feat: split recording vs STT-processing time in turn logs

Log the captured speech-clip duration (녹음/음성) separately from the Whisper
transcription time (STT처리) so it's clear whether a slow turn is the
listening/recording or the transcription, per the user's request.

bridge/server.py

@@ -459,14 +459,31 @@ def http_converse_stream():
             # own Date.now() capture timestamps (same host, same clock).
             return int(time.time() * 1000)
 
+        # Length of the captured speech clip (16-bit mono PCM). This is the
+        # "음성 인식(녹음)" portion — how long the user actually spoke (+ the
+        # bot's trailing silence cutoff) — as opposed to "STT 처리", the Whisper
+        # transcription time below. Splitting them shows whether a slow turn is
+        # the listening/recording or the transcription.
+        try:
+            _frames, _sr = _read_wav_pcm(raw)
+            audio_sec = (len(_frames) / 2) / _sr if _sr else 0.0
+        except Exception:
+            audio_sec = 0.0
+
         t0 = time.monotonic()
         stt = transcribe(raw)
         t_stt = time.monotonic()
         transcript = stt.get("text", "")
         if not transcript:
+            print(
+                f"[bridge] ⏱️ turn 녹음(음성)={audio_sec:.1f}s STT처리(whisper)={t_stt - t0:.1f}s "
+                f"→ 인식 결과 없음 ({stt.get('note', '빈 결과')})",
+                flush=True,
+            )
             yield json.dumps({"type": "meta", "transcript": "", "language": stt.get("language"),
                               "reply": "", "error": stt.get("error"),
                               "note": stt.get("note", "빈 결과"),
+                              "audio_sec": round(audio_sec, 1),
                               "stt_sec": round(t_stt - t0, 1), "broadcast_action": None}) + "\n"
             yield json.dumps({"type": "end"}) + "\n"
             return
@@ -482,6 +499,7 @@ def http_converse_stream():
             "reply": reply,
             "error": result.get("error"),
             "note": "ok" if reply.strip() else "답변 없음",
+            "audio_sec": round(audio_sec, 1),
             "stt_sec": round(t_stt - t0, 1),
             "think_sec": round(t_think - t_stt, 1),
             # Wall-clock LLM window (epoch ms) for the transcript-channel timing
@@ -516,8 +534,9 @@ def http_converse_stream():
             "tts_end_ms": tts_end_ms,
         }) + "\n"
         print(
-            f"[bridge] ⏱️ turn stt={t_stt - t0:.1f}s think(LLM)={t_think - t_stt:.1f}s "
+            f"[bridge] ⏱️ turn 녹음(음성)={audio_sec:.1f}s STT처리(whisper)={t_stt - t0:.1f}s "
-            f"tts={tts_total:.1f}s total={time.monotonic() - t0:.1f}s replylen={len(reply)} "
+            f"think(LLM)={t_think - t_stt:.1f}s tts={tts_total:.1f}s "
+            f"total(STT~TTS)={time.monotonic() - t0:.1f}s replylen={len(reply)} "
             f"transcript={transcript[:40]!r}",
             flush=True,
         )