feat: update Cerebras inference provider to support dynamic model listing

- update Cerebras to use OpenAIMixin
- enable openai completions tests
- enable openai chat completions tests
- disable with n > 1 tests
- add recording for --setup cerebras --subdirs inference --pattern openai

test with: `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai`

tests/integration/inference/test_openai_completion.py

@@ -40,7 +40,6 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
         "inline::sentence-transformers",
         "inline::vllm",
         "remote::bedrock",
-        "remote::cerebras",
         "remote::databricks",
         # Technically Nvidia does support OpenAI completions, but none of their hosted models
         # support both completions and chat completions endpoint and all the Llama models are
@@ -98,6 +97,8 @@ def skip_if_doesnt_support_n(client_with_models, model_id):
         #  the entered value was 2. Update the candidateCount value and try again.', 'status': 'INVALID_ARGUMENT'}
         "remote::tgi",  # TGI ignores n param silently
         "remote::together",  # `n` > 1 is not supported when streaming tokens. Please disable `stream`
+        # Error code 400 - {'message': '"n" > 1 is not currently supported', 'type': 'invalid_request_error', 'param': 'n', 'code': 'wrong_api_format'}
+        "remote::cerebras",
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")
 
@@ -109,7 +110,6 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
         "inline::sentence-transformers",
         "inline::vllm",
         "remote::bedrock",
-        "remote::cerebras",
         "remote::databricks",
         "remote::runpod",
         "remote::watsonx",  # watsonx returns 404 when hitting the /openai/v1 endpoint