tune: raise Tier 2 threshold 4K→10K tok, 6→10 turns for VLM

More conversations now route to VLM as primary. 9B VLM has 262K
context window and 88 tok/s average — well suited for moderate
conversations. Dense absorbs overflow and heavy reasoning.

router/router.py

@@ -218,8 +218,8 @@ def route(rd, tier):
         result = select_best_gpu(fallback, "lightweight_fallback")
         if result: return result
     
-    # TIER 2: Simple conversations — short context, any prompt → VLM first, Dense second
+    # TIER 2: Simple conversations — VLM primary (up to 10K tok), any prompt → VLM first, Dense second
-    if t <= 4000 and turns <= 6 and "qwen3.5-9b-vlm" in avail:
+    if t <= 10000 and turns <= 10 and "qwen3.5-9b-vlm" in avail:
         if not is_gpu_busy("qwen3.5-9b-vlm"):
             return {"model":"qwen3.5-9b-vlm","reason":"simple_conv"}
         # VLM busy — fall back to Dense, then MoE