Proactive associative memory for DSH: system-prompt recall before the model speaks, three-layer auto-consolidation, skill crystallization, and Astra-style context management - handoff ledgers, PLAN whiteboard, water-level sensing. Local-first, model-agnostic, zero deps. 主动联想记忆+Astra 式上下文管理：自动唤回/自动沉淀/技能固化/交接账本与白板跨窗口续命/水位感知。
One-line fix: inject a fixed system-prompt section so the agent always thinks and replies in Chinese, whatever the user's language · 中文思考：注入固定提示词，让 agent 始终用中文思考与回复（无论用户语言）
DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.
Context window optimization for DeepSeek Harness agents. Sandboxes tool output in-process (only what you print enters the conversation), persists session memory in an FTS5 knowledge base, and enforces routing via a system-prompt routing section.
