chore: turn OpenAIMixin into a pydantic.BaseModel (#3671)

# What does this PR do?

- implement get_api_key instead of relying on
LiteLLMOpenAIMixin.get_api_key
 - remove use of LiteLLMOpenAIMixin
 - add default initialize/shutdown methods to OpenAIMixin
 - remove __init__s to allow proper pydantic construction
- remove dead code from vllm adapter and associated / duplicate unit
tests
 - update vllm adapter to use openaimixin for model registration
 - remove ModelRegistryHelper from fireworks & together adapters
 - remove Inference from nvidia adapter
 - complete type hints on embedding_model_metadata
- allow extra fields on OpenAIMixin, for model_store, __provider_id__,
etc
 - new recordings for ollama
 - enhance the list models error handling
- update cerebras (remove cerebras-cloud-sdk) and anthropic (custom
model listing) inference adapters
 - parametrized test_inference_client_caching
- remove cerebras, databricks, fireworks, together from blanket mypy
exclude
 - removed unnecessary litellm deps

## Test Plan

ci

llama_stack/providers/registry/inference.py

@@ -52,9 +52,7 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="cerebras",
             provider_type="remote::cerebras",
-            pip_packages=[
-                "cerebras_cloud_sdk",
-            ],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.cerebras",
             config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
             description="Cerebras inference provider for running models on Cerebras Cloud platform.",
@@ -169,7 +167,7 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="openai",
             provider_type="remote::openai",
-            pip_packages=["litellm"],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.openai",
             config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
             provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
@@ -179,7 +177,7 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="anthropic",
             provider_type="remote::anthropic",
-            pip_packages=["litellm"],
+            pip_packages=["anthropic"],
             module="llama_stack.providers.remote.inference.anthropic",
             config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
             provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
@@ -189,9 +187,7 @@ def available_providers() -> list[ProviderSpec]:
             api=Api.inference,
             adapter_type="gemini",
             provider_type="remote::gemini",
-            pip_packages=[
-                "litellm",
-            ],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.gemini",
             config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
             provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
@@ -202,7 +198,6 @@ def available_providers() -> list[ProviderSpec]:
             adapter_type="vertexai",
             provider_type="remote::vertexai",
             pip_packages=[
-                "litellm",
                 "google-cloud-aiplatform",
             ],
             module="llama_stack.providers.remote.inference.vertexai",
@@ -233,9 +228,7 @@ Available Models:
             api=Api.inference,
             adapter_type="groq",
             provider_type="remote::groq",
-            pip_packages=[
-                "litellm",
-            ],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.groq",
             config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
             provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
@@ -245,7 +238,7 @@ Available Models:
             api=Api.inference,
             adapter_type="llama-openai-compat",
             provider_type="remote::llama-openai-compat",
-            pip_packages=["litellm"],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.llama_openai_compat",
             config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
             provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
@@ -255,9 +248,7 @@ Available Models:
             api=Api.inference,
             adapter_type="sambanova",
             provider_type="remote::sambanova",
-            pip_packages=[
-                "litellm",
-            ],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.sambanova",
             config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
             provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
@@ -287,7 +278,7 @@ Available Models:
             api=Api.inference,
             provider_type="remote::azure",
             adapter_type="azure",
-            pip_packages=["litellm"],
+            pip_packages=[],
             module="llama_stack.providers.remote.inference.azure",
             config_class="llama_stack.providers.remote.inference.azure.AzureConfig",
             provider_data_validator="llama_stack.providers.remote.inference.azure.config.AzureProviderDataValidator",