Backfill issue -209 — The AI Toolchain

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   # 7 tools matched

AI & LLM Tooling

◆ AI Coding Agents

Anthropic Claude Code

v2.1.14 NOTES

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 v2.1.14 adds history-based Tab autocomplete in bash mode, plugin search, SHA pinning, and a VSCode /usage command.

└──▷ GET THIS VERSION

$ git clone --branch v2.1.14 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.14

└──▷ TRY IT

Quickly re-run a recent shell command in bash mode without retyping it — type the start of the command after ! and press Tab to pull from history.

$ ! git log --on<Tab>   # completes to a previously run git command from your bash history

›Adds history-based Tab autocomplete in bash mode (!) — type a partial command and press Tab to complete from your shell history.
›Adds search/filter to the installed plugins list — type to filter by plugin name or description.
›Supports pinning plugins to specific git commit SHAs, enabling marketplace entries to install exact versions.
›Improves backspace to delete pasted text as a single token rather than one character at a time.
›[VSCode] Adds /usage command to display current plan usage.

Was this useful?

GitHub Copilot CLI

v0.0.388 2 RELEASES · 2026-01-20 NOTES STABLE

GitHub Copilot CLI v0.0.388 adds a /review command and expands --enable-all-github-mcp-tools to read-write MCP tools.

└──▷ GET THIS VERSION

$ git clone --branch v0.0.388 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.388

└──▷ TRY IT

Enable read-write GitHub MCP tools to allow Copilot to perform write operations on your behalf.

$ gh copilot --enable-all-github-mcp-tools

›Adds /review command to analyze code changes directly in the CLI.
›The --enable-all-github-mcp-tools flag now enables read-write GitHub MCP tools, expanding beyond the previous read-only scope.
›Redesigns the CLI header with a branded mascot and streamlined welcome message.
›Session event messages are now more concise and visually clean.
›/share gist now shows a helpful error message when used on GitHub Enterprise Cloud with data residency.

1 more release in this issue · 2026-01-20

v0.0.387 NOTES STABLE

GitHub Copilot CLI v0.0.387 adds interactive clarification, plan mode, and large-directory support

└──▷ GET THIS VERSION

$ git clone --branch v0.0.387 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.387

›Adds ask_user tool for interactive clarification questions during sessions
›Adds plan mode with a dedicated panel for viewing implementation plans
›Skill tool now handles large directories without exceeding context limits

Was this useful?

SST OpenCode

v1.1.28 2 RELEASES · 2026-01-20 NOTES STABLE

The open source coding agent.

OpenCode v1.1.28 adds macOS restart/reload menus, ACP audience support, and a new desktop settings page.

└──▷ GET THIS VERSION

$ git clone --branch v1.1.28 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.1.28

›Adds Restart and Reload menu items on macOS in the desktop app.
›Supports ACP audience by mapping to ignore and synthetic.
›Adds a settings page to the desktop app.
›Adds tooltips to sidebar new session and workspace buttons in the desktop app.
›Adds color scheme preview on hover in the appearance dropdown.

+4 moreshow less

›Renders font options in their respective fonts in the font selector.
›Adds Windows end-to-end tests for the app.
›Changes the new-terminal keybind to Ctrl+Alt+T in the desktop app.
›Adjusts Codex prompt to encourage more autonomous decision-making and fewer unnecessary questions.

1 more release in this issue · 2026-01-20

v1.1.27 NOTES STABLE

OpenCode v1.1.27 adds a space-toggle hint in tool selection and lets you select project directory text in the web UI.

└──▷ GET THIS VERSION

$ git clone --branch v1.1.27 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.1.27

›Adds space-toggle hint to the tool selection prompt so keyboard navigation is more discoverable.
›Enables selecting and copying project directory text in the web interface.

Was this useful?

Alibaba Qwen Code

v0.7.2 4 RELEASES · 2026-01-20 NOTES STABLE

Qwen Code v0.7.2 adds experimental skills settings, a user feedback dialog, and improved QWEN.md file loading.

└──▷ GET THIS VERSION

$ git clone --branch v0.7.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.7.2

›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
›Adds a user feedback dialog for submitting feedback directly from the CLI.
›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.

3 more releases in this issue · 2026-01-20

v0.7.2-preview.2 NOTES STABLE

Qwen Code v0.7.2-preview.2 adds experimental skills settings, a user feedback dialog, and improved QWEN.md file loading.

└──▷ GET THIS VERSION

$ git clone --branch v0.7.2-preview.2 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.7.2-preview.2

›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
›Adds a user feedback dialog for submitting feedback directly from the CLI.
›Improves QWEN.md file loading by filtering out system files and limiting scope.

v0.7.2-preview.1 NOTES STABLE

Qwen Code v0.7.2-preview.1 adds experimental skills settings, improved QWEN.md loading, and a user feedback dialog.

└──▷ GET THIS VERSION

$ git clone --branch v0.7.2-preview.1 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.7.2-preview.1

›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
›Adds a user feedback dialog to the CLI interface.

v0.7.1-preview.0 NOTES STABLE

Qwen Code v0.7.1-preview.0 adds experimental skills settings, improved QWEN.md loading, and a user feedback dialog.

└──▷ GET THIS VERSION

$ git clone --branch v0.7.1-preview.0 https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:
$ git checkout v0.7.1-preview.0

›Adds settings support for experimental skills under the experimental namespace in CLI configuration.
›Improves QWEN.md file loading by filtering out system files and limiting scope to relevant directories.
›Adds a user feedback dialog to the CLI interface.

