Plugins

Volcengine Ark provider plugin for DeepSeek Harness (DSH): registers Agent Plan, Coding Plan, and postpaid routes on the native pi-ai adapter so Ark models appear in the model picker.

Claude Code-style auto-memory, natively: typed memory files (user/feedback/project/reference) with a MEMORY.md index auto-injected into the system prompt (zero footprint when empty); memory_write/read/list/delete follow Claude Code write rules (dedupe-and-update, absolute dates, cross-links); workspace-scoped and user-scoped layers, cross-process file locking with orphan-lock recovery, plain Markdown on disk, no external services, no embeddings.

Prompt market beside the composer: browse and search three built-in online prompt sources, bookmark or write your own, and insert into the input box.

Gives the companion a mood judged each turn and shown as a short context note, with a panel for mood, emotion dimensions and timeline.

Filters tool outputs, prunes stale context and discloses skills on demand for DSH 0.2.1-alpha.1.

Reads DSH conversations aloud using the DeepSeek web page's built-in read-aloud, driven by a small browser extension.

Turns explicit DSH session experience into reviewable native Skill drafts that are saved only after user approval.

Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.

Create editable Blender product scenes in DSH. Start from speaker, cup and lamp recipes or imported models; view saved results on the Lighttable, compare revisions, and adjust dimensions, materials, cameras and lights. Place static models on actual mesh surfaces in one saved operation. Render images or saved-shot videos and export an editable revision with its assets. Native geometry inspections, immutable revisions and an approval gate help preserve existing work. Supports DSH 0.2.1-rc.1 and the legacy host, with 19 tools for modeling, review and delivery.

Causal memory for dsh: a zero-dependency MCP stdio bridge that mounts the 17 tools of the causal-memory server under clean names (no mcp__ prefix) — decision → outcome edges with typed relations (caused / enabled / prevented) in a local SQLite store that survives compaction — plus a pinned system-prompt section. Requires the causal-memory server binary on PATH (pip install causal-memory, or a prebuilt release).

Gives DeepSeek Harness control of the Tabbit Browser: auto-loads the tabbit-browser skill on install, detects official Tabbit and Tabbit Browser releases (>= 1.9.0), checks the tabbit-cli persistent runtime, diagnoses the per-platform DSH sandbox mode needed to call the CLI, and downloads the region-matched official installer via a background job when no qualifying version is present.

Model-directed context compaction for PTC mode, grouping program runs into blocks and replacing completed block messages with model-written summaries.

Visualize the DSH process network path on Windows or WSL with layered DNS/TCP/TLS/HTTP probes, detect stale proxy configuration, and apply snapshot-guarded repairs.

DSH session manager: delete with trash/restore/purge, restore archived sessions, recent-activity stats, continue/pause, open log folder, unread markers, fork into a new chat, workspace grouping and sorting, context compaction threshold.

Drop-in enhanced fork of the official todo_write tool: priority tags on each task, full checklist rendering in the conversation, and a draggable in-session floating task panel with position memory, double-click reset and a live indicator of the action currently being executed.

Local image and MP4 video backgrounds for DSH Web and Desktop, plus Codex, Cursor, Doubao and WorkBuddy: a sidebar Background panel, saved named themes, a sound switch, restore-last-background, a background-only "slack" mode, and /bg, /bg-theme, /bg-clear commands.

Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness

Generates game art from reference images via Seedream image generation and MiniMax image-to-video, assembling eight-direction sprites, sequence frames, and skeleton animations with local green-screen keying.

View and manage an agent’s tools and skills in a visual menu. Set each capability to Resident, On-demand, or Disabled; agents can find and use on-demand capabilities while reducing context usage.

Sidebar billing dashboard: real usage aggregated from session logs (per-model and per-day calls/tokens/cache), cost estimated in CNY from a current multi-provider pricing catalog, subscription-plan (coding/token/agent) routes exempt, and per-provider health dots.

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Evidence-first attention supervision for DeepSeek Harness with C0–C3 policy, deduplicated Inbox alerts, quiet hours, and redacted outcome records.

Renders agent HTML output as real UI in the DeepSeek Harness web GUI, with visual cards, KaTeX math, Mermaid diagrams, built-in open-source fonts, and design-spec injection.

dsh 浏览器扩展（全端）的桌面端一半：把浏览器扩展连到 dsh，提供 browser_* 工具，并在需要时替你识别页面上的图片。这是它的全部配置项。