Skip to main content
v1.4.0-prerelease3

Changelog

This release hardens SSO/SCIM security, adds cluster synchronization for routing rules, introduces reliable replication, and picks up OSS Azure passthrough, new pricing tiers, and a set of streaming/async safety fixes.

✨ Features

  • Reliable Replication - New replication logic for more dependable state propagation across cluster nodes
  • Routing Rule Cluster Sync - Routing rules now synchronize across the cluster via dedicated message handling, keeping all nodes in agreement
  • Leader-Only Cluster Pricing Sync - Only the cluster leader fetches pricing URLs, then broadcasts DB reloads to followers - cuts redundant fetches and keeps pricing consistent
  • Terraform Account ID - Account ID surfaced for Terraform integrations
  • Azure Passthrough - Native Azure passthrough support added upstream
  • OAuth MCP Hints - OAuth MCP client creation response now includes next-step hints for a smoother setup flow
  • 272k Token Tier Pricing - Pricing support for the 272k token tier
  • Flex & Priority Tier Pricing - Pricing support for flex and priority service tiers
  • Dockerfile Upgrades - Base image and tooling upgrades across environment Dockerfiles

🐞 Fixed

  • SSO Role Enforcement - SSO login is now denied when the user has no role claims and no matching group-to-role mapping; removed the Okta Org Auth Server special case that auto-granted Admin to the first user (security hardening)
  • SCIM Provider Fixes - Broad fixes across SCIM controller, mapping, and Entra/Google/Keycloak/Okta/SailPoint/Zitadel providers; new SCIM tables, migrations, and config-store wiring
  • LB Routing for GenAI & Bedrock - Load balancing routing fixes for GenAI and Bedrock integrations
  • Streaming Post-Hook Race - Fixed a race where fasthttp RequestCtx could be recycled before transport post-hooks finished in streaming goroutines; request/response snapshots are now captured eagerly
  • Async User Values - User values are now propagated through all async inference handlers and job submissions
  • Trace Completer Safety - Trace completer accepts transport logs as a parameter instead of reading from a potentially recycled context
  • Async Log Store Exceptions - Fixed exception handling in async log store jobs
  • Model Alias Tracking - Split ModelRequested into OriginalModelRequested and ResolvedModelUsed for accurate alias resolution tracking
  • MCP Tool Discovery - Added discovered tools and tool-name mapping columns to MCP clients
  • Guardrails Plugin - Guardrail plugin cleanup and Bedrock guardrail adjustments

📀 Base OSS version

transports/v1.5.0-prerelease3

🔌 If you are compiling plugin against this release - use following deps