LlamaCasty/Services/WebView2Manager.cs

using System;
using System.Drawing;
using System.IO;
using System.Text.Json;
using System.Windows;
using System.Windows.Controls;
using System.Windows.Media;
using System.Windows.Media.Imaging;
using System.Windows.Threading;
using Microsoft.Web.WebView2.Core;
using Microsoft.Web.WebView2.Wpf;
using ytLive.Helpers;
using ytLive.Models;

namespace ytLive.Services;

public sealed class WebView2Manager : IDisposable
{
    private readonly Panel _hostPanel;
    private readonly Dispatcher _dispatcher;
    private readonly Dictionary<string, WebSourceSession> _sessions = new();

    public event Action<string, WriteableBitmap>? PreviewBitmapChanged;

    private sealed class WebSourceSession
    {
        public required WebView2 Control { get; init; }
        public required DispatcherTimer CaptureTimer { get; init; }
        public VideoFrame? LatestFrame;
        public bool Disposed;
        public bool Initialized;

        // Buffer reuse (2026-09-04): every capture tick used to mint a fresh
        // 8.3MB canvas array + a fresh crop array (~83MB/s of LOH at 10Hz →
        // gen2 pauses surfaced as the pump's 35-40ms "worst render" spikes).
        // CanvasScratch is reused while the size holds. The frame handed to the
        // compositor is always the FULL canvas (transparent margins reveal layers
        // beneath); the crop is only for the preview WriteableBitmap. Epoch is
        // monotonic per canvas generation (identity-keyed consumers see each frame).
        public byte[]? CanvasScratch;
        public readonly byte[]?[] OutRing = new byte[8][];
        public int OutRingNext;
        public long Epoch;
        public WriteableBitmap? PreviewBitmap;

        public byte[] RentOutBuffer(int size)
        {
            for (var tries = 0; tries < OutRing.Length; tries++)
            {
                var idx = (OutRingNext + tries) % OutRing.Length;
                var buf = OutRing[idx];
                if (buf != null && buf.Length == size)
                {
                    OutRingNext = (idx + 1) % OutRing.Length;
                    return buf;
                }
            }
            var slot = OutRingNext;
            OutRingNext = (slot + 1) % OutRing.Length;
            var fresh = new byte[size];
            OutRing[slot] = fresh;
            return fresh;
        }
    }

    public WebView2Manager(Panel hostPanel, Dispatcher dispatcher)
    {
        _hostPanel = hostPanel;
        _dispatcher = dispatcher;
    }

    public void Register(Source source)
    {
        if (_sessions.ContainsKey(source.Id)) return;

        // OBS model: the page renders at the MASTER CANVAS size (1920×1080),
        // stable, never tracked. Full-bleed widgets (designed for the canvas)
        // render fully instead of being clipped to a small box-sized viewport;
        // dragging the box never reflows the page. The capture is tightly
        // cropped to the widget's ALPHA bounding box (FindContentBounds) and
        // the display (Stretch=Fill) maps it flush under the box, anchored at
        // (0,0) — no DOM query, so no timing fragility; worst case is the
        // full frame, which is the confirmed-good rendering.
        var webView = new WebView2
        {
            Width = 1920,
            Height = 1080,
            DefaultBackgroundColor = System.Drawing.Color.Transparent,
            Visibility = System.Windows.Visibility.Visible,
        };
        Canvas.SetLeft(webView, -5000);
        Canvas.SetTop(webView, -5000);

        _hostPanel.Children.Add(webView);

        var timer = new DispatcherTimer
        {
            Interval = TimeSpan.FromMilliseconds(100),
        };

        var session = new WebSourceSession
        {
            Control = webView,
            CaptureTimer = timer,
        };

        _sessions[source.Id] = session;

        timer.Tick += (_, _) =>
        {
            if (!session.Disposed && session.Initialized)
                _ = CaptureFrame(source.Id);
        };

        _ = InitializeAsync(source, session);
    }

    public void Unregister(string sourceId) => RemoveSession(sourceId);

    public void OnWebUriChanged(Source source)
    {
        if (!_sessions.TryGetValue(source.Id, out var session)) return;
        if (session.Disposed || !session.Initialized) return;

        if (string.IsNullOrEmpty(source.WebUri))
        {
            session.LatestFrame = null;
            session.Control.CoreWebView2?.NavigateToString(
                "<html><body style='background:transparent;margin:0'></body></html>");
            return;
        }

        Navigate(source.WebUri, session);
    }

    public VideoFrame? GetLatestFrame(string sourceId)
    {
        return _sessions.TryGetValue(sourceId, out var session) ? session.LatestFrame : null;
    }

    private async Task InitializeAsync(Source source, WebSourceSession session)
    {
        try
        {
            await session.Control.EnsureCoreWebView2Async();

            var cws = session.Control.CoreWebView2!;

            cws.NavigationStarting += (_, _) =>
            {
                _ = cws.ExecuteScriptAsync(
                    "document.documentElement.style.background='transparent';" +
                    "document.documentElement.style.overflow='hidden';" +
                    "document.body.style.background='transparent';" +
                    "document.body.style.overflow='hidden';");
            };

            cws.NavigationCompleted += (_, _) =>
            {
                _ = cws.ExecuteScriptAsync(
                    "document.documentElement.style.background='transparent';" +
                    "document.documentElement.style.overflow='hidden';" +
                    "document.body.style.background='transparent';" +
                    "document.body.style.overflow='hidden';");
                _ = CaptureFrame(source.Id);
            };

            session.Initialized = true;

            session.Control.CoreWebView2.NavigateToString(
                "<html><body style='background:transparent;margin:0'></body></html>");

            if (!string.IsNullOrEmpty(source.WebUri))
                Navigate(source.WebUri, session);

            session.CaptureTimer.Start();
        }
        catch (Exception ex)
        {
            AppLog.Write($"WebView2Manager: init failed for '{source.Name}': {ex.Message}");
            RemoveSession(source.Id);
        }
    }

    private void Navigate(string url, WebSourceSession session)
    {
        try { session.Control.CoreWebView2?.Navigate(url); }
        catch (Exception ex) { AppLog.Write($"WebView2Manager: navigate failed: {ex.Message}"); }
    }

