Qwen Code v0.22.0 ships review-loop explanations, renderer OOM fix and sandbox hardening
qwen-code-ci-bot · ghdev · 2026-08-22
Alibaba's QwenLM/qwen-code released v0.22.0 with notable changes:
- review: explains to the author why a review loop isn't settling; folds one-hop import widening into fetch-pr --since
- web-shell: bounds daemon transcript retention to fix renderer OOM crashes; keeps a turn expanded while its background shell runs; fixes parallel-agents collapse
- autofix: audits the approach instead of stopping on growth-budget breach; binds sandbox image to its pulled digest; designs runner-level isolation for PAT-bearing steps
- security: disables install scripts in release CI and guards security-checks workflow; listdirectory now opt-in (disabled by default)
- Docs: inline terminal image previews and Session documentation
More from coding & agent
- Agentic coding accessibility will reshape understanding of software complexity — pixlpa · 2026-08-24
- Devin Agent bypasses Slack block by finding emails in git logs — sandylikesfrogs · 2026-08-24
- Developer habits shift: Agents become collaborators from simple tools — latticecut · 2026-08-24
- Dev bottleneck shifts from writing to reading code: exe.dev co-founder — thursdai_pod · 2026-08-24
- The biggest AI mistake: trying to reinvent the wheel instead of using tools — Tired40s · 2026-08-24
- DeepPaperNote turns research papers into Obsidian notes — tom_doerr · 2026-08-24