Plugins

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Capybara secretary for DSH: desktop pet notifications with ding sound, alert inbox API, session-aware alerts (turn done / approval needed / turn blocked), check scripts, and daily high-star plugin recommendations.

Auto-continue an interrupted dsh session after a web restart by injecting a "continue" follow-up; one-shot per process, no duplicate-injection loops.

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.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

DSH bundle that registers 13 native codegraph_* tools wrapping the codegraph CLI, so agents bootstrap, maintain, and query a pre-indexed code knowledge graph (symbol query, explore, node trail, callers/callees, impact, affected tests) instead of grepping files.

Ranked subagent delegation: role-based model routing with failover, per-route reasoning effort, model-transparent labels, fork delegation, and a visual route editor.

Turn histogram navigation rail for DeepSeek Harness Web with mixed, DeepSeek, and Codex visual variants.

Polishes the draft in the composer into a clearer, better-structured prompt from the ✨ button or Alt+O; streams the result live over SSE with reasoning shown first, and follows the session's default model with zero configuration or any OpenAI-compatible endpoint.

Shows a floating toolbar above text selected in a conversation, with copy, quote, ask, explain, translate, summarize, and custom prompt actions.

Desktop profile for dsh: native Tauri window over the harness web surface with tray, native notifications, a file-manager panel, and one-click updates.

UI enhancement suite for DeepSeek Harness: one-click workspace open (copy path, reveal in Finder, open in an auto-discovered editor), DeepSeek-web-style user-message nav rail, session to-do marks, flat-list polish, and a hard-restart button.

Left-edge conversation rail for the Web UI: one bar per turn, length scaled to the turn text, hover for a question and answer preview, click to jump; bars come from a host-side outline of the whole session log, so turns outside the loaded window are drawn too and history is paged in on click.

Add six languages (繁體中文, 日本語, 한국어, Français, Deutsch, Español) to the DeepSeek Harness Web UI language options, with hand-polished per-language translations and automatic fallbacks (Simplified-to-Traditional conversion for zh-TW, English for the others) covering upstream updates and third-party plugins.

Parses natural-language relative time (e.g. "in 2 hours") into ISO timestamps, fail-fast.

Workspace-owned durable process supervision, readiness checks, and a Runtime Center for DeepSeek Harness.

Auto-approval permission guard: a middle tier between workspace-write and danger-full-access — auto-allows safe operations inside trust directories, always asks a human for destructive ones, with 11 per-category switches and an audit trail.

Pre-execution guardrail: vetoes dangerous shell commands and blocks secret/credential leaks before they run.

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

Smart provider routing: composer-button one-click enable/disable, any channel error (including 4xx) auto-falls-back to the next channel, chain names shown in the model selector without exposing internal channels/models, multi-chain management with settings UI.

vision_analyze tool: analyze a local image or URL with an OpenAI-compatible vision model.

Codex-style token usage dashboard: five stat cards, GitHub-style activity heatmap (daily/weekly views), insights & model ranking; persisted snapshot with incremental sync, survives session deletion.

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.

DSH 网页版网易云音乐播放器插件：顶部条迷你播放器 + 展开面板，扫码登录，支持 AI 对话控制