Skip to content

azure-ai-projects_2.4.0

Latest
Latest

Choose a tag to compare

View all tags
@azure-sdk-automation azure-sdk-automation released this 27 Jul 21:42
azure-ai-projects_2.4.0
97af294
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

2.4.0 (2026-07-24)

Features Added

  • New stable toolbox tool ToolSearchToolboxTool (discriminator toolbox_search) for storing a tool-search tool in a toolbox.
    This replaces ToolboxSearchPreviewToolboxTool, which is still present but will be removed in a future release of the package. Please migrate your code to use the stable tool.
  • New class TaskGenerationDataGenerationJobOptions (discriminator task_generation) with data generation job options for multi-turn evaluation scenarios.
  • Support for non-fatal input-quality advisories from rubric evaluator generation. See new class RubricGenerationInputQualityWarning and new enums RubricGenerationInputQualityWarningCode, RubricGenerationInputQualityWarningSeverity, and RubricGenerationInputQualityWarningSource.
  • New enum GenerationWarningType.
  • New enum AgentIdentityStatus and new optional status property on class AgentIdentity.
  • New read-only property input_quality_warnings on class EvaluatorGenerationJob.
  • New read-only properties generation_job_id and warnings on class EvaluatorVersion.
  • New optional property max_stalls on class OptimizationOptions.

Breaking Changes

Breaking changes in beta methods:

  • Method .beta.evaluators.create_generation_job renamed to .beta.evaluators.begin_create_generation_job and is now a long-running operation returning LROPoller[EvaluatorVersion] (previously returned EvaluatorGenerationJob).
  • Method .beta.datasets.create_generation_job renamed to .beta.datasets.begin_create_generation_job and is now a long-running operation returning LROPoller[DataGenerationJobResult].
  • Method .beta.agents.create_optimization_job renamed to .beta.agents.begin_create_optimization_job and is now a long-running operation returning LROPoller[OptimizationJobResult].

Sample updates

  • Added new optimization polling samples sample_optimization_job_basic_polling.py and sample_optimization_job_basic_polling_async.py under samples/agents/optimization/.
  • Added new evaluation samples sample_endpoint_evaluator_with_api_key.py and sample_endpoint_evaluator_with_entra_id.py under samples/evaluations/.
  • Added new Hosted Agent sample sample_agent_user_identity_isolation.py under samples/hosted_agents/, demonstrating per-user response-chain isolation with delegated end-user identities sent in the x-ms-user-identity header.
  • Added new Hosted Agent routine samples sample_routines_with_github_issue_trigger.py and sample_routines_with_teams_message_trigger.py, demonstrating GitHub issue and Microsoft Teams channel-message triggers for routines backed by a temporary Hosted Agent version.
  • Added new Hosted Agent sample sample_toolbox_with_reminder_preview.py under samples/hosted_agents/, demonstrating a Reminder Preview toolbox tool wired through a Foundry Toolbox MCP endpoint.
  • Updated Hosted Agent toolbox asset samples/hosted_agents/assets/toolbox-agent/main.py to use FoundryToolbox and as_skills_provider() for toolbox MCP skill discovery and wiring, replacing the earlier manual MCP session, auth, and HTTP client setup.
  • Renamed toolbox tool-search samples sample_toolboxes_with_search_preview.py and sample_toolboxes_with_search_preview_async.py to sample_toolboxes_with_search.py and sample_toolboxes_with_search_async.py.
  • Renamed the Hosted Agent image-based creation samples from sample_create_hosted_agent.py and sample_create_hosted_agent_async.py to sample_create_hosted_agent_from_image.py and sample_create_hosted_agent_from_image_async.py.
  • Relocated Hosted Agent routine trigger samples sample_routines_with_dispatch.py, sample_routines_with_schedule_trigger.py, and sample_routines_with_timer_trigger.py from samples/routines/ to samples/hosted_agents/.
  • Removed Hosted Agent endpoint samples sample_agent_endpoint.py and sample_agent_endpoint_async.py.
  • Removed routine sample samples/routines/sample_routines_crud.py.
  • Removed prompt-agent toolbox skill sample samples/agents/tools/sample_agent_toolbox_skill.py because skill-in-toolbox is not yet supported in Prompt Agents.
  • Updated Hosted Agent toolbox samples to create temporary Hosted Agent versions for execution flows, assign Azure AI User RBAC before invoking Toolbox MCP endpoints, restore the prior endpoint, and clean up temporary resources during teardown.
Assets 2
Loading