loki + promtail new monitoring services

litellm/litellm.yaml

@@ -28,11 +28,19 @@ data:
           model: ollama/glm-4.7-flash
           api_base: http://10.88.20.12:11434
       # Used by the platform-engineer Hermes agent (deployed in ns platform-engineer).
-      # model_name is the alias Hermes requests; the underlying Ollama model is qwen3.6:27b.
-      - model_name: qwen3.6:27b
+      # model_name is the alias Hermes requests; the underlying Ollama model is
+      # qwen3.6:latest (the fast non-27b tag). 27b is a slow reasoning model.
+      # `ollama_chat/` (not `ollama/`) uses Ollama's NATIVE /api/chat endpoint.
+      # `think: false` + `chat_template_kwargs.enable_thinking: false` disable
+      # Qwen3 thinking so the model emits content directly (otherwise the
+      # OpenAI-compat translation returns empty content with reasoning split off).
+      - model_name: qwen3.6
         litellm_params:
-          model: ollama/qwen3.6:27b
+          model: ollama_chat/qwen3.6:latest
           api_base: http://10.88.20.12:11434
+          think: false
+          chat_template_kwargs:
+            enable_thinking: false
     litellm_settings:
       #set_verbose: True  # Uncomment this if you want to see verbose logs; not recommended in production
       callbacks: ["arize_phoenix"]