Fix speech input test native VAD startup (#686)

Avoid loading the unused native Silero VAD during tray speech input startup so the Record test path no longer enters the native ONNX dependency before microphone capture. Keep the existing managed energy VAD behavior in AudioPipeline and add a source contract test.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: christineyan4

src/OpenClaw.Tray.WinUI/Services/AudioPipeline.cs

@@ -18,8 +18,6 @@ public sealed class AudioPipeline : IAsyncDisposable
 {
     private readonly IOpenClawLogger _logger;
     private readonly SpeechToTextService _stt;
-    private readonly VoiceActivityDetector _vad;
-
     private WasapiCapture? _capture;
     private WaveFormat? _captureFormat;
     private AudioPipelineOptions _options = new();
@@ -40,6 +38,8 @@ public sealed class AudioPipeline : IAsyncDisposable
     // State
     private AudioPipelineState _state = AudioPipelineState.Stopped;
     private CancellationTokenSource? _cts;
+    private const int PipelineSampleRate = 16000;
+    private const int VadChunkSamples = 512;
 
     // Backpressure: cap how many transcription Task.Run callbacks may be
     // outstanding at once. Each holds its own copy of the audio samples
@@ -94,11 +94,10 @@ public sealed class AudioPipeline : IAsyncDisposable
     /// <summary>When true, incoming audio is ignored (prevents echo during TTS playback).</summary>
     public bool IsMuted { get; set; }
 
-    public AudioPipeline(IOpenClawLogger logger, SpeechToTextService stt, VoiceActivityDetector vad)
+    public AudioPipeline(IOpenClawLogger logger, SpeechToTextService stt)
     {
         _logger = logger;
         _stt = stt;
-        _vad = vad;
     }
 
     /// <summary>Start capturing and processing audio.</summary>
@@ -111,7 +110,7 @@ public async Task StartAsync(AudioPipelineOptions options, CancellationToken can
         _cts = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
 
         // Calculate silence threshold: how many VAD chunks = silence timeout
-        float chunkDurationSec = (float)VoiceActivityDetector.ChunkSamples / VoiceActivityDetector.SampleRate;
+        float chunkDurationSec = (float)VadChunkSamples / PipelineSampleRate;
         _silenceChunksThreshold = Math.Max(1, (int)(options.SilenceTimeoutSeconds / chunkDurationSec));
 
         SetState(AudioPipelineState.Starting);
@@ -331,10 +330,10 @@ private void OnDataAvailable(object? sender, WaveInEventArgs e)
 
     private void ProcessVadChunks()
     {
-        while (_resampleBuffer.Count >= VoiceActivityDetector.ChunkSamples)
+        while (_resampleBuffer.Count >= VadChunkSamples)
         {
-            var chunk = _resampleBuffer.GetRange(0, VoiceActivityDetector.ChunkSamples).ToArray();
-            _resampleBuffer.RemoveRange(0, VoiceActivityDetector.ChunkSamples);
+            var chunk = _resampleBuffer.GetRange(0, VadChunkSamples).ToArray();
+            _resampleBuffer.RemoveRange(0, VadChunkSamples);
 
             // Compute RMS energy of this chunk
             float energy = 0;
@@ -387,7 +386,7 @@ private void ProcessVadChunks()
                     _silenceChunksCount = 0;
 
                     // Only transcribe if we had enough speech (not just a brief noise)
-                    var durationSec = (float)samples.Length / VoiceActivityDetector.SampleRate;
+                    var durationSec = (float)samples.Length / PipelineSampleRate;
                     if (_speechChunkCount < 10) // less than ~320ms of actual speech
                     {
                         try { DiagnosticMessage?.Invoke("Speak now — I'm listening"); } catch { }
@@ -445,7 +444,7 @@ private async Task TranscribeSamplesAsync(float[] samples, CancellationToken? ov
         }
 
         // Skip very short segments (< 0.3 seconds)
-        if (samples.Length < VoiceActivityDetector.SampleRate * 0.3f)
+        if (samples.Length < PipelineSampleRate * 0.3f)
         {
             DiagnosticMessage?.Invoke("Segment too short, skipped");
             return;

src/OpenClaw.Tray.WinUI/Services/VoiceService.cs

@@ -1,7 +1,6 @@
 using System;
 using System.Collections.Generic;
 using System.Diagnostics;
-using System.IO;
 using System.Linq;
 using System.Threading;
 using System.Threading.Tasks;
@@ -28,15 +27,11 @@ public sealed class VoiceService : IAsyncDisposable
     private readonly IOpenClawLogger _logger;
     private readonly SettingsManager _settings;
     private readonly SpeechToTextService _stt;
-    private readonly VoiceActivityDetector _vad;
     private readonly WhisperModelManager _modelManager;
     private AudioPipeline? _pipeline;
     private VoiceMode _currentMode = VoiceMode.Inactive;
     private CancellationTokenSource? _sessionCts;
 
