run black to fix formatting

Author: paulbatum

sdk/ai/azure-ai-projects/tests/agents/tools/multitool/test_agent_code_interpreter_and_function.py

@@ -69,17 +69,17 @@ def test_calculate_and_save(self, **kwargs):
             description="Agent with Code Interpreter and Function Tool.",
         )
         print(f"Agent created (id: {agent.id})")
-        
+
         # Use the agent
         response = openai_client.responses.create(
             input="Calculate 5 + 3 and save the result.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
         print(f"Response received (id: {response.id})")
-        
+
         assert response.id is not None
         print("✓ Code Interpreter + Function Tool works!")
-        
+
         # Cleanup
         project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
 
@@ -129,16 +129,16 @@ def test_generate_data_and_report(self, **kwargs):
             description="Agent for data generation and reporting.",
         )
         print(f"Agent created (id: {agent.id})")
-        
+
         # Request data generation and report
         response = openai_client.responses.create(
             input="Generate a list of 10 random numbers between 1 and 100, calculate their average, and create a report.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         print(f"Response received (id: {response.id})")
         assert response.id is not None
         print("✓ Data generation and reporting works!")
-        
+
         # Cleanup
         project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)

sdk/ai/azure-ai-projects/tests/agents/tools/multitool/test_agent_file_search_and_code_interpreter.py

@@ -41,11 +41,12 @@ def test_find_and_analyze_data(self, **kwargs):
         # Create data file
         txt_content = "Sample data: 10, 20, 30, 40, 50"
         vector_store = openai_client.vector_stores.create(name="DataStore")
-        
+
         from io import BytesIO
-        txt_file = BytesIO(txt_content.encode('utf-8'))
+
+        txt_file = BytesIO(txt_content.encode("utf-8"))
         txt_file.name = "data.txt"
-        
+
         file = openai_client.vector_stores.files.upload_and_poll(
             vector_store_id=vector_store.id,
             file=txt_file,
@@ -66,18 +67,18 @@ def test_find_and_analyze_data(self, **kwargs):
             description="Agent with File Search and Code Interpreter.",
         )
         print(f"Agent created (id: {agent.id})")
-        
+
         # Use the agent
         response = openai_client.responses.create(
             input="Find the data file and calculate the average.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
         print(f"Response received (id: {response.id})")
-        
+
         assert response.id is not None
         assert len(response.output_text) > 20
         print("✓ File Search + Code Interpreter works!")
-        
+
         # Cleanup
         project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
         openai_client.vector_stores.delete(vector_store.id)
@@ -109,11 +110,12 @@ def test_analyze_code_file(self, **kwargs):
 """
 
         vector_store = openai_client.vector_stores.create(name="CodeAnalysisStore")
-        
+
         from io import BytesIO
-        code_file = BytesIO(python_code.encode('utf-8'))
+
+        code_file = BytesIO(python_code.encode("utf-8"))
         code_file.name = "fibonacci.py"
-        
+
         file = openai_client.vector_stores.files.upload_and_poll(
             vector_store_id=vector_store.id,
             file=code_file,
@@ -134,23 +136,24 @@ def test_analyze_code_file(self, **kwargs):
             description="Agent for code analysis.",
         )
         print(f"Agent created (id: {agent.id})")
-        
+
         # Request analysis
         response = openai_client.responses.create(
             input="Find the fibonacci code and explain what it does. What is the computational complexity?",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_text = response.output_text
         print(f"Response: {response_text[:300]}...")
-        
+
         assert len(response_text) > 50
         response_lower = response_lower = response_text.lower()
-        assert any(keyword in response_lower for keyword in ["fibonacci", "recursive", "complexity", "exponential"]), \
-            "Expected analysis of fibonacci algorithm"
-        
+        assert any(
+            keyword in response_lower for keyword in ["fibonacci", "recursive", "complexity", "exponential"]
+        ), "Expected analysis of fibonacci algorithm"
+
         print("✓ Code file analysis completed")
-        
+
         # Cleanup
         project_client.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
         openai_client.vector_stores.delete(vector_store.id)

sdk/ai/azure-ai-projects/tests/agents/tools/multitool/test_agent_file_search_and_function.py

