fix: raise heavy threshold — 4000→12000 tokens, 8→15 turns

2026-05-19 20:10:07 +00:00
parent 5971ceee4e
commit e90bf0216d
1 changed files with 2 additions and 2 deletions
@@ -181,8 +181,8 @@ def route(rd, tier):
        if "qwen3.6-27B-code" in avail and not is_gpu_busy("qwen3.6-27B-code"):
            return {"model":"qwen3.6-27B-code","reason":"simple_conv_fallback"}
    
-    # TIER 3: Heavy reasoning — large context or very long conversations
-    if t > 4000 or turns > 8:
+    # TIER 3: Heavy reasoning — very large context or very long conversations
+    if t > 12000 or turns > 15:
        candidates = [m for m in ["qwen3.6-27B-code","qwen3.6-35B-A3B","qwen3.5-9b-vlm"] if m in avail]
        result = select_best_gpu(candidates, "heavy_reasoning")
        if result: return result