Plugins

Per-turn and per-step cost ledger for DeepSeek Harness: a Turns tab beside Chat and Trajectory with tokens, estimated cost, cache savings, and an inspector for tool arguments, raw results, and source. Client-only; prices are estimated from recorded model usage.

A customized usage-statistics-panel dashboard with a 52-week square heatmap, bar-only token trends, and ended-turn labels, using the upstream collector and history. Same package name as upstream HaoyueQin/dsh-usage-statistics-panel, so the two cannot be installed together.

Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.

Download pets from petdex.dev and keep one on the desktop, following the DSH session status; the appearance is adjustable and an enterprise WeChat bot can push a notification when the agent needs confirmation or finishes a turn. Desktop mode needs macOS 12+ or Windows 10 1903+; the bundled companion is prebuilt.

ChatGPT-style composer predictions for DeepSeek Harness: after each assistant turn, suggest the user's next message as ghost text in the composer. Tab accepts, Escape dismisses.

rulemux rules inside DeepSeek Harness (dsh): asks the rulemux CLI for the rules it renders for this workspace and injects them into the session once, on the first turn (nothing written to disk for rules). Also syncs skills into the native skills dirs (.ds

Feishu IM bridge for dsh: create a dedicated Feishu bot by scanning a QR code, get one Card JSON 2.0 notice per finished turn, answer tool approvals and structured questions from the chat, and drive a session from it — listing and switching the bound session with /sessions and /resume, steering a running turn, and choosing per-chat permission modes (read-only, workspace, Auto Review, full). Long output paginates instead of being cut. Owner binding: the QR scan binds the scanner; with manually entered credentials the first sender claims ownership and everyone else is refused.

Sidebar tab that lists a session's file changes by turn, expands line-level diffs and undoes them, with a matching review card at the end of each chat turn. Needs dsh-better-sidebar installed separately. DSH 0.2.x port of Lzh3070/dsh-file-review-tab; do not install both.

Zero-key web search provider for the built-in web_search tool: scrapes Bing China, 360 and SearXNG through a backend fallback chain and returns real URLs with snippets and publish dates. No API key and no settings card are required. SearXNG is used only when you set your own instance URL, and installing this plugin switches web_search to it and turns off the official DeepSeek search row.

Session and message surgery in one plugin: recall or edit prompts and replies (reasoning included), regenerate from the original prompt, delete any turn at the model-context level, and archive, delete, move or migrate sessions across workspaces. Targets DSH 0.1.5 and 0.2.x, verified on 0.2.1-rc.3. A combined fork of three MIT plugins (dsh-message-recall from Jipcon/DSH-plugins, dsh-session-manager from hkkz9522, dsh-delete-turn from DDDMUC) with added reply editing, regeneration and workspace migration. Do not enable it together with those plugins or other session movers or message deleters.

Minimal theme for dsh that removes shadows, glass blur, and brand tinting while tightening radii, plus UI extras: sidebar archive tabs with type-to-filter, model and reasoning-effort controls under the composer, per-turn subagent topology cards, colored cache-hit and context meters, and per-turn duration.

Turns the DeepSeek Harness window into frosted acrylic glass so the desktop shows through, stacking on top of the active theme instead of replacing it. Desktop show-through on Windows 11 also needs the bundled installer (npx github:InkStain258/dsh-glass-skin), which makes a backed-up edit to the DSH Desktop app.asar.

A DSH plugin that turns one provider API key into a managed pool + more built-in LLM Providers

Turn-granular context memory for DeepSeek Harness.

Make the Naiwa desktop pet laugh whenever a DeepSeek Harness agent turn ends. Windows only; requires the Naiwa desktop pet installed.

Mirrors assistant streaming frames (deltas, blocks, commits, turn fences) to a configurable NDJSON sink for external consumers.

DeepSeek Harness plugin for rulemux: asks the local rulemux CLI for the rules rendered for this workspace (rulemux inject --agent dsh) and injects the output into the session at the first user turn, once per session. Nothing is written into the workspace for rules; skills are the only part that lands on disk.

Sends an Edge/Windows desktop notification when a tool call waits for approval, the agent asks you to choose an option, or a session finishes a turn, and only while the DSH page is in the background or unfocused; an optional chime covers cases where the browser or Windows suppresses the notification.

Settings page for agent modes (presets): switch up to 15 capabilities per mode (commands, files or read-only files, web, subagents, and more) or individual plugin rows; edit each mode's system prompt with variable checks, a full preview, version history, optional live updates for running sessions, and an approval-gated mode_prompt chat tool; create modes from four starter templates or copies; merge built-in updates after a dsh upgrade while keeping your changes, and turn off rows that fail to load.

Runs a second agent: hands independent subtasks to a local Codex CLI in parallel (up to three at a time), and asks it to review a design or a plan before the user sees it, returning conclusion, evidence, counterexamples and a verification step. A dispatch missing its timeout or its acceptance check is rejected by the plugin, not by the model remembering to check.

Turns PDF, Word, PowerPoint and Excel files into Markdown or plain text with heading levels preserved where the source allows it, and refuses scanned PDFs that have no text layer instead of writing an empty file, naming the OCR alternative instead. Requires Python 3.10+ and pip install -r requirements.

DocChain knowledge base, document conversion and knowledge-graph toolkit — filename, content and metadata search, locate-by-doc_id/name with content reading, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, per-document image descriptions saved to a sidecar markdown (flowcharts and architecture diagrams are turned into PlantUML sketches, other images into text descriptions; the original image is replaced by a clickable link), a deep-research workflow, and a knowledge-graph layer (ontology inspection, read-only Cypher, ontology/entity/relation writes). Every script-backed capability also ships as a native DSH tool executed in-process: doc search, content search, filename search, topic info, metadata search, upload, image search, image describe, doc2markdown, plus kg schema / kg cypher / kg upsert node / kg upsert relation / kg delete node / kg delete relation. All graph operations go through the DocChain API, so no Neo4j password is needed. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown); image descriptions additionally need an OpenAI-compatible multimodal endpoint (defaults to an internal gateway model, configurable).

Reads a local video or page link with ffmpeg and Paraformer ASR, returning a timestamped transcript plus key-frame images the agent can open; finds candidate videos by keyword and installs its own runtime dependencies on first use. Requires Python 3.8+ on PATH; video_discover also needs a one-time douyin/xiaohongshu login.

Agent tool that returns the running DSH Web GUI URL including its per-process launch token, so browser automation can open the GUI instead of getting a 401.