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 v2.1.3 adds release channel switching, unreachable-rule warnings, and a 10-minute hook timeout.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.3 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.3
└──▷ TRY IT
Switch between stable and latest release channels without leaving the CLI.
$ /config
Audit your permission rules for unreachable entries and get fix guidance before they silently do nothing.
$ /doctor
›Adds release channel toggle (stable or latest) to /config, letting you switch update tracks in-product.
›New detection and warnings for unreachable permission rules surfaced in /doctor and after saving rules, with source attribution and actionable fix guidance.
›Extends tool hook execution timeout from 60 seconds to 10 minutes, enabling longer-running hook scripts.
›[VSCode] Adds clickable destination selector for permission requests, letting you choose where settings are saved: this project, all projects, shared with team, or session only.
›Merges slash commands and skills into a unified concept, simplifying the mental model.
Claude Code v2.1.2 adds OSC 8 hyperlinks, winget support, plan-mode shortcut, and full large-output persistence to disk.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.2 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.2
└──▷ TRY IT
Force plugin autoupdates in CI or locked-down environments where the main auto-updater is disabled.
$ FORCE_AUTOUPDATE_PLUGINS=1 claude
›Adds clickable OSC 8 hyperlinks for file paths in tool output in supported terminals (e.g., iTerm).
›Adds Windows Package Manager (winget) installation detection with automatic update instructions.
›Adds Shift+Tab keyboard shortcut in plan mode to instantly select the "auto-accept edits" option.
›Adds FORCE_AUTOUPDATE_PLUGINS environment variable to enable plugin autoupdate even when the main auto-updater is disabled.
›Adds agent_type field to SessionStart hook input when --agent is specified.
+3 moreshow less
›Adds source path metadata to images dragged onto the terminal so Claude knows where images originated.
›Large bash command outputs and tool outputs are now saved to disk instead of truncated, giving Claude access to full content via file references.
›Unifies plugins and MCPs in the /plugins installed tab with scope-based grouping.
└──▷ BREAKING ON UPGRADE
!The Windows managed settings path C:\ProgramData\ClaudeCode\managed-settings.json is deprecated; administrators must migrate to C:\Program Files\ClaudeCode\managed-settings.json.
!The minimum zod peer dependency is now ^4.0.0 (SDK).
OpenCode v1.1.10 adds Bedrock API key prompting, plugin deduplication, per-session pane visibility, and opt-in server mode.
└──▷ GET THIS VERSION
$ git clone --branch v1.1.10 https://github.com/sst/opencode.git
# already have the repo? check out this version:$ git checkout v1.1.10
›Disables the server by default; must now be explicitly opted in to start.
›Reports config errors at startup instead of silently terminating.
›Adds API key prompt for Amazon Bedrock during auth login.
›Deduplicates plugins by name using priority-based resolution when multiple plugins share the same name.
›Stores terminal and review pane visibility per session in the desktop app.
└──▷ BREAKING ON UPGRADE
!The server is now disabled unless explicitly opted in; setups that relied on the server starting automatically will need to opt in to restore that behavior.
Qwen Code v0.7.0 adds multi-provider model configuration support and changes user vs. workspace settings precedence.
└──▷ GET THIS VERSION
$ git clone --branch v0.7.0-nightly.20260109.f776075a https://github.com/QwenLM/qwen-code.git
# already have the repo? check out this version:$ git checkout v0.7.0-nightly.20260109.f776075a
›Adds multi-provider model configuration support, allowing multiple AI providers to be configured simultaneously.
›Changes the selection order of user settings and workspace settings, giving workspace settings a different precedence relative to user settings.
LangChain Core 0.3.82 adds usage_metadata to trace metadata in LangChainTracer.
└──▷ GET THIS VERSION
$ git clone --branch langchain-core==0.3.82 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-core==0.3.82
›Adds usage_metadata field to metadata emitted by LangChainTracer, surfacing token/usage information directly in traces.
langchain-core 1.2.7 adds custom message separators in get_buffer_string() and expands ignored file extensions in HTML link extraction.
└──▷ GET THIS VERSION
$ git clone --branch langchain-core==1.2.7 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-core==1.2.7
└──▷ USE IT
Separate chat history messages with a custom delimiter instead of the default when serializing a buffer — useful when feeding history into prompts that require a specific format.
python
from langchain_core.messages import get_buffer_string
buffer = get_buffer_string(messages, human_prefix="Human", ai_prefix="AI", separator="\n---\n")
›Supports a custom message separator parameter in get_buffer_string() for flexible buffer formatting.
›Adds more file extensions to the ignore list in HTML link extraction utilities.
SGLang gateway v0.3.1 delivers 10-12x faster cache-aware routing, 99% memory reduction, JWT/OIDC auth, and a new Classification API.
└──▷ GET THIS VERSION
$ git clone --branch gateway-v0.3.1 https://github.com/sgl-project/sglang.git
# already have the repo? check out this version:$ git checkout gateway-v0.3.1
›Adds JWT/OIDC authentication for control plane APIs (tokenizer management, worker registration, admin endpoints) with native support for Google, Azure, Oracle, and GitHub identity providers.
›Adds PrefixHash load balancing policy — a new KV cache-aware routing strategy using prefix hashing to improve cache hit rates in multi-tenant environments.
›Adds native Classification API support with dedicated pipeline stages and protocol types for serving classification models alongside inference workloads.
›Adds Nemotron Nano V3 reasoning parser support.
›Adds in-flight request age metrics for observability and SLA monitoring.
+3 moreshow less
›Radix tree / cache-aware routing engine overhauled: INSERT throughput up from 38 MB/s to 440 MB/s, MATCH throughput up from 83 MB/s to 253 MB/s, latency down from 52.9 µs to 4.6 µs per operation, and memory per node down from ~180 KB to ~1.4 KB (~99% reduction).
›Organizes CLI arguments into logical groups for improved discoverability.
›HTTP Router fan-out replaced from serial execution to concurrent streams for reduced latency under load.
llama.cpp b7681 adds remote preset support, letting a single HF repo reference multiple GGUF sources.
└──▷ GET THIS VERSION
$ git clone --branch b7681 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b7681
›Adds remote preset support via --offline option awareness, allowing argument configurations to be fetched from a remote Hugging Face repo — including one HF repo pointing to multiple HF repos for multi-GGUF use cases.
THE AI TOOLCHAIN