: AccessUnit, format: CMVideoFormatDescription
    ) -> CMSampleBuffer? {
-        self == .av1
-            ? AV1.sampleBuffer(au: au, format: format)
-            : AnnexB.sampleBuffer(au: au, format: format, codec: self)
+        switch self {
+        case .av1: return AV1.sampleBuffer(au: au, format: format)
+        case .pyrowave: return nil
+        default: return AnnexB.sampleBuffer(au: au, format: format, codec: self)
+        }
    }
 }
@@ -26,12 +26,18 @@ public enum VideoCodec: Equatable {
    case h264
    case hevc
    case av1
+    /// PyroWave wavelet (opt-in wired-LAN low-latency codec): not a NAL/OBU codec and not
+    /// VideoToolbox-decoded at all — the Metal wavelet decoder consumes the raw AUs
+    /// (Stage2Pipeline's PyroWave pump). Only ever resolved when this client both advertised
+    /// and preferred it.
+    case pyrowave

    /// Resolve from the wire `Welcome.codec` byte (`PUNKTFUNK_CODEC_*`; unknown → HEVC).
    public init(wire: UInt8) {
        switch wire {
        case 0x01: self = .h264 // PUNKTFUNK_CODEC_H264
        case 0x04: self = .av1 // PUNKTFUNK_CODEC_AV1
+        case 0x08: self = .pyrowave // PUNKTFUNK_CODEC_PYROWAVE
        default: self = .hevc // PUNKTFUNK_CODEC_HEVC — the default / older-host codec
        }
    }
@@ -147,8 +153,8 @@ public enum AnnexB {
            sets = [vps, sps, pps]
        case .h264:
            sets = [sps, pps]
-        case .av1:
-            return nil // OBU stream, no parameter-set NALs — handled in AV1.swift, never here
+        case .av1, .pyrowave:
+            return nil // no parameter-set NALs — dispatched in AV1.swift, never reaches here
        }

        var format: CMVideoFormatDescription?
@@ -184,8 +190,8 @@ public enum AnnexB {
                    parameterSetSizes: sizes,
                    nalUnitHeaderLength: 4,
                    formatDescriptionOut: &format)
-            case .av1:
-                break // unreachable — the .av1 arm above already returned
+            case .av1, .pyrowave:
+                break // unreachable — the arm above already returned
            }
        }
        return status == noErr ? format : nil
@@ -149,6 +149,28 @@ fragment float4 pf_frag(VOut in [[stage_in]],
    return float4(sampleRgb(lumaTex, chromaTex, in.uv, csc), 1.0);
 }

+// PyroWave planar SDR: three separate R8 planes (Y full-res, Cb/Cr half-res 4:2:0) from the
+// Metal wavelet decoder — the Metal twin of pf-presenter's planar_csc.frag. Same bicubic luma
+// and left-cosited chroma correction as the biplanar path (chromaUV self-disables at 4:4:4).
+fragment float4 pf_frag_planar(VOut in [[stage_in]],
+                               texture2d<float> lumaTex [[texture(0)]],
+                               texture2d<float> cbTex [[texture(1)]],
+                               texture2d<float> crTex [[texture(2)]],
+                               constant CscUniform& csc [[buffer(0)]]) {
+    constexpr sampler s(filter::linear, address::clamp_to_edge);
+#ifdef PF_BILINEAR_LUMA
+    float lumaY = lumaTex.sample(s, in.uv).r;
+#else
+    float lumaY = catmullRomLuma(lumaTex, s, in.uv);
+#endif
+    float2 cuv = chromaUV(lumaTex, cbTex, in.uv);
+    float3 yuv = float3(lumaY, cbTex.sample(s, cuv).r, crTex.sample(s, cuv).r);
+    float3 rgb = saturate(float3(dot(csc.r0.xyz, yuv) + csc.r0.w,
+                                 dot(csc.r1.xyz, yuv) + csc.r1.w,
+                                 dot(csc.r2.xyz, yuv) + csc.r2.w));
+    return float4(rgb, 1.0);
+}
+
 // HDR: 10-bit P010 / 4:4:4 (BT.2020, PQ-encoded Y′CbCr) → full-range PQ R′G′B′, output as-is —
 // the CAMetalLayer's itur_2100_PQ colour space + edrMetadata tell the compositor the samples are
 // PQ, so it does the PQ→display tone-map. No EOTF here. The rows fold in the exact 10-bit
@@ -215,8 +237,16 @@ public final class MetalVideoPresenter {
    /// tvOS only: the in-shader PQ→SDR tone-map fallback (pf_frag_hdr_tv → bgra8), used whenever
    /// the display is composited without HDR headroom — see `setDisplayHeadroom`. nil elsewhere.
    private let pipelineHDRToneMap: MTLRenderPipelineState?
+    /// PyroWave's 3-plane SDR path (pf_frag_planar → bgra8) — see `renderPlanar`.
+    private let pipelinePlanar: MTLRenderPipelineState
    private var textureCache: CVMetalTextureCache?

