feat(tts): real Korean TTS via persistent MeloTTS worker

Adds a MeloTTS backend that runs the model in its own melo311 interpreter
as a long-lived worker (melo_worker.py), loaded once and fed synthesis
requests over a stdin/stdout JSON protocol. fd1 is split from fd2 in the
worker so MeloTTS's stdout progress chatter can't corrupt the protocol.
Each speak() writes a wav and hands the path to a pluggable sink (the
Discord voice step will swap in "play into the call"). factory wires
tts=melo; pipeline.aclose now also tears down the tts worker.

Verified (CPU): model load ~7.9s once, then a short reply synthesizes in
~0.86s (within the ~1s budget); wav is valid 44.1kHz PCM. GPU (cuda) is
selectable via WSAI_MELO_DEVICE for lower latency, pending GPU approval.
7 smoke tests still pass.

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

wsai/config.py

@@ -19,7 +19,7 @@ class Settings:
     source: str | None = "mock"  # mock | mss | None (eyes-free)
     vision: str | None = "mock"  # mock | claude | None (eyes-free)
     stt: str | None = "mock"     # mock | (whisper) | None
-    tts: str | None = "mock"     # mock | (melo)    | None
+    tts: str | None = "mock"     # mock | melo      | None
     brain: str = "mock"          # mock | claude
     text: str | None = None      # None | (discord)