Warm up local LLM before live corrections

config.json

@@ -21,6 +21,7 @@
     "post_correct_ollama_url": "http://127.0.0.1:11434/api/generate",
     "post_correct_llm_timeout": 8.0,
     "post_correct_keep_alive": "30m",
+    "post_correct_warmup_timeout": 20.0,
     "post_correct_min_overlap": 0.45,
     "post_correct_debug": false,
     "llm_paragraph": false,

engine_llm.py

@@ -43,8 +43,34 @@ def run_llm_processor(in_queue, out_queue, args):
             print(f"[LLM] Ollama health check failed ({exc}). Local LLM features may fall back.")
             return False
 
+    def warmup_ollama_model():
+        try:
+            response = requests.post(
+                getattr(args, "post_correct_ollama_url", "http://127.0.0.1:11434/api/generate"),
+                json={
+                    "model": args.post_correct_model,
+                    "prompt": "Return exactly: ok",
+                    "stream": False,
+                    "options": {"temperature": 0.0},
+                    "keep_alive": getattr(args, "post_correct_keep_alive", "30m"),
+                },
+                timeout=getattr(args, "post_correct_warmup_timeout", 20.0),
+            )
+            response.raise_for_status()
+            body = response.json()
+            if body.get("response", "").strip():
+                total_s = body.get("total_duration", 0) / 1_000_000_000
+                load_s = body.get("load_duration", 0) / 1_000_000_000
+                print(f"[LLM] Ollama warmup OK for {args.post_correct_model} (load={load_s:.2f}s total={total_s:.2f}s).")
+                return True
+        except Exception as exc:
+            print(f"[LLM] Ollama warmup failed for {args.post_correct_model} ({exc}).")
+        return False
+
     if not is_openai:
         check_ollama_health()
+        if getattr(args, "post_correct_llm", False) or getattr(args, "llm_paragraph", False):
+            warmup_ollama_model()
 
     def normalize_english_caption(text):
         normalized = " ".join((text or "").split()).strip()

main_v2.py

@@ -53,6 +53,7 @@ def main():
     parser.add_argument("--post-correct-ollama-url", type=str, default=defaults.get("post_correct_ollama_url", "http://127.0.0.1:11434/api/generate"))
     parser.add_argument("--post-correct-llm-timeout", type=float, default=defaults.get("post_correct_llm_timeout", 8.0))
     parser.add_argument("--post-correct-keep-alive", type=str, default=defaults.get("post_correct_keep_alive", "30m"))
+    parser.add_argument("--post-correct-warmup-timeout", type=float, default=defaults.get("post_correct_warmup_timeout", 20.0))
     parser.add_argument("--post-correct-min-overlap", type=float, default=defaults.get("post_correct_min_overlap", 0.45))
     parser.add_argument("--post-correct-debug", action="store_true", default=defaults.get("post_correct_debug", False))
     parser.add_argument("--llm-paragraph", action="store_true", default=defaults.get("llm_paragraph", False))