core/v1.10.2
maximhq/bifrostcore/v1.10.2Sep 24, 2026by akshaydeo
Upgrading?
AI Summary
This core release adds support for GPT-6 prompt caching and pinned routing keys, while fixing integration issues with OpenAI, Anthropic, and Bedrock.
Key Highlights
- Pinned provider keys are now supported on routing fallbacks via key_id.
- Added prompt-cache breakpoints for GPT-6 family and reasoning effort 'none' for specific models.
- Fixed wire shapes for structured MCP tools and session affinity routing logic.
Breaking Changes
- `ResponsesMCPApprovalResponse.ApprovalResponseID` is now `ApprovalRequestID`.
- Message type is now `mcp_approval_response`.
- `ResponsesToolMessage.Error` and `ResponsesParameters.Conversation` are now union types (previously `*string`).
New Features
- Forward OpenAI async tools, output_schema and tunnel_id on Responses
- Prompt-cache breakpoints for the GPT-6 family
- Reasoning effort 'none' for gpt-6-sol and gpt-6-luna
Full Release Notes
## Core Release v1.10.2 - feat: pinned provider keys on routing fallbacks via key_id on each fallback (#7470) - feat: forward OpenAI async tools, output_schema and tunnel_id on Responses, stripping async for unsupported models with a SupportsAsyncTools datasheet override (#7242) - feat: prompt-cache breakpoints for the GPT-6 family with a SupportsPromptCacheBreakpoint datasheet override (#7240) - feat: reasoning effort none for gpt-6-sol and gpt-6-luna (#7492) - fix: strip unsupported temperature, top_logprobs and logprobs alongside top_p for OpenAI reasoning models, and count an omitted effort as none only for models that default to no reasoning (#7239) - fix: Responses wire shapes for structured MCP tool errors, object-form conversation, array-form MCP allowed_tools, approval_request_id and in/nin file search filters (#7241) <Warning>Go SDK callers: `ResponsesMCPApprovalResponse.ApprovalResponseID` is now `ApprovalRequestID`, the message type is now `mcp_approval_response`, and `ResponsesToolMessage.Error` and `ResponsesParameters.Conversation` are now union types, where they used to be `*string`.</Warning> - fix: keep cache_control breakpoints for Anthropic models routed through OpenRouter (#7521) - fix: move routing key pins with their provider when session affinity reorders the chain (#7468) - fix: match session affinity routes on provider and model together, and drop bindings the request followed into a failure (#7473) - fix: merge multiple system and developer messages for Databricks-hosted Gemini models (#7461) - fix: treat Bedrock's cross-account or cross-model encrypted reasoning rejection as recoverable and retry without it - fix: decision emulation uses tool_choice auto for gpt-oss on Bedrock Mantle, and recovers leaked parameter tags with surrounding whitespace - fix: report Gemini transcription usage even when the transcript is empty ### Installation ```bash go get github.com/maximhq/bifrost/core@v1.10.2 ``` --- _This release was automatically created from version file: `core/version`_
Related Repositories
ollama/ollama★ 184,248
Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
fatedier/frp★ 110,069
A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.
infiniflow/ragflow★ 92,636
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
gohugoio/hugo★ 90,198
The world’s fastest framework for building websites.
junegunn/fzf★ 83,715
:cherry_blossom: A command-line fuzzy finder