perf(capture): slice 8 — buffer ring + paste-cache Epoch; gen2 visibility (take-11 spikes)

Take 11 (c10ce06c) validated the off-UI architecture: typical frames land
work ~10ms + wait ~6.8ms = 16.7 exactly on the deadline; 212/300 best yet.
The ENTIRE remaining gap is periodic 35-65ms render spikes that WORSENED
across the take (189 -> 147) — the signature of gen2 GC pauses. Biggest
churner is structural: the screen capture minted a fresh ~8.3MB byte[] per
DWM frame (~500MB/s of LOH), a producer OBS never does (it owns fixed
surface pools).

- ScreenCaptureFrameSource: 4-deep buffer ring with size-matched slots (a
  <=17ms consumer cannot be lapped at 60Hz) + reused downscale row scratch.
- VideoFrame.Epoch: monotonic per producer frame. The paste cache keys on
  array IDENTITY, so recycled arrays MUST be distinguished — epoch joins the
  PasteKey. Producers handing fresh arrays leave it 0 (key unchanged effect).
- Stats print 'gen2 +N' per 5s window: next take acquits or convicts GC
  without another guess (rule: prove the stage).
- Test (the ONE): PasteCache_RecycledArrayWithNewEpoch_ReRasterizes_NotStaleHits
  — same array, new content, bumped epoch; fails on the old key by
  construction. 37/37 compositor/pump, clean build.
- Next suspect if gen2 stays hot: the 10Hz WebView2 capture (full-canvas PNG
  decode + fresh arrays on the UI thread) — recorded, untouched.

Creator audio ask queued in the same working session (+40% post-mix master
gain before the -1dBFS limiter) lands as its own commit next.

HANDOFF.md

@@ -60,12 +60,24 @@ RealApp boot-smoke. Scope-check passed.
    `avg wait` so render+submit+wait ≈ period (accounting closed — nothing can hide). Webcam now
    routes through the paste cache too (bypass re-sampled 156k px even between identical device
    frames). 52/52 per-class green, clean build 0 warnings, committed this slice.
-4. **Take 11 (user, ~30s record-only):** read the superscript; expect `≈300/300 frames, wait ≈ the true remainder, worst render` now visible. If ~300: playback must be honest 1x — saga CLOSED, Unit B starts. If still ~250-280 with worst-render spikes: raster-miss spikes (web capture ~ every second) — next slice is pre-rasterizing on content change rather than on first-tick-after-change (cache the miss behind a swap-in). If wait is STILL large: the context theory was wrong and I have egg to eat — re-instrument, don't guess.
+4. **Take 11 ran + slice 8 (2026-09-04, committed with the audio unit below):** off-UI loop
-   ~22, wait ~0-3` — honest 60fps IF render+submit ≤ ~16.7. If wait is near zero and n/300 sits at
+   WORKED — typical frames land exactly on the deadline (work ~10 + wait ~6.8 = 16.7; 212/300).
-   ~200, the remaining gap is pure render 22ms → next slice = per-phase compositor timing (the stats
+   Remaining gap = periodic 35-65ms spikes growing across the take = gen2 GC pauses; the capture
-   can split blit phases the same way they split resolve; that is the honest path, not a guess).
+   path minted a fresh ~8.3MB byte[] per DWM frame (~500MB/s LOH). Slice 8: 4-deep buffer ring
-   If take 10 lands at ~300/300 → recording saga CLOSED.
+   in ScreenCaptureFrameSource (size-matched slots, reused row scratch) + `VideoFrame.Epoch`
-5. **Unit B — the top bar + session logic (user spec 2026-09-04 re-sent twice + decisions settled in Q&A):**
+   joins the paste-cache key so recycled arrays can never false-hit + `gen2 +N` per stats window
+   (suspect-or-acquit — never guess at the tail again). Test `PasteCache_RecycledArrayWithNewEpoch_
+   ReRasterizes_NotStaleHits` fails on the old key by construction. 37/37 compositor/pump green.
+4b. **AUDIO (creator ask 2026-09-04):** post-mix volume up ~40% — constant master gain applied
+   in AudioMixer.FillAndMix BEFORE the −1 dBFS limiter (limiter still owns the ceiling: the
+   gain can't add clipping, it just makes the limiter bind sooner on hot material). If the
+   creator reports pumping on loud game audio → the constant is the tuning knob (or per-input
+   defaults need raising instead — discuss with data).
+5. **Take 12 (user, ~30s record + talk):** stats: `gen2 +N` should be ~0-1/window, `worst render`
+   → ~16-20ms, n/300 → 300; playback honest speed; file audio ~40% hotter than before. If gen2
+   still >2/window: next suspect is the 10Hz WebView2 capture (full-canvas PNG decode + fresh
+   arrays on the UI thread) — throttle or move it, cited pattern first.
+6. **Unit B — the top bar + session logic (user spec 2026-09-04 re-sent twice + decisions settled in Q&A):**
    - Two-line top bar. Line 1: center = REC + **LIVE** pills (text renamed from ON-AIR; pills become
      mutually-exclusive RADIOS — record-OR-stream ruling), right = avatar + **Login/Logout** button
      (no account status light). Line 2: centered primary **Start** (grayed while NO pill armed —

