qwen-code SDK v0.1.13 fixes microcompaction to preserve prompt-cache reuse in long agent sessions
github-actions[bot] · ghdev · 2026-09-19
QwenLM released qwen-code TypeScript SDK v0.1.13 (bundling CLI 0.24.1) with two notable fixes: managed auto-memory now respects the memory.enableManagedAutoMemory setting so hosts that disable it no longer get remember/dream requests injected into the system prompt, and size-triggered microcompaction now clears old tool results toward a low watermark instead of rewriting the conversation prefix each turn — preserving provider prompt-cache reuse in long tool-heavy sessions and cutting cached-input costs.
More from coding & agent
- Human Oversight Is 70-75% of AI Agent Costs in Banking, McKinsey Finds — mikeflache · 2026-11-04
- Over 80% of Major Financial Institutions Now Run Agentic AI in Production — mikeflache · 2026-11-04
- Mnemos MCP nears launch after shared memory layer fix — RileyRalmuto · 2026-11-04
- Moving mobile dev to remote machines makes it multiplayer across product, design, engineering — rudrank · 2026-11-04
- Kuaishou's EvoRec: self-evolving agentic recommender lifts ad revenue 4.6% — _reachsumit · 2026-11-04
- TRIO: three specialized agents with aligned objectives refine retrieval-augmented generation — _reachsumit · 2026-11-04