Reduce Ollama load: 10min cycle, fast-gate skip for confident qwen, 60s scalp, 75s stagger per bot

bot.py

@@ -348,7 +348,13 @@ def llm_vote(cfg, price, mom, mom_score, conn):
     v1 = fast_v if fast_v in ("UP","DOWN","SKIP") else "SKIP"
     c1 = fast_c if fast_v in ("UP","DOWN","SKIP") else 0.50
 
-    # Model 2: ornith deep verify (GamingPC RTX 3070)
+    # Fast-gate skip: if qwen is confident enough, skip ornith entirely
+    fast_gate_conf = cfg.get("fast_gate_conf", 0.65)
+    if v1 in ("UP","DOWN") and c1 >= fast_gate_conf:
+        LOG.info(f"[fast-gate {v1} {c1:.2f}] skipping ornith — qwen confident")
+        return v1, c1, f"[fast-gate {v1} {c1:.2f}] {fast_w[:80]}"
+
+    # Model 2: ornith deep verify (GamingPC RTX 3070) — only on borderline/uncertain
     try:
         r2 = requests.post("http://10.30.20.186:11434/api/generate",
             json={"model": "ornith:latest", "prompt": prompt, "stream": False, "think": False, "keep_alive": "10m",
@@ -806,7 +812,7 @@ def run():
                             LOG.info(f"skip {ticker}: {why}")
         except Exception as e:
             log_event(conn, "error", f"loop error: {e}")
-        time.sleep(15)  # scalp loop: watch constantly
+        time.sleep(cfg.get("scalp_interval_sec", 60))  # configurable scalp loop
 
 if __name__ == "__main__":
     run()