Services/Compositor/SceneCompositor.cs

@@ -19,10 +19,11 @@ public sealed class SceneCompositor
     // chat/web/image layers are identical frame after frame. Same shape as OBS (the
     // source surface is cached, the compositor blits): a scaled/round-clipped/mirrored
     // layer rasterizes once and is pasted (row-copy/blend) on every later tick.
-    // Keyed by the SOURCE FRAME IDENTITY — every producer (capture, webcam, chat
+    // Keyed by the SOURCE FRAME IDENTITY (array + Epoch) — producers hand out fresh
-    // renderer, web capture, static cache) hands out immutable byte[], so "same pixels
+    // immutable byte[], or recycled-ring arrays whose monotonic Epoch distinguishes
-    // array + same target rect" ⇒ same raster. Bounds-checked eviction clears wholesale.
+    // each generation (screen capture, take-11 fix), so "same array+epoch + same
-    private sealed record PasteKey(byte[] Pixels, int SrcW, int SrcH, int DstW, int DstH, bool Round, bool Mirror);
+    // target rect" ⇒ same raster. Bounds-checked eviction clears wholesale.
+    private sealed record PasteKey(byte[] Pixels, long Epoch, int SrcW, int SrcH, int DstW, int DstH, bool Round, bool Mirror);
     private static readonly Dictionary<PasteKey, VideoFrame> _pasteCache = new();
     private static readonly object _pasteGate = new();
     private const int MaxPasteEntries = 48;
@@ -284,7 +285,7 @@ public sealed class SceneCompositor
         VideoFrame? raster = null;
         lock (_pasteGate)
         {
-            key = new PasteKey(frame.BgraPixels, frame.Width, frame.Height, dw, dh, isRound, mirror);
+            key = new PasteKey(frame.BgraPixels, frame.Epoch, frame.Width, frame.Height, dw, dh, isRound, mirror);
             _pasteCache.TryGetValue(key, out raster);
         }
 

Services/ScreenCaptureFrameSource.cs

@@ -30,6 +30,18 @@ public sealed class ScreenCaptureFrameSource : IScreenCaptureSource
     private bool _framePending;
     private DateTime _lastErrorLog = DateTime.MinValue;
 
+    // Buffer recycling (take-11 spikes, 2026-09-04): a fresh ~8.3MB byte[] per DWM
+    // frame ≈ 500MB/s of LOH churn — the gen2 pauses it forces surfaced as the
+    // "worst render 35-65ms" spikes that capped fps at ~42 long after the compositor
+    // itself was fast. A 4-deep ring rotated round-robin is never lapped by a
+    // ≤17ms consumer at 60Hz; each hand-out carries an Epoch so identity-keyed
+    // consumers (the compositor's paste cache) cannot false-hit a recycled array.
+    private readonly byte[]?[] _frameRing = new byte[4][];
+    private int _ringNext;
+    private long _epoch;
+    private byte[]? _row0;
+    private byte[]? _row1;
+
     // The composition master frame (see ai.md "Resolution tiers"): the background
     // is an input layer, so we never hold a CPU frame bigger than the master.
     private const int MaxBackgroundWidth = 1920;
@@ -157,7 +169,26 @@ public sealed class ScreenCaptureFrameSource : IScreenCaptureSource
         }
     }
 
