azure-ai-projects_2.6.0

2.6.0 (2026-09-04)

Features Added

• Added supporting AgentInsight* models and enums covering monitors, runs, generated insights, proposed fixes, highlighted and linked traces, costs, token usage, severity, status, and run triggers.
• Added Microsoft 365 agent publishing.
• Added optional Hosted Agent session defaults through HostedAgentDefinition.session_configuration and SessionConfiguration, including idle-timeout configuration.
• Added content-safety moderation support for custom request, response, and streaming invocation body formats.
• Added the optional authorization argument to .beta.routines.create_or_update, with RoutineAuthorization and RoutineDispatchIdentity for selecting the agent or routine creator identity.
• Added ShellToolboxTool and supporting container environment and network policy models, with the new ToolboxToolType.SHELL enum member.
• Added WebIQPreviewTool and WebIQPreviewToolboxTool, with new ToolType.WEB_IQ_PREVIEW and ToolboxToolType.WEB_IQ_PREVIEW enum members.
• Added the optional external_web_access property to WebSearchTool and WebSearchToolboxTool for disabling live internet access.

Sample updates

• Added sample_toolbox_with_shell.py under samples/agents/tools/, demonstrating a Prompt Agent invoking a ShellToolboxTool.
• Added sample_toolbox_with_shipping_skill.py under samples/agents/tools/, demonstrating a Prompt Agent using a skill through a Toolbox MCP endpoint.
• Added sample_toolbox_with_shell_and_skill.py under samples/agents/tools/, demonstrating a Prompt Agent using a skill with a ShellToolboxTool through a Toolbox MCP endpoint.
• Added sample_synthetic_multiturn_evaluation.py under samples/evaluations/, demonstrating simulation seed generation from an agent followed by multi-turn conversation simulation and evaluation.
• Added sample_responses_model_router.py under samples/responses/, demonstrating a Responses API request to a model router deployment and selection of a model by the router.

Bugs Fixed

• Fixed Responses API instrumentation for with_raw_response streaming calls (GitHub issue 48646).