Qwen Code v0.23.2 ships GPT-5/6 reasoning config, remote one-command start, web-shell upgrades
qwen-code-ci-bot · ghdev · 2026-09-09
QwenLM/qwen-code released v0.23.2 with no breaking changes. Highlights: GPT-5 and GPT-6 reasoning effort configuration; web-shell improvements including split-view session navigation, opt-in browser task notifications, and separating Plan workflow from execution permissions; one-command remote start with generated token, same-origin shell access, and pairing QR; native interactive DingTalk cards for tool permission requests; built-in websearch enabled by default on ModelStudio Standard/Token Plan; journaling and null-settling of failed agents.
More from coding & agent
- Warning: uncurated Opus 5 writes poison your codebase style for every other agent — bclavie · 2026-09-09
- Apodex Open-Sources FrontierAgent: One-Command Local Agent Framework With Agent Team Mode — aakashgupta · 2026-09-09
- Testing GPT-6 Astra for image labeling: magical until you see the usage bill — chris_j_paxton · 2026-09-09
- Apodex 1.1 review: Statement Review independently verifies agent conclusions — aakashgupta · 2026-09-09
- Apodex agents absorb mid-task requirement changes with a partial replan — aakashgupta · 2026-09-09
- Debugging Agents Is Harder Than Building Them: Observability Is the Real Bottleneck — omar-felde5315v · 2026-09-09