From d4e5e7f3f738b0ba3941970ac6b8d39e2297077d Mon Sep 17 00:00:00 2001
From: javis-bot <claude@tkrmagid.kr>
Date: Sun, 14 Jun 2026 00:04:03 +0900
Subject: [PATCH] perf: pre-warm Whisper + chat model + TTS at bridge startup

The first spoken turn paid a ~10s cold start because Whisper (default
"medium") and the Ollama chat model loaded lazily on the first request.
Warm them (and ping the TTS worker) in a background thread at startup so
the server accepts requests immediately while models load, and the first
real utterance is fast.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---
 bridge/server.py | 57 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/bridge/server.py b/bridge/server.py
index e33199a..e05095d 100644
--- a/bridge/server.py
+++ b/bridge/server.py
@@ -525,8 +525,65 @@ def http_converse_stream():
     return Response(stream_with_context(gen()), mimetype="application/x-ndjson")
 
 
+def _warm_ollama(base_url: str, model: str) -> None:
+    """Load ``model`` into Ollama (GPU if available) with a long keep_alive so it
+    is resident before the first real turn. Best-effort."""
+    if not base_url or not model:
+        return
+    import urllib.request
+
+    try:
+        req = urllib.request.Request(
+            f"{base_url.rstrip('/')}/api/generate",
+            data=json.dumps(
+                {"model": model, "prompt": "", "stream": False,
+                 "keep_alive": "30m", "options": {"num_predict": 1}}
+            ).encode("utf-8"),
+            headers={"Content-Type": "application/json"},
+        )
+        with urllib.request.urlopen(req, timeout=120) as resp:
+            ok = resp.status == 200
+        print(f"[bridge] {'✅' if ok else '⚠️'} ollama warm (model={model})", flush=True)
+    except Exception as e:  # pragma: no cover - depends on local ollama
+        print(f"[bridge] ollama warmup skipped (model={model}): {e}", flush=True)
+
+
+def _warmup() -> None:
+    """Pre-load Whisper + the chat model + TTS so the FIRST real utterance does
+    not pay the cold-start cost (observed ~10s on the first STT). Best-effort and
+    runs in a background thread so the HTTP server (and /health) is up
+    immediately."""
+    try:
+        _ensure_brain()
+        # JIT the Whisper transcribe path on a short silent buffer. We call the
+        # model directly (not transcribe()) because the VAD gate short-circuits
+        # silence before Whisper would run, leaving the model un-warmed.
+        if _whisper is not None:
+            try:
+                import numpy as np
+
+                dummy = np.zeros(8000, dtype=np.float32)  # 0.5s @ 16kHz
+                segs, _info = _whisper.transcribe(dummy, beam_size=1, language=STT_LANGUAGE)
+                for _ in segs:
+                    pass
+                print("[bridge] ✅ whisper warm", flush=True)
+            except Exception as e:  # pragma: no cover
+                print(f"[bridge] whisper warmup skipped: {e}", flush=True)
+        if _cfg is not None:
+            _warm_ollama(getattr(_cfg, "ollama_base_url", ""), getattr(_cfg, "ollama_chat_model", ""))
+        # Nudge the TTS worker to warm (MeloTTS loads its model before binding
+        # its port, so a ready ping confirms it; Piper loads on first synth).
+        if _tts_ready():
+            print("[bridge] ✅ tts warm", flush=True)
+    except Exception as e:  # pragma: no cover
+        print(f"[bridge] warmup error: {e}", flush=True)
+
+
 def main():
     print(f"[bridge] listening on http://{BRIDGE_HOST}:{BRIDGE_PORT}", flush=True)
+    # Warm the models in the background so the first spoken turn is fast while
+    # the server is already accepting requests.
+    threading.Thread(target=_warmup, name="bridge-warmup", daemon=True).start()
     # threaded=True so STT (slow) on one request doesn't block /health, etc.
     app.run(host=BRIDGE_HOST, port=BRIDGE_PORT, threaded=True)