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.
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 v2.1.73 adds modelOverrides for custom provider model IDs and actionable SSL error guidance for corporate proxy users.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.73 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.73
└──▷ USE IT
Route model picker selections to a specific Bedrock inference profile ARN instead of the default model ID.
json
# In your Claude Code settings (e.g. ~/.claude/settings.json)
{
"modelOverrides": {
"claude-opus-4-5": "arn:aws:bedrock:us-east-1::foundation-model/your-inference-profile-arn"
}
}
›Adds modelOverrides setting to map model picker entries to custom provider model IDs (e.g., Bedrock inference profile ARNs).
›Adds actionable guidance when OAuth login or connectivity checks fail due to SSL certificate errors (corporate proxies, NODE_EXTRA_CA_CERTS).
›Updates default Opus model on Bedrock, Vertex, and Microsoft Foundry to Opus 4.6.
›Enables /effort command to work while Claude is responding, matching /model behavior.
└──▷ BREAKING ON UPGRADE
!The /output-style command is deprecated; output style is now fixed at session start for better prompt caching — use /config instead.
Qwen Code v0.12.1 adds a VS Code sidebar view with multi-position chat layout and a CONCAT merge strategy for MCP allowed/excluded lists.
└──▷ GET THIS VERSION
$ git clone --branch v0.12.1 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.12.1
›Adds CONCAT merge strategy for MCP allowed/excluded lists, giving practitioners control over how MCP server permission lists are combined across configs.
›Adds sidebar view and multi-position chat layout to the VS Code IDE companion extension.
›Changes temporary filename prefix to qwen-edit- for files opened during edit operations.
Zed v0.227.1 adds parallel subagents, Vercel AI Gateway, GPT-5.3-Codex support, and git diff stats in the git panel.
└──▷ GET THIS VERSION
$ git clone --branch v0.227.1 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:$ git checkout v0.227.1
└──▷ USE IT
Set a custom highlight color for vim yank operations to make yanked regions visually distinct in your theme.
json
"vim": {
"yank": {
"background": "#f5c842"
}
}
›Adds spawn_agent tool enabling the Zed Agent to spin up subagents for parallel task execution and better context management.
›Adds cmd-y keybinding for accepting changes in the agent diff review, matching the git diff review shortcut.
›Adds ctrl-enter keybinding (macOS) to type a newline in search bars.
›Adds configurable vim.yank.background theme color for vim yank highlight.
›Adds editor: Open excerpts action (option-enter) to jump to a file from a diff inside an agent conversation.
+19 moreshow less
›Adds Vercel AI Gateway as a new LLM provider in Zed.
›Adds support for GPT-5.3-Codex as a bring-your-own-key model in the OpenAI provider.
›Adds support for providing an API key to OpenAI-compatible edit prediction providers.
›Adds support for specifying settings for the Go LSP adapter.
›Registers .prettierrc as a JSON file type.
›Migrates all built-in agents to the ACP Registry, making them individually removable and manageable.
›Adds git diff stats to git panel entries.
›Adds trusted workspace support for Zed's git integration.
›Adds support for listing tree-sitter tokens in the highlights tree view, including their resolved theme keys; semantic token entries also show resolved theme keys.
›Adds support for compound emojis.
›Adds file icons for YAML, Helm, and GitLab files; uses the Docker icon for Containerfile.
›Adds persistence for draft prompts across Zed restarts.
›Adds persistence for the thinking mode toggle and thinking effort when selecting a thread from history.
›Adds restoration of token counts and scroll position when loading a previous agent thread.
›Makes file mention chips in the chat input clickable to open referenced files in the editor.
›Changes the language selector to auto-select the current buffer's language when opened.
›Changes miniprofiler file extension to .miniprof.json.
›Adds truncation for long file names in tab titles.
›Improves redaction of sensitive environment variables from debugger error logs.
Jan v0.7.8 adds xAI provider, OpenClaw agent integration, a Jan CLI, and dynamic context allocation.
└──▷ GET THIS VERSION
$ git clone --branch v0.7.8 https://github.com/janhq/jan.git
# already have the repo? check out this version:$ git checkout v0.7.8
›Adds xAI as a new model provider, expanding the roster of supported remote inference backends.
›Integrates OpenClaw, an agent framework, including sandbox config isolation, an agent mode toggle, quality-of-life keyboard shortcuts, Docker validation on Windows and Linux, and a pre-installed Bun runtime replacing all Node/npm dependencies.
›Introduces a Jan CLI (jan-cli) shipped alongside the desktop app, including in the Windows NSIS installer as jan-cli.exe.
›Jan now manages context allocation dynamically, automatically sizing context windows based on available resources rather than requiring manual configuration.
›Adds a refreshed starter screen and updated download management UI for the initial model setup flow.
+1 moreshow less
›Improves the settings panel with better organization and expanded model provider options.
llama.cpp b8269 adds concurrent SME and NEON kernel execution via KleidiAI on ARM.
└──▷ GET THIS VERSION
$ git clone --branch b8269 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b8269
›Enables concurrent SME and NEON kernel execution in the KleidiAI backend, improving throughput on ARM hardware that supports both instruction sets simultaneously.
llama.cpp b8268 adds RISC-V Vector (RVV) repacked GEMM/GEMV for q8_0, iq4_nl, q4_0, q4_K, and q2_K quantization types.
└──▷ GET THIS VERSION
$ git clone --branch b8268 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b8268
›Adds RVV (RISC-V Vector) repacked GEMM and GEMV kernel implementations for quantization types q8_0, iq4_nl, q4_0, q4_K, and q2_K, enabling accelerated CPU inference on RISC-V hardware with vector extensions.
Phoenix client v2.0.0 adds session conversation APIs, trace_ids filtering, parent_id filtering, and six new first-class LLM providers.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-client-v2.0.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-client-v2.0.0
└──▷ USE IT
Retrieve only the spans belonging to a specific set of traces — useful when you already know the trace IDs from a CI run or incident and want to pull just those spans for analysis.
Phoenix v13.14.0 adds a session conversation API to Python and TypeScript clients and a new tracing onboarding layout.
└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v13.14.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:$ git checkout arize-phoenix-v13.14.0
›Adds session conversation API to both the Python and TypeScript Phoenix clients.
›New tracing onboarding page layout to guide users through trace setup.
THE AI TOOLCHAIN