feat(openai): add configurable base_url support with OPENAI_BASE_URL env var

- Add base_url field to OpenAIConfig with default "https://api.openai.com/v1"
- Update sample_run_config to support OPENAI_BASE_URL environment variable
- Modify get_base_url() to return configured base_url instead of hardcoded value
- Add comprehensive test suite covering:
  - Default base URL behavior
  - Custom base URL from config
  - Environment variable override
  - Config precedence over environment variables
  - Client initialization with configured URL
  - Model availability checks using configured URL

This enables users to configure custom OpenAI-compatible API endpoints
via environment variables or configuration files.

llama_stack/providers/remote/inference/openai/openai.py

@@ -65,9 +65,9 @@ class OpenAIInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
         """
         Get the OpenAI API base URL.
 
-        Returns the standard OpenAI API base URL for direct OpenAI API calls.
+        Returns the OpenAI API base URL from the configuration.
         """
-        return "https://api.openai.com/v1"
+        return self.config.base_url
 
     async def initialize(self) -> None:
         await super().initialize()