v1.9.0: Fix audio gaps, pre-buffer, and lip sync neutral pose

- Remove silence padding accumulation bug: QueueAudio'd silence was
  accumulating in USoundWaveProcedural's internal buffer during TTS gaps,
  delaying real audio by ~800ms. USoundWaveProcedural with
  INDEFINITELY_LOOPING_DURATION generates silence internally instead.
- Fix pre-buffer bypass: guard OnProceduralUnderflow with bPreBuffering
  check — the audio component never stops (INDEFINITELY_LOOPING_DURATION)
  so it was draining AudioQueue during pre-buffering, defeating it entirely.
- Audio pre-buffer default 2000ms (max 4000ms) to absorb ElevenLabs
  server-side TTS inter-chunk gaps (~2s between chunks confirmed).
- Add diagnostic timestamps [T+Xs] in HandleAudioReceived and
  AudioQueue DRY/recovered logs for debugging audio pipeline timing.
- Fix lip sync not returning to neutral: add snap-to-zero (< 0.01)
  in blendshape smoothing pass and clean up PreviousBlendshapes to
  prevent asymptotic Lerp residuals keeping mouth slightly open.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Unreal/PS_AI_Agent/Config/DefaultEngine.ini

@@ -1,8 +1,8 @@
 
 
 [/Script/EngineSettings.GameMapsSettings]
-GameDefaultMap=/Game/TestMap.TestMap
-EditorStartupMap=/Game/TestMap.TestMap
+GameDefaultMap=/Game/Demo_VoiceOnly.Demo_VoiceOnly
+EditorStartupMap=/Game/Demo_VoiceOnly.Demo_VoiceOnly
 
 [/Script/Engine.RendererSettings]
 r.AllowStaticLighting=False
@@ -24,6 +24,9 @@ r.DefaultFeature.AutoExposure.ExtendDefaultLuminanceRange=True
 r.DefaultFeature.LocalExposure.HighlightContrastScale=0.8
 
 r.DefaultFeature.LocalExposure.ShadowContrastScale=0.8
+r.GPUSkin.Support16BitBoneIndex=True
+r.GPUSkin.UnlimitedBoneInfluences=True
+SkeletalMesh.UseExperimentalChunking=1
 
 [/Script/WindowsTargetPlatform.WindowsTargetSettings]
 DefaultGraphicsRHI=DefaultGraphicsRHI_DX12
@@ -91,4 +94,3 @@ ConnectionType=USBOnly
 bUseManualIPAddress=False
 ManualIPAddress=
 
-