For AI agents: a documentation index is available at the root level at /llms.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
New
- Playground: all users can now switch between the current and new Playground experiences.
- Cache visibility: cache tables now show last used time, expiry, and hit count columns.
- Dataset row deletion: users can now delete individual dataset records from the logs table with a confirmation flow.
- Reports: reports now include an activity panel and inspector for easier review of report-related changes.
Improved
- Dashboard charts: improved metrics controls with timezone-aware ranges, chart expansion, drag-to-zoom, synced hover, layout reset behavior, and graph customizations.
- Experiments: improved the creation flow, model preset selection, log table wrapping, running indicators, and live result refresh while traces are still being written.
- Prompt and Playground navigation: prompt identity is now driven by URL parameters for more reliable sharing, reloads, and navigation.
- Tables: added infinite scrolling support, column reordering, better timestamp formatting, and improved table preview behavior.
- Logs and traces: improved preview table sizing and paused live streaming during bulk selection so selected rows stay stable.
- Views and preferences: scoped display preferences are now preserved more reliably after reloads.
Fixed
- Dataset uploads and experiment results: fixed a regression where dataset uploads could silently fail and experiment runs could complete without results.
- OAuth login: fixed a rate-limiting issue that could break OAuth or social login.
- Gateway prompt variables: prompt variables now resolve with consistent precedence across Chat and Responses APIs.
- Logging reliability: streaming logs now retry failed batch writes and route undeliverable batches to a recoverable queue instead of dropping them.
- Streaming reliability: stalled streaming consumers now recover automatically, reducing delayed logs and background processing gaps.
- Gateway credentials: dedicated deployments for one model no longer block shared credentials for other models under the same provider.