test: change mistral model

service tier exceeded

litellm/proxy/_new_secret_config.yaml

@@ -3,7 +3,19 @@ model_list:
     litellm_params:
       model: "gpt-4o"
       api_key: os.environ/OPENAI_API_KEY
+<<<<<<< HEAD
   - model_name: "gemini-2.0-flash"
+=======
+
+guardrails:
+  - guardrail_name: azure-prompt-shield
+    litellm_params:
+      guardrail: azure/prompt_shield
+      mode: pre_call # "During_call" is also available
+      api_key: os.environ/AZURE_GUARDRAIL_API_KEY
+      api_base: os.environ/AZURE_GUARDRAIL_API_BASE 
+  - guardrail_name: azure-text-moderation
+>>>>>>> 6ebc8d473 (test: change mistral model)
     litellm_params:
       model: "gemini/gemini-2.0-flash"
       api_key: os.environ/GEMINI_API_KEY

tests/local_testing/test_completion.py

@@ -131,6 +131,7 @@ def test_null_role_response():
 
         assert response.choices[0].message.role == "assistant"
 
+
 @pytest.mark.skip(reason="Cohere having RBAC issues")
 def test_completion_azure_command_r():
     try:
@@ -175,7 +176,6 @@ def test_completion_azure_ai_gpt_4o(api_base):
         pytest.fail(f"Error occurred: {e}")
 
 
-
 def predibase_mock_post(url, data=None, json=None, headers=None, timeout=None):
     mock_response = MagicMock()
     mock_response.status_code = 200
@@ -905,7 +905,7 @@ def test_completion_mistral_api_mistral_large_function_call():
     try:
         # test without max tokens
         response = completion(
-            model="mistral/open-mistral-7b",
+            model="mistral/mistral-medium-latest",
             messages=messages,
             tools=tools,
             tool_choice="auto",
@@ -1475,7 +1475,6 @@ HF Tests we should pass
 """
 
 
-
 @pytest.mark.parametrize(
     "provider", ["openai", "hosted_vllm", "lm_studio", "llamafile"]
 )  # "vertex_ai",
@@ -1560,6 +1559,7 @@ async def test_openai_compatible_custom_api_video(provider):
 
         mock_call.assert_called_once()
 
+
 def test_lm_studio_completion(monkeypatch):
     monkeypatch.delenv("LM_STUDIO_API_KEY", raising=False)
     monkeypatch.delenv("OPENAI_API_KEY", raising=False)
@@ -1578,6 +1578,7 @@ def test_lm_studio_completion(monkeypatch):
     except litellm.APIError as e:
         print(e)
 
+
 # ################### Hugging Face Conversational models ########################
 # def hf_test_completion_conv():
 #     try:
@@ -1625,7 +1626,6 @@ def mock_post(url, **kwargs):
     return mock_response
 
 
-
 def test_ollama_image():
     """
     Test that datauri prefixes are removed, JPEG/PNG images are passed
@@ -4394,6 +4394,7 @@ def test_humanloop_completion(monkeypatch):
         messages=[{"role": "user", "content": "Tell me a joke."}],
     )
 
+
 def test_completion_novita_ai():
     litellm.set_verbose = True
     messages = [
@@ -4403,10 +4404,11 @@ def test_completion_novita_ai():
             "content": "Hey",
         },
     ]
-    
+
     from openai import OpenAI
+
     openai_client = OpenAI(api_key="fake-key")
-    
+
     with patch.object(
         openai_client.chat.completions, "create", new=MagicMock()
     ) as mock_call:
@@ -4417,21 +4419,22 @@ def test_completion_novita_ai():
                 client=openai_client,
                 api_base="https://api.novita.ai/v3/openai",
             )
-            
+
             mock_call.assert_called_once()
-            
+
             # Verify model is passed correctly
-            assert mock_call.call_args.kwargs["model"] == "meta-llama/llama-3.3-70b-instruct"
+            assert (
+                mock_call.call_args.kwargs["model"]
+                == "meta-llama/llama-3.3-70b-instruct"
+            )
             # Verify messages are passed correctly
             assert mock_call.call_args.kwargs["messages"] == messages
-            
+
         except Exception as e:
             pytest.fail(f"Error occurred: {e}")
 
 
-@pytest.mark.parametrize(
-    "api_key", ["my-bad-api-key"]
-)
+@pytest.mark.parametrize("api_key", ["my-bad-api-key"])
 def test_completion_novita_ai_dynamic_params(api_key):
     try:
         litellm.set_verbose = True
@@ -4442,12 +4445,15 @@ def test_completion_novita_ai_dynamic_params(api_key):
                 "content": "Hey",
             },
         ]
-        
+
         from openai import OpenAI
+
         openai_client = OpenAI(api_key="fake-key")
-        
+
         with patch.object(
-            openai_client.chat.completions, "create", side_effect=Exception("Invalid API key")
+            openai_client.chat.completions,
+            "create",
+            side_effect=Exception("Invalid API key"),
         ) as mock_call:
             try:
                 completion(
@@ -4461,11 +4467,12 @@ def test_completion_novita_ai_dynamic_params(api_key):
             except Exception as e:
                 # This should fail with the mocked exception
                 assert "Invalid API key" in str(e)
-                
+
             mock_call.assert_called_once()
     except Exception as e:
         pytest.fail(f"Unexpected error: {e}")
 
+
 def test_deepseek_reasoning_content_completion():
     try:
         litellm.set_verbose = True

tests/local_testing/test_streaming.py

@@ -952,7 +952,7 @@ def test_completion_mistral_api_mistral_large_function_call_with_streaming():
     try:
         # test without max tokens
         response = completion(
-            model="mistral/mistral-large-latest",
+            model="mistral/mistral-medium-latest",
             messages=messages,
             tools=tools,
             tool_choice="auto",
@@ -2892,6 +2892,7 @@ def test_azure_streaming_and_function_calling():
         pytest.fail(f"Error occurred: {e}")
         raise e
 
+
 @pytest.mark.asyncio
 async def test_azure_astreaming_and_function_calling():
     import uuid
@@ -4022,4 +4023,4 @@ def test_is_delta_empty():
             tool_calls=None,
             audio=None,
         )
-    )
+    )