Qwen Code ships v0.25.3 nightly with session-targeted Skill refresh and managed-agent upgrades
qwen-code-review-bot · ghdev · 2026-10-20
QwenLM/qwen-code released v0.25.3-nightly.20261019 with 10+ changes:
- daemon: session-targeted Skill and Extension refresh support
- managed-agent: ships a configuration template in the reference distribution; supports local and SSH workspace file references; adds a read-only --check preflight; recovers committed wakes after writer loss; bounds initial publication guard waits
- runtime-broker: session-create warm for workspace-isolated bound sessions
- serve: private CSI file turns run through Hosted Harness; hosted stdio MCP servers contained in a process group
- sdk/CLI: session create sized from the daemon session budget; slow-host scheduling budgets for tests and ENOTEMPTY retry in hosted harness teardowns
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23