Skip preflight IO (memory/URL/fast-tools) when no_inference=True

In no_inference mode only the routing decision matters — fetching
memories and URLs adds latency without affecting the classification.

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

agent.py

@@ -446,6 +446,10 @@ async def _run_agent_pipeline(
         print(f"[agent] running: {clean_message[:80]!r}", flush=True)
 
         # Fetch URL content, memories, and fast-tool context concurrently
+        # Skip preflight IO in no_inference mode — only routing decision needed
+        if no_inference:
+            url_context = memories = fast_context = None
+        else:
             url_context, memories, fast_context = await asyncio.gather(
                 _fetch_urls_from_message(clean_message),
                 _retrieve_memories(clean_message, session_id),