44 results
Readable thinking display for DeepSeek Harness: live per-paragraph summaries of the reasoning stream, rendered in the chat history where the 'Think' row is, with a user-chosen summary model (thinking disabled on summary requests).
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers. (daha1216 fork: reading-view display support for dsh-retrace — shadowed-row hiding, markers, and edit references)
J-Space Cognition Suite SV1 native Agent Preset and standalone plugin for DeepSeek Harness
DSH host plugin: force the agent's chain-of-thought / reasoning / planning / tool-invocation deliberation to stay in Simplified Chinese — 让 Agent 的内部思考（思维链）始终使用简体中文。
Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling
A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.
Xiaomi MiMo v2.5 adapter for DeepSeek Harness LLM seam with thinking chain support
DSH reasoning effort slider with 7 levels and cool visual effects
Structured context for DeepSeek Harness: split the conversation into typed sub-contexts (reasoning / tool calls / replies) and index them with a table of contents. 结构化 dsh 上下文:按类型拆分小上下文(思考/工具调用/正式回复),以结构化目录为索引。
Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box
Replace the DSH Web reasoning-effort chooser with a compact animated FX slider that scales with effort level.
在 dsh 模型目录的每一行直接设置该模型的思考强度范围与支持的输入模态 (Per-model reasoning-effort range and accepted input modalities, right in the dsh Models catalog)
Merge consecutive reasoning blocks in the DeepSeek Harness host stream
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
DSH plugin: model reasoning levels plus CLI request mimic, with a unified Daily Optimization settings section.
Require and relay concise action summaries before tool calls in DeepSeek Harness
Codex 风格 6 档性能滑杆：每档绑定模型 + 推理等级，并切换 31 张本地人物背景。 / Codex-style 6-level performance slider for DeepSeek Harness (dsh web).
Context-branching conversation tree plugin for DeepSeek Harness. Avoid cold-start waste and show full tool/reasoning steps.
DeepSeek Harness plugin: make the chain of thought open with "We need" instead of "Let me"