-    private static VideoFrame CopyToVideoFrame(SoftwareBitmap bitmap)
+    private byte[] RentRingBuffer(int size)
+    {
+        for (var tries = 0; tries < _frameRing.Length; tries++)
+        {
+            var idx = (_ringNext + tries) % _frameRing.Length;
+            var buf = _frameRing[idx];
+            if (buf is { Length: var len } && len == size)
+            {
+                _ringNext = (idx + 1) % _frameRing.Length;
+                return buf;
+            }
+        }
+        var slot = _ringNext;
+        _ringNext = (slot + 1) % _frameRing.Length;
+        var fresh = new byte[size];
+        _frameRing[slot] = fresh;
+        return fresh;
+    }
+
+    private VideoFrame CopyToVideoFrame(SoftwareBitmap bitmap)
     {
         var sw = bitmap.PixelWidth;
         var sh = bitmap.PixelHeight;
@@ -178,21 +209,23 @@ public sealed class ScreenCaptureFrameSource : IScreenCaptureSource
             var dw = Math.Max(1, (int)(sw * scale));
             var dh = Math.Max(1, (int)(sh * scale));
             // DWM delivers an opaque surface (alpha 255); bilinear keeps it 255.
-            return new VideoFrame(dw, dh, DownscaleBgra(data, sw, sh, srcStride, dw, dh)) { IsOpaque = true };
+            var scaled = RentRingBuffer(dw * dh * 4);
+            return new VideoFrame(dw, dh, DownscaleBgra(data, sw, sh, srcStride, dw, dh, scaled))
+                { IsOpaque = true, Epoch = ++_epoch };
         }
 
-        var pixels = new byte[count];
+        var pixels = RentRingBuffer(count);
         Marshal.Copy(data, pixels, 0, pixels.Length);
-        return new VideoFrame(sw, sh, pixels) { IsOpaque = true };
+        return new VideoFrame(sw, sh, pixels) { IsOpaque = true, Epoch = ++_epoch };
     }
 
     // Bilinear downscale to the master frame. Reads each source row pair through
     // Marshal.Copy (no unsafe), writing tightly packed BGRA output.
-    private static byte[] DownscaleBgra(IntPtr src, int sw, int sh, int srcStride, int dw, int dh)
+    private byte[] DownscaleBgra(IntPtr src, int sw, int sh, int srcStride, int dw, int dh, byte[] dst)
     {
-        var row0 = new byte[srcStride];
+        // Row scratch is per-capture-thread and reused across frames (same churn lesson).
-        var row1 = new byte[srcStride];
+        var row0 = _row0 != null && _row0.Length >= srcStride ? _row0 : (_row0 = new byte[srcStride]);
-        var dst = new byte[dw * dh * 4];
+        var row1 = _row1 != null && _row1.Length >= srcStride ? _row1 : (_row1 = new byte[srcStride]);
         var xs = sw / (double)dw;
         var ys = sh / (double)dh;
 

Services/VideoFrame.cs

@@ -13,6 +13,13 @@ public sealed class VideoFrame
     public byte[] BgraPixels { get; }
     public int Stride => Width * 4;
 
+    /// <summary>Producer frame epoch — a monotonically increasing number stamped by
+    /// sources that RECYCLE their pixel buffers (the screen-capture ring, take-11 spike
+    /// fix). Consumers that key caches on buffer identity (the compositor's paste cache)
+    /// MUST include it, or a recycled array false-hits with stale content. Producers
+    /// that hand out fresh arrays per frame leave it 0 — identity alone is then enough.</summary>
+    public long Epoch { get; init; }
+
     /// <summary>Producer contract: every alpha byte in <see cref="BgraPixels"/> is 255
     /// (DWM capture surfaces and MediaCapture video carry no alpha — the OS fills 255).
     /// Lets the compositor take a straight-copy fast path for a full-canvas opaque

