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.
LangChain Core 1.2.4 adds usage_metadata to trace metadata in LangChainTracer.
└──▷ GET THIS VERSION
$ git clone --branch langchain-core==1.2.4 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-core==1.2.4
›Adds usage_metadata field to metadata recorded by LangChainTracer, making token-usage information available in traces.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.0.74 adds LSP code-intelligence tools, expands terminal setup support, and improves theme controls.
└──▷ GET THIS VERSION
$ git clone --branch v2.0.74 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.0.74
└──▷ TRY IT
Configure optimal key bindings and shell integration for Kitty, Alacritty, Zed, or Warp in one step.
$ /terminal-setup
Quickly toggle syntax highlighting off for a distraction-free diff review while browsing themes.
$ /theme # then press ctrl+t to toggle syntax highlighting on/off
›Adds LSP (Language Server Protocol) tool enabling code-intelligence features: go-to-definition, find references, and hover documentation.
›Adds /terminal-setup support for Kitty, Alacritty, Zed, and Warp terminals.
›Adds ctrl+t shortcut in /theme to toggle syntax highlighting on/off.
›Adds syntax highlighting info display inside the theme picker.
›Improves /context command visualization with skills and agents grouped by source, slash commands listed, and token counts sorted.
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Goose v1.18.0 adds slash commands for prompt/history management, OpenRouter & xAI streaming, and skills discovery paths.
└──▷ GET THIS VERSION
$ git clone --branch v1.18.0 https://github.com/block/goose.git
# already have the repo? check out this version:$ git checkout v1.18.0
└──▷ TRY IT
Browse available prompts and run one by name during an interactive session — useful for quickly invoking saved prompt templates.
$ /prompts
/prompt my-security-review-prompt
Inspect a prompt's parameters and metadata before executing it, helpful when you want to understand a recipe's required inputs.
$ /prompt my-security-review-prompt --info
Compact or clear conversation history mid-session to stay within context limits without starting a new session.
$ /compact
# or, to wipe the full history:
/clear
›Adds /prompts slash command to list available prompts, /prompt to execute a prompt or inspect it with --info, /compact to compact conversation history, and /clear to clear conversation history.
›Adds recipe slash command parsing with improved parameter handling.
›Adds streaming support for OpenRouter and xAI providers.
›Adds skills auto-discovery from .agents/skills and ~/.config/agent/skills paths.
›Adds a Goose PR reviewer workflow for automated code review.
+2 moreshow less
›Adds pricing integration with the canonical model registry.
›Adds ability to disable the auto-update feature for the CLI.
Lightweight coding agent that runs in your terminal
Codex CLI gains /ps command, ExternalSandbox policy, model list UI, admin-scoped skills, and system-wide UNIX config support.
└──▷ GET THIS VERSION
$ git clone --branch rust-v0.76.0 https://github.com/openai/codex.git
# already have the repo? check out this version:$ git checkout rust-v0.76.0
└──▷ TRY IT
Inspect processes currently running inside a Codex session — useful when debugging long-running agent tasks.
$ /ps
›Adds /ps command to list running processes from within the TUI.
›Introduces ExternalSandbox policy for delegating sandbox enforcement to an external process.
›Supports system-wide /etc/codex/requirements.toml on UNIX for admin-managed dependency configuration.
›Adds a model list UI for browsing and selecting available models interactively.
›Enables skills by default (previously opt-in), with support for admin-scoped skills.
+4 moreshow less
›Supports shortDescription field for skills entries, surfaced in the skills popup.
›Adds macOS DMG build target for easier distribution and installation.
›Improves terminal detection metadata to enable per-terminal scroll tuning.
›Updates bundled system skills included with the CLI.
└──▷ BREAKING ON UPGRADE
!The exclude setting now defaults to true in the app server, changing behavior for existing app-server deployments that relied on the previous default.
›Exports getAvailableModels, getApiKeyForModel, findModel, login, logout, and getOAuthProviders from @mariozechner/pi-coding-agent so custom AgentSession scripts can reuse OAuth token storage and model resolution.
›Adds xhigh thinking level option for gpt-5.2 and gpt-5.2-codex models in the thinking level selector and shift+tab cycling.
Pi v0.24.0 adds multi-agent orchestration, Kitty keyboard protocol, dynamic OAuth refresh, and a new /hotkeys command.
└──▷ GET THIS VERSION
$ git clone --branch v0.24.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.24.0
└──▷ USE IT
Cancel a long-running shell command from a custom tool or hook if it exceeds a time limit.
typescript
const result = await pi.exec("npm test", { timeout: 30000 });
if (result.killed) console.error("Process timed out and was terminated");
Display all available keyboard shortcuts at any point during a session.
$ /hotkeys
›Adds a comprehensive subagent orchestration example with scout/planner/reviewer/worker agents and multi-agent pipeline workflow commands.
›Enables pi.exec() to accept { signal, timeout } options in custom tools and hooks, with a killed flag on the result when the process is terminated.
›Supports the Kitty keyboard protocol, enabling Shift+Enter, Alt+Enter, Shift+Tab, Ctrl+D, and all Ctrl+key combos in Ghostty, Kitty, WezTerm, and other modern terminals.
