feat(dashboard): per-stage STT/LLM/TTS timing + rename 두뇌 -> LLM

- voice_turn now records three separate timed steps (STT, LLM, TTS) instead of
  one combined "STT+두뇌+TTS" step, so each stage's latency shows in the turn.
- Rename 두뇌 -> LLM everywhere user-facing: component chip, sub header, demo
  banner, model label, brain-failure log, startup print, pipeline step name.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

wsai/pipeline.py

@@ -87,7 +87,7 @@ class Pipeline:
         try:
             async with turn.step("화면 맥락"):
                 screen = await self.context.latest()
-            async with turn.step("두뇌(생각)"):
+            async with turn.step("LLM(생각)"):
                 reply = await self.brain.respond(utt.text, screen, self._history)
             turn.replied(reply.text)
             self._remember(utt.text, reply.text)