Qwen Code v0.26.2 preview adds session permission rules, auto-approval and experimental shared agent loop
qwen-code-review-bot · ghdev · 2026-10-27
QwenLM/qwen-code shipped v0.26.2-preview.1 with notable changes:
- Managed agent upgrades: new session permission rules plus an Auto-approval mechanism, and zombie registered processes are now retired before startup waits
- Experimental shared agent loop in core, with headless execution support
- Security fix: hardened serve token resolution against project env injection
- UX fixes: VSCode now leaves edit mode after a refused edit; rewind resolves legacy turns by source identity; OpenTUI cancellation/retry aligned with Ink
- Requests to Qwen AI platform/QwenCloud are attributed via a source-config header
The release also adds tests covering managed workspace activation refusals and fixes first-run scheduled-task gate docs.
More from coding & agent
- Dev builds open-source Excalidraw MCP after AI-generated diagrams kept overlapping text and arrows — pikahikmag · 2026-10-28
- DeepSeek vs Haiku pricing debunk: accounting for peak rates and token use, 1017 is 2-2.5x cheaper — teortaxesTex · 2026-10-28
- Viral screenshot shows an agent spawning 32 parallel workspaces in ~30 seconds — cephaloform · 2026-10-28
- Grok Bot 0.78.1 hides unreleased per-bot logins with manager-only team sharing — faraz0x · 2026-10-28
- Uber Built a Legal Redlining Agent for Its Lawyers—Here's What It Learned — AxSaucedo · 2026-10-28
- GraphRAG's hub-node trap: same two-hop Cypher costs 71 DB hits normally, 60,013 on a hub — JeremyCMorgan · 2026-10-28