Changelog
This release upgrades the base OSS version from v1.4.11 to v1.4.12, bringing a full-featured prompt repository with RBAC, large payload optimization, WebSocket-based responses API, Anthropic passthrough, session stickiness, and a unified pricing engine. On the enterprise side, this release adds KV store gossip protocol support, RBAC for the prompt repository, and build/deployment improvements.✨ Features
- Prompt Repository — Full prompt management system with folders, prompts, versions, sessions, playground, versioning, deployment features, and Jinja2 variable support
- Prompt Repository RBAC — Added role-based access control for prompt repository operations
- Large Payload Optimization — End-to-end large payload support with streaming primitives, detection hooks, passthrough eligibility, provider support, plugin awareness, and enterprise settings UI
- WebSocket Responses aAPI — Added WebSocket transport for OpenAI responses API and realtime API support
- Anthropic Passthrough — Added native Anthropic passthrough endpoint
- KV Store Gossip Protocol — Added gossip-based KV store for distributed state synchronization
- Session Stickiness — Added session stickiness in key selection for consistent routing
- Model Parameters API — Added model parameters table and API endpoint with in-memory caching
- Virtual Key Limit Resets — Added virtual key limit reset functionality
- Pricing Engine Refactor — Unified cost calculation with quality-based image and video pricing
- Image Configuration — Added size/aspect ratio config for Gemini and size-to-resolution conversion for Replicate
- Streaming Request Decompression — Threshold-gated streaming decompression with pooled readers
- Raw Request/Response Storage — Allow storing raw request/response without returning them to clients
- Weighted Routing Targets — Added weighted routing targets for probabilistic routing rules with key selection support
- API Key Selection by ID — Added API key selection by ID with priority over name selection
- TLS Configuration — Added TLS configuration support for all providers and TLS termination inside Bifrost server
- K8s Deployment Workflow — Added workflow to deploy Bifrost Enterprise to Maxim K8s cluster
🐞 Fixed
- Deterministic Tool Schema — Fixed deterministic tool schema serialization for Anthropic prompt caching
- CORS Wildcard — Fixed CORS issue with allowing * origin
- Bedrock toolChoice — Fixed toolChoice silently dropped on Bedrock /converse and /converse-stream endpoints
- Count Tokens Passthrough — Fixed request body passthrough for count tokens endpoint for Anthropic and Vertex
- Chat Finish Reason — Map chat finish_reason to responses status and preserve terminal stream semantics
- Tool Call Indexes — Fixed streaming tool call indices for parallel tool calls in chat completions stream
- Video Pricing — Fixed video pricing calculation
- SQLite Migration — Prevented CASCADE deletion during routing targets migration
- Log Serialization — Reduced logstore serialization overhead and batch cost updates
- Log List Queries — Avoid loading raw_request/raw_response in log list queries
- MCP Reconnection — Improved MCP client reconnection with exponential backoff and connection timeout
- Create Manifest Flow — Fixed create manifest flow
- Build Pipeline — Fixed builds skipping latest changes
- BigQuery Import — Fixed import for codeEditor in bigqueryFormFragment.tsx
- OSS Build Integration — Support latest-main OSS build with go.mod replace directives
📀 Base OSS version
transports/v1.4.12
