rename(litellm): qwen-image-judge alias -> image-judge

stacks/litellm/conf/config.yaml

@@ -45,7 +45,7 @@ model_list:
   #     on ana-ml2 GPU 1, :8014. REPLACED qwen3.6-35b-a3b (operator 2026-06-19; the
   #     qwen36 VL judge was downed + its FP8 weights freed ~33GB). Multimodal — image
   #     + prompt in, a 5-dim verdict out (overall quality / prompt match / aesthetic /
-  #     LoRA activation / confidence). qwen-image-judge is a duplicate-entry alias.
+  #     LoRA activation / confidence). image-judge is a duplicate-entry alias.
   #     ⚠️ arbo's hero-judge was bound to qwen3.6-35b-a3b — comfy-dev notified to
   #     repoint (different I/O than the old general VL judge). ---
   - model_name: qwen-image-bench
@@ -55,7 +55,7 @@ model_list:
       api_key: os.environ/VLLM_API_KEY
     model_info:
       mode: chat
-  - model_name: qwen-image-judge
+  - model_name: image-judge
     litellm_params:
       model: hosted_vllm/qwen-image-bench
       api_base: http://10.250.50.54:8014/v1