@@ -61,11 +61,12 @@ def test_data_analysis_workflow(self, **kwargs):
         # Create vector store and upload
         vector_store = openai_client.vector_stores.create(name="SalesDataStore")
         print(f"Vector store created (id: {vector_store.id})")
-        
+
         from io import BytesIO
-        txt_file = BytesIO(txt_content.encode('utf-8'))
+
+        txt_file = BytesIO(txt_content.encode("utf-8"))
         txt_file.name = "sales_data.txt"
-        
+
         file = openai_client.vector_stores.files.upload_and_poll(
             vector_store_id=vector_store.id,
             file=txt_file,
@@ -108,31 +109,31 @@ def test_data_analysis_workflow(self, **kwargs):
 
         # Request analysis
         print("\nAsking agent to analyze the sales data...")
-        
+
         response = openai_client.responses.create(
             input="Analyze the sales data and calculate the total revenue for each product. Then save the results.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         print(f"Initial response completed (id: {response.id})")
-        
+
         # Check if function was called
         function_calls_found = 0
         input_list: ResponseInputParam = []
-        
+
         for item in response.output:
             if item.type == "function_call":
                 function_calls_found += 1
                 print(f"Function call detected (id: {item.call_id}, name: {item.name})")
-                
+
                 assert item.name == "save_analysis_results"
-                
+
                 arguments = json.loads(item.arguments)
                 print(f"Function arguments: {arguments}")
-                
+
                 assert "summary" in arguments
                 assert len(arguments["summary"]) > 20
-                
+
                 input_list.append(
                     FunctionCallOutput(
                         type="function_call_output",
@@ -142,7 +143,7 @@ def test_data_analysis_workflow(self, **kwargs):
                 )
 
         assert function_calls_found > 0, "Expected save_analysis_results function to be called"
-        
+
         # Send function results back
         if input_list:
             response = openai_client.responses.create(
@@ -214,23 +215,23 @@ def test_empty_vector_store_handling(self, **kwargs):
 
         # Request analysis of non-existent file
         print("\nAsking agent to find non-existent data...")
-        
+
         response = openai_client.responses.create(
             input="Find and analyze the quarterly sales report.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_text = response.output_text
         print(f"Response: '{response_text[:200] if response_text else '(empty)'}...'")
-        
+
         # Verify agent didn't crash
         assert response.id is not None, "Agent should return a valid response"
         assert len(response.output) >= 0, "Agent should return output items"
-        
+
         # If there's text, it should be meaningful
         if response_text:
             assert len(response_text) > 10, "Non-empty response should be meaningful"
-        
+
         print("\n✓ Agent handled missing data gracefully")
 
         # Teardown
@@ -267,11 +268,12 @@ def calculate_sum(numbers):
 
         # Create vector store and upload
         vector_store = openai_client.vector_stores.create(name="CodeStore")
-        
+
         from io import BytesIO
-        code_file = BytesIO(python_code.encode('utf-8'))
+
+        code_file = BytesIO(python_code.encode("utf-8"))
         code_file.name = "sample_code.py"
-        
+
         file = openai_client.vector_stores.files.upload_and_poll(
             vector_store_id=vector_store.id,
             file=code_file,
@@ -313,22 +315,23 @@ def calculate_sum(numbers):
 
         # Request code analysis
         print("\nAsking agent to find and analyze the Python code...")
-        
+
         response = openai_client.responses.create(
             input="Find the Python code file and tell me what the calculate_sum function does.",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_text = response.output_text
         print(f"Response: {response_text[:300]}...")
-        
+
         # Verify agent found and analyzed the code
         assert len(response_text) > 50, "Expected detailed analysis"
-        
+
         response_lower = response_text.lower()
-        assert any(keyword in response_lower for keyword in ["sum", "calculate", "function", "numbers", "code", "python"]), \
-            "Expected response to discuss the code"
-        
+        assert any(
+            keyword in response_lower for keyword in ["sum", "calculate", "function", "numbers", "code", "python"]
+        ), "Expected response to discuss the code"
+
         print("\n✓ Agent successfully found code file using File Search")
 
