dsh-token-counter
Token counter: shows the account balance and, after every conversation turn, that turn's token usage and what it cost.
1027 results
Token counter: shows the account balance and, after every conversation turn, that turn's token usage and what it cost.
DSH web plugin: live Markdown + KaTeX math preview docked ABOVE the composer, via the official conversation.input.dock slot. Zero patches to DSH core.
DSH Web GUI 全屏 Markdown 阅读器插件:GFM、KaTeX、Mermaid、目录与阅读进度、外部文件变更同步、图片/代码/表格/长章节增强,以及打印与另存 PDF。工作区门禁的只读路由;零构建、零运行时依赖。
AI-agent-driven automated testing platform for DeepSeek Harness (dsh): Markdown case library, bug reports, per-project serial queue, development board and built-in load testing.
Browse, search and install SkillHub skills inside DeepSeek Harness. / 在 DeepSeek Harness 内浏览、搜索并安装 SkillHub 技能。
DSH Feedback Bridge(DSH 社区反馈)— a DeepSeek Harness plugin that helps users prepare privacy-aware community feedback.
SSH remote workspaces and a graphical directory picker for DeepSeek Harness Desktop.
DSH bundle plugin: a petdex.dev companion-pet market in the Settings UI with a native macOS desktop pet. Browse, search, install, enable, rename, and delete pets; previews are proxied same-origin to dodge CORS.
DeepSeek Harness 用户消息修改插件:在用户发言下方的复制按钮旁增加修改(✎)按钮,支持一键回填编辑与重新发送。
OpenAI-completions-compatible transport takeover 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, a </think> split on the receive side, multimodal true-send (image/audio/video/PDF) with a modality gate, and an llmOpenaiCompletions prompt-source seam — no pi-ai behavior guessing.
划词追问:在助手回答里选中文字后右键追问,问答全部留在右侧面板,并从主对话中隐藏。
DeepSeek Harness plugin: one-click OAuth (PKCE) connect to the Qixin Insight MCP server, mounted as a single plugin entry
智能体表情包系统:随插件内置默认表情包(零配置即用),也支持添加任意自定义表情包文件夹;智能体在回复中用 ::文件名:: 标记引用表情,Host 端自动转写为图片,让回复更生动可爱。
Community skill marketplace for DeepSeek Harness: browse, search, and one-click install skills from awesome-skills-cn and the wider Claude Code / OpenClaw skill ecosystem.
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。
Image generation tool for DeepSeek Harness 0.2.x — provider-table driven (Doubao Seedream / Aliyun qwen / any OpenAI-compatible gateway / local deployments), user-configurable model per channel, watermark-free, inline in-chat display.
Floating theme widget for DeepSeek Harness: switch the official appearance, and set a custom background (picture or solid colour) with four parameters and four fit modes.
Share a selected range of chat messages as Markdown, HTML, TXT, or PNG (Web /share command, Session-header dialog, redaction, tool calls, subagent conversations, auto-save)
Multi-tab preview panel plugin for DeepSeek Harness
Render Markdown to standalone, self-contained HTML in the DeepSeek Harness — a model-facing md_html_render tool that works headless, plus a browse/preview/export drawer in the web GUI. One renderer behind both. Zero runtime dependencies.
Solve the AI goldfish brain: a personal memory layer for DeepSeek Harness — preferences, project conventions, workflows, and error lessons, stored locally as auditable, evidence-backed Markdown/JSON. 解决 AI 金鱼脑:偏好、项目约定、工作方式与纠错教训的本地可审计记忆层。
Memory Standard Protocol (mm) for the DeepSeek Harness: layered MEMORY.md + deterministic budgets + frozen snapshots + cross-agent markdown/URI interop + session-log digestion. Ships as a dsh bundle (tools: mem_read, mem_write, mem_search, mem_budget, mem_digest) and a standalone CLI.
A lazy MCP and skill capability broker for DeepSeek Harness and other MCP clients
dsh plugin: scan the dsh plugin ecosystem — collect stars/npm downloads/release assets per plugin, segment the market, compute growth deltas from snapshots, and surface high-growth plugins and niches.