From bf02cd846fdc39db80291746e06ca547e5afdbdb Mon Sep 17 00:00:00 2001
From: Matthew Farrellee <matt@cs.wisc.edu>
Date: Sat, 6 Sep 2025 15:25:13 -0400
Subject: [PATCH] chore: update the sambanova inference impl to use
 openai-python for openai-compat functions (#3345)

# What does this PR do?

update SambaNova inference provider to use OpenAIMixin for openai-compat
endpoints

## Test Plan

```
$ SAMBANOVA_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::sambanova --run
...
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model sambanova/Meta-Llama-3.3-70B-Instruct tests/integration/inference -k 'not store'
...
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-True] - AttributeError: 'NoneType' object has no attribute 'delta'
FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-False] - llama_stack_client.InternalServerError: Error code: 500 - {'detail': 'Internal server error: An une...
=========== 2 failed, 16 passed, 68 skipped, 8 deselected, 3 xfailed, 13 warnings in 15.85s ============
```

the two failures also exist before this change. they are part of the
deprecated inference.chat_completion tests that flow through litellm.
they can be resolved later.
---
 llama_stack/providers/registry/inference.py   |  2 +-
 .../remote/inference/sambanova/sambanova.py   | 26 ++++++++++++++++++-
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py
index 1bb3c3147..7a95fd089 100644
--- a/llama_stack/providers/registry/inference.py
+++ b/llama_stack/providers/registry/inference.py
@@ -270,7 +270,7 @@ Available Models:
             api=Api.inference,
             adapter=AdapterSpec(
                 adapter_type="sambanova",
-                pip_packages=["litellm"],
+                pip_packages=["litellm", "openai"],
                 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",
diff --git a/llama_stack/providers/remote/inference/sambanova/sambanova.py b/llama_stack/providers/remote/inference/sambanova/sambanova.py
index 96469acac..ee3b0f648 100644
--- a/llama_stack/providers/remote/inference/sambanova/sambanova.py
+++ b/llama_stack/providers/remote/inference/sambanova/sambanova.py
@@ -4,13 +4,26 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+
 from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
 from .config import SambaNovaImplConfig
 from .models import MODEL_ENTRIES
 
 
-class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
+class SambaNovaInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
+    """
+    SambaNova Inference Adapter for Llama Stack.
+
+    Note: The inheritance order is important here. OpenAIMixin must come before
+    LiteLLMOpenAIMixin to ensure that OpenAIMixin.check_model_availability()
+    is used instead of LiteLLMOpenAIMixin.check_model_availability().
+
+    - OpenAIMixin.check_model_availability() queries the /v1/models to check if a model exists
+    - LiteLLMOpenAIMixin.check_model_availability() checks the static registry within LiteLLM
+    """
+
     def __init__(self, config: SambaNovaImplConfig):
         self.config = config
         self.environment_available_models = []
@@ -24,3 +37,14 @@ class SambaNovaInferenceAdapter(LiteLLMOpenAIMixin):
             download_images=True,  # SambaNova requires base64 image encoding
             json_schema_strict=False,  # SambaNova doesn't support strict=True yet
         )
+
+    # Delegate the client data handling get_api_key method to LiteLLMOpenAIMixin
+    get_api_key = LiteLLMOpenAIMixin.get_api_key
+
+    def get_base_url(self) -> str:
+        """
+        Get the base URL for OpenAI mixin.
+
+        :return: The SambaNova base URL
+        """
+        return self.config.url