fix(kon): resolve ort version conflict — stub VAD, fix audio crate

- VAD stubbed: voice_activity_detector and silero-vad-rust both pin ort rc.10
  which conflicts with transcribe-rs requiring ort rc.12. Stubbed until ort
  ecosystem aligns at 2.0.0 stable. All audio treated as speech (matches v0.2).
- Refreshed Cargo.lock to resolve ort rc.12 + whisper-rs 0.16 correctly
- clippy clean

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/audio/Cargo.toml

@@ -10,8 +10,9 @@ kon-core = { path = "../core" }
 # Microphone capture
 cpal = "0.17"
 
-# Voice activity detection (Silero VAD V5)
+# Voice activity detection — deferred until ort version conflict between
-voice_activity_detector = "0.2"
+# VAD crates (ort rc.10) and transcribe-rs (ort rc.12) is resolved upstream.
+# silero-vad-rust = { version = "6", default-features = false }
 
 # High-quality resampling (sinc interpolation)
 rubato = "0.15"

crates/audio/src/vad.rs

@@ -1,50 +1,35 @@
-use voice_activity_detector::VoiceActivityDetector;
+// Voice Activity Detection — stubbed.
+//
+// Both `voice_activity_detector` and `silero-vad-rust` pin ort 2.0.0-rc.10
+// which conflicts with transcribe-rs requiring ort 2.0.0-rc.12.
+// When the ort ecosystem aligns (likely at 2.0.0 stable), add Silero VAD here.
+//
+// For now, all audio is treated as speech. This matches v0.2 behaviour
+// (no VAD) and doesn't affect core functionality.
 
-use kon_core::constants::{VAD_SPEECH_THRESHOLD, WHISPER_SAMPLE_RATE};
+use kon_core::constants::VAD_SPEECH_THRESHOLD;
-use kon_core::error::{KonError, Result};
 
-/// VAD chunk size for 16kHz audio (required by Silero VAD V5).
+/// Stub speech detector. Treats all audio as speech.
-const VAD_CHUNK_SIZE: usize = 512;
+#[derive(Default)]
-
-/// Wraps Silero VAD V5 for speech detection.
 pub struct SpeechDetector {
-    vad: VoiceActivityDetector,
     threshold: f64,
 }
 
 impl SpeechDetector {
-    /// Create a new speech detector with the default threshold.
+    pub fn new() -> Self {
-    pub fn new() -> Result<Self> {
+        Self {
-        let vad = VoiceActivityDetector::builder()
-            .sample_rate(WHISPER_SAMPLE_RATE as i64)
-            .chunk_size(VAD_CHUNK_SIZE)
-            .build()
-            .map_err(|e| KonError::AudioCaptureFailed(format!("VAD init failed: {e}")))?;
-
-        Ok(Self {
-            vad,
             threshold: VAD_SPEECH_THRESHOLD,
-        })
+        }
     }
 
-    /// Predict whether a chunk of 16kHz f32 audio contains speech.
+    /// Always returns true (no VAD filtering until ort conflict resolved).
-    /// Returns the speech probability (0.0 to 1.0).
+    pub fn is_speech(&self, _samples: &[f32]) -> bool {
-    pub fn predict(&mut self, samples: &[f32]) -> f32 {
+        true
-        self.vad.predict(samples.iter().copied())
     }
 
-    /// Returns true if the chunk contains speech above the threshold.
+    pub fn threshold(&self) -> f64 {
-    pub fn is_speech(&mut self, samples: &[f32]) -> bool {
+        self.threshold
-        self.predict(samples) > self.threshold as f32
     }
 
-    /// Reset the internal VAD state (call between recording sessions).
+    pub fn reset(&mut self) {}
-    pub fn reset(&mut self) {
-        self.vad.reset();
-    }
-
-    /// The required chunk size for this VAD instance.
-    pub fn chunk_size(&self) -> usize {
-        VAD_CHUNK_SIZE
-    }
 }