Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -229, December 31, 2025

THE AI TOOLCHAIN NO. -229
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED DECEMBER 31, 2025 · EVERY WEEKDAY
EDITIONS tail grep head diff uniq

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.

VIEW
ISSUE VIEW full issue
Do you prefer this view?
$ tct list   # 2 tools matched
AI & LLM Tooling
◆  AI Coding Agents

SST OpenCode

Sources Release notes → v1.0.221 3 RELEASES · 2025-12-31 NOTES STABLE

The open source coding agent.

OpenCode v1.0.221 adds LSP watched-file notifications and OpenAI-compatible provider fallback.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.221 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.221
  • Defaults to ai-sdk/openai-compatible provider when no npm package is specified, broadening out-of-the-box model support.
  • Adds LSP workspace/didChangeWatchedFiles notification support, keeping the language server in sync with file-system changes.
  • Improved model selector UI in the desktop app.
  • Auto-accept colors and better auto-accept affordance added to the desktop app.
  • New keybind tooltip component added to the desktop app.
+1 moreshow less
  • Adds input changes functionality to the desktop app.
2 more releases in this issue · 2025-12-31
v1.0.220 NOTES STABLE

OpenCode v1.0.220 adds a debug agent subcommand, MCP prompt tags in autocomplete, and a unified diff toggle in the desktop app.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.220 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.220
└──▷ TRY IT
Quickly validate an agent's behavior in isolation before using it in a real session.
$ opencode debug agent <name>
  • New debug agent <name> subcommand lets you test agents in isolation without a full session.
  • Displays MCP tag for prompts in autocomplete so users can distinguish MCP-sourced prompts at a glance.
  • Adds unified diff toggle to the desktop application for switching diff views.
  • Redesigned desktop header replaces the status bar with new header elements and an improved new-session button.
v1.0.219 NOTES STABLE

OpenCode v1.0.219 adds MCP prompts as slash commands, model usage stats, rustfmt support, and configurable MCP timeouts.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.219 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.0.219
└──▷ TRY IT
Invoke an MCP-defined prompt directly as a slash command in the TUI instead of constructing it manually.
$ /<mcp-prompt-name>
  • Adds MCP prompts as slash commands, making MCP-defined prompts directly invocable from the TUI.
  • Adds model usage statistics with input/output token breakdown to the stats command.
  • Adds rustfmt formatter support for Rust files.
  • Adds Gemini 3 Flash to the fast models list.
  • Bundles @ai-sdk/vercel v1.0.31 for AI SDK v5 support.
+3 moreshow less
  • Adds configurable timeout for MCP tool calls to prevent hanging requests.
  • Adds configurable CORS hosts.
  • Adds model variants support to the desktop app.
Was this useful?

Alibaba Qwen Code

Sources Release notes → v0.6.0-preview.2 2 RELEASES · 2025-12-31 NOTES STABLE

Qwen Code v0.6.0-preview.2 adds locale-based LLM output language detection and ChatCompletionContentPart merging support.

└──▷ GET THIS VERSION
$ git clone --branch v0.6.0-preview.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-preview.2
  • Supports merging ChatCompletionContentPart payloads and filters empty messages for cleaner API interactions.
  • Auto-detects LLM output language from the system locale, eliminating the need to manually configure response language.
1 more release in this issue · 2025-12-31
v0.6.0-nightly.20251231.105ad743 NOTES STABLE

Qwen Code v0.6.0-nightly adds locale-based LLM language auto-detection and ChatCompletionContentPart merging support.

└──▷ GET THIS VERSION
$ git clone --branch v0.6.0-nightly.20251231.105ad743 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.6.0-nightly.20251231.105ad743
  • Auto-detects the desired LLM output language from the system locale, removing the need to manually configure response language.
  • Supports merging ChatCompletionContentPart entries and filters empty messages from API payloads.
  • Adds Russian locale translation strings for i18n coverage.
Was this useful?
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →