Qwen Code v0.26.9 ships agent perf fixes, GitHub channel recovery and QQBot updates
qwen-code-review-bot · ghdev · 2026-11-07
QwenLM/qwen-code released v0.26.9 with 14 contributors, focused on stability and performance:
- Fix keeping GitHub inbound recovery armed after a failed read
- Managed-agent perf work: indexed activation lease lookup, narrowed SSH settlement and worktree locking, journal snapshots off tenant guards
- Core perf: read Managed message bodies once per process, lazy-load MCP Google auth providers, keep writer grants refreshed during renewal
- verify-pr: sandboxed round now gets the PR's review threads; autofix-pr refusals now carry a code and next step
- QQBot delivers proactive loop messages as active group messages
- Session list titles survive transcript rebuilds; image input support for Llama 3.2 Vision
More from coding & agent
- Gemini /teamwork agents caught live: four parallel task logs all running that second — RyanSpunk · 2026-11-13
- Codex CLI 0.168.0 adds model provider picker, side-by-side TUI workspace and animated GIF generation — github-actions[bot] · 2026-11-13
- Free MCP server lets Claude read Altium, Allegro, KiCad and Gerber PCB files directly — woodisruff · 2026-11-13
- a16z Partner Clones Open-Source Game with Fable 5.2 Agent, Which Finds Its Own Horse Animation Asset — FinanceYF5 · 2026-11-13
- OpenAI team shares how it runs and governs fleets of persistent agents internally — romainhuet · 2026-11-13
- Perplexity's Decider scanned 1B tokens across 7,000 agent sessions, found 14 security fixes — denisyarats · 2026-11-13