perf: pre-warm ollama at the engine's num_ctx (8192) so first turn is hot

The startup warm-up loaded qwen at the default context, but the reply
engine chats at num_ctx=8192 — a different Ollama instance — so the first
real turn still cold-reloaded. Warm at OLLAMA_NUM_CTX via /api/chat.

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

bridge/server.py

@@ -527,23 +527,31 @@ def http_converse_stream():
 
 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."""
+    is resident before the first real turn. Best-effort.
+
+    Warms at the SAME num_ctx the reply engine uses (OLLAMA_NUM_CTX, default
+    8192). Ollama keeps a distinct loaded instance per (model, num_ctx), so
+    warming at the default context would load the wrong instance and the first
+    real chat call (8192) would still cold-reload (~3.4s)."""
     if not base_url or not model:
         return
     import urllib.request
 
+    num_ctx = int(os.environ.get("OLLAMA_NUM_CTX", "8192"))
     try:
         req = urllib.request.Request(
-            f"{base_url.rstrip('/')}/api/generate",
+            f"{base_url.rstrip('/')}/api/chat",
             data=json.dumps(
-                {"model": model, "prompt": "", "stream": False,
-                 "keep_alive": "30m", "options": {"num_predict": 1}}
+                {"model": model,
+                 "messages": [{"role": "user", "content": "."}],
+                 "stream": False, "keep_alive": "30m",
+                 "options": {"num_ctx": num_ctx, "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)
+        print(f"[bridge] {'✅' if ok else '⚠️'} ollama warm (model={model}, num_ctx={num_ctx})", flush=True)
     except Exception as e:  # pragma: no cover - depends on local ollama
         print(f"[bridge] ollama warmup skipped (model={model}): {e}", flush=True)