2026 Aug 7 Release

Conversation UI
Improved progress feedback for tools and model activity
Web search and document generation now provide clearer in-progress status details, making it easier to understand what the assistant is doing during longer-running requests. Model reasoning indicators have also been refined so internal status content does not appear in the final response.
Administration
Provider setup wizard
A new guided wizard simplifies provider configuration and helps administrators complete setup more efficiently. The wizard also displays provider save errors instead of failing without clear feedback.
Improved favicon guidance
The favicon configuration experience now informs administrators that customers may need to perform a hard refresh before a newly configured favicon appears.
Improved AI usage and spend tracking
AI Portal now accounts for cached tokens when tracking model usage and normalizes model pricing to a per-million-token rate. Improved mapping between model variants and their billing models provides administrators with more accurate usage and spend calculations.
Bug Fixes
Fixed an issue where the active item in the prompt sidebar could be displayed incorrectly.
Fixed an issue where embedding model deployment failed when the selected model was unsupported in the configured Azure region. AI Portal now uses a fallback deployment option when appropriate.
Fixed an issue where model-generated thinking content could appear as part of the assistant’s final response.