fix: add z-ai to NIM model providers

z-ai/glm-5.2 is hosted on NVIDIA NIM (build.nvidia.com/z-ai/glm-5.2).
The NIM rotation was incorrectly excluding it. Add "z-ai" to the
known NIM provider list in both LiteLLM and direct httpx paths.

src/cai/sdk/agents/models/openai_chatcompletions.py

@@ -3677,6 +3677,7 @@ class OpenAIChatCompletionsModel(Model):
                 "llama", "nemotron", "codellama", "mixtral", "phi",
                 "qwen", "yi", "deepseek", "gemma", "stable-diffusion",
                 "sdxl", "cosxl", "proteus", "realistic-vision",
+                "z-ai",
             }
             return provider in nim_providers
 
@@ -3804,6 +3805,7 @@ class OpenAIChatCompletionsModel(Model):
                         "llama", "nemotron", "codellama", "mixtral", "phi",
                         "qwen", "yi", "deepseek", "gemma", "stable-diffusion",
                         "sdxl", "cosxl", "proteus", "realistic-vision",
+                        "z-ai",
                     }
                     return provider in nim_providers
                 if (