dsh-left-sidebar-collapse
Auto-collapse / fully-collapse the DSH left sidebar on session select, as a standalone installable plugin. General-settings toggles plus a single floating expand button.
290 results
Auto-collapse / fully-collapse the DSH left sidebar on session select, as a standalone installable plugin. General-settings toggles plus a single floating expand button.
DeepSeek Harness-native Feishu (Lark) gateway: chat with the DSH agent from Feishu via long connection, with persistent sessions, /new, Markdown replies, live streaming progress cards, native Typing reactions, click-to-answer approval / Q&A cards, and proactive push.
Interactive per-Turn execution graph visualization for DeepSeek Harness trajectories.
Stop runaway agent loops in DeepSeek Harness: denies repeated identical tool calls and enforces a per-agent call cap, outside the model where instructions cannot reach.
DeepSeek Harness plugin: aligns markdown tables in assistant replies right after each turn (surface-replace, replay-safe) and adds a /clear-history command that empties the model-visible conversation while keeping the append-only log.
DeepSeek Harness settings page: cap every configured model service to a working context window, clamped to what each model can actually hold
Local SKILL browser plugin for DeepSeek Harness: discovers local skills with live filesystem updates and surfaces them in the web UI with a Use button that explains how to invoke each skill.
Codex-compatible desktop pet for the DeepSeek Harness web GUI: animated pets that follow the agent state
Codex-style turn folding: collapse each group of reasoning + tool-call nodes (between visible outputs) into a single disclosure unit
A global Automation Center with fresh, auditable scheduled Agent runs for DeepSeek Harness
自动模式 Auto Mode: an AI pre-judgment layer for DeepSeek Harness — a flash-model router that picks the best agent preset (standard/code/minimal/cordis) for each new session and lets the user confirm before execution.
Conversation navigation dots for DSH Web: a vertical rail of clickable markers on the right side of the conversation view. Each marker represents a user message — click to jump, hover for preview, active marker highlighted. | DSH 网页端对话导航点:对话右侧一列可点击的导航标记,每个标记对应一条用户消息。点击跳转,悬停预览,当前点高亮。
A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.
Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent turn's system prompt.
Custom UI suite for DeepSeek Harness: theme gallery is the first module (23 themes with ~121 full token mappings each); future modules (fonts, layout, interactions) will live here too.
开源的 Prompt 构建与增强工具包:方法工坊(Studio)+ 对话快捷增强器(QuickEnhancer)。内置 22 个 Markdown 思考方法(含技术开发/数据分析等场景卡 + frontmatter + prompt 正文),可作为 npm 库嵌入,也可直接安装为 DSH 浏览器插件。
CodeAct agent loop for the DeepSeek Harness: a persistent IPython session as the model's action space, with harness tools bridged in as a virtual `__dsh__.tools` module.
当任意会话的 agent 向用户提问(ask_user_question)、请求审批或有会话任务完成时,把 EAC 任务栏图标常亮高亮(非闪烁,直到窗口回前台熄灭)并自动切换会话;显式点击时置顶 EAC 窗口(保持原窗口大小状态);提供 /activate 端点供 EAC 主进程通知联动
One-click / auto model sync for DeepSeek Harness providers — reconciles stored model lists against each provider's /v1/models endpoint, with a Settings page toggle and conversation-open auto-sync.
对话圆点导航:页面上纵向圆点快速跳转到用户提问位置
A floating right-side table of contents (TOC) for the DeepSeek Harness Web UI: one entry per user question, click to scroll to that message.
opencode-style custom agents for dsh: define agents as markdown files with their own system prompt and model, then call them from chat with an @mention — each mention dispatches a subagent
图解教学(Illustrated Teaching):DeepSeek Harness 插件,把任何知识点自动渲染成精美图解画廊——8 套模板、真实图片检索、一键导出,专为本科阶段学习设计
Independent-model advisory review for DeepSeek Harness: after each tool step, a reviewer model audits the agent's operations and injects concerns/guidance into the next step.