Plugins

Audio Copilot for DeepSeek Harness: transcribe audio (ASR) and synthesize speech (TTS) — gives text-only agents ears and a voice. Windows-local SAPI TTS out of the box; OpenAI-compatible ASR/TTS endpoints configurable. Includes an in-composer voice-input

Feishu/Lark IM channel for DeepSeek Harness agents with native thinking-process messages, approval cards, live goal and todo cards, workflow fan-out lines, session text search, and background job and subagent settlement notices. Access is bounded by the Feishu app's own visibility scope by design — anyone the app admits can drive the agent and answer its approvals unless the optional sender, group and approver allowlists are filled in.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Turns each DSH workspace into a project: every new session auto-injects a project-workspace convention (read code before acting, empty folder means a brand-new project); a per-session Project toggle in the composer downgrades the session to a plain workspace with an explicit notice, with the state kept in the session log.

Cross-session memory plugin for DSH (v0.3.0): auto-extraction, SQLite FTS5 indexing, RRF semantic recall, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. Zero-config.

Project memory for DeepSeek Harness: project files are indexed into searchable summaries as they are read, so after context loss the agent retrieves hits on demand instead of re-reading files, with source citations and BM25 ranking.

Inline image previews in chat for pasted images bridged by dsh-tool-vision on text-only models (click to zoom, old messages get previews too).

Current-session message outline rail for the DSH web UI — your messages show as slim bars on the left edge; hover to expand the full outline (line number + text), click to jump instantly to that message. Pure frontend, zero external service dependencies, sessions-snapshot driven with zero polling.

Adaptive Reversible Context (ARC) for DeepSeek Harness — provider-aware, cache-conscious context governance with reversible recovery.

Registers the remove-pdf-background-gray skill for DSH: whitens gray/off-white scan backgrounds in image-based PDFs while preserving resolution, page geometry, and anti-aliased text edges (lossless Flate write-back), via a single Python script (pypdf + Pillow + numpy).

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Lazy-loading router for MCP servers: auto-discovers compatible MCPs and keeps only a shared router in the tool catalog, revealing a server's schemas when a turn needs them and hiding them again at turn end, so many installed MCPs stop costing context on every request. Falls open to normal visibility on any uncertainty, and the original MCP keeps ownership of execution, permissions and process lifecycle. Also supports explicit lazy connections with warm reuse, bounded reconnection, stdio and Streamable HTTP.

Select text in a finished assistant reply to add numbered comments beside the quote; collect drafts and submit the batch through the official composer as one user message.

Cross-agent conversation management plugin adapted for DeepSeek Harness, with search, type filters, individual and batch selection, reversible hide, restore, and undo, plus independent reasoning and answer units whose sidecar state preserves the original Session.

Type normally; about two seconds after you pause, it rewrites your draft into a version more likely to get a good answer, leaving pasted code, links and long text untouched and keeping multi-part questions numbered.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Automatic context compression for DeepSeek Harness: compresses tool outputs before they reach the model and keeps every lossy compression reversible via CCR retrieval tools.

A DSH Web plugin that turns chat sessions into editable mind maps, with Markdown, Mermaid, PlantUML, XMind text, and TODO exports.

DeepSeek Harness 动态上下文管理插件（Dynamic Context Pruning for dsh），对标 opencode-dcp

DeepSeek Harness(DSH) web plugin: paste files into the composer, inbox storage, thumbnails. Text via read_inbox; image understanding needs your vision skill (bundled image-reader + ARK_API_KEY).

Official DSH plugin for nuphus-mcp (by the nuphus-mcp maintainers): desktop and browser automation (38 tools) with PaddleOCR element perception and Chrome CDP browsing, via a persistent stdio MCP child process.

Sidebar meters for DeepSeek Harness Web: a DeepSeek account balance bar (orange, with a low-balance alarm) and a conversation context-usage bar (blue), rendered above the plugin store with a hover detail popover.

Continuous water-flow light for the dsh web 'Deep diving...' turn status: three parallax gradient currents sweep the text like flowing water, replacing the stock single-band shimmer. Light/dark themes and reduced-motion respected.