The daily firehose — everything the toolchain shipped today, already filtered.
// HOW THIS ISSUE IS MADE
We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.
$ git clone --branch @continuedev/[email protected] https://github.com/continuedev/continue.git
# already have the repo? check out this version:$ git checkout @continuedev/[email protected]
›Adds agent skills support to the cli (new agent skills capability for headless agent workflows).
›Adds automatic WSL detection in the cli to spawn the appropriate shell when running inside Windows Subsystem for Linux.
›Adds new OVHcloud models as selectable providers.
›Adds proportional output truncation for read and bash tool outputs instead of hard-cutting content.
›Raises an informative error for large files rather than silently truncating them.
+1 moreshow less
›Adds automatic retry logic for overloaded/rate-limit errors from model providers.
Qwen Code v0.9.0 adds multi-modal input, concurrent batch CLI, LSP support, extra_body for OpenAI providers, and a Zed extension.
└──▷ GET THIS VERSION
$ git clone --branch v0.9.0-nightly.20260131.bd900d36 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.9.0-nightly.20260131.bd900d36
›Adds extra_body support for OpenAI-compatible providers, enabling pass-through of provider-specific request fields.
›Adds contextWindowSize configuration key to control the model context window size.
›Adds parentToolCallId and subagentType fields for ACP subagent tracking.
›Adds a concurrent runner for batch CLI execution, enabling parallel multi-session runs.
›Adds multi-modal input support (image, PDF, audio) across all content generators.
+6 moreshow less
›Adds experimental LSP (Language Server Protocol) support for code intelligence.
›Adds a Zed extension for the Qwen Code agent server.
›Supports model selection through ACP in the VS Code IDE companion.
›Improves retry logic with better handling of 429 and 5xx errors.
›Clarifies output formats for non-interactive mode.
›Implements a unified web UI architecture with a shared component library.
›Adds --nopipelineparallel flag to disable pipeline parallel, which is now on by default in CLI.
›Adds --noflashattention flag to disable flash attention, which is now on by default in CLI.
›Adds --downloaddir option to specify where model downloads are stored when using URL references.
›Adds --sdvaeauto flag to enable TAE SD support for Flux2.
›Adds Vulkan (Older PC) GPU support in oldpc builds, providing Vulkan acceleration without AVX2 or AVX CPU intrinsics.
+11 moreshow less
›Adds support for SDXS, a fast Stable Diffusion image generation model capable of generating images on CPU in under 10 seconds on a Raspberry Pi, or under half a second on GPU.
›Adds support for ESRGAN 4x upscaler (RealESRGAN), loadable as an upscaler model to upscale generated images.
›Adds Flux Klein image model support (requires separate image model, VAE, and text encoder).
›Increases image generation hard total resolution limit from 1 megapixel to 1.6 megapixels.
›Adds upstream model support for Step 3.5 Flash and Kimi Linear.
›Adds GLM4.7-NoThink adapter template for GLM 4.7 Flash.
›Adds experimental TTS chunked streaming mode in Kobold Lite, compatible with all TTS APIs.
›Adds customizable sampler presets in Kobold Lite.
›Adds error as a possible stop reason (e.g. when the backend fails to generate).
›Adds Vulkan speedup via occam's coopmat1 optimization, benefiting AMD GPUs with matrixcores such as 7000 and 9000 series.
›Reworks the newbie help menu with simple starter configs.
└──▷ BREAKING ON UPGRADE
!Pipeline parallel is now enabled by default in CLI; existing setups relying on it being off must explicitly add --nopipelineparallel.
!Flash attention is now enabled by default in CLI; existing setups relying on it being off must explicitly add --noflashattention.
!The CLBlast backend has been fully removed; users requiring CLBlast must use an earlier version.
llama-quantize gains --tensor-type-file to specify per-tensor quantization types via a file.
└──▷ GET THIS VERSION
$ git clone --branch b7897 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b7897
└──▷ TRY IT
Apply custom per-tensor quantization types from a file instead of specifying them inline, useful for fine-grained control over large model quantization.
THE AI TOOLCHAIN