+    /// The PyroWave Metal decoder records on the presenter's device + queue: one device means
+    /// decode, CSC and present share textures with zero interop, and one queue means Metal's
+    /// hazard tracking orders a ring-slot rewrite after the render still sampling it.
+    var metalDevice: MTLDevice { device }
+    var metalQueue: MTLCommandQueue { queue }
+
    /// Current layer configuration — switched in `configure(hdr:)` when a frame's HDR-ness differs.
    /// Render-thread confined once the pipeline runs (Stage2Pipeline.start's one pre-thread
    /// `configure` call is ordered before the thread starts, so it doesn't race).
@@ -258,6 +288,7 @@ public final class MetalVideoPresenter {
        let pipelineSDR: MTLRenderPipelineState
        let pipelineHDR: MTLRenderPipelineState
        let pipelineHDRToneMap: MTLRenderPipelineState?
+        let pipelinePlanar: MTLRenderPipelineState
        do {
            // DEBUG A/B lever: PUNKTFUNK_BILINEAR_LUMA=1 compiles the shader with Catmull-Rom OFF
            // (plain bilinear luma) by prepending a #define ahead of the source. Default (unset) is
@@ -292,6 +323,11 @@ public final class MetalVideoPresenter {
            #else
            pipelineHDRToneMap = nil
            #endif
+            let planar = MTLRenderPipelineDescriptor()
+            planar.vertexFunction = vtx
+            planar.fragmentFunction = library.makeFunction(name: "pf_frag_planar")
+            planar.colorAttachments[0].pixelFormat = .bgra8Unorm // PyroWave is 8-bit SDR
+            pipelinePlanar = try device.makeRenderPipelineState(descriptor: planar)
        } catch {
            return nil
        }
@@ -331,12 +367,14 @@ public final class MetalVideoPresenter {

        return MetalVideoPresenter(
            device: device, queue: queue, pipelineSDR: pipelineSDR, pipelineHDR: pipelineHDR,
-            pipelineHDRToneMap: pipelineHDRToneMap, textureCache: textureCache, layer: layer)
+            pipelineHDRToneMap: pipelineHDRToneMap, pipelinePlanar: pipelinePlanar,
+            textureCache: textureCache, layer: layer)
    }

    private init(
        device: MTLDevice, queue: MTLCommandQueue, pipelineSDR: MTLRenderPipelineState,
        pipelineHDR: MTLRenderPipelineState, pipelineHDRToneMap: MTLRenderPipelineState?,
+        pipelinePlanar: MTLRenderPipelineState,
        textureCache: CVMetalTextureCache, layer: CAMetalLayer
    ) {
        self.device = device
@@ -344,6 +382,7 @@ public final class MetalVideoPresenter {
        self.pipelineSDR = pipelineSDR
        self.pipelineHDR = pipelineHDR
        self.pipelineHDRToneMap = pipelineHDRToneMap
+        self.pipelinePlanar = pipelinePlanar
        self.textureCache = textureCache
        self.layer = layer
    }
@@ -514,6 +553,67 @@ public final class MetalVideoPresenter {
                pixelBuffer, plane: 1, format: tenBit ? .rg16Unorm : .rg8Unorm, cache: textureCache)
        else { return false }

