feat(dashboard): browser STT recognition test on the GPU

The status page was view-only, so there was no way to actually verify Korean
recognition end-to-end. Add a live test: record from the mic (localhost/https)
or upload an audio file (works over LAN http, where browsers block getUserMedia),
POST it to a new /api/stt endpoint that ffmpeg-normalises the blob to 16 kHz
mono and runs the real GPU faster-whisper, then shows the recognised text +
latency + device. Results also land in the live turn feed.

The dashboard now optionally holds a WhisperSTT and drives it from a private
asyncio loop thread. New `python -m wsai --stt-test` serves the page with STT
enabled and pre-warms the GPU worker so the first recognition is instant.
WhisperSTT.resolved_device is exposed for the UI.

Verified: wav and browser-style webm/opus uploads both return the correct
Korean text on device=cuda in ~240-280ms. 12 tests pass.

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

wsai/__main__.py

@@ -65,12 +65,49 @@ async def _run(
     await build(settings, monitor=monitor).run()
 
 
+def _run_stt_test(host: str, port: int) -> None:
+    """Serve the dashboard with a real GPU STT backend so a human can test
+    recognition from the browser (record mic or upload an audio file). No mock
+    conversation loop — the page just hosts the recognition test."""
+    import time
+
+    from .backends.whisper import WhisperSTT
+    from .dashboard import Dashboard
+    from .monitor import Monitor
+
+    monitor = Monitor()
+    stt = WhisperSTT()
+    dash = Dashboard(monitor, host=host, port=port, stt=stt)
+    dash.start()
+    monitor.set_components({"source": "none", "vision": "none", "stt": "whisper",
+                            "brain": "none", "tts": "none"})
+    monitor.set_status(running=True, listening=False)
+    monitor.log("info", "STT 인식 테스트 서버 시작 — GPU 워밍업 중…")
+    print("\n  STT 워밍업 중… (모델 로드 + CUDA 예열)")
+    dash.warm()  # load + warm the GPU worker so the first recognition is instant
+    dev = getattr(stt, "resolved_device", None) or "?"
+    monitor.log("info", f"STT 준비 완료 (device={dev}). 녹음/파일 업로드로 인식하세요.")
+
+    shown = host if host not in ("0.0.0.0", "") else _lan_ip()
+    print(f"\n  음성 인식 테스트 사이트:  http://{shown}:{port}   (STT device: {dev})")
+    print(f"  (로컬:                  http://127.0.0.1:{port} )\n")
+    try:
+        while True:
+            time.sleep(3600)
+    except KeyboardInterrupt:
+        pass
+    finally:
+        dash.stop()
+
+
 def main() -> None:
     ap = argparse.ArgumentParser(prog="wsai")
     ap.add_argument("--voice", action="store_true", help="eyes-free voice loop (STT -> Brain -> TTS)")
     ap.add_argument("--dashboard", action="store_true", help="serve the live status website")
     ap.add_argument("--dashboard-loop-demo", action="store_true",
                     help="keep generating mock demo utterances forever (off by default)")
+    ap.add_argument("--stt-test", action="store_true",
+                    help="serve the dashboard with a live GPU STT recognition test")
     ap.add_argument("--live", action="store_true", help="capture screen + Claude backends")
     ap.add_argument("--env", action="store_true", help="build from WSAI_* env vars")
     ap.add_argument("--port", type=int, default=int(os.environ.get("WSAI_DASHBOARD_PORT", "8787")),
@@ -85,6 +122,10 @@ def main() -> None:
         format="%(levelname)s %(name)s: %(message)s",
     )
 
+    if args.stt_test:
+        _run_stt_test(args.host, args.port)
+        return
+
     if args.dashboard:
         # Default to the eyes-free voice preset for the demo; env can override.
         settings = Settings.from_env() if args.env else Settings.voice()