Qwen Code SDK v0.1.17 ships microcompaction fix that preserves prompt-cache reuse
github-actions[bot] · ghdev · 2026-09-29
Qwen Code released its TypeScript SDK v0.1.17 bundling CLI 0.24.7. Key fixes from the 0.23.0 CLI: managed memory now respects the memory.enableManagedAutoMemory setting (#6941), so hosts disabling it no longer get remember/dream requests or managed-memory prompt instructions; and size-triggered microcompaction now clears old tool results toward a low watermark (#8464), no longer rewriting the conversation prefix every turn — preserving provider prompt-cache reuse across long tool-heavy sessions and cutting cached-input cost.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16