dsh-api-usage-bar
Cache-aware API token usage bar for the DeepSeek Harness Web UI
287 results
Cache-aware API token usage bar for the DeepSeek Harness Web UI
A DeepSeek Harness plugin + skill that scouts the DSH ecosystem: the core deepseek-harness repo and every dsh-plugin-tagged repository, discovers harnesses related to your goal, and judges whether each is worth trying.
DSH client plugin — flip to the back of the page for a floating glass task console: live background jobs, subagents, session overview and workspace of the current session, with mouse-draggable and mouse-resizable cards (bottom-right handle, size persisted per card); the top-right card conversation calls a temporary agent session to refactor each card's style and internal controls from natural language, and any conversation can author cards via [taskcard] blocks (text/heading/note/stats/progress/trend/kv/links/chips/checklist/counter/button/table/code/toggle/countdown/bars/image). Cards can be published as copies onto a fullscreen infinite canvas with named boards, share strings and a zero-dependency WebSocket relay for multi-user editing, and a right-hand dock renders the project's archify architecture diagram (embedded, sandboxed, resizable).
DSH (DeepSeek Harness) scaffold plugin & preset: strict 5-phase init runbook, engineering standards, and six runnable starter templates (node-ts / react-vite / python / go / spring-boot / monorepo). 项目初始化脚手架预设:严格流程 + 工程规范 + 六套模板。
A floating desktop pet for the DeepSeek Harness Web UI: idle breathing, occasional direction turns, random actions, and screen wandering.
并行多角色代码评审小队:/review 一条命令派出安全/正确性/测试/风格四名只读评审员子代理(每人可单独指定模型与思考强度),汇总为按严重度分组的结构化报告。Parallel multi-role code review squad: /review dispatches security/correctness/tests/style reviewer subagents (each on its own model) and aggregates one severity-grouped report.
Education toolkit for DeepSeek Harness agents: lesson-plan skeletons, quiz validation, question scaffolding, analytic rubrics, grading sheets, study plans, class statistics, flashcards and readability levels
A DeepSeek Harness (DSH) static market plugin that adds an 'MCP 服务' management page in Settings: list / add / edit / delete the MCP servers registered in cordis.patch.yml, and run a real MCP initialize connection handshake per server to verify each service connects normally.
DeepSeek Harness plugin that turns the CLIs you already subscribe to into provider routes. Ships the Claude Code bridge; each bridge can be enabled or disabled on its own.
Renders chat Markdown image references () as a gallery under each closing assistant message
DeepSeek Harness plugin: cron-driven scheduled items. Each item carries a title, a prompt, and a croner expression; executions spawn a fresh agent session in a bound workspace (or the default cwd) and run on schedule or on demand. Includes a full-page management UI.
Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).
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.
DSH plugin: API retry settings page - view and edit each LLM provider's request retry policy (mode, maxRetries) over the settings wire
DSH Web UI plugin: fold consecutive tool calls in one assistant turn into a single line (Codex-style), with live running-tool label, call count, and expand/collapse. Pure Slot/React implementation, no DOM patching.
Fluid streaming rendering and silky scrolling for DeepSeek Harness replies, including Markdown, code blocks, tables, and tool results.
Selection-based comments for the DeepSeek Harness Web UI: select text in the chat, comment on each selection, then submit all comments as one message.
Local-first AI teaching workspace for DeepSeek Harness — context, unit packages, assessment diagnosis, and next-lesson feedback loops
Generic Web content fetcher plugin for DeepSeek Harness with dual pluggable data sources (CDP browser + Tavily). Each data source is registered as its own tool so the LLM can pick context-appropriately. Zero-intrusion bundle plugin; follows strategy pattern.
A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.
Codex-style generated-image gallery and lightbox for DeepSeek Harness
Per-workspace Claude Code command hooks for DeepSeek Harness: each session discovers .claude/settings.json from its own cwd
Extensible workbench shell for DeepSeek Harness with generic side and bottom view registration.