configure litellm models

litellm/litellm.yaml

@@ -11,22 +11,38 @@ metadata:
 data:
   config.yaml: |
     model_list:
-      - model_name: gpt-5-mini
+      - model_name: gpt-5.6-luna
         litellm_params:
-          model: openai/gpt-5-mini-2025-08-07
+          model: openai/gpt-5.6-luna
           api_key: "os.environ/OPENAI_API_KEY"
-      - model_name: claude-4.5-haiku
+      - model_name: claude-haiku-4.5
         litellm_params:
           model: "anthropic/claude-haiku-4-5-20251001"
           api_key: "os.environ/ANTHROPIC_API_KEY"
+      - model_name: claude-sonnet-5
+        litellm_params:
+          model: "anthropic/claude-sonnet-5"
+          api_key: "os.environ/ANTHROPIC_API_KEY"
       - model_name: gemini-3-flash
         litellm_params:
           model: gemini/gemini-3-flash-preview
           api_key: "os.environ/GEMINI_API_KEY"
+      - model_name: hy3
+        litellm_params:
+          model: openrouter/tencent/hy3:free
+          api_key: "os.environ/OPENROUTER_API_KEY"
+      - model_name: glm-5.2
+        litellm_params:
+          model: openrouter/z-ai/glm-5.2
+          api_key: "os.environ/OPENROUTER_API_KEY"
       - model_name: glm-4.7-flash
         litellm_params:
           model: ollama/glm-4.7-flash
           api_base: http://10.88.20.12:11434
+      - model_name: qwen-3.6
+        litellm_params:
+          model: ollama/qwen-3.6
+          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:latest (the fast non-27b tag). 27b is a slow reasoning model.