Plugins

Local knowledge base for DeepSeek Harness: five tools to ingest Markdown, plain text and PDF files, search them with BM25 or hybrid BM25 plus optional local embeddings, and answer with cited source passages. Runs offline with no database server. Requires Node.js 18+ and Python 3.9+; PDF ingest needs pymupdf.

Local knowledge base for DSH: one Markdown file per note, with tags, hierarchical folders, full-text search, attachment opening via the system default app, zero-dependency Office text extraction, and citation into the conversation. Built for host DSH 0.2.0-rc.2; on Windows the default root is E:/dsh-kb.

Launches the local compound-memory MCP server through uvx and injects a short usage reminder once per session.

Export a session as a ZIP archive with its attachments, and import such an archive as a new standalone session in the current workspace.

Adds a Continue button to resume tasks interrupted by a process exit or restart.

Reads a local Hermes Agent session store read-only and imports sessions into the current conversation as bounded, untrusted background context: a composer button opens a searchable list across every profile, plus the hermes_sessions_list and hermes_session_import tools.

Cross-session and in-chat keyword search with context highlighting, keyboard navigation, and instant message jumping.

Ask side questions using the current conversation context, with independent streaming and cancellation.

Ctrl+F find-in-session for the conversation, powered by the session store rather than the DOM - labels every hit by source (you / assistant / reasoning / tool call / tool result / system), groups results by turn, merges identical snippets, offers prose-vs-everything scope, regex / case / whole-word options, highlights all matches, and copies or exports the result set as Markdown.

Per-turn checkpoints of the whole workspace: every turn ends with a snapshot, the files it changed are listed under that turn in the chat, and any turn can be restored — files, the conversation, or both. Capture is a whole-tree scan rather than a hook on write/edit tools, so edits made by shell commands, external editors or git leave a record too. Restoring the conversation forks it from that turn instead of cutting the original, and a restore can itself be undone. History sits in a shadow git repository under DSH_HOME and never touches your project .git. Requires Git >= 2.20 and Node.js >= 20.

Read-only session-log projector (drsc) for DSH: scans ~/.dsh/sessions/**, decodes zstd/tiled-frame logs with a vendored leaf decoder and rewrites per-session projections into its own SQLite (node:sqlite, segments / replaces + FTS5), exposed through a single fenced HTTP route — surface ledger, recall/compression pair accounting and Chinese-capable full-text search. Token counts share the exact DeepSeek-V4 tokenizer and formula as CCI verify, falling back to a labelled chars/4 basis when assets are absent. Never writes session files; all output lands in its own data directory. Serves three consumer plugins: context-compression-improved (surface marking + recall reconciliation), session-steward (search-corpus switch), prime-memory (historical anchor backfill). Hosts 0.1.0-rc.2 .. 0.2.1-rc.2 (17-tag exact engines.dsh enum). npm: dsh-reference-session-collector.

Self-hosted chat room where the owner and coding agents share one room: a local Node server (SQLite, REST, SSE) that the plugin starts when it is not running, a DSH sidebar entry that opens the room in a panel, five tools (room_join, room_send, room_read, room_status, room_leave) that push an incoming message into the session as a user message labelled with its sender before flushing it to the session log, and a Codex CLI connector that forwards room messages through `codex queue`. Every message carries a server-assigned author, platform and seq, and messages from anyone other than the owner are delivered as data with the sender named. Requires Node.js 24+.

Connects a QQ Bot to DeepSeek Harness with per-peer sessions, group mention and keyword triggers, image generation and voice replies. Access defaults to OPEN for both direct and group chats, and an empty allowlist means everyone — set access.c2cMode / access.groupMode to allowlist (or disabled) before exposing the bot; IM input can run tools on the host.

Adds DSH 0.2.x kernel support to the SenseTime XiaoHuanXiong desktop-app models, reusing that app's stored sign-in so no API key is needed.

New API gateway provider: several gateways with one active at a time, per-gateway model lists with context and modality details, quota, and image and video generation tools.

Model failover for DeepSeek Harness: pick one or more providers and the pool becomes every model inside them; when a request fails (rate limit, quota, timeout, server or transport error) the next untried model in the pool retries automatically, and the original error surfaces once the pool is exhausted. Configure from a seat beside the composer model picker or the model_failover tool, with no restart needed.

Adds the official Google Antigravity ACP agent as a DeepSeek Harness model provider, with tool execution and approval kept in DSH, Node 22.19+ and a signed-in Antigravity account required, a per-model quota pill and a settings page.

Registers the workbuddy model provider by mounting dsh-llm-workbuddy, supervises the local wb2api gateway, and runs a bundled Responses-to-chat-completions bridge so Codex CLI can use the same gateway. Skips work that is already running or already registered, and reports each part through a status tool. Requires a local wb2api gateway and a WorkBuddy account.

Connects a locally-signed-in Cursor desktop app to dsh as a native LlmAdapter — reads the Cursor login token from state.vscdb or auth.json, drives the private agent.v1.AgentService/Run HTTP/2 bidi stream, and translates InteractionUpdate deltas into dsh StreamChunks. No loopback proxy. macOS, Windows and Linux.

Two-level model routing: pick the best model group first, then the best channel within that model; a failure switches channel before switching model. Preference mode pins one model across its channels, a status bar under the composer shows the live model, channel health and the day's token usage, and a speed/intelligence report can be imported as the routing prior. Exposes a model_orchestrator tool and a /route command.

Ranks the models a DeepSeek Harness install already discovered by measured connectivity and speed, and switches to the next candidate inside the same turn when the one in use fails without producing any output. Ships a settings page with a grouped model list, per-model and per-channel switches, and a quota-aware cooldown that rests an exhausted model until the next day.

Fork of dsh-reasoning-effort with a two-level model picker in the composer: a provider list, a model pane that slides out beside it, search, and compact rows, alongside the reasoning-effort slider and its max-level effects.

Adds the Liquid Inference auction exchange as a model route, with liquid.auto and its ranking variants, and four tools that read offers, markets, routers and job receipts. Requires a Liquid Inference API key (LIQUID_API_KEY, spend scope).

Route DSH subagent delegations to configured models with per-role routing for explore, plan and patch subagents, round-robin or random distribution, cross-provider failover, and active-window slicing of fork seeds.