qwen-code SDK v0.1.15 ships managed-memory fix and prompt-cache-preserving microcompaction
github-actions[bot] · ghdev · 2026-09-25
QwenLM/qwen-code released SDK TypeScript v0.1.15, bundling CLI 0.24.5. Key changes land in bundled CLI 0.23.0:
- Managed memory fix: availability now respects the memory.enableManagedAutoMemory setting, so hosts with managed auto memory disabled no longer see remember/dream requests admitted or managed-memory instructions in the system prompt.
- Microcompaction optimization: size-triggered microcompaction now clears old tool results to a low watermark instead of rewriting other parts of the conversation prefix each turn, preserving provider prompt-cache reuse in long tool-heavy sessions and reducing cached-input cost.
The release also backfills the missing GitHub release for npm version 0.1.5.
More from coding & agent
- AI compliance startup CompAI hits 1,000+ paying business customers in under a year — JosephJacks_ · 2026-09-25
- Sleep Data for Personal AI? Separating Daily Signals from Hard Rules — sujingshen · 2026-09-25
- Markdown Is the New Source Code: How to Manage Runbooks, Prompts and Rules for Agents — arpit_bhayani · 2026-09-25
- The personal agent supercycle needs hard authorization boundaries, not autonomy — sujingshen · 2026-09-25
- Mnemos.Field nears launch: a virtual world where humans and AI agents both register and participate — RileyRalmuto · 2026-09-25
- SemIf open-sources a Jev-style interface: typed option probabilities from a 4B model, no JSON parsing — JeremyCMorgan · 2026-09-25