Add ASR capture timeout handling in DuplexPipeline and enhance EOU detection logic. Introduce _ASR_CAPTURE_MAX_MS constant and manage capture state timing to ensure timely end of utterance processing, even during silence. Update EouDetector to allow silence-only EOU when VAD state is lost.

engine/processors/eou.py

@@ -53,6 +53,18 @@ class EouDetector:
 
         if vad_status == "Silence":
             if not self.is_speaking:
+                # Fallback path: ASR has already started but VAD speaking state
+                # was lost (e.g. VAD flicker). Allow silence-only EOU so the
+                # turn can still close instead of stalling forever.
+                if not force_eligible:
+                    return False
+                if self.silence_start_time is None:
+                    self.silence_start_time = now
+                silence_duration = now - self.silence_start_time
+                if silence_duration >= self.threshold and not self.triggered:
+                    self.triggered = True
+                    self.silence_start_time = None
+                    return True
                 return False
             if self.silence_start_time is None:
                 self.silence_start_time = now