feat(litellm): add gen-nt / gen-reasoning-nt (noop-tool + tool_choice:none compat variants)

Same Qwopus gen model as gen / gen-reasoning (served-name qwen3.5-122-a10b @
:8013, thinking off/on respectively), but each bakes a dummy 'noop' function tool
+ tool_choice:none into litellm_params so a NON-EMPTY tools array always reaches
vLLM — for consumers where the global strip_empty_tools hook isn't the right fix
(they need a valid tools structure present, not stripped). tool_choice:none means
the noop is never called. api_base = the real LAN endpoint http://10.250.50.54:8013
(the requested http://vllm:8000 template wouldn't resolve from the ana-docker
litellm container). Verified: gen-nt + gen-reasoning-nt both survive a client
tools:[] send; noop never invoked; reasoning split intact.

stacks/litellm/conf/config.yaml

@@ -134,6 +134,55 @@ model_list:
           enable_thinking: true
     model_info:
       mode: chat
+  # --- gen-nt / gen-reasoning-nt: same Qwopus `gen` model, but with a dummy `noop`
+  #     tool + tool_choice:"none" baked into the record so a NON-EMPTY tools array
+  #     always reaches vLLM (which 400s on an empty `tools:[]`). For consumers where
+  #     the global strip_empty_tools hook isn't the right fix — i.e. they need a valid
+  #     tools structure PRESENT rather than stripped. tool_choice:none disables actual
+  #     calling, so the noop is never invoked. api_base = the real LAN endpoint (the
+  #     operator's `http://vllm:8000` template wouldn't resolve from ana-docker). ---
+  - model_name: gen-nt
+    litellm_params:
+      model: hosted_vllm/qwen3.5-122-a10b
+      api_base: http://10.250.50.54:8013/v1
+      api_key: os.environ/VLLM_API_KEY
+      extra_body:
+        chat_template_kwargs:
+          enable_thinking: false
+      tools:
+        - type: function
+          function:
+            name: noop
+            description: "No-op tool. Do not call this tool; it exists only for compatibility."
+            parameters:
+              type: object
+              properties: {}
+              required: []
+              additionalProperties: false
+      tool_choice: "none"
+    model_info:
+      mode: chat
+  - model_name: gen-reasoning-nt
+    litellm_params:
+      model: hosted_vllm/qwen3.5-122-a10b
+      api_base: http://10.250.50.54:8013/v1
+      api_key: os.environ/VLLM_API_KEY
+      extra_body:
+        chat_template_kwargs:
+          enable_thinking: true
+      tools:
+        - type: function
+          function:
+            name: noop
+            description: "No-op tool. Do not call this tool; it exists only for compatibility."
+            parameters:
+              type: object
+              properties: {}
+              required: []
+              additionalProperties: false
+      tool_choice: "none"
+    model_info:
+      mode: chat
 
   # --- Selene 1 Mini 8B (AtlaAI judge, FP8) — restored on GPU1 after the
   #     llama-swap teardown (was the Q6_K GGUF in the swap zoo). vLLM dynamic fp8,