dsh-theme-eink-retro
A paper-and-ink client-side theme for DeepSeek Harness with Balanced and Immersive modes.
297 results
A paper-and-ink client-side theme for DeepSeek Harness with Balanced and Immersive modes.
Matrix-style night-friendly dark skin for the dsh web GUI: near-black green background, ink-green monospace text, low-opacity digital rain (forces dark, no system-theme follow)
Matrix rain for expanded thinking in DeepSeek Harness Web
DSH 自定义模型思考等级管理、渠道重试策略与偏好记忆插件:原生设计语言、全档位思考配置、渠道级重试控制与无感隔离式跨会话偏好记忆。
DeepSeek Harness plugin: gzip /api responses for DSH versions before 0.1.2-rc.1 — fixes history loading failures over slow links; DSH 0.1.2-rc.1+ is unsupported
Official Weixin iLink text, image, and file bridge for DeepSeek Harness
第三方模型思考努力度配置(DeepSeek Harness 插件):在设置页为模型声明 reasoningEfforts 档位、路由默认档位与 Anthropic token 预算,写入 llm-pi-ai 命名空间;档位调节复用原生模型框 Effort 面板。
One-click phone access to DeepSeek Harness via a Cloudflare quick tunnel, with the link pushed to your WeChat through your chosen channel (ServerChan / PushPlus / Bark / ntfy / custom webhook).
DSH plugin: notify personal WeChat via ilink protocol (Weixin ClawBot) when a task completes, errors, or needs user input. Built-in QR login flow and WebUI settings panel.
DeepSeek Harness (DSH) plugin: export conversations to an Obsidian vault, plus read/search/list/tags/backlinks tools and automatic vault discovery.
DeepSeek Harness plugin for lightweight LAN access to the current Web UI from phones, tablets, and other computers.
DSH web plugin: a dedicated 模型能力 settings page (per-provider request headers, gateway compat switches and per-model capabilities, including catalog routes) plus automatic thinking-tier defaults. 模型能力独立设置页 + 思考档位默认注入。
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
Live reasoning-token badge — Think(5.2K) — on every Think disclosure row of the DSH web UI, ticking while streaming · 在 web 界面 Think 行标题后实时显示思考内容 token 数的 DeepSeek Harness 插件
DeepSeek 中转站(OpenAI 兼容网关)思考强度适配插件:让 UI 出现 Off/Low/High/Max 推理等级选项,并按中转站格式发送 reasoning_effort / thinking
V CYBER — multi-theme plugin for the DeepSeek Harness Web client: NEON (cyber neon pink × electric blue) and TACTICAL (SOC dashboard + FUI cyan neon)
把 N 次 LLM 调用压成 1 次 —— DeepSeek Harness(DSH)的极致调用压缩插件:标题短路 + 飞行去重 + 24h 回放缓存 + 批量归并。
Replace DSH web tool icons with emoji: think 🤔, read/search 🧐, pwsh 👨💻, edit ☝️🤓, error 😫
LLM Wiki workbench for dsh-better-sidebar: browse and lint a Karpathy-style interlinked markdown wiki, open pages with the native markdown viewer, clickable [[wikilinks]] and provenance/relative .md links, and backlinks. Ships the llm-wiki agent skill.
Per-turn thinking-token statistics for DeepSeek Harness, folded once by a durable session projection and read by the composer dock.
Hover timestamps for DSH web chat nodes — start–end (and duration) on Think, Bash and every tool/step row · 在 web 界面 hover Think/Bash 等会话节点行时显示开始-结束时间与用时的 DeepSeek Harness 插件
V 技能映射 — DeepSeek Harness Web 的 '/' 菜单插件:映射技能(配置目录的一级子目录含 SKILL.md,选中注入全文)+ 自定义指令(followup 型)+ 快捷按钮(输入框下方网格,点击追加 Prompt 进输入框,可选自动发送)+ 设置页可视化编辑(目录/指令/按钮 CRUD)。