voice: quieter thinking tone, log cleanup, and small ui polish

- Add scripts/lower-thinking-tone.mjs to scale the thinking-tone PCM
  amplitude in-place; apply it at 0.1 so the cue is a soft indicator
  instead of triggering the VAD via mic feedback.
- Drop the "Received first voice_audio_chunk" log that re-fires every
  summary window because the chunk counter is reset.
- Match Spoke message icon and label sizing to the standard tool-call
  badge.
- Append a spoken-input instruction so voice replies route through the
  speak tool.

packages/app/src/components/message.tsx

@@ -1740,8 +1740,8 @@ const speakMessageStylesheet = StyleSheet.create((theme) => ({
   },
   headerLabel: {
     fontFamily: Fonts.sans,
-    fontSize: 12,
-    fontWeight: "500",
+    fontSize: theme.fontSize.base,
+    fontWeight: theme.fontWeight.normal,
     color: theme.colors.foregroundMuted,
   },
   text: {
@@ -1769,7 +1769,7 @@ export const SpeakMessage = memo(function SpeakMessage({
   return (
     <View testID="speak-message" style={containerStyle}>
       <View style={speakMessageStylesheet.header}>
-        <ThemedMicVocal size={14} uniProps={foregroundMutedColorMapping} />
+        <ThemedMicVocal size={12} uniProps={foregroundMutedColorMapping} />
         <Text style={speakMessageStylesheet.headerLabel}>Spoke</Text>
       </View>
       <Text style={speakMessageStylesheet.text}>{message}</Text>