chore(tests): fix responses and vector_io tests

tests/integration/non_ci/responses/fixtures/test_cases/responses.yaml

@@ -137,7 +137,7 @@ test_response_multi_turn_tool_execution:
         server_url: "<FILLED_BY_TEST_RUNNER>"
       output: "yes"
     - case_id: "experiment_results_lookup"
-      input: "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me what you found."
+      input: "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me the boiling point in Celsius."
       tools:
       - type: mcp
         server_label: "localmcp"
@@ -149,7 +149,7 @@ test_response_multi_turn_tool_execution_streaming:
   test_params:
     case:
     - case_id: "user_permissions_workflow"
-      input: "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step."
+      input: "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response."
       tools:
       - type: mcp
         server_label: "localmcp"
@@ -157,7 +157,7 @@ test_response_multi_turn_tool_execution_streaming:
       stream: true
       output: "no"
     - case_id: "experiment_analysis_streaming"
-      input: "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Please stream your analysis process."
+      input: "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Return only one tool call per step.  Please stream your analysis process."
       tools:
       - type: mcp
         server_label: "localmcp"

tests/integration/non_ci/responses/test_responses.py

@@ -363,6 +363,9 @@ def test_response_non_streaming_file_search_empty_vector_store(request, compat_c
     ids=case_id_generator,
 )
 def test_response_non_streaming_mcp_tool(request, compat_client, text_model_id, case):
+    if not isinstance(compat_client, LlamaStackAsLibraryClient):
+        pytest.skip("in-process MCP server is only supported in library client")
+
     with make_mcp_server() as mcp_server_info:
         tools = case["tools"]
         for tool in tools:
@@ -485,8 +488,11 @@ def test_response_non_streaming_multi_turn_image(request, compat_client, text_mo
     responses_test_cases["test_response_multi_turn_tool_execution"]["test_params"]["case"],
     ids=case_id_generator,
 )
-def test_response_non_streaming_multi_turn_tool_execution(request, compat_client, text_model_id, case):
+def test_response_non_streaming_multi_turn_tool_execution(compat_client, text_model_id, case):
     """Test multi-turn tool execution where multiple MCP tool calls are performed in sequence."""
+    if not isinstance(compat_client, LlamaStackAsLibraryClient):
+        pytest.skip("in-process MCP server is only supported in library client")
+
     with make_mcp_server(tools=dependency_tools()) as mcp_server_info:
         tools = case["tools"]
         # Replace the placeholder URL with the actual server URL
@@ -541,8 +547,11 @@ def test_response_non_streaming_multi_turn_tool_execution(request, compat_client
     responses_test_cases["test_response_multi_turn_tool_execution_streaming"]["test_params"]["case"],
     ids=case_id_generator,
 )
-async def test_response_streaming_multi_turn_tool_execution(request, compat_client, text_model_id, case):
+def test_response_streaming_multi_turn_tool_execution(compat_client, text_model_id, case):
     """Test streaming multi-turn tool execution where multiple MCP tool calls are performed in sequence."""
+    if not isinstance(compat_client, LlamaStackAsLibraryClient):
+        pytest.skip("in-process MCP server is only supported in library client")
+
     with make_mcp_server(tools=dependency_tools()) as mcp_server_info:
         tools = case["tools"]
         # Replace the placeholder URL with the actual server URL
@@ -634,7 +643,7 @@ async def test_response_streaming_multi_turn_tool_execution(request, compat_clie
         },
     ],
 )
-def test_response_text_format(request, compat_client, text_model_id, text_format):
+def test_response_text_format(compat_client, text_model_id, text_format):
     if isinstance(compat_client, LlamaStackAsLibraryClient):
         pytest.skip("Responses API text format is not yet supported in library client.")
 
@@ -653,7 +662,7 @@ def test_response_text_format(request, compat_client, text_model_id, text_format
 
 
 @pytest.fixture
-def vector_store_with_filtered_files(request, compat_client, text_model_id, tmp_path_factory):
+def vector_store_with_filtered_files(compat_client, text_model_id, tmp_path_factory):
     """Create a vector store with multiple files that have different attributes for filtering tests."""
     if isinstance(compat_client, LlamaStackAsLibraryClient):
         pytest.skip("Responses API file search is not yet supported in library client.")