ai.md

@@ -794,6 +794,18 @@ seam:** `Func<Scene?>`, `Func<SceneElement, VideoFrame?>` resolver, `Func<Compos
   (the ONE — inline-pumping SyncContext proves continuations never return to the starting thread) +
   70/70. Take 9 verdict: wait ≈ true remainder (period → 16.7, n → ~300); `worst render` names any
   remaining raster-miss spikes; render+submit+wait still == period — the accounting holds.
+- **Slice 8 — capture buffer ring + paste-cache Epoch (take 11, 2026-09-04):** take 11 validated
+  the architecture — typical frames now land `work ~10ms + wait ~6.8ms = 16.7`, exactly the deadline
+  (212/300). The whole remaining gap is PERIODIC 35-65ms worst-render spikes that worsened across
+  the take (189→147 frames/5s) — the signature of gen2 GC pauses, now provable via `gen2 +N` in
+  every stats window. Biggest churn was structural: `ScreenCaptureFrameSource` minted a fresh
+  ~8.3MB `byte[]` per DWM frame (~500MB/s LOH). It now rotates a 4-deep ring (a ≤17ms consumer can
+  never be lapped at 60Hz), size-matched per slot, with reused downscale row scratch. Recycled
+  arrays would poison the paste cache (it keys on array IDENTITY), so `VideoFrame.Epoch` —
+  monotonic per producer frame, 0 for fresh-array producers — joins the key. Regression test
+  `PasteCache_RecycledArrayWithNewEpoch_ReRasterizes_NotStaleHits` fails on the old key by
+  construction. Next suspect if gen2 stays hot: the 10Hz WebView2 capture loop (full-canvas PNG
+  decode + fresh arrays on the UI thread) — recorded as follow-up, untouched this slice.
 - **Stop ordering matters:** `StopAsync` stops the encoder (closes stdin → EOF → ffmpeg finalizes+exits)
   **before** awaiting the loop, because closing stdin unblocks a write stuck on pipe backpressure — the
   reverse order would deadlock. `ProcessFailed` self-stops the pump. `Failed` while live flips

ytLive.Tests/SceneCompositorTests.cs

@@ -211,6 +211,49 @@ public class SceneCompositorTests
         AssertColor(third, 101, 101, 255, 0, 0);
     }
 
+    /// <summary>The ONE integration test for the capture buffer ring + paste-cache epoch
+    /// (take-11 spike fix): a recycled capture buffer hands out the SAME byte[] with
+    /// different content; only VideoFrame.Epoch can keep the paste cache honest. Without
+    /// the epoch in the key, frame 2 false-hits frame 1's raster and the recording shows
+    /// stale pixels for as long as the array keeps cycling — the exact bug this pins.</summary>
+    [Fact]
+    public void PasteCache_RecycledArrayWithNewEpoch_ReRasterizes_NotStaleHits()
+    {
+        var pixels = new byte[64 * 32 * 4];
+        for (var i = 0; i < pixels.Length; i += 4)
+        {
+            pixels[i] = 0; pixels[i + 1] = 0; pixels[i + 2] = 255; pixels[i + 3] = 255; // red
+        }
+        var gen1 = new VideoFrame(64, 32, pixels) { IsOpaque = true, Epoch = 1 };
+
+        var webcam = new WebcamSceneConfig { X = 4, Y = 4, Width = 32, Height = 16 };
+        var scene = new Scene { Name = "Live" };
+        scene.Elements.Add(webcam);
+        var options = new CompositorOptions
+        {
+            SourceRectX = 0, SourceRectY = 0, SourceRectWidth = 128, SourceRectHeight = 64,
+            OutputWidth = 128, OutputHeight = 64,
+        };
+
+        var compositor = new SceneCompositor();
+        var out1 = compositor.Render(scene, _ => gen1, null, options);
+        AssertColor(out1, 20, 12, 255, 0, 0);
+
+        // Generation 2: the SAME array, new content, bumped epoch (what the capture
+        // ring does 60 times a second).
+        for (var i = 0; i < pixels.Length; i += 4)
+        {
+            pixels[i] = 0; pixels[i + 1] = 255; pixels[i + 2] = 0; pixels[i + 3] = 255; // green
+        }
+        var gen2 = new VideoFrame(64, 32, pixels) { IsOpaque = true, Epoch = 2 };
+        var out2 = compositor.Render(scene, _ => gen2, null, options);
+        AssertColor(out2, 20, 12, 0, 255, 0); // a stale hit would still be red
+
+        // And the same epoch twice still hits the cache (idempotent paste).
+        var out3 = compositor.Render(scene, _ => gen2, null, options);
+        Assert.Equal(out2.BgraPixels, out3.BgraPixels);
+    }
+
     [Fact]
     public void Render_VerticalTier_Outputs_1080x1920_From_The_Center_Crop()
     {