fix: heavy threshold → 50000 tokens, 25 turns (agent contexts are huge)

2026-05-19 21:08:18 +00:00
parent 3cbf38e3e2
commit 3156c093d5
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 — very large context or very long conversations
-    if t > 12000 or turns > 15:
+    # TIER 3: Heavy reasoning — extremely large context or very long conversations
+    if t > 50000 or turns > 25:
        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