Qwen Code v0.2.0 ships model-proposed goals, fixes auto-approval permission flaw
github-actions[bot] · ghdev · 2026-09-02
QwenLM/qwen-code released live-host-v0.2.0 with notable changes: the model can now propose a Goal for user approval in a dialog; web-shell gains standalone chats and an experimental session workflow cockpit; a security fix stops the AUTO-mode classifier from auto-approving out-of-workspace writes, always falling back to manual approval; plus hot-reloading of modelProviders without session restart and OpenTUI migration batch 4.
More from coding & agent
- Developer asks: is LangChain still worth it vs rolling your own agent harness? — curious_vii · 2026-09-03
- Inference Engineering Is Just a Recipe: vLLM/SGLang, Replicas, Cache-Aware Routing — GabGarrett · 2026-09-03
- Developer accidentally built an entire agent factory with Fable 5.1 — 0xkarasy · 2026-09-03
- Microsoft adds Fabric data agents to Foundry agents via Fabric IQ (preview) — adnan_hashmi · 2026-09-03
- Databricks pitches agent-native data infrastructure, Lakebase Postgres at VLDB 2026 — matei_zaharia · 2026-09-03
- doodlestein ships a comprehensive web app review skill after months of debugging — doodlestein · 2026-09-03