-    // Path to the bundled Silero VAD model (deployed with the app)
-    private string? _vadModelPath;
-
     /// <summary>Current voice interaction mode.</summary>
     public VoiceMode CurrentMode => _currentMode;
 
@@ -106,7 +101,6 @@ public VoiceService(IOpenClawLogger logger, SettingsManager settings)
         _logger = logger;
         _settings = settings;
         _stt = new SpeechToTextService(logger);
-        _vad = new VoiceActivityDetector(logger);
         _modelManager = new WhisperModelManager(SettingsManager.SettingsDirectoryPath, logger);
     }
 
@@ -118,26 +112,6 @@ public async Task InitializeAsync(
         IProgress<(long downloaded, long total)>? downloadProgress = null,
         CancellationToken cancellationToken = default)
     {
-        // Load VAD model
-        if (!_vad.IsLoaded)
-        {
-            var vadPath = FindVadModelPath();
-            if (vadPath == null)
-            {
-                // Auto-download Silero VAD model
-                DiagnosticMessage?.Invoke("Downloading voice activity model…");
-                vadPath = await DownloadVadModelAsync(cancellationToken);
-            }
-            if (vadPath != null)
-            {
-                _vad.LoadModel(vadPath);
-            }
-            else
-            {
-                _logger.Info("Silero VAD model not found — VAD will be unavailable");
-            }
-        }
-
         // Download Whisper model if needed
         var modelName = _settings.SttModelName;
         if (!_modelManager.IsModelDownloaded(modelName))
@@ -172,7 +146,7 @@ public async Task StartPushToTalkAsync()
         SetMode(VoiceMode.PushToTalk);
 
         _sessionCts = new CancellationTokenSource();
-        _pipeline = new AudioPipeline(_logger, _stt, _vad);
+        _pipeline = new AudioPipeline(_logger, _stt);
         WirePipelineEvents(_pipeline);
 
         var options = new AudioPipelineOptions
@@ -214,7 +188,7 @@ public async Task StartVoiceChatAsync()
         SetMode(VoiceMode.VoiceChat);
 
         _sessionCts = new CancellationTokenSource();
-        _pipeline = new AudioPipeline(_logger, _stt, _vad);
+        _pipeline = new AudioPipeline(_logger, _stt);
         WirePipelineEvents(_pipeline);
 
         var options = new AudioPipelineOptions
@@ -276,7 +250,7 @@ public async Task<SttListenResult> ListenOnceAsync(SttListenArgs args, Cancellat
         using var timeoutCts = new CancellationTokenSource(args.TimeoutMs);
         using var linkedCts = CancellationTokenSource.CreateLinkedTokenSource(cancellationToken, timeoutCts.Token);
 
-        var pipeline = new AudioPipeline(_logger, _stt, _vad);
+        var pipeline = new AudioPipeline(_logger, _stt);
         WirePipelineEvents(pipeline);
         var tcs = new TaskCompletionSource<SttListenResult>();
         var sw = Stopwatch.StartNew();
@@ -368,7 +342,7 @@ public async Task<SttTranscribeResult> TranscribeFixedDurationAsync(
 
         await EnsureInitializedAsync();
 
-        var pipeline = new AudioPipeline(_logger, _stt, _vad);
+        var pipeline = new AudioPipeline(_logger, _stt);
         var sw = Stopwatch.StartNew();
         try
         {
@@ -504,91 +478,9 @@ private void SetMode(VoiceMode mode)
         _logger.Info($"Voice mode changed: {mode}");
     }
 