›Adds dynamic OAuth token refresh for GitHub Copilot and Anthropic OAuth before each LLM call, preventing auth failures in long-running agent loops.
›Adds /hotkeys command to display all keyboard shortcuts in a formatted table.
+2 moreshow less
›Exports getMarkdownTheme() from @mariozechner/pi-coding-agent so custom tools can use the same markdown styling as the main UI.
›Renders markdown tables with proper top and bottom borders.
└──▷ BREAKING ON UPGRADE
!Auto-discovered custom tools now require an index.ts entry point inside a subdirectory: the old pattern ~/.pi/agent/tools/mytool.ts must become ~/.pi/agent/tools/mytool/index.ts. Explicit paths via --tool or settings.json still accept any .ts file.
!The ToolResultEventresult: string field is removed; hook handlers must replace { result: "..." } returns with { content: [{ type: "text", text: "..." }] }, and access content via content: (TextContent | ImageContent)[] instead. ToolResultEventResult.result is renamed/removed — use content instead.
Qwen Code v0.5.1 adds chat recording toggle, a /resume slash command, and exposes gitCoAuthor in settings.json
└──▷ GET THIS VERSION
$ git clone --branch v0.5.1 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.5.1
└──▷ USE IT
Enable git co-author attribution so AI-assisted commits credit the model automatically.
json
{
"gitCoAuthor": true
}
›Adds gitCoAuthor setting to settings.json to control git co-author attribution in commits.
›Adds /resume slash command in the CLI to switch between sessions interactively.
›Adds chat recording toggle accessible via CLI flags and the settings UI.
›IDE companion discovery switches to lock files under ~/.qwen/ide, changing where the tool looks for IDE connections.
└──▷ BREAKING ON UPGRADE
!IDE companion discovery now uses ~/.qwen/ide lock files instead of the previous location; existing IDE companion setups may fail to connect until updated.
Qwen Code v0.5.1 adds chat recording toggle, /resume slash command, and gitCoAuthor setting in settings.json
└──▷ GET THIS VERSION
$ git clone --branch v0.5.1-preview.0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.5.1-preview.0
└──▷ USE IT
Attribute AI-assisted commits to the model by setting gitCoAuthor in your Qwen Code settings.
json
{
"gitCoAuthor": true
}
›Adds gitCoAuthor setting to settings.json to control git co-author attribution in commits.
›Adds /resume slash command in the CLI UI to switch between sessions interactively.
›Adds chat recording toggle available via CLI flag and settings.
›IDE companion discovery switches to ~/.qwen/ide lock files for locating running IDE instances.
Qwen Code SDK gains a VSCode extension, session-resume command, chat recording toggle, Russian i18n, and a terminal bell setting.
└──▷ GET THIS VERSION
$ git clone --branch sdk-typescript-v0.1.1-nightly.20251219.e4468cfc https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout sdk-typescript-v0.1.1-nightly.20251219.e4468cfc
└──▷ TRY IT
Resume a previous Qwen Code session by name without re-entering the full chat history manually.
$ /resume
Enable git co-author attribution and disable the terminal bell in your personal settings.
json
{
"gitCoAuthor": true,
"terminalBell": false
}
›Adds gitCoAuthor setting to settings.json to control git co-author behaviour and exposes it in documentation.
›Adds /resume slash command to switch between saved sessions from within the CLI UI.
›Adds chat recording toggle via CLI flag and the settings.json settings interface; recording is disabled in test runs.
›Adds channel field support in client identification requests.
›Adds terminal bell setting to settings.json to enable or disable audio notifications.
+6 moreshow less
›New VSCode Extension implementation bundled into the VSCode release package, including IDE companion with authentication and completion menu support.
›Shows the session-resume command on CLI exit so users can quickly re-enter a previous session.
›Adds Russian (ru) language support via the /language command.
›Adds ACP usage metadata reporting and an ACP authenticate update message.
›Removes input-prompt vertical borders in the terminal UI for easier copy/paste.
›Adds comprehensive MCP Quick Start guides and examples to documentation.
$ git clone --branch v0.5.1-nightly.20251219.d07ae35c https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.5.1-nightly.20251219.d07ae35c
└──▷ TRY IT
Resume a previous Qwen Code session quickly from the command line using the new short alias.
$ qwen -r
Set a git co-author for all AI-assisted commits without touching the CLI each time.
llama.cpp b7484 adds true Q8_0 quantization on the Hexagon NPU for more accurate mixed-precision matmul.
└──▷ GET THIS VERSION
$ git clone --branch b7484 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b7484
›Adds a CMake option for configuring FP32 quantize group size on the Hexagon NPU backend (ggml-hexagon).
›Implements true Q8_0 quantization on the Hexagon NPU (ggml-hexagon) for more accurate mixed-precision matrix multiply operations, replacing the previous approximate path.
└──▷ BREAKING ON UPGRADE
!Linux releases will migrate from .zip archives to .tar.gz archives — deployment scripts that fetch or unpack Linux release artifacts will need to be updated.
llama.cpp b7480 adds cascading presets with a global section and multi-source preset merging.
