Plugins

DSH Web right-side output dock: session-scoped tabs for reports, images, data, video, and audio, with inline previews, output quality checks, and a searchable per-turn history.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

This plugin exports a reusable function that takes a file path or a Buffer, extracts the content via @firecrawl/anydoc, and returns GitHub‑Flavored Markdown (GFM). It also includes configuration options and an example usage.

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Generate self-contained interactive HTML reports from Markdown, tables, charts, China province maps, flowcharts, math, and drill-down tables — a DeepSeek Harness (dsh) plugin

Customize the visible DSH Web thinking status with lifecycle-safe CSS.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Import local Codex, Grok, Claude, OpenCode, and CC Switch logins into DSH; pick sources and enable models in Settings.

Dual knowledge-graph RAG for Markdown notes with half-life memory decay: prerequisite + similarity graphs (P/S-Agent traversal), paragraph chunking, n-gram/embedding hybrid search, and an explicit weight-feedback loop — a native Cordis plugin, npm-installable as @eqman00003/knowlp-rag.

Export the current session to portable, schema-versioned Markdown and JSON files via the `session_export` tool and slash commands, with cross-platform-safe filenames.

Group installed DSH plugins into named sets and enable, disable or exclusively apply them by rewriting the profile bundle list. Can also render a set as an agent preset that a single conversation uses.

Per-model jailbreak armor: a Settings table arms model patterns with spells (25 spells: 20 across 11 model families, plus a model-agnostic armor, an upstream preferences file and three stackable persona layers), previews the exact injected block, and writes it into the armed model's system prompt only, leaving every other model untouched.

Groups the sidebar's panel rows: two stay pinned, the rest fold under a collapsible Tools row, and rows can be dragged between the two groups.

Pins each message's action row — copy/like/dislike/branch controls, timestamp, and third-party additions — so it stays visible without hovering.

Development-preview DSH plugin to import recordings from compatible BLE recorder cards, with optional transcription and fingerprint-linked archives. Requires recorder hardware, Host Bluetooth and Python dependencies.

A fork of dsh-livestream (MIT) - install it instead of that plugin, not alongside it. Lets DSH host a Bilibili livestream: chat and gift replies, queued viewer video requests on a skinnable stage, Doubao TTS voice, and automatic OBS/Bilibili streaming setup; needs OBS Studio 28+ and a Bilibili live room, and the voice stays silent until you add a Doubao TTS API key (Python + faster-whisper optional for transcribing subtitle-less videos).

Browse, install, inspect, update, and remove MCP server connections inside DeepSeek Harness, with an online catalog and native Streamable HTTP/stdio support.

Scan and fix Low integrity labels, non-inherited S-1-4 sandbox ACEs, and related Everyone deny ACEs in DSH workspaces on Windows. Maps live DSH workspaces, defaults to read-only, repairs after confirmation, verifies the result, and keeps one replaceable ACL rollback record per workspace.

Five-layer intent recognition pipeline (rules, pgvector retrieval, Jev scoring, fine-tuned arbitration, LLM fallback) with scenario management UI, PostgreSQL storage and distributable API services.

Blocks a tool call whose arguments lost their boundary, keeps a closing turn open when a step silently never ran so the model can re-issue it, and replaces damaged output on the model-visible surface after a fork. Zero dependencies.

Sessivra: drag sessions into resizable split views, insert native @ references into drafts, exchange linked replies and review delegated work before queued follow-ups. npm package dsh-plugin-sessivra.

Manage which models appear in the composer model menu. A settings page lists every provider's models with a per-model switch, provider-level show/hide, collapsible groups and filters by kind; switched-off models leave the menu while the model in use in the current session stays. The list can be searched by name or ID and filtered by capability (multimodal, reasoning) and by minimum context window (128K / 256K / 512K / 1M). Rows show the model kind, and chat models also show reasoning support with the adapter's effort levels, their context window and input modalities. Labels merge manual overrides, the settings document, the adapter, the relay's GET /models response, a built-in pi-ai / models.dev catalog, name inference and vendor corrections in that priority order, with the source named on hover and dashed borders marking inferred values. Any model can be edited by hand (kind, context window, modalities, effort levels); those edits are stored outside the profile and can be written back into the model provider's settings. A hard re-fetch drops every cache and asks the adapter and all relays again. A switch, on by default, lets relay routes whose models declare text-only input accept images in memory, without editing configuration files. The hidden list is stored in the profile patch and mirrored to $DSH_HOME.

Obsidian-style notes panel in the DSH right sidebar: a tree over a local folder, Markdown preview with line numbers, edit and save, Obsidian callouts, tables and wikilinks, screenshot paste into the vault, one-click insert of a note path into the chat input, and batch archive or delete for sessions and workspaces.