         # Teardown
@@ -344,7 +347,7 @@ def calculate_sum(numbers):
     def test_multi_turn_search_and_save_workflow(self, **kwargs):
         """
         Test multi-turn workflow: search documents, ask follow-ups, save findings.
-        
+
         This tests:
         - File Search across multiple turns
         - Function calls interspersed with searches
@@ -383,13 +386,14 @@ def test_multi_turn_search_and_save_workflow(self, **kwargs):
         # Create vector store and upload documents
         vector_store = openai_client.vector_stores.create(name="ResearchStore")
         print(f"Vector store created: {vector_store.id}")
-        
+
         from io import BytesIO
-        file1 = BytesIO(doc1_content.encode('utf-8'))
+
+        file1 = BytesIO(doc1_content.encode("utf-8"))
         file1.name = "ml_healthcare.txt"
-        file2 = BytesIO(doc2_content.encode('utf-8'))
+        file2 = BytesIO(doc2_content.encode("utf-8"))
         file2.name = "ai_ethics.txt"
-        
+
         uploaded1 = openai_client.vector_stores.files.upload_and_poll(
             vector_store_id=vector_store.id,
             file=file1,
@@ -437,32 +441,32 @@ def test_multi_turn_search_and_save_workflow(self, **kwargs):
             input="What does the research say about machine learning in healthcare?",
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_1_text = response_1.output_text
         print(f"Response 1: {response_1_text[:200]}...")
         assert "95" in response_1_text or "accuracy" in response_1_text.lower()
-        
+
         # Turn 2: Follow-up for specifics
         print("\n--- Turn 2: Follow-up for details ---")
         response_2 = openai_client.responses.create(
             input="What specific applications are mentioned?",
             previous_response_id=response_1.id,
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_2_text = response_2.output_text
         print(f"Response 2: {response_2_text[:200]}...")
         response_2_lower = response_2_text.lower()
         assert any(keyword in response_2_lower for keyword in ["imaging", "drug", "risk", "prediction"])
-        
+
         # Turn 3: Save the finding
         print("\n--- Turn 3: Save finding ---")
         response_3 = openai_client.responses.create(
             input="Please save that finding about ML accuracy.",
             previous_response_id=response_2.id,
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         # Handle function call
         input_list: ResponseInputParam = []
         function_called = False
@@ -471,38 +475,38 @@ def test_multi_turn_search_and_save_workflow(self, **kwargs):
                 function_called = True
                 print(f"Function called: {item.name} with args: {item.arguments}")
                 assert item.name == "save_finding"
-                
+
                 args = json.loads(item.arguments)
                 assert "topic" in args and "finding" in args
                 print(f"  Topic: {args['topic']}")
                 print(f"  Finding: {args['finding'][:100]}...")
-                
+
                 input_list.append(
                     FunctionCallOutput(
                         type="function_call_output",
                         call_id=item.call_id,
                         output=json.dumps({"status": "saved", "id": "finding_001"}),
                     )
                 )
-        
+
         assert function_called, "Expected save_finding to be called"
-        
+
         # Send function result
         response_3 = openai_client.responses.create(
             input=input_list,
             previous_response_id=response_3.id,
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
         print(f"Response 3: {response_3.output_text[:150]}...")
-        
+
         # Turn 4: Switch to different topic (AI ethics)
         print("\n--- Turn 4: New search topic ---")
         response_4 = openai_client.responses.create(
             input="Now tell me about AI ethics concerns mentioned in the research.",
             previous_response_id=response_3.id,
             extra_body={"agent": {"name": agent.name, "type": "agent_reference"}},
         )
-        
+
         response_4_text = response_4.output_text
         print(f"Response 4: {response_4_text[:200]}...")
         response_4_lower = response_4_text.lower()