Plugins

Doubao-style voice chat for DSH: press-and-hold mic in the composer converts speech to text and auto-sends, and AI replies are read aloud. Optional LLM condensing (long replies summarized into short spoken lines, following the current conversation model), TTS-friendly text cleaning, selectable Edge TTS voices, adjustable silence auto-stop, and settings embedded in DSH settings dialog.

An independent approval subagent judges every sandbox escalation, with a configurable model and an audit log.

Image understanding for any DSH model: vision, OCR, grounding, and crop tools with domain presets for histopathology, cell biology, anatomy, clinical images and scientific figures.

Three-tier agent memory harness: L1 always-on CLAUDE.md, L2 index, L3 detail skeleton with templates, a gate that blocks writes to protected files without a one-time approval token, zero-judgement event logging, weekly distillation, and a TDD execution-loop skill.

Sidebar session-search toggle between title and content: title filters by session title, content searches historical messages through DSH's built-in full-text index, grouped per session with the strongest snippet and message-type tags.

Decision split view for DSH web UI: a decision summary card in the main window plus the full plan in an independently scrollable side panel, so you can review the whole plan while writing decisions and send them back to the agent with one click.

Markdown viewer for the dock workbench: GFM rendering with DOMPurify sanitization, document outline and relative-path image/link resolution, with one-click switch to editing.

Task-scoped Workspace to Task to Session control center for DSH Web, with Session boards, archived conversation viewing, and bounded long-term memory shared across linked Sessions.

Web chat entry for DeepSeek Harness: a sidebar button opening chat.deepseek.com in a dedicated desktop window under dsh-desktop, with in-webview fallback for plain web environments.

Task-completion chime for DeepSeek Harness, playing the original opencode sounds for done, question, plan-review and error events with zero external dependencies.

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

Local code knowledge graph for agents: parse a codebase (Python/JS/TS/Go/Java/Rust) into a SQLite index and answer callers, callees, deps, dependents, impact and full-text questions over it.

Evidence-driven company and job due-diligence for DSH: logs sources with evidence levels, adds evidence-bounded claims, verifies the legal entity against official registries, and renders a PROCEED/VERIFY/STOP report with a verification checklist and interview questions.

Background stream listeners that wake the DeepSeek Harness agent — put a watch on a command or file and receive new lines as in-session notices. Ships a daemon host so a watcher can run unattended for weeks.

Install tab in Settings → Plugins: install, update and remove any plugin by npm spec, `github:user/repo` or local path through the same `dsh plugin add` CLI path; update checks against npm latest or GitHub HEAD with a downgrade guard and resolved-version verification, a pnpm 11 release-cooldown bypass on every add/remove, and service restart via the DSH Desktop shell or a relay process under standalone `dsh web`.

DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.

Model-driven /init command: the agent analyzes the current repo and generates/updates a high-signal AGENTS.md, with a persistent system-prompt reminder to keep it maintained.

Folio (兰亭) @nyantused/folio-dsh-events: session-protocol events — auto session-start reminder + auto-save on session close; pair with @nyantused/folio-dsh-tools.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

Adds persistent execution contracts, recursive work graphs, critical clarification, and evidence gates for long or underspecified Harness tasks.

In-chat preview for produced files: click a produced-file chip to render Markdown (server-side markdown-it + highlight.js), images, or plain text right in the conversation; system-app open and reveal-in-folder stay one click away.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Docker tools for agents: ps/images/logs/inspect/exec/manage/health with JSON output, env-configurable CLI path, approval-gated exec and zero runtime dependencies.