    // The widget's extent is measured from the captured frame itself: the
    // bounding box of non-transparent pixels (the background is injected
    // transparent, so the alpha channel IS the widget). This is immune to
    // DOM timing (fonts/images/animations), needs no JS round-trip, and
    // CANNOT break the render: if the widget fills the canvas the box equals
    // the full frame; if it floats in transparent margin the box is the
    // measured content extent — used ONLY for the preview bitmap / selection.
    // The frame handed to the compositor is always the FULL canvas, so the
    // page's transparent margins keep revealing the layers beneath (the
    // "black square over webcam" was the crop fed to the compositor:
    // UniformToFill zoomed the opaque content box to cover the whole element).
    internal static (int X, int Y, int W, int H) FindContentBounds(byte[] pixels, int pixW, int pixH, int stride)
    {
        int minX = pixW, minY = pixH, maxX = -1, maxY = -1;
        for (var y = 0; y < pixH; y++)
        {
            var row = y * stride;
            for (var x = 0; x < pixW; x++)
            {
                if (pixels[row + x * 4 + 3] == 0) continue;
                if (x < minX) minX = x;
                if (x > maxX) maxX = x;
                if (y < minY) minY = y;
                if (y > maxY) maxY = y;
            }
        }
        if (maxX < minX || maxY < minY) return (0, 0, pixW, pixH);
        return (minX, minY, maxX - minX + 1, maxY - minY + 1);
    }

    private async Task CaptureFrame(string sourceId)
    {
        if (!_sessions.TryGetValue(sourceId, out var session) || session.Disposed) return;

        try
        {
            var webView = session.Control;
            if (webView.CoreWebView2 == null) return;

            using var ms = new MemoryStream();
            await webView.CoreWebView2.CapturePreviewAsync(
                CoreWebView2CapturePreviewImageFormat.Png, ms);

            ms.Position = 0;

            var bitmap = new BitmapImage();
            bitmap.BeginInit();
            bitmap.StreamSource = ms;
            bitmap.CacheOption = BitmapCacheOption.OnLoad;
            bitmap.EndInit();
            bitmap.Freeze();

            var formatted = new FormatConvertedBitmap(bitmap,
                PixelFormats.Bgra32, null, 0);

            var pixW = formatted.PixelWidth;
            var pixH = formatted.PixelHeight;

            if (pixW < 1 || pixH < 1) return;

            var need = pixW * pixH * 4;
            var pixels = session.CanvasScratch is { } scratch && scratch.Length >= need
                ? scratch
                : (session.CanvasScratch = new byte[need]);
            formatted.CopyPixels(pixels, pixW * 4, 0);

            var stride = pixW * 4;

            var (cropX, cropY, cropW, cropH) = FindContentBounds(pixels, pixW, pixH, stride);

            var outPixels = session.RentOutBuffer(cropW * cropH * 4);
            if (cropW == pixW && cropH == pixH && cropX == 0 && cropY == 0)
                Buffer.BlockCopy(pixels, 0, outPixels, 0, outPixels.Length);
            else
                for (var r = 0; r < cropH; r++)
                    Buffer.BlockCopy(pixels, (cropY + r) * stride + cropX * 4, outPixels, r * cropW * 4, cropW * 4);

            if (session.PreviewBitmap == null
                || session.PreviewBitmap.PixelWidth != cropW || session.PreviewBitmap.PixelHeight != cropH)
                session.PreviewBitmap = new WriteableBitmap(cropW, cropH, 96, 96, PixelFormats.Bgra32, null);
            session.PreviewBitmap.WritePixels(new Int32Rect(0, 0, cropW, cropH), outPixels, cropW * 4, 0);

            session.LatestFrame = new VideoFrame(pixW, pixH, pixels)
            {
                Epoch = ++session.Epoch,
                CropBounds = (cropX, cropY, cropW, cropH),
            };

            // The preview bitmap is now MUTABLE and reused (CameraManager precedent):
            // WPF re-renders it after WritePixels; handlers must not Freeze it.
            var preview = session.PreviewBitmap;
            _ = _dispatcher.BeginInvoke(() =>
            {
                PreviewBitmapChanged?.Invoke(sourceId, preview);
            });
        }
        catch (ObjectDisposedException) { }
        catch (InvalidOperationException) { }
        catch (Exception ex)
        {
            AppLog.Write($"WebView2Manager: capture failed for '{sourceId}': {ex.Message}");
        }
    }

    private void RemoveSession(string sourceId)
    {
        if (!_sessions.TryGetValue(sourceId, out var session)) return;
        session.Disposed = true;
        session.CaptureTimer.Stop();
        _hostPanel.Children.Remove(session.Control);
        try { session.Control.Dispose(); } catch { }
        _sessions.Remove(sourceId);
    }

    public void Dispose()
    {
        foreach (var id in _sessions.Keys.ToList())
            RemoveSession(id);
    }
}