Was this useful?

Zed

v0.219.5 NOTES

Zed v0.219.5 adds support for GPT-5.2-Codex via OpenAI API Key.

└──▷ GET THIS VERSION

$ git clone --branch v0.219.5 https://github.com/zed-industries/zed.git
# already have the repo? check out this version:
$ git checkout v0.219.5

›Adds support for GPT-5.2-Codex via OpenAI API Key.

Was this useful?

◆ AI Agent Frameworks

OpenAI Agents SDK

v0.6.9 NOTES

OpenAI Agents SDK v0.6.9 adds input-based responses compaction with store-aware auto mode.

└──▷ GET THIS VERSION

$ git clone --branch v0.6.9 https://github.com/openai/openai-agents-python.git
# already have the repo? check out this version:
$ git checkout v0.6.9

›Adds input-based responses compaction with a store-aware auto mode, enabling smarter context management when responses are stored.

Was this useful?

◆ Local LLM Runtimes

vLLM

v0.14.0 NOTES

vLLM v0.14.0 adds a gRPC server, --max-model-len auto, async scheduling by default, and broad new model/quantization support.

└──▷ GET THIS VERSION

$ git clone --branch v0.14.0 https://github.com/vllm-project/vllm.git
# already have the repo? check out this version:
$ git checkout v0.14.0

└──▷ TRY IT

Start vLLM with automatic context-length fitting to avoid OOM errors on GPU memory-constrained deployments.

$ vllm serve meta-llama/Llama-3-8B-Instruct --max-model-len auto

Inspect a model's attention backends, modules, and quantization config before serving.

$ VLLM_LOG_MODEL_INSPECTION=1 vllm serve Qwen/Qwen3-8B --max-model-len 8192

Query the new /server_info endpoint to retrieve environment and runtime details from a running vLLM instance.

$ curl http://localhost:8000/server_info

›Adds --max-model-len auto flag to automatically fit context length to available GPU memory, eliminating OOM startup failures.
›Adds --no-async-scheduling flag to disable the newly default async scheduling (overlaps engine core scheduling with GPU execution for higher throughput).
›Adds -ep shorthand flag for --enable-expert-parallel.
›Adds --enable-log-deltas CLI flag (renamed in this release) for iteration delta logging.
›Adds --default-chat-template-kwargs CLI flag to pass default kwargs to chat templates.

+25 moreshow less

›Adds --input-len flag and auto-discovery to bench serve for benchmark configuration.
›Adds VLLM_LOG_MODEL_INSPECTION=1 environment variable (or printing the LLM object) to inspect a model's modules, attention backends, and quantization configuration.
›Adds attention_config parameter to the LLM() constructor for programmatic attention configuration.
›Adds reasoning_effort parameter to the API for controlling reasoning depth.
›Adds gRPC server entrypoint as an alternative to the REST API, supporting binary protocol and HTTP/2 multiplexing.
›Adds /server_info API endpoint exposing environment information.
›Adds continue_final_message field to the /embeddings API endpoint.
›Adds MCP streaming support in the Responses API.
›Adds MFU (Model FLOP Utilization) metrics to the API.
›Adds spec-decode acceptance stats reporting via CLI.
›Adds offline FastAPI documentation endpoint.
›Adds FunctionGemma and GLM-4.7 tool-calling parsers.
›Adds new model architecture support: Grok-2 (with tiktoken tokenizer), LFM2-VL, MiMo-V2-Flash, openPangu MoE, IQuestCoder, Nemotron Parse 1.1, GLM-ASR audio, Isaac vision model v0.1/v0.2, Kanana-1.5-v-3b-instruct, and K-EXAONE-236B-A23B MoE.
›Expands LoRA support to multimodal tower/connector models (LLaVA, BLIP2, PaliGemma, Pixtral, DotsOCR, GLM4-V) and additional architectures (DeepSeek-OCR, Qwen3-Next, NemotronH, PLaMo 2/3).
›Adds enable_thinking: false config option for GLM-4.5/GLM-4.7 models.
›Adds Marlin quantization support for Turing (sm75) GPUs.
›Adds Quark int4-fp8 w4a8 MoE quantization.
›Adds MXFP4 W4A16 quantization for dense models.
›Adds ModelOpt FP8 variants: FP8_PER_CHANNEL_PER_TOKEN and FP8_PB_WO.
›Adds XBO (Extended Dual-Batch Overlap) for large-scale serving.
›Adds NIXL asymmetric TP support (P > D tensor-parallel-size).
›Async scheduling now also works with speculative decoding and structured outputs.
›Adds hybrid allocator + KV connector with multiple KV cache groups.
›Adds SM103 hardware support.
›Adds weights_only=True to torch.load calls, reducing deserialization attack surface.

└──▷ BREAKING ON UPGRADE

!Async scheduling is now enabled by default; disable with --no-async-scheduling if issues arise (pipeline parallel, CPU backend, and non-MTP/Eagle spec decoding are excluded and remain unaffected).
!PyTorch 2.9.1 is now required and the default wheel is compiled against cu129.
!Deprecated quantization schemes have been removed.
!When using speculative decoding, unsupported sampling parameters now fail with an error rather than being silently ignored.

Was this useful?

// END OF TRANSMISSION

The AI Toolchain · curated daily · January 20, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

The AI Toolchain — issue -209, January 20, 2026

Anthropic Claude Code

GitHub Copilot CLI

SST OpenCode

Alibaba Qwen Code

Zed

OpenAI Agents SDK

vLLM