+        #if os(tvOS)
+        // HDR splits by the display's headroom (kept in step with the layer by `configure` above):
+        // PQ passthrough into an HDR-composited display, the tone-map shader otherwise.
+        let hdrPipeline = hdrPassthroughActive ? pipelineHDR : (pipelineHDRToneMap ?? pipelineHDR)
+        let pipeline = hdrActive ? hdrPipeline : pipelineSDR
+        #else
+        let pipeline = hdrActive ? pipelineHDR : pipelineSDR
+        #endif
+        let decodedSize = CGSize(
+            width: CVPixelBufferGetWidth(pixelBuffer), height: CVPixelBufferGetHeight(pixelBuffer))
+        return encodePresent(
+            decodedSize: decodedSize, targetFromLayout: targetFromLayout, pipeline: pipeline,
+            presentAtMediaTime: presentAtMediaTime, onPresented: onPresented,
+            // Hold the CVMetalTextures + source pixel buffer (its IOSurface) alive until the GPU
+            // finishes sampling — releasing them at scope exit could free the backing mid-read.
+            keepAlive: [luma, chroma, pixelBuffer]
+        ) { encoder in
+            encoder.setFragmentTexture(CVMetalTextureGetTexture(luma), index: 0)
+            encoder.setFragmentTexture(CVMetalTextureGetTexture(chroma), index: 1)
+            encoder.setFragmentBytes(&csc, length: MemoryLayout<CscUniform>.stride, index: 0)
+        }
+    }
+
+    /// Draw one PyroWave planar frame (three R8 planes off the Metal wavelet decoder) and
+    /// present it. RENDER THREAD, same contract as `render` — PyroWave is 8-bit SDR, so the
+    /// layer always takes the plain SDR config, and the CSC rows arrive precomputed from the
+    /// stream's own sequence-header signaling (no CVPixelBuffer to inspect).
+    @discardableResult
+    func renderPlanar(
+        _ planes: WaveletPlanes,
+        presentAtMediaTime: CFTimeInterval? = nil,
+        onPresented: ((Int64?) -> Void)? = nil
+    ) -> Bool {
+        stagingLock.lock()
+        let targetFromLayout = drawableTarget
+        stagingLock.unlock()
+        configure(hdr: false)
+        var csc = planes.csc
+        return encodePresent(
+            decodedSize: CGSize(width: planes.width, height: planes.height),
+            targetFromLayout: targetFromLayout, pipeline: pipelinePlanar,
+            presentAtMediaTime: presentAtMediaTime, onPresented: onPresented,
+            // The ring textures stay valid by ring depth; retaining them here also pins the
+            // slot's set until the sample completes (mirrors the biplanar keep-alive).
+            keepAlive: [planes.y, planes.cb, planes.cr]
+        ) { encoder in
+            encoder.setFragmentTexture(planes.y, index: 0)
+            encoder.setFragmentTexture(planes.cb, index: 1)
+            encoder.setFragmentTexture(planes.cr, index: 2)
+            encoder.setFragmentBytes(&csc, length: MemoryLayout<CscUniform>.stride, index: 0)
+        }
+    }
+
+    /// The shared present tail of `render`/`renderPlanar`: size the drawable, encode one
+    /// fullscreen triangle with `pipeline` (`bind` supplies the fragment resources), schedule
+    /// the present and the on-glass callback.
+    private func encodePresent(
+        decodedSize: CGSize, targetFromLayout: CGSize, pipeline: MTLRenderPipelineState,
+        presentAtMediaTime: CFTimeInterval?, onPresented: ((Int64?) -> Void)?,
+        keepAlive: [Any], bind: (MTLRenderCommandEncoder) -> Void
+    ) -> Bool {
        // Size the drawable to the LAYER's pixels (its laid-out frame × contentsScale, pushed here by
        // SessionPresenter.layout via `setDrawableTarget` — not read off the layer, whose geometry the
        // main thread owns) so the Catmull-Rom shader performs the decoded→on-screen scale in one pass:
@@ -522,8 +622,6 @@ public final class MetalVideoPresenter {
        // Before the first layout (zero target) fall back to the decoded size. drawableSize does NOT
        // track bounds (defaults to 0), so set it BEFORE nextDrawable; re-set only on a change
        // (layout / Reconfigure / HDR flip — and every frame of a live resize, which is fine).
-        let decodedSize = CGSize(
-            width: CVPixelBufferGetWidth(pixelBuffer), height: CVPixelBufferGetHeight(pixelBuffer))
        let targetSize = (targetFromLayout.width > 0 && targetFromLayout.height > 0)
            ? targetFromLayout : decodedSize
        if layer.drawableSize != targetSize { layer.drawableSize = targetSize }
@@ -542,17 +640,8 @@ public final class MetalVideoPresenter {
        guard let encoder = commandBuffer.makeRenderCommandEncoder(descriptor: pass) else {
            return false
        }
-        #if os(tvOS)
-        // HDR splits by the display's headroom (kept in step with the layer by `configure` above):
-        // PQ passthrough into an HDR-composited display, the tone-map shader otherwise.
-        let hdrPipeline = hdrPassthroughActive ? pipelineHDR : (pipelineHDRToneMap ?? pipelineHDR)
-        encoder.setRenderPipelineState(hdrActive ? hdrPipeline : pipelineSDR)
-        #else
-        encoder.setRenderPipelineState(hdrActive ? pipelineHDR : pipelineSDR)
-        #endif
-        encoder.setFragmentTexture(CVMetalTextureGetTexture(luma), index: 0)
-        encoder.setFragmentTexture(CVMetalTextureGetTexture(chroma), index: 1)
-        encoder.setFragmentBytes(&csc, length: MemoryLayout<CscUniform>.stride, index: 0)
+        encoder.setRenderPipelineState(pipeline)
+        bind(encoder)
        encoder.drawPrimitives(type: .triangle, vertexStart: 0, vertexCount: 3)
        encoder.endEncoding()
        if let onPresented {
@@ -580,9 +669,8 @@ public final class MetalVideoPresenter {
        } else {
            commandBuffer.present(drawable)
        }
-        // Hold the CVMetalTextures + source pixel buffer (its IOSurface) alive until the GPU finishes
-        // sampling — releasing them at scope exit could free the backing mid-read.
-        commandBuffer.addCompletedHandler { _ in _ = (luma, chroma, pixelBuffer) }
+        // Keep the bound sources alive until the GPU finishes sampling (see the callers).
+        commandBuffer.addCompletedHandler { _ in _ = keepAlive }
        commandBuffer.commit()
        return true
    }
@@ -183,18 +183,12 @@ enum WaveletBitstream {
            }
            return state.pushPackets(UnsafeBufferPointer(start: base, count: count))
        }
-        guard ok, var frame = state.finish() else { return nil }
+        guard ok, let frame = state.finish() else { return nil }
        // Upstream decode_is_ready(allow_partial=true): with no SOF the frame is undecodable;
        // at half the blocks or fewer it is presumed garbage.
        guard frame.totalBlocks > 0, frame.decodedBlocks > frame.totalBlocks / 2 else {
            return nil
        }
-        // The dequant kernel indexes the offset table by the LAYOUT's block space; the wire's
-        // total_blocks only counts blocks the encoder emitted. They agree for a full-coverage
-        // frame, but size the table by the layout.
-        if frame.offsets.count != frame.layout.blockCount32 {
-            frame.offsets = Array(frame.offsets.prefix(frame.layout.blockCount32))
-        }
        return frame
    }