-    /// <summary>
-    /// Locate the Silero VAD ONNX model. Looks in the app's Assets folder
-    /// and the models directory.
-    /// </summary>
-    private string? FindVadModelPath()
-    {
-        if (_vadModelPath != null && File.Exists(_vadModelPath))
-            return _vadModelPath;
-
-        // Check Assets directory (deployed with the app)
-        var assetsPath = Path.Combine(AppContext.BaseDirectory, "Assets", "silero_vad.onnx");
-        if (File.Exists(assetsPath))
-        {
-            _vadModelPath = assetsPath;
-            return assetsPath;
-        }
-
-        // Check models directory
-        var modelsPath = Path.Combine(SettingsManager.SettingsDirectoryPath, "models", "silero_vad.onnx");
-        if (File.Exists(modelsPath))
-        {
-            _vadModelPath = modelsPath;
-            return modelsPath;
-        }
-
-        return null;
-    }
-
-    private const string VadDownloadUrl = SileroVadModelManifest.DownloadUrl;
-
-    /// <summary>Download the Silero VAD ONNX model if not already present.
-    /// SHA-256 is verified before the atomic rename so a tampered or
-    /// truncated file never lands at the canonical path. See
-    /// <see cref="SileroVadModelManifest"/>.</summary>
-    private async Task<string?> DownloadVadModelAsync(CancellationToken cancellationToken)
-    {
-        var destPath = Path.Combine(SettingsManager.SettingsDirectoryPath, "models", SileroVadModelManifest.FileName);
-        if (File.Exists(destPath))
-            return destPath;
-
-        _logger.Info("Downloading Silero VAD model...");
-        Directory.CreateDirectory(Path.GetDirectoryName(destPath)!);
-        var tempPath = destPath + ".tmp";
-        try
-        {
-            using var http = new System.Net.Http.HttpClient();
-            http.Timeout = TimeSpan.FromMinutes(5);
-            using var response = await http.GetAsync(VadDownloadUrl, cancellationToken);
-            response.EnsureSuccessStatusCode();
-            using (var fs = new FileStream(tempPath, FileMode.Create, FileAccess.Write, FileShare.None))
-            {
-                await response.Content.CopyToAsync(fs, cancellationToken);
-            }
-
-            // SECURITY: verify SHA-256 BEFORE the atomic rename so a
-            // tampered file never reaches ONNX Runtime.
-            using (var sha = System.Security.Cryptography.SHA256.Create())
-            using (var verifyStream = new FileStream(tempPath, FileMode.Open, FileAccess.Read, FileShare.Read, 81920, useAsync: true))
-            {
-                var actual = await sha.ComputeHashAsync(verifyStream, cancellationToken);
-                var actualHex = Convert.ToHexString(actual).ToLowerInvariant();
-                if (!string.Equals(actualHex, SileroVadModelManifest.Sha256, StringComparison.OrdinalIgnoreCase))
-                {
-                    throw new System.Security.SecurityException(
-                        "Silero VAD model failed integrity check. The downloaded file does not match the pinned SHA-256.");
-                }
-            }
-
-            File.Move(tempPath, destPath, overwrite: true);
-            _logger.Info($"Silero VAD model downloaded and verified ({new FileInfo(destPath).Length:N0} bytes)");
-            _vadModelPath = destPath;
-            return destPath;
-        }
-        catch (Exception ex)
-        {
-            _logger.Error("Failed to download VAD model", ex);
-            try { if (File.Exists(tempPath)) File.Delete(tempPath); } catch { }
-            return null;
-        }
-    }
-
     public async ValueTask DisposeAsync()
     {
         await StopAsync();
         _stt.Dispose();
-        _vad.Dispose();
     }
 }

tests/OpenClaw.Tray.Tests/SpeechInputContractTests.cs

@@ -0,0 +1,46 @@
+namespace OpenClaw.Tray.Tests;
+
+public sealed class SpeechInputContractTests
+{
+    private static string RepoRoot()
+    {
+        var env = Environment.GetEnvironmentVariable("OPENCLAW_REPO_ROOT");
+        if (!string.IsNullOrWhiteSpace(env) && Directory.Exists(env))
+            return env;
+
+        var d = new DirectoryInfo(AppContext.BaseDirectory);
+        while (d != null)
+        {
+            if (File.Exists(Path.Combine(d.FullName, "openclaw-windows-node.slnx")) &&
+                Directory.Exists(Path.Combine(d.FullName, "src")))
+                return d.FullName;
+            d = d.Parent;
+        }
+
+        throw new InvalidOperationException(
+            "Could not find repository root. Set OPENCLAW_REPO_ROOT to the repo path.");
+    }
+
+    private static string Read(params string[] parts)
+        => File.ReadAllText(Path.Combine(new[] { RepoRoot() }.Concat(parts).ToArray()));
+
+    [Fact]
+    public void VoiceService_DoesNotLoadNativeVad_OnRecordStartup()
+    {
+        var cs = Read("src", "OpenClaw.Tray.WinUI", "Services", "VoiceService.cs");
+
+        Assert.DoesNotContain("new VoiceActivityDetector", cs);
+        Assert.DoesNotContain(".LoadModel(vad", cs, StringComparison.OrdinalIgnoreCase);
+        Assert.DoesNotContain("DownloadVadModelAsync", cs);
+    }
+
+    [Fact]
+    public void AudioPipeline_UsesManagedEnergyVad_NotNativeVad()
+    {
+        var cs = Read("src", "OpenClaw.Tray.WinUI", "Services", "AudioPipeline.cs");
+
+        Assert.DoesNotContain("VoiceActivityDetector", cs);
+        Assert.Contains("energy >= startThreshold", cs);
+        Assert.Contains("energy >= stayThreshold", cs);
+    }
+}