fix(dashboard): stop infinite mock loop; add demo-mode warning banner

--dashboard defaulted to looping mock STT forever, so the status page
piled up thousands of fake "conversations" (all mock, 0ms, same reply)
that looked like real traffic. Now it plays 3 sample utterances then
idles; a loud 데모 모드 banner states the turns are mock samples, not
real STT/Brain/TTS. Continuous demo moved behind --dashboard-loop-demo.

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

wsai/__main__.py

@@ -2,12 +2,13 @@
 
     python -m wsai              # mock pipeline (no deps, no keys) — runs a demo
     python -m wsai --voice      # eyes-free voice loop demo (STT -> Brain -> TTS)
-    python -m wsai --dashboard  # live status website + a continuous voice demo
+    python -m wsai --dashboard  # live status website + a short voice demo, then idle
     python -m wsai --live       # capture this screen + Claude eyes/brain
     python -m wsai --env        # build from WSAI_* environment variables
 
 The mock run is bounded (a few frames + a scripted conversation) so it exits on
-its own; --dashboard/--live/--env run until Ctrl-C.
+its own; --dashboard keeps the site open after a short demo; --live/--env run
+until Ctrl-C.
 """
 
 from __future__ import annotations
@@ -34,7 +35,14 @@ def _lan_ip() -> str:
         return "127.0.0.1"
 
 
-async def _run(settings: Settings, demo: bool, monitor: Monitor | None) -> None:
+async def _run(
+    settings: Settings,
+    demo: bool,
+    monitor: Monitor | None,
+    *,
+    demo_loop: bool = False,
+    keep_dashboard_open: bool = False,
+) -> None:
     if demo:
         # Bounded demo so CI / a quick check terminates.
         from .backends.mock import MockFrameSource, MockSTT
@@ -43,11 +51,16 @@ async def _run(settings: Settings, demo: bool, monitor: Monitor | None) -> None:
         if pipe.source is not None:  # keep eyes-free configs eyes-free
             pipe.source = MockFrameSource(interval=0.3, limit=4)
         if pipe.stt is not None:
-            # When serving the dashboard, keep talking forever so there's always
-            # something live to watch; otherwise stay bounded so the demo exits.
-            loop = monitor is not None
-            pipe.stt = MockSTT(interval=2.0 if loop else 0.4, loop=loop)
+            pipe.stt = MockSTT(interval=2.0 if demo_loop else 0.4, loop=demo_loop)
         await pipe.run()
+        if keep_dashboard_open:
+            # Keep the status page alive without generating fake conversations
+            # forever. The previous default looped mock STT indefinitely, which
+            # made the dashboard look like it had heard thousands of real users.
+            if monitor is not None:
+                monitor.set_status(running=True, listening=False)
+                monitor.log("info", "mock 데모 완료 — 실제 음성 파이프라인 연결 대기")
+            await asyncio.Event().wait()
         return
     await build(settings, monitor=monitor).run()
 
@@ -55,7 +68,9 @@ async def _run(settings: Settings, demo: bool, monitor: Monitor | None) -> None:
 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 (voice demo loops)")
+    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("--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")),
@@ -96,7 +111,15 @@ def main() -> None:
         print(f"  (로컬:              http://127.0.0.1:{args.port} )\n")
 
     try:
-        asyncio.run(_run(settings, demo, monitor))
+        asyncio.run(
+            _run(
+                settings,
+                demo,
+                monitor,
+                demo_loop=args.dashboard and args.dashboard_loop_demo,
+                keep_dashboard_open=args.dashboard and demo and not args.dashboard_loop_demo,
+            )
+        )
     except KeyboardInterrupt:
         pass
     finally:

wsai/dashboard.py

@@ -179,6 +179,9 @@ PAGE = r"""<!DOCTYPE html>
   .ev.error{color:var(--err)}
   .ev .et{flex:0 0 68px;color:#5f7488}
   code{background:#0c1219;padding:1px 5px;border-radius:5px;border:1px solid var(--line)}
+  .demobar{background:#2a2210;border:1px solid #6b5417;color:var(--warn);border-radius:12px;
+    padding:11px 15px;margin:0 0 16px;font-size:13px;line-height:1.55}
+  .demobar b{color:#ffe08a}
 </style>
 </head>
 <body>
@@ -196,6 +199,7 @@ PAGE = r"""<!DOCTYPE html>
   </div>
 </header>
 <main>
+  <div class="demobar" id="demobar" style="display:none"></div>
   <div class="comp" id="comp"></div>
   <div id="turns"></div>
   <div id="empty" class="empty">아직 대화가 없습니다. 사용자가 말하면 여기에 단계별로 나타납니다.</div>
@@ -232,6 +236,18 @@ function renderStatus(s){
   $('dot').className = 'dot ' + (listening ? 'live' : 'off');
   $('listen').textContent = listening ? '듣는 중' : (s.running ? '실행 중 (대기)' : '중지됨');
   const comps = s.components || {};
+  // Demo banner: if the ears/brain/mouth are still mock, everything below is
+  // replayed sample data, not a real conversation. Say so loudly.
+  const mockParts = ['stt','brain','tts'].filter(k => comps[k]==='mock');
+  const bar = $('demobar');
+  if(mockParts.length){
+    bar.style.display='block';
+    bar.innerHTML = '⚠ <b>데모 모드</b> — 실제 음성/STT/두뇌/TTS가 아직 연결되지 않아, 아래 대화는 '
+      + '실제로 들은 내용이 아니라 <b>목(mock) 예시 스크립트</b>입니다. '
+      + '실제 엔진(faster-whisper·Claude·MeloTTS)을 붙이면 이 자리에 진짜 발화·지연·오류가 표시됩니다.';
+  } else {
+    bar.style.display='none';
+  }
   const el = $('comp'); el.innerHTML = '';
   const names = {source:'눈(소스)', vision:'시각', stt:'귀(STT)', brain:'두뇌', tts:'입(TTS)', text:'텍스트'};
   for(const k of Object.keys(names)){