qwen-code ships nightly v0.24.0 with subagent tool allowlists and per-model API selection
qwen-code-ci-bot · ghdev · 2026-09-19
QwenLM/qwen-code released v0.24.0-nightly with a dozen fixes and a few new features:
- Features: agent() can now narrow a subagent to an explicit tool allowlist; the OpenAI wire API is selectable per model.
- Fixes: restore managed auto-memory extraction, fix web-shell context loss after refresh, stop dropping daemon credentials on two navigation paths, avoid false interruption after completed slash commands, and fix Stop-hook block counting across tool round trips.
- Other: close 12 OpenTUI parity gaps against ink, green the remaining 3 Windows CI failures, plus docs and CI improvements.
More from coding & agent
- Anthropic's Head of Product Drops a 28-Minute Masterclass on Agents in Production — ifioknkem · 2026-09-20
- Teknium: Jev can't compact context well — Hermes summarizes 95% of it away — Teknium · 2026-09-20
- HarnessRouter open-sources a unified API to run Codex, Claude Code and more as agent backends — daniel_mac8 · 2026-09-20
- HarnessRouter: routing agent harnesses instead of models, a fresh infra idea — daniel_mac8 · 2026-09-20
- MCP tool naming: short generic verbs vs explicit prefixes for LLM tool selection — skvark · 2026-09-20
- GameToMac launched 10 days ago and already runs AoE IV, CS2 and Diablo IV on Apple Silicon — nickbaumann_ · 2026-09-20