@@ -293,17 +287,17 @@ enum WaveletBitstream {

 /// One decoded frame's output planes, handed to the presenter's planar render path. The
 /// textures belong to the decoder's ring — ring depth (4) plus same-queue hazard tracking keep
-/// them valid while referenced.
-struct WaveletPlanes {
-    let y: MTLTexture
-    let cb: MTLTexture
-    let cr: MTLTexture
-    let csc: CscUniform
-    var width: Int { y.width }
-    var height: Int { y.height }
+/// them valid while referenced. Public because it rides inside `ReadyImage`.
+public struct WaveletPlanes: @unchecked Sendable {
+    public let y: MTLTexture
+    public let cb: MTLTexture
+    public let cr: MTLTexture
+    public let csc: CscUniform
+    public var width: Int { y.width }
+    public var height: Int { y.height }
 }

-final class MetalWaveletDecoder {
+public final class MetalWaveletDecoder {
    /// Matches the Vulkan client's ring: deep enough that a slot is never rewritten while the
    /// presenter still samples it in practice; same-queue hazard tracking is the hard backstop.
    private static let ringDepth = 4
@@ -312,7 +306,7 @@ final class MetalWaveletDecoder {
    /// dequant kernel needs simdgroup prefix sums with its 16 header lanes inside one
    /// simdgroup, so compile the real kernels once and check the pipeline facts. Apple6 (A13)
    /// and every Mac2 device pass the family check; the compile probe is authoritative.
-    static let supported: Bool = {
+    public static let supported: Bool = {
        guard let device = MTLCreateSystemDefaultDevice() else { return false }
        guard device.supportsFamily(.apple6) || device.supportsFamily(.mac2) else { return false }
        do {
@@ -358,6 +352,12 @@ final class MetalWaveletDecoder {
    private var slots: [Slot] = []
    private var nextSlot = 0

