关注连接模型的工具：AI Agent、MCP、模型网关、编程助手、推理引擎和自动化工作流。
## What's changed - Added `x-claude-code-request-class`, `x-claude-code-agent-type`, `x-claude-code-prev-tool-durations`, `x-claude-code-compaction` and `x-claude-code-context-compacted` request headers for LLM gateways; opt in with `CLAUDE_CODE_GATEWAY_HINT_H
llama.cpp build changes resulted in duplicate symbols between libllama and libmtmd. This moves the compat patch into libllama with exported symbols.
## What's Changed * MLX safetensors `ollama create` no longer experimental. GGUF model creation now requires using llama.cpp tooling for safetensor conversion and quantization. * Improved MLX memory handling on Apple Silicon * Runaway repeat token detection no
Qwen CUA Driver prebuilt binaries (vendored under `packages/cua-driver`). - **macOS**: codesigned + notarized universal binary + `QwenCuaDriver.app` - **Linux**: unsigned (x86_64 + arm64, glibc 2.31 floor) - **Windows**: unsigned UIAccess worker + native SDK p
Drop support for creating new models with typical_p parameters, while retaining support for existing GGUF models with the setting.
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
## What's changed - Bug fixes and reliability improvements
## What's changed - Added fast mode in Claude Code Remote sessions (cloud and self-hosted runners): the host's fast-mode setting or `/fast` typed in the session applies where your organization allows it - Added mouse support to the `/config` panel in fullscree
## What's Changed * test: record what the Windows inode gates are hiding, and un-skip one by @yiliang114 in https://github.com/QwenLM/qwen-code/pull/11853 * fix(cua): preserve Linux observations and REPL diagnostics by @DragonnZhang in https://github.com/QwenL
mlx: add mlx patch to docker build context (#18440)
## Highlights _See the complete change list below._ ## Breaking Changes - Removes configurable message-prefix filtering from channels, so eligible messages now follow normal sender, group, mention, and pairing policies without a prefix. ([#11571](https://githu
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
## What's changed - Fixed read-only git commands in Bash unexpectedly asking for permission after a session had been running for a while (regression in 2.1.269)
## What's changed - Added `claude plugin eval`: run a plugin's eval suite against Claude Code and get scored, reproducible results (JSON + HTML report); see `claude plugin eval --help` - Added `/output-style [name]` to list and switch output styles, including
Changes since langchain-core==1.6.2 release(core): 1.6.3 (#40407) feat(core): Allow model name and provider tracing metadata override based on gateway response (#40406) test(core): cover the deprecated `.text()` access path (#40243) docs(core): remove stale Ar
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
Changes since langchain-anthropic==1.7.1 release(anthropic): 1.7.2 (#40387) fix(anthropic): preserve invalid tool use blocks (#40372)
This blog post is the fourth and final installment of The Economics of Agent Optimization, which shares the strategies, capabilities, and proof points that can help you optimize agent costs and run AI as a managed investment system on Microsoft Foundry. The po
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
# Release v5.17.0 ## New Model additions ### HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
## Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output p
Build and launch cloud agents with the Agents API, a managed service powered by the Codex harness for orchestration, long-running sessions, and tool use.
## What's Changed ### Features - Add telemetry to track checkpoint runtime and CLI usage. ### Bug Fixes - Fix gateway errors reported inside an HTTP 200 response. - Keep deploy push on the AMP create source. - Report scrape failures instead of raising IndexErr
Changes since langchain-openai==1.6.1 release(openai): 1.6.2 (#40339) fix(openai): add GPT-6 Astra reasoning efforts (#40330) chore(deps): bump httpx2 from 2.10.0 to 2.12.0 in /libs/partners/openai (#40309)
## Verify Docker Image Signature All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d
Changes since langchain-openai==1.6.0 fix(openai): bump `max_completion_tokens` in cache breakpoint integration test (#40284) release(openai): 1.6.1 (#40268) chore(model-profiles): refresh model profile data (#40217) fix(openai): support Azure AD auth with Ope
## Highlight - **Realtime Voice Agent**: Introduced a realtime voice agent with DashScope backends and local transport support. - **A2A Protocol Support**: Added `A2AAgent` class to the agent module, enabling agent-to-agent communication. - **New Pipeline Modu
`pip install -U mcp`. Docs: https://py.sdk.modelcontextprotocol.io/ A few defaults changed in this release. If you run a server or client on 2.x, skim these first: ## Behaviour changes **HTTP client redirects are only followed within the endpoint's origin** (#
Maintenance release of the 1.x line. 2.x is the current line; 1.x docs are at https://py.sdk.modelcontextprotocol.io/v1/. A few defaults changed in this release. If you run a server or client on 1.x, skim these first: ## Behaviour changes **HTTP client redirec
