DeepSeek Harness (DSH) plugins for peer-to-peer AI session collaboration and communication across workspaces on one computer. 同机 AI 会话跨工作区对等协作与通信：公告、消息投递、侧栏面板。
Multi-agent orchestration and LLM model routing for DeepSeek Harness (DSH): semantic AI agent profiles, exact model routes, declarative teams and strategies, and bounded subagent delegation - a TypeScript plugin that adds no second runtime.
Crossfire (针锋) for DeepSeek Harness: put a settled result on the stand, let red-team experts attack it from chosen dimensions, and adjudicate every single defect yourself. The machine only finds flaws; the human always owns the verdict.
Multi-instance ComfyUI orchestration for DeepSeek Harness: give the agent a live view of every GPU in the farm and dispatch each generation job to the idlest instance instead of always hitting the busiest endpoint.
📦 记忆搬家：把 Claude / ChatGPT 的历史记忆搬进 DeepSeek Harness —— 逐字证据由代码回原文核对，你逐条批准，全程本地 | Move your Claude & ChatGPT memory into DSH, with machine-verified verbatim evidence
Delete one finished turn from a DSH session without deleting the session. A trash button removes that turn's question, reply and tool records from the conversation and the model context, while the session, later turns and the append-only log stay. Independent continuation of hanshenmesen/dsh-turn-delete (DSH 0.1.5-rc.2 + 0.2.0-rc.1).
DSH token-saving toolkit: proactively slim large text/JSON/CSV before they enter context (diet_text / diet_json / diet_csv / diet_estimate). Zero-dependency pure functions.
Solidify DSH session history step by step: rewrite tool results in place to the facts the model actually kept, so long conversations stop re-sending noise every turn. Costs tokens and time: a ~770-character contract in every request, plus one extra full-context request and round-trip per step when stepSummary is on.
