Плагины

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Sidebar disk browser for DeepSeek Harness - browse any folder on the server (including hidden ones) with text preview, streaming download and upload (multi-select / drag-and-drop, overwrite confirm), responsive on desktop and mobile.

Adds a structured TextIn xParse tool and document parsing skill to DeepSeek Harness, supporting document parsing, cached-content navigation and durable multi-document tasks, with AppKey or Device OAuth authentication, paid-operation approval and bundled cross-platform CLI binaries.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

Real-time token estimates for the DSH conversation composer, combining the current context baseline with the draft and showing exact or heuristic counts.

Input prediction for the DSH composer: your next prompt suggested as ghost text after each turn, accepted with Tab. (autocomplete / input prediction / prompt suggestion)

In-session "Files" tab (conversation.view, order 20) for dsh Web that browses the active session's workspace directory with breadcrumbs and previews files inline — sanitized Markdown (marked + DOMPurify), images, line-numbered text and PDF — served by read-only /dsh-files host routes registered on ctx.webServer; no write endpoints. Bilingual zh/en.

Keeps a local model's context at a size the GPU handles well: measures prefill speed on every request and, before each step, warns or compacts early on a hard token ceiling, an observed time-to-first-token budget, or a predicted cold-prefill budget; /context-budget shows the numbers and the cost of compacting now.

An agent preset that turns a one-line idea into requirements, tech plan and maintenance baseline — every step is restated and confirmed by you before proceeding. No scenario presets: 73 atomic skills (6 master skills + a verify dispatcher + 66 sub-skills) load by context.

Floating card showing DeepSeek balance, peak/off-peak tier countdown, and remaining tasks estimated from historical per-task token usage and the current context.

Agent instruction manager for DSH — edit and template the AGENTS.md files the harness actually reads (global + per-workspace)

Keeps DSH agents from forgetting your requirements during long tasks. It saves important conditions and completion evidence locally, brings them back after context compaction or session resume, and stops partial work from being reported as the whole task done.

Force the agent's chain-of-thought, planning, tool-invocation reasoning, and internal deliberation to stay in Chinese — the language constraint is injected at the top of the system prompt before every reasoning step, so it cannot be diluted by tool-returned content. A settings panel lets you edit the constraint text on the fly.

Auto-fold context/system messages in DSH conversation — collapse think blocks, tool calls, and tool results into grouped expandable bars.

Turns attached files into versioned evidence: `search_documents` builds a private local index (SQLite FTS5 after a startup capability probe, dependency-free JS fallback otherwise) and returns compact evidence blocks carrying an exact coordinate — PDF page, PPTX slide, text/DOCX line range, or quoted XLSX `Sheet!Range` — which `read_document` expands only while the content version still matches. Contiguous CJK runs are indexed as overlapping bigrams and queried as phrases, so word order is preserved; uploaded raster images take the native vision attachment path instead.

Streaming speech-to-text for DeepSeek Harness using AllModels.io.

DeepSeek Harness (DSH) plugin: complete WeChat Official Account article downloader — wechat_article_fetch tool plus a zero-dependency anti-bot fetcher CLI (title/time/author/content with text-images-videos-links, read/like/wow stats and comments with a lo

Editable local and desktop dictation for DeepSeek Harness

Automatic, bounded type context and edit diagnostics for DeepSeek Harness

Control which tool schemas are injected into the DeepSeek Harness model context. Registers a tool_visibility manager tool AND a settings-page UI (Settings → 工具注入控制) with per-tool toggles; backed by the framework-native tools.restrict filter and persisted

Ranks OpenRouter providers for the current DSH model by quantization, speed, cache-heavy price, context, and uptime, with one-click switching to help reduce token costs.

Drag-and-drop PDF, Office, images, and text/code files into DSH conversations. The host extracts (and OCRs) them into the prompt; attach_* tools cover notebook cells, PDF-page OCR, image describe, and save.