Directories ¶ Show internal Expand all Path Synopsis a2a as_function_tools command polling_for_task_completion command protocol_selection command stream_reconnection command agents message-injection command step01_running command step02_multiturn_conversation command step03_using_function_tools command step04_using_function_tools_with_approvals command step05_structured_output command step06_persisted_conversation command step07_3rdparty_session_storage command step08_observability command step09_dependency_injection command This sample shows how to use dependency injection to register an Agent and use it from a hosted service with a user input chat loop. This sample shows how to use dependency injection to register an Agent and use it from a hosted service with a user input chat loop. step10_as_mcp_tool command step11_using_images command step12_as_function_tool command step13_middleware command This sample shows how to write custom agent middleware. This sample shows how to write custom agent middleware. step13_using_audio_and_files command step17_additional_ai_context command step18_compaction_pipeline command step19_loop_reinvocation command step21_shell_with_environment command step22_foundry_memory command step23_planning_with_todos command agui step01_getting_started/client command step01_getting_started/server command step02_backend_tools/client command step02_backend_tools/server command step03_frontend_tools/client command step03_frontend_tools/server command step04_human_in_loop/client command step04_human_in_loop/server command step05_state_management/client command step05_state_management/server command mcp agent_mcp_server command local_stdio_mcp command providers a2a command anthrophic command anthrophic/thinking command azure/ai_project command azure/foundry_model command azure/openai_chat_completion command azure/openai_responses command azure/openai_responses_background command This sample demonstrates long-running agent operations using the OpenAI Responses API "background" option. This sample demonstrates long-running agent operations using the OpenAI Responses API "background" option. foundry/step01_basic command foundry/step02_1_multiturn command foundry/step02_2_multiturn_with_server_conversations command foundry/step03_function_tools command foundry/step04_function_tools_with_approvals command foundry/step05_structured_output command foundry/step06_persisted_conversations command foundry/step07_observability command foundry/step09_mcp_client_as_tools command foundry/step10_images command foundry/step11_as_function_tool command foundry/step12_middleware command foundry/step13_plugins command foundry/step14_code_interpreter command foundry/step21_web_search command foundry/step23_local_mcp command gemini command gemini/thinking command github-copilot command openai command openai/filesearch command openai/hosted_mcp command openai/reasoning command skills internal/skillhelpers step01_file_based_skills command step02_code_defined_skills command step03_mixed_skills command Click to show internal directories. Click to hide internal directories.