+    /// The current geometry (from the last SOF that built the resources) — the pump reports
+    /// decoded-size changes to the resize overlay from this. PUMP THREAD.
+    var decodedSize: (width: Int, height: Int)? {
+        layout.map { ($0.width, $0.height) }
+    }
+
    /// The pump thread owns `decode`; everything mutable is confined to it.
    init?(device: MTLDevice, queue: MTLCommandQueue) {
        self.device = device
@@ -37,6 +37,7 @@
 #if canImport(Metal) && canImport(QuartzCore)
 import AVFoundation
 import Foundation
+import Metal
 import QuartzCore

 /// PUNKTFUNK_PRESENT_DEBUG=1: the render thread prints a once-per-second line with the decode
@@ -257,6 +258,7 @@ public final class Stage2Pipeline {
    /// the pipeline's lifetime; SessionPresenter resolves it per session (see PresentPacing).
    private let pacing: PresentPacing
    private let endToEndMeter: LatencyMeter?
+    private let decodeMeter: LatencyMeter?
    private let displayMeter: LatencyMeter?
    private let recovery = KeyframeRecovery()
    /// Post-loss freeze-until-reanchor gate (shared core policy via the C ABI). Created here seeded 0;
@@ -306,6 +308,7 @@ public final class Stage2Pipeline {
        self.presenter = presenter
        self.pacing = pacing
        self.endToEndMeter = endToEndMeter
+        self.decodeMeter = decodeMeter
        self.displayMeter = displayMeter
        let ring = ring
        let recovery = recovery
@@ -362,7 +365,21 @@ public final class Stage2Pipeline {
        let presenter = presenter
        let pumpStopped = pumpStopped
        let reanchorGate = gate
-        let thread = Thread {
+        // PyroWave rides a different decode half: no CMFormatDescription/VideoToolbox machinery
+        // (a wavelet AU has no parameter sets), no keyframe recovery or re-anchor freeze (the
+        // stream is all-intra and Phase 4's partial delivery WANTS lossy frames on glass as
+        // localized blur, not a freeze). The ready ring, render thread, pacing and meters are
+        // shared unchanged.
+        let thread: Thread
+        if connection.videoCodec == .pyrowave {
+            thread = Self.makePyroWavePump(
+                connection: connection, token: token, pumpStopped: pumpStopped,
+                ring: ring, renderSignal: renderSignal,
+                device: presenter.metalDevice, queue: presenter.metalQueue,
+                decodeMeter: decodeMeter,
+                onFrame: onFrame, onSessionEnd: onSessionEnd, onDecodedSize: onDecodedSize)
+        } else {
+            thread = Thread {
            defer { pumpStopped.signal() } // let stop() join the pump (bounded) before decoder.reset()
            var format: CMVideoFormatDescription?
            // Report coded dims to the resize overlay only on a CHANGE (new-mode IDR), not per
@@ -445,6 +462,7 @@ public final class Stage2Pipeline {
                }
                }
            }
+            }
        }
        thread.name = "punktfunk-stage2-pump"
        thread.qualityOfService = .userInteractive
@@ -504,9 +522,7 @@ public final class Stage2Pipeline {
                let presentAt = vsyncEnabled
                    ? vsyncClock.nextVsync(after: CACurrentMediaTime()) : nil
                let renderStarted = CACurrentMediaTime()
-                let rendered = presenter.render(
-                    frame.pixelBuffer, isHDR: frame.isHDR, presentAtMediaTime: presentAt
-                ) { presentedNs in
+                let onGlass: (Int64?) -> Void = { presentedNs in
                    // Stage-3: the flip reached glass (or was dropped) — free the present slot,
                    // then re-signal so the freshest waiting ring frame goes out immediately.
                    if let gate {
@@ -525,6 +541,18 @@ public final class Stage2Pipeline {
                    displayMeter?.record(ptsNs: UInt64(frame.decodedNs), atNs: atNs, offsetNs: 0)
                    debugStats?.presented(atNs: presentedNs)
                }
+                // One present tail, two decode sources: the VideoToolbox biplanar buffer or the
+                // PyroWave Metal planes — the ring, pacing and meters are agnostic to which.
+                let rendered: Bool
+                switch frame.image {
+                case .video(let pixelBuffer, let isHDR):
+                    rendered = presenter.render(
+                        pixelBuffer, isHDR: isHDR, presentAtMediaTime: presentAt,
+                        onPresented: onGlass)
+                case .planar(let planes):
+                    rendered = presenter.renderPlanar(
+                        planes, presentAtMediaTime: presentAt, onPresented: onGlass)
+                }
                debugStats?.renderReturned(
                    ok: rendered, tookMs: (CACurrentMediaTime() - renderStarted) * 1000)
                if !rendered {
@@ -592,6 +620,93 @@ public final class Stage2Pipeline {
        renderSignal.signal() // wake the render thread so it can observe the stop and exit
    }

