Plugins

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

ShiGuang Memory Engine (SGME) bridge: multi-agent shared long-term memory via HTTP — L0/L1/L1.5/L2 distillation, scenario-based injection, unified search, and proactive care signals (memory_search / wiki_search / signal_pull / signal_claim / signal_ack), installable as `dsh-sgme`.

Installs Herta as a DeepSeek Harness agent: a preset carrying her persona and memory prompt sections, six memory and voice tools, a narrative layer that separates her thinking from what she says, 80 bundled voice clips, offline and MiniMax speech synthesis, and two conversation views that render the session with her own components.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Visual round-table meetings for DeepSeek Harness — expert nodes on a ring with directed edges, an aggregation gateway, proxy thinking for black-box worker models, and adversarial review (red-team) of settled plans with per-viewpoint endorse/reject.

Git Bash shell tool for Windows: runs commands through the bash bundled with Git for Windows, with timeout, sandbox, output truncation, and background jobs, replacing the slow pwsh tool and the WSL-only bash tool.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Connector only, it renders nothing itself: subscribes to DeepSeek Harness session events and folds them into a 12-phase work state (planning / thinking / executing-tool / streaming / waiting-input / voice / awaiting-approval / complete / error / paused / idle / heartbeat), then POSTs each phase to a desktop-pet backend at http://127.0.0.1:8000/api/plugin/dsh/ingest. It holds no window. No API key or token is needed. Requires the Mao Live2D pet application to be separately installed and running (that is a Windows Electron app with its own PowerShell 7 / Python 3.10+ / Node 18+ prerequisites); without it this plugin has nothing to push to.

Reads animated GIF and WebP as animations: a pasted one keeps playing in the UI while the model gets a labelled sheet of frames sampled across it, and the read_animation tool samples a file on demand.

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Scheduled cron tasks, background automation and agent execution for DeepSeek Harness.

Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

General-purpose knowledge base for DSH: import md/txt/json/yml/docx/pdf, folder management, FTS5 full-text search (BM25), and a Web management UI.

Reads Harness replies aloud through an existing local TTS runtime: built-in IndexTTS and GPT-SoVITS launchers, a protocol-based local HTTP/JSONL entry, and model-folder loading for Kokoro, F5-TTS, VoxCPM, Qwen3-TTS and CosyVoice SDK environments. Ships no models. Derived from 1624318455/dsh-plugin-tts; it isolates its row id and settings, so both can be installed side by side with duplicate features deactivated.

A novel-writing workbench for DeepSeek Harness: you tap thumbs-up or thumbs-down on candidate passages, and the model distils them into a short preference profile that carries into later drafting calls while the manuscript stays out of the drafting context. Adds a chapter board, per-chapter writing packs, annotation-scoped revision that rewrites only the annotated paragraph and verifies the rest byte-for-byte, a project ledger, and local pacing checks.

Patent-writing gatekeeper for dsh - screens the idea against Chinese prior art first, then runs five-party alignment interviews, eight-chapter disclosure drafting, figures and simulation runs, seven-dimension review and docx/PDF export. Skills work out of the box; the search, export and experiment tools come from a bundled Python MCP service that ships disabled - one line in ~/.dsh/patent-services.yaml enables it, and uvx fetches the wheel from PyPI.

Local literature knowledge-base RAG for DSH: hybrid BM25 + vector retrieval, cross-encoder reranking, cited answers with section- and page-level provenance, metadata-only refresh and background ingest with progress polling, over a SQLite index.

Trellis-style workflow for DeepSeek Harness: per-turn phase breadcrumbs via agent/pre-step, bundled skill provider, and DSH-native task/phase state with git-cleanliness guardrails.

DSH-native integration layer for the Minta memory engine: composes the official dsh-mcp-client row, registers the minta-memory-governance skill plus a session-start memory prewarm, and ships a Minta agent preset; requires the separately deployed Minta engine (Python/Docker) to provide the 19 MCP tools - not usable without it.

Programming Mode agent preset bundle: the standard coding agent with its persona mandating the Superpowers discipline (skills first, brainstorming before building, plans before code, TDD, systematic debugging, verification before completion) plus an always-on Ponytail code-volume discipline (7-rung minimal-code ladder, default full); ships all twenty skills bundled (14 superpowers + 6 ponytail) and mechanically injects the full using-superpowers skill into every new session's first request.

Keeps a pool of API keys per provider with auto-created clone routes, switches to the next key on quota or rate-limit errors, probes cooled keys for recovery, and exposes the pools, cooldown and switch codes in a Settings section.

Plays Inception Mercury's diffusion (denoising) stream live in the dsh Web UI answer bubble: for routes that support it, the request is re-sent with `diffusing: true` and the real frames are replayed from noise to final text, while only the converged answer reaches the session log. Support is detected per provider/model with a probe that is rejected before any token is generated, a floating per-model toggle turns it on, and attachments, auxiliary calls or unsupported routes fall back to the original adapter. Replaces the assistant-message renderer for all models while enabled.