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

tests/integration/suites.py

@@ -131,6 +131,27 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
             "embedding_model": "fireworks/accounts/fireworks/models/qwen3-embedding-8b",
         },
     ),
+    "anthropic": Setup(
+        name="anthropic",
+        description="Anthropic Claude models",
+        defaults={
+            "text_model": "anthropic/claude-3-5-haiku-20241022",
+        },
+    ),
+    "llama-api": Setup(
+        name="llama-openai-compat",
+        description="Llama models from https://api.llama.com",
+        defaults={
+            "text_model": "llama_openai_compat/Llama-3.3-8B-Instruct",
+        },
+    ),
+    "groq": Setup(
+        name="groq",
+        description="Groq models",
+        defaults={
+            "text_model": "groq/llama-3.3-70b-versatile",
+        },
+    ),
 }