└──▷ GET THIS VERSION
$ git clone --branch b7480 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b7480
›Adds a global section to preset configuration, enabling cascade presets sourced from different origins to merge in a defined order.
›Filters server-controlled args before to_ini() serialization, preventing server-managed values from being written back into preset files.
›Linux releases will switch from .zip to .tar.gz archives in an upcoming release.
└──▷ BREAKING ON UPGRADE
!Linux release archives will soon change from .zip to .tar.gz format, requiring updates to any deployment scripts that reference or extract the current archive format.
›Adds GGML_VK_PERF_LOGGER_CONCURRENT=1 env var to enable concurrent Vulkan perf logger mode, which times groups of overlapping GPU work rather than individual operations with barriers — useful for understanding whether operation-level or group-level optimization is needed (requires GGML_VK_PERF_LOGGER also set).
›Adds GGML_VK_SYNC_LOGGER=1 env var, replacing the previous ENABLE_SYNC_LOGGING compile-time switch and making sync logging configurable at runtime without recompilation.
└──▷ BREAKING ON UPGRADE
!Linux releases will switch from .zip archives to .tar.gz archives — deployment scripts that unzip Linux builds will need to be updated.
Reset the prefix cache on a running disaggregated prefill/decode deployment without restarting the server.
$ curl -X POST http://localhost:8000/reset_prefix_cache
›Replaces VLLM_ATTENTION_BACKEND environment variable with --attention-backend CLI argument via new AttentionConfig.
›Adds encoding_format=bytes_only to the embeddings API for binary-format embedding output.
›Adds /reset_prefix_cache endpoint to KV connectors for cache reset in disaggregated prefill/decode deployments.
›Adds compile_ranges config for conditional/selective kernel compilation.
›Adds xxHash as a high-performance hash option for prefix caching.
+33 moreshow less
›Adds multi-vector retrieval API for pooling tasks.
›Adds chunked prefill support for ALL pooling tasks.
›Adds MCP type infrastructure, Browser/Container MCP tools, and full MCP Python loop to the Responses API.
›Adds extra body parameters support to the Responses API.
›Adds min-p sampling support in Model Runner V2.
›Adds NaN detection in logits in Model Runner V2.
›Adds prefill KV compute metric that excludes cached tokens.
›Adds layer-wise NVTX profiling and a profiling CLI config.
›Adds automatic TokenClassification model conversion.
›Adds support for NVIDIA Blackwell Ultra SM103 (GB300) with CUDA 13.
›Adds W4A8 grouped GEMM quantization on Hopper GPUs.
›Adds online FP8 quantization with streaming post-processing.
›Adds FP8 weight reloading for RLHF workflows.
›Adds AWQ Marlin and GPTQ Marlin quantization support for MoE + LoRA.
›Adds TRITON_MLA attention support without requiring prefix-caching.
›Adds PrefixLM support for FlexAttention and TritonAttention backends.
›Adds CUDA graphs for 3D Triton attention.
›Adds Mooncake Transfer Engine as a KV connector.
›Adds KV events support and failure recovery config for KV connectors.
›Adds external launcher mode for multi-node serving.
›Adds NIXL compatibility checking in handshake and large-batch proxy support.
›Adds AMD ROCm MXFP4 w4a4 inference and Aiter quantization kernels.
›Adds Intel XPU wNa16 compressed tensor support.
›Delivers ~3x Whisper throughput improvement (V1 now faster than V0), with encoder batching and CPU backend support.
›Adds Eagle/Eagle3 speculative decoding via the Transformers backend.
›Adds new models: BAGEL, AudioFlamingo3, JAIS 2, and latent MoE architecture.
›Adds tool parsers for DeepSeek-V3.2, Gigachat 3, and Holo2 reasoning.
›Adds Qwen3-VL embeddings support and Efficient Video Sampling (EVS).
›Adds BitsAndBytes quantization support for Qwen3-Omni-MoE.
›Adds support for multiple images/audio per embeddings request.
›Adds tokenization_kwargs override for embeddings requests.
›Enables DeepEP High-Throughput CUDA graph by default for ~5.3% throughput and ~4.4% TTFT improvement on DeepSeek models.
›Adds CUDA 13 aarch64 wheels and x86 CPU wheel pipeline.
└──▷ BREAKING ON UPGRADE
!VLLM_ATTENTION_BACKEND environment variable is replaced by the --attention-backend CLI argument; existing env-var-based attention backend configuration will no longer work.
!PassConfig flags have been renamed per RFC #27995; existing configs using the old flag names will break.
!The -O.xx flag has been removed; any scripts or configs using it will fail.
!Deprecated plugin and compilation fields have been removed; configs referencing them will break.
!Deprecated task, seed, and multimodal (MM) settings have been removed.
!embed_input_ids and embed_multimodal fallback fields have been removed; requests relying on them will fail.
!The tokenizer setter has been removed; code that set the tokenizer via this interface will break.
!--convert reward CLI flag is replaced by --convert embed; existing scripts using --convert reward will fail.
THE AI TOOLCHAIN