Qwen-code v0.21.7 Released: Fixes Sandbox and Review Logic
qwen-code-ci-bot · ghdev · 2026-08-07
Qwen-code has released version v0.21.7, primarily addressing several edge cases in engineering execution and code review, alongside a few minor features.
- Engineering Fixes: Resolved flakiness in glob external-path tests, normalized Live Host signing identities, and added runtime probing before selecting a sandbox. It also fixes symlink resolution before granting read permissions.
- Review & Performance: Serialized scan-and-pick issue runs to avoid concurrency conflicts, capped a streaming response's total lifetime, and slimmed down the review fan-out launch.
- Features: Added support for trusted private ASR (Automatic Speech Recognition) base URLs and the ability to render inline terminal images.
More from coding & agent
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- Comparing AI Subscriptions: DeepSeek API vs. Claude Pro vs. Local LLMs — Unlikely_Bluejay5392 · 2026-08-24
- Claude Code introduces 'Remote Control' feature to boost coding efficiency — rohanpaul_ai · 2026-08-24
- rauchg lays out fx extension philosophy: MCP, Skills, Plugins and Unix composition — AccBalanced · 2026-08-24
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- smolvm passes Simon Willison's Fable 5 agent test as a secure sandbox — yawnxyz · 2026-08-24