+    /// The PyroWave pump: AUs go straight into the Metal wavelet decoder (no VideoToolbox, no
+    /// format descriptions), decoded planes ride the same ready ring / render thread. All-intra
+    /// stream, so none of the VT pump's recovery machinery applies: keyframe/RFI requests are
+    /// silenced host-side for this codec, and a lossy (partial-delivery) frame is MEANT to
+    /// present as localized blur — never a freeze. Static + capture-by-parameter for the same
+    /// reason the VT pump avoids capturing `self` (a missed stop must not leak a live pipeline).
+    private static func makePyroWavePump(
+        connection: PunktfunkConnection, token: StopFlag, pumpStopped: DispatchSemaphore,
+        ring: ReadyRing, renderSignal: DispatchSemaphore,
+        device: MTLDevice, queue: MTLCommandQueue,
+        decodeMeter: LatencyMeter?,
+        onFrame: (@Sendable (AccessUnit) -> Void)?,
+        onSessionEnd: (@Sendable () -> Void)?,
+        onDecodedSize: (@Sendable (Int, Int) -> Void)?
+    ) -> Thread {
+        // The chunk-aligned parse window = the session's negotiated shard payload (Welcome);
+        // the 64-byte floor mirrors the Rust client's guard against a nonsense value.
+        let windowSize = max(64, Int(connection.shardPayload))
+        return Thread {
+            defer { pumpStopped.signal() }
+            // Compiles the two compute kernels on the session's first frames' thread — ~tens of
+            // ms, once per session. Failure = this device can't run the negotiated codec (the
+            // advertisement probe should have prevented this); end the session cleanly.
+            guard let decoder = MetalWaveletDecoder(device: device, queue: queue) else {
+                if !token.isStopped { onSessionEnd?() }
+                return
+            }
+            // Newest decoded frame index — a late partial (the reassembler's 30 ms fuse can
+            // deliver one behind a newer complete frame) must not travel back in time.
+            var newestIndex: UInt32?
+            var lastDims: (w: Int, h: Int)?
+            var alive = true
+            while alive, !token.isStopped {
+                alive = autoreleasepool { () -> Bool in
+                    do {
+                        guard let au = try connection.nextAU(timeoutMs: 100) else { return true }
+                        onFrame?(au)
+                        if let newest = newestIndex,
+                           Int32(bitPattern: au.frameIndex &- newest) <= 0 {
+                            return true // stale (or duplicate) frame — skip
+                        }
+                        guard !token.isStopped else { return true }
+                        let chunkAligned =
+                            au.flags & PunktfunkConnection.userFlagChunkAligned != 0
+                        let ptsNs = au.ptsNs
+                        let receivedNs = au.receivedNs
+                        let flags = au.flags
+                        let submitted = decoder.decode(
+                            au: au.data, chunkAligned: chunkAligned, windowSize: windowSize
+                        ) { planes in
+                            // Metal completed-handler thread — stamp + enqueue, don't block
+                            // (the exact contract of the VT output callback).
+                            guard let planes else { return }
+                            var ts = timespec()
+                            clock_gettime(CLOCK_REALTIME, &ts)
+                            let decodedNs =
+                                Int64(ts.tv_sec) * 1_000_000_000 + Int64(ts.tv_nsec)
+                            decodeMeter?.record(
+                                ptsNs: UInt64(receivedNs), atNs: decodedNs, offsetNs: 0)
+                            ring.submit(
+                                ReadyFrame(
+                                    ptsNs: ptsNs, receivedNs: receivedNs, decodedNs: decodedNs,
+                                    image: .planar(planes), flags: flags))
+                            renderSignal.signal()
+                        }
+                        if submitted {
+                            newestIndex = au.frameIndex
+                            // Decoded-size changes come from the SOF dims (this is also how a
+                            // mid-stream Reconfigure lands here) — report like the VT pump.
+                            if let size = decoder.decodedSize,
+                               lastDims?.w != size.width || lastDims?.h != size.height {
+                                lastDims = (size.width, size.height)
+                                onDecodedSize?(size.width, size.height)
+                            }
+                        }
+                        // A dropped AU (malformed / SOF lost / too few blocks) is just skipped:
+                        // every PyroWave frame is independently decodable, the next one heals.
+                        return true
+                    } catch {
+                        if !token.isStopped { onSessionEnd?() }
+                        return false // session closed
+                    }
+                }
+            }
+        }
+    }
+
    /// Convert a `CADisplayLink.targetTimestamp` (CACurrentMediaTime basis) to a `CLOCK_REALTIME`
    /// nanosecond instant — the present clock the AU pts + skew offset live in. Projects to the target
    /// present time (when the frame is actually on glass), not the moment we drew.
@@ -12,7 +12,23 @@ import CoreVideo
 import Foundation
 import VideoToolbox

