How to Build a Cost-Aware LLM Routing System with NadirClaw Using Local Prompt Classification and Gemini Model Switching

if proxy_alive():
   print("\n[10] Mixed 10-prompt workload…")
   workload = [
       "Capital of France?",
       "Read foo.py",
       "Type hint for a list of dicts",
       "Lowercase: HELLO",
       "One-sentence summary of REST",
       "Refactor a callback chain into async/await with proper error handling",
       "Design a sharded multi-region key-value store with linearizable reads",
       "Analyze the asymptotic complexity of this code and prove the bound rigorously",
       "Debug why our gRPC stream stalls when the client TCP window saturates",
       "Compare and contrast B-trees and LSM-trees for write-heavy workloads",
   ]
   runs = []
   client = OpenAI(base_url=f"http://localhost:{PORT}/v1", api_key="local")
   for p in workload:
       t0 = time.time()
       try:
           r = client.chat.completions.create(
               model="auto",
               messages=[{"role": "user", "content": p}],
               max_tokens=140,
           )
           usage = getattr(r, "usage", None)
           runs.append({
               "prompt": p[:55],
               "model": r.model,
               "latency_s": round(time.time() - t0, 2),
               "in_tok": getattr(usage, "prompt_tokens", 0) if usage else 0,
               "out_tok": getattr(usage, "completion_tokens", 0) if usage else 0,
           })
       except Exception as e:
           runs.append({"prompt": p[:55], "model": "ERROR",
                        "latency_s": None, "in_tok": 0, "out_tok": 0,
                        "error": str(e)[:80]})
   rdf = pd.DataFrame(runs)
   print(rdf.to_string(index=False))
   PRICE = {
       "flash": {"in": 0.30 / 1e6, "out": 2.50 / 1e6},
       "pro":   {"in": 1.25 / 1e6, "out": 10.0 / 1e6},
   }
   def price_for(model_str, in_t, out_t):
       m = (model_str or "").lower()
       tier = "flash" if "flash" in m else "pro"
       return in_t * PRICE[tier]["in"] + out_t * PRICE[tier]["out"]
   cost_routed = sum(price_for(r["model"], r["in_tok"], r["out_tok"]) for r in runs)
   cost_no_route = sum(price_for("gemini-2.5-pro", r["in_tok"], r["out_tok"]) for r in runs)
   print(f"\n[10] Cost (NadirClaw routed)        : ${cost_routed:.6f}")
   print(f"     Cost (always-Pro baseline)     : ${cost_no_route:.6f}")
   if cost_no_route > 0:
       print(f"     Estimated savings on this run  : "
             f"{(1 - cost_routed/cost_no_route) * 100:.1f}%")
print("\n[11] `nadirclaw report` (parses the JSONL request log):")
rep = subprocess.run(["nadirclaw", "report"], capture_output=True, text=True, timeout=60)
print(rep.stdout or rep.stderr)
if proxy_alive():
   print("\n[12] Stopping the proxy…")
   try:
       if hasattr(os, "killpg"):
           os.killpg(os.getpgid(server_proc.pid), signal.SIGTERM)
       else:
           server_proc.terminate()
       server_proc.wait(timeout=10)
   except Exception:
       try:
           server_proc.kill()
       except Exception:
           pass
   print("    ✓ proxy stopped.")
print("\nDone. 🎉")