Plugins

把长文本渲染成图片发送，利用每图 384 token 封顶压缩 LLM 输入 token，专为DeepSeek Harness设计的插件；Pack long text into images to cut LLM input tokens (384/image cap) — a DeepSeek Harness plugin.

Time-traveling stream rules for DeepSeek Harness — project rules stay dormant until a regex matches the live token stream, then the request is aborted, the rule injected as a system reminder, and the request retried from the same point. Zero per-turn cont

Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.

The small deterministic operations an agent needs mid-task. JSON/YAML round-trip, JSON Schema validation, text diff, JWT decode, regex testing, SQL dialect transpiling, QR codes, timezone and unit conversion, page screenshots.

附件自动降级：DSH 图片准入（单边 ≤2000px / ≤3.5MB / ≤4000万像素）超限图片不再拒绝，用 sharp 自动缩小/重编码后入库，用户上传手机原图不再踩线。

DeepSeek Harness plugin + browser extension bridge: lets DSH agents read and control Firefox/Chrome/Edge via a localhost WebSocket. Node side: browser_* tools over a localhost WebSocket; browser side: WebExtension.

88API Image Studio for DSH: four Image2 and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.

A draggable sticky note for dsh web: a floating memo window that expands into an editable notepad and collapses into a small draggable icon. Single global note, position and content persist across reloads.

DeepSeek Harness 的 MCP 服务管理器：在 设置 → 插件 → MCP 标签页中发现 GitHub 上的 MCP 服务仓库（topic:mcp-server / modelcontextprotocol），探测 npm / PyPI 发布状态与 README 启动线索，详情查看后一键安装 / 移除。服务以 @deepseek-ai/dsh-mcp-client 行登记进 cordis.patch.yml，HMR 热重载，无需重启。支持 GitHub 代理。

Cross-border commerce: HS codes, customs invoices, mainland reachability. HS/HTS code lookup and classification, commercial invoices, live exchange rates, IBAN and EAN/UPC checks, amount-in-English for documents, and whether your site is actually reachabl

Lovstudio dev click-to-source for DeepSeek Harness web: runtime-only, reads React _debugSource on Shift+Option click and opens the editor. No build-time markers; works in vite dev (jsxDEV __source).

DSH 静态 bundle 插件：在左侧工作区浏览目录与文件。双入口（文件浏览/打开目录）、320px 浏览面板、文件预览、一键打开系统资源管理器、文件引用添加到聊天。A static-bundle DSH plugin: workspace file explorer in the left sidebar.

Firefox browser control for DeepSeek Harness: token-authenticated WebSocket bridge + text-first browser_* tools driving the user's own Firefox via the companion AMO extension

Lovstudio in-place application restart for the DeepSeek Harness web surface: a host half exposing restart/status routes and a settings-header button with live running-conversation monitoring, confirmation dialog, and in-flight spinner.

Offline identifier checks and Chinese money/tax arithmetic. Checksum-verified identifiers (mainland ID, USCC, bank card, plate, VIN, ISBN, IMEI, IBAN, EAN/UPC) plus amount-in-words, IIT, VAT, mortgage schedules and 调休-aware workday counts.

Backs the native web_search and web_fetch tools with your self-hosted SearXNG instance, keyless and private.

Adds a Windows Explorer right-click "Open DeepSeek Harness here" menu item that boots dsh in the clicked folder.

Provider-neutral search and extraction tools for DeepSeek Harness

Linux crontab-style scheduled tasks for DeepSeek Harness: the LLM can schedule recurring workflow runs and prompt-driven tasks with cron expressions, plus proactive task suggestions inferred from the chat.

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

One-click Claude Code and Codex hooks for DeepSeek Harness: auto-discovers your existing hooks config and runs it on the official bridge plugins.

GLM 视觉模型插件：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。

LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.

DeepSeek Harness plugin for accurLex Open Platform legal tools