Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-09-06 · high
The update also adds a Skills runtime scoped to your workspace and opt-in git worktree isolation for named tasks.
Why now: The change is in the v0.23.1-preview.0 release, posted September 6, 2026.
Qwen Code's v0.23.1-preview.0 release, posted September 6, 2026, turns off todo bookkeeping by default. PR #10645 makes the change. It's a direct token cut for anyone whose agent has been narrating a checklist it never reads back. Turning it back on takes a flag; the default assumes most sessions don't need one.
The Skills runtime is next. PR #10697 adds a workspace-scoped Skills runtime inside serve. PR #10761 loads custom output styles from ~/.qwen/output-styles. PR #10723 installs zvec-grep as a built-in skill.
Worktree isolation rounds out the release. PR #10643 adds /session new <name> --worktree as an opt-in command for named tasks. Each response carries an ownership marker and a persisted-v1 attestation, so it's clear which worktree produced which output.
Todo lists in coding agents are meant to show the model's plan to the user. Whether that plan changes the next action is a separate question. Qwen Code answered it by making tracking opt-in instead of default.
Each link below shares sources, entities, or timing with this story.
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
The trick is one line in a file you never read. Manifold Security published eight findings across seven coding agents (Claude Code, Codex, Cursor, Grok Build, Qwen Code, goose, Hermes Agent) that all reduce to the same mechanism. A repository's own .git/config sets core.fsmoni...
Blaizzy/nativ (1,163 stars, Swift, MIT, macOS 26+) comes from the mlx-vlm author and bundles that server into a SwiftUI app that discovers MLX models already in your HF cache. It exposes OpenAI-compatible chat, Responses, image, audio and model endpoints plus Anthropic Message...
The repo, a CLI+web board that runs 10+ coding agents (Claude Code, Codex, Gemini CLI, Copilot, Cursor, OpenCode, Qwen Code) each in an isolated git worktree, is sunsetting as a company product, with Bloop shutting hosted services and refunding subscriptions. The code lives on...
YC W26 open-source desktop app for running 21+ CLI coding agents in parallel (Claude Code, Codex, Gemini, Qwen Code, OpenCode), each in isolated Git worktrees. Best-of-N mode runs multiple agents on the same task. Diff view, Kanban view, Linear/GitHub/Jira integration. The mos...
A GitHub repo cataloging Claude Code tips doesn't normally warrant a top story. But shanraisshan/claude-code-best-practice at 53.4K stars isn't a tips list anymore. It's the de facto reference for how an entire generation of developers is learning to work with AI coding agents...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.