-/// One decoded frame waiting to be presented. Owns a retained `CVPixelBuffer` until shown.
+/// A decoded frame's pixels — which present path they take. VideoToolbox codecs deliver a
+/// biplanar `CVPixelBuffer` (NV12/P010/444v/x444); the PyroWave Metal decoder delivers three
+/// separate R8 plane textures straight off its compute pass (there is no CVPixelBuffer — the
+/// planes never leave the GPU).
+public enum ReadyImage: @unchecked Sendable {
+    /// 8-bit NV12 / 4:4:4 biplanar (SDR) or 10-bit P010 / x444 (HDR), Metal-compatible.
+    /// `isHDR` = the stream is BT.2020 PQ and the presenter must configure EDR output.
+    case video(CVPixelBuffer, isHDR: Bool)
+    #if canImport(Metal)
+    /// PyroWave planar output (Y full-res + Cb/Cr half-res, 8-bit SDR) with its precomputed
+    /// CSC rows — presented by `MetalVideoPresenter.renderPlanar`.
+    case planar(WaveletPlanes)
+    #endif
+}
+
+/// One decoded frame waiting to be presented. Owns its image (a retained `CVPixelBuffer`, or
+/// the PyroWave ring textures) until shown.
 public struct ReadyFrame: @unchecked Sendable {
    /// Host capture clock (the AU's pts), in nanoseconds.
    public let ptsNs: UInt64
@@ -22,15 +38,26 @@ public struct ReadyFrame: @unchecked Sendable {
    public let receivedNs: Int64
    /// Client `CLOCK_REALTIME` instant decode completed, in nanoseconds.
    public let decodedNs: Int64
-    /// The decoded image — 8-bit NV12 biplanar (SDR) or 10-bit P010 biplanar (HDR), Metal-compatible.
-    public let pixelBuffer: CVPixelBuffer
-    /// True when the stream is HDR (BT.2020 PQ): the buffer is 10-bit P010 and the presenter must
-    /// configure EDR + BT.2020 PQ output. Derived from the decoded buffer's pixel format.
-    public let isHDR: Bool
+    /// The decoded image and which present path it takes.
+    public let image: ReadyImage
    /// The AU's wire `user_flags` (`AccessUnit.flags`), threaded through the decode via the frame
    /// context so the re-anchor gate can classify this decoded frame (IDR / RFI anchor / recovery
    /// mark) at present time — the async decode callback has no other access to it. 0 when unknown.
    public let flags: UInt32
+
+    /// The VideoToolbox path's buffer; nil for a PyroWave planar frame. (Kept as the accessor
+    /// the decode round-trip tests assert against.)
+    public var pixelBuffer: CVPixelBuffer? {
+        if case .video(let buffer, _) = image { return buffer }
+        return nil
+    }
+
+    /// Whether this frame presents on the HDR path. PyroWave planar frames are 8-bit SDR by
+    /// contract.
+    public var isHDR: Bool {
+        if case .video(_, let hdr) = image { return hdr }
+        return false
+    }
 }

 /// Per-frame context threaded through the VideoToolbox frame refcon: the AU's receipt instant (for
@@ -286,6 +313,6 @@ public final class VideoDecoder: @unchecked Sendable {
        onDecoded(
            ReadyFrame(
                ptsNs: ptsNs, receivedNs: receivedNs, decodedNs: decodedNs,
-                pixelBuffer: imageBuffer, isHDR: isHDR, flags: flags))
+                image: .video(imageBuffer, isHDR: isHDR), flags: flags))
    }
 }