chore: create OpenAIMixin for inference providers with an OpenAI-compat API that need to implement openai_* methods (#2835)

# What does this PR do?

add an `OpenAIMixin` for use by inference providers who remote endpoints
support an OpenAI compatible API.

use is demonstrated by refactoring
- OpenAIInferenceAdapter
- NVIDIAInferenceAdapter (adds embedding support)
- LlamaCompatInferenceAdapter

## Test Plan

existing unit and integration tests

tests/unit/providers/inference/test_inference_client_caching.py

@@ -10,6 +10,8 @@ from unittest.mock import MagicMock
 from llama_stack.distribution.request_headers import request_provider_data_context
 from llama_stack.providers.remote.inference.groq.config import GroqConfig
 from llama_stack.providers.remote.inference.groq.groq import GroqInferenceAdapter
+from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
+from llama_stack.providers.remote.inference.llama_openai_compat.llama import LlamaCompatInferenceAdapter
 from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
 from llama_stack.providers.remote.inference.openai.openai import OpenAIInferenceAdapter
 from llama_stack.providers.remote.inference.together.config import TogetherImplConfig
@@ -50,7 +52,7 @@ def test_openai_provider_openai_client_caching():
         with request_provider_data_context(
             {"x-llamastack-provider-data": json.dumps({inference_adapter.provider_data_api_key_field: api_key})}
         ):
-            openai_client = inference_adapter._get_openai_client()
+            openai_client = inference_adapter.client
             assert openai_client.api_key == api_key
 
 
@@ -71,3 +73,18 @@ def test_together_provider_openai_client_caching():
             assert together_client.client.api_key == api_key
             openai_client = inference_adapter._get_openai_client()
             assert openai_client.api_key == api_key
+
+
+def test_llama_compat_provider_openai_client_caching():
+    """Ensure the LlamaCompat provider does not cache api keys across client requests"""
+    config = LlamaCompatConfig()
+    inference_adapter = LlamaCompatInferenceAdapter(config)
+
+    inference_adapter.__provider_spec__ = MagicMock()
+    inference_adapter.__provider_spec__.provider_data_validator = (
+        "llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator"
+    )
+
+    for api_key in ["test1", "test2"]:
+        with request_provider_data_context({"x-llamastack-provider-data": json.dumps({"llama_api_key": api_key})}):
+            assert inference_adapter.client.api_key == api_key