routing benchmark: 1s strict deadline per query

QUERY_TIMEOUT=1s — classification and routing must complete within
1 second or the query is recorded as 'timeout'.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

benchmarks/run_routing_benchmark.py

@@ -30,7 +30,7 @@ import httpx
 ADOLF_URL = "http://localhost:8000"
 DATASET = Path(__file__).parent / "benchmark.json"
 RESULTS = Path(__file__).parent / "routing_results_latest.json"
-QUERY_TIMEOUT = 30  # seconds — routing is fast, no LLM wait
+QUERY_TIMEOUT = 1  # 1s strict deadline — routing must decide within 1 second
 
 
 # ── Log helpers ────────────────────────────────────────────────────────────────
@@ -139,9 +139,10 @@ async def run(queries: list[dict]) -> list[dict]:
             except Exception:
                 pass  # timeout or connection issue — check logs anyway
 
-            await asyncio.sleep(0.3)
             logs_after = get_log_tail(300)
             actual = extract_tier_from_logs(logs_before, logs_after)
+            if actual is None:
+                actual = "timeout"
 
             elapsed = time.monotonic() - t0
             match = actual == expected or (actual == "fast" and expected == "medium")
@@ -149,7 +150,7 @@ async def run(queries: list[dict]) -> list[dict]:
                 correct += 1
 
             mark = "✓" if match else "✗"
-            actual_str = actual or "?"
+            actual_str = actual
             print(f"{actual_str:8}  {mark:3}  {elapsed:5.1f}s  {category:22}  {query_